Data Intelligence Just Accepted MS. - Am MIT spezialisierte KI-Forschung

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

Rezension

Submitted: November 18, 2022; Überarbeitet: Dezember 12, 2022; Accepted February 7, 2023

Zitat: Tao, Z.C, Lyu, S.F. A Survey on automatic delineation of radiotherapy target volume

based on machine learning. Datenintelligenz 5(2023). doi: https://doi.org/10.1162/dint_a_00204

A Survey on Automatic Delineation of Radiotherapy Target Volume based on

Machine Learning

Zhenchao Tao, 1, 2, 3, Shengfei Lyu*, 3

1. School of Data Science, University of Science and Technology of China, Hefei,

Anhui 230026, China

2. The First Afﬁliated Hospital of USTC, School of Life Sciences and Medicine,

University of Science and Technology of China, Hefei 230031, China

3. Nanyang Technological University, 639798, Singapur

* Korrespondierender Autor. Email: shengfei.lyu@ntu.edu.sg

Schlüsselwörter: Automatic delineation, Machine learning, Radiotherapy target volume,

Medical image matching, Cancer

Abstrakt

Radiotherapy is one of the main treatment methods for cancer, and the delineation

of the radiotherapy target area is the basis and premise of precise treatment. Artificial

intelligence technology represented by machine learning has done a lot of research in

this area, improving the accuracy and efficiency of target delineation. This article will

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

review the applications and research of machine learning in medical image matching,

normal organ delineation and treatment target delineation according to the procudures

of doctors to delineate the target volume, and give an outlook on the development

prospects.

Einführung

To estimate the global burden of Cancer-based on the cancer and mortality

information provided by the International Agency for Research on Cancer in

GLOBOCAN 2020 [1], von 2020, Globally, there are an estimated 19.3 million new

cancer cases (18.1 million excluding non-melanoma skin cancer) and nearly 10 Million

cancer deaths (9.9 million excluding non-melanoma skin cancer). The global cancer

patients will be expected to reach 28.4 million cases by 2040, A 47% increase from 2020.

Malignant tumors will surpass all other chronic diseases and become the “number one

killer” that threatens human life and health. Radiotherapy is one of the main treatments

for malignant tumors. Its principle is to use the high-energy ionizing radiation to kill

cells of tumors. About 60%-70% of tumor patients need to receive radiotherapy.

According to statistics, the current average progression-free survival rate of malignant

tumors is about 55%, of which radiotherapy contributes 40% of the tumor cure [2], Und

the therapeutic effect has been widely recognized in clinical practice. The rapid

development of artificial intelligence represented by machine learning can be applied

to all aspects of clinical practice of radiotherapy [3-6], making radiotherapy decision-

making more simplified, individualized and precise, and improving the automation of

the entire process of radiotherapy. The precise determination of radiotherapy target

volume is the basis and premise of precision radiotherapy. The automatic delineation

of radiotherapy target volume based on machine learning is essential in the research of

artificial intelligence in the field of radiotherapy application, which greatly improves

the efficiency and accuracy of target volume delineation [7]. This article will review

medical image matching, normal organ delineation and treatment target delineation.

1. Application of machine learning in radiotherapy

Kürzlich, with the development and progress of medical and computer technology,

radiotherapy has entered a new era of precision radiotherapy, and more and more

precision radiotherapy technologies have entered the practice of clinical tumor

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

treatment. Precision radiotherapy is playing an increasingly important role in improving

curative effect, delaying disease progression, improving prognosis and improving

Patienten’ quality of life [8-9].

In the 1930s, radiation technology has been used to treat tumor patients [10], und in

the 1960s with the widespread applications of medical linear accelerators [11]. Jedoch,

X-ray simulation localization is used for tumor localization during radiotherapy in this

Zeitraum. The doctor obtains the location of the tumor from the patient’s fluoroscopic

Bild, and marks the irradiation range on the patient’s body surface according to the

localization image, and performs treatment through the body surface projection field.

Due to the failure to clearly define the tumor and normal tissue, and the poor uniformity

of radiation dose distribution, it is easy to miss the tumor or normal tissue is irradiated

with a higher dose, resulting in a lower cure rate and higher complications. In 1959,

Takahashi et al [12] proposed the concept of three-dimensional conformal radiation

therapy (3D-CRT). The prototype is based on the three-dimensional morphological

structure of the tumor, using lead blocks to irradiate in multiple radiation directions

through the blocking part field, so that the shape of the irradiated area is the same as

that of the tumor target, while reducing the radiation dose received by the blocked area.

In the 1970s, the widespread application of computer systems and the emergence of

computed tomography (CT), magnetic resonance imaging (MRT) and other equipment

promoted radiotherapy to three-dimensional space, enabling 3D-CRT to be realized.

In recent years, three-dimensional digital precise radiotherapy technology has

gradually replaced traditional two-dimensional radiotherapy technology, and has

become an important development direction of tumor radiotherapy in the 21st century.

The three-dimensional digital precise radiotherapy technology focuses on precise

positioning and precise treatment, and performs conformal or intensity-modulated

radiotherapy at the three-dimensional level through dose segmentation, so that the

internal irradiation dose of the lesion in the target area is the largest, and the surrounding

normal tissue is the smallest, the irradiation dose is evenly distributed, and has the

advantages of high precision, high efficacy and low damage [13]. In addition to 3D-CRT,

the currently recognized precision radiotherapy techniques also include stereotactic

body radiotherapy (SBRT), intensity modulated radiotherapy (IMRT), and image

guided radiation therapy (IGRT), usw. The technique system of precise radiotherapy for

tumor is gradually perfection, and the treatment accuracy is increasingly improved.

At present, the steps of precise radiotherapy are to first obtain the anatomical

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

images of the patient on the treatment couch by simulated positioning, then manually

delineate the target area and organs at risk by the doctor, and then configure the

radiation dose, number of fields, field angle and other parameters can be used to

generate a radiotherapy plan suitable for the shape and dose of the tumor target. Endlich,

after the radiotherapy plan is verified and correct, the treatment can be carried out.

Among them, target delineation is the core work of radiotherapy physicians. Accurate

target delineation is the premise and crucial step of precise tumor radiotherapy. Der

quality of delineation has a great impact on the treatment effect of patients and the

occurrence of complications [14]. If the treatment target volume is too large, it will

increase the radiation dose received by the surrounding organs, thereby increasing the

probability of complications [15]. Umgekehrt, if the tumor area is not completely

covered, it will lead to insufficient doses to kill all cancer cells, greatly increasing the

possibility of recurrence after treatment [16].

Currently, the therapeutic target volume that needs to be manually delineated by

radiologists mainly includes the gross tumor volume (GTV) visible on the image; Die

clinical target volume (CTV) is delineated based on the knowledge of tumor pathology,

tumor invasion range, and lymph node metastasis pathway. Zusätzlich, the target area

of the organ at risk (OAR) within the irradiation range also needs to be accurately

delineated to avoid over-irradiation of the OARs, causing serious side effects and

complications of radiotherapy [17]. The above-mentioned delineation quality of the

therapeutic target volume and OARs completely depends on the professional

knowledge and experience of the doctor, and certain errors will occur. Darüber hinaus, diese

large-scale structures are delineated manually layer by layer for the radiologists, Und

the time cost is also very high. With the development of artificial intelligence

Technologie, deep learning methods based on the big data of radiotherapy patient images

can automatically delineate the therapeutic target area and OARs of patients. The speed

and accuracy are greatly improved, which helps to reduce the workload of doctors and

reduce manual delineation. uncertainty, further improving the precision of radiotherapy

[18-19].

As the main method in the field of artificial intelligence, machine learning can be

divided into supervised learning, unsupervised learning, and semi-supervised learning

which combines the two [20-22]. Specifically in the field of radiotherapy, supervised

learning-assisted radiotherapy is mainly used [23]. Combining multiple simple machine

learning models to obtain an ensemble learning model with better performance can

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

design a combination scheme for specific machine learning problems to get a better

solution [24]. Neural networks are a form of machine learning inspired by the way the

brain works, referencing the connection structure of neurons [25-27]. When the neural

network has many hidden layers, it is defined as a deep neural network. Deep learning

methods use deep neural networks to solve various classification and prediction

problems. Compared with traditional machine learning methods, deep learning methods

have the advantage of being able to automatically learn features in data and avoid

manual feature selection. A large amount of data accumulation and the improvement of

hardware computing power have made deep learning methods more and more applied

in the medical field, and they have shown better performance than traditional machine

learning methods [28-31].

2. Medical image registration based on machine learning

The electron density of CT images is linearly related to the density of the human

Körper, which can be directly used to calculate the radiation dose, and has become the

most commonly used radiotherapy positioning equipment. It has a good effect on bone

and lung tissue observation, while soft tissue MRI images have better observation

Effekte, and PET images can indicate areas with strong metabolism. daher, multi-

modal imaging registration is often used in clinical assessment of disease. Medical

image registration is to find the optimal spatial transformation between the source

image and the target image to match all the feature points or at least all the

corresponding points with diagnostic significance on the two images, and provide

doctors with more abundant clinical information. Common registration methods

include rigid registration and non-rigid registration.

2.1 Rigid registration

Rigid deformation can be described by a few transformation parameters. In the

field of radiotherapy, rigid registration is very common and highly accepted, Und

clinicians will fuse images of different modalities through this transformation to obtain

more information about areas of interest. The registration method is to align the two

images by finding the rotation-translation transformation matrix between the fixed

image and the moving image [32]. The methods used include linear transformations such

as translation and rotation, which can ensure that the overall structure or line parallelism

of the image remains unchanged after spatial transformation. Gleichzeitig, es hat

the advantages of simple calculation and low time complexity, and is suitable for

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

images with little deformation.

Rigid registration not only provides a prerequisite for further non-rigid registration

and saves the calculation time of image optimization iterations, but also can intuitively

display the anatomical structure differences between images between different

modalities, assisting doctors in accurate delineation. Traditional registration methods

include surface-based methods, point-based methods (usually based on anatomical

markers), and voxel-based methods [33]. Among them, voxel-based methods have been

widely used by virtue of the rapid development of computer technology. The goal of

this method is to obtain geometric transformation parameters by computing the

similarity between two input images without pre-extracting features [34]. Jedoch, diese

traditional registration methods often require iterative calculation of similarity

measures such as mean square error, mutual information and normalized mutual

Information, usw. Due to the non-convexity of similarity measures in parameter space,

the registration process is relatively expensive. sometimes with poor robustness [35].

Besides, other methods such as intensity-based feature selection algorithms perform

image registration by extracting image features corresponding to the intensity, Jedoch,

the extracted features are difficult to correspond well in anatomy [36].

2.2 Non-rigid registration

Since medical images are affected by factors such as imaging time, Bildgebung

Ausrüstung, and patient posture, it is difficult to spatially register multimodal images. In

addition, the internal tissue structure of the human body is complicated and has time-

varying characteristics. Zum Beispiel, the tissues and organs in the lung scan images will

move with the patient’s breathing. For the deformation of the images with large

differences in each direction, the rigid registration method cannot meet the requirements.

In this case, a non-rigid registration technology needs to be used, and the same parts of

different images are corresponding to each other by means of the spatial registration

deformation field. The entire registration process will also introduce different degrees

of registration errors due to the chosen optimization method.

Non-rigid transformation includes translation, rotation, scaling, and affine

transformation based on an affine matrix and other linear and nonlinear transformation

Formen. Compared with rigid transformation, it has better deformation accuracy, aber die

calculation speed is slower. Gu et al. [37] proposed a B-spline affine transformation

registration method, using affine transformation to replace the traditional displacement

of each B-spline control point, and using a two-way distance cost function to replace

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

the traditional one-way distance cost function to achieve bidirectional registration of

two images. Pradhan et al. [38] used a P-spline function with a penalty added to the B-

spline for brain image registration. The method based on the physical model regards

the deformation of the floating image as the physical change caused by the external

force, takes the original image as the input, and calculates the result of the image that

is changed by the external force under the physical rules through the physical model.

The physical models used are mainly viscous fluid models and optical flow field models.

Wodzinski et al. [39] applied the algorithm of the optical flow field model to breast

cancer tumor localization, compared it with the B-spline method, and obtained a better

registration effect.

With the development of deep learning technology, significant progress has been

made in the field of image processing, mainly including the use of unsupervised or self-

supervised deep learning to calculate deformation parameters and similarity measures.

Zum Beispiel, Hessam et al. [40] used a large number of artificially generated

displacement vector fields for training to integrate image content from multiple scales,

thereby directly estimating the displacement vector field from the input image.

Hongming et al. [41] proposed a new non-rigid image registration algorithm based on a

fully convolutional network, and optimized and learned the spatial transformation

process between images through a self-supervised learning framework. Jedoch, until

Jetzt, the non-rigid registration algorithm is still not mature enough compared with the

rigid registration algorithm, and the algorithm acceptance is not enough [42].

3. Automatic delineation of normal tissue based on machine learning

3.1 Atlas based automatic contouring

After multimodal image registration, clinicians will delineate contour information

on the planned CT. The delineated targets mainly included therapeutic targets and

OARs. The shape of OARs is relatively definite, and the location generally does not

change much. In terms of automatically delineating OARs, the most widely used

clinically is the automatic segmentation technology based on the atlas library [43]. Atlas

refers to medical images and their corresponding binary delineation results, since even

among different groups of people, the relative spatial positions and spatial shapes of

normal organs in the body are similar, and the image textures have the same

characteristics. The delineation principle is to pre-establish one or several sets of OARs

templates, and machine learning methods automatically match the appropriate

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

templates [44].

The delineation methods based on atlas libraries can be basically divided into two

categories: delineation methods based on single atlases and delineation methods based

on multiple atlases [45]. The delineation method based on a single map can be regarded

as a deformation registration problem. Erste, the atlas is registered to the image to be

delineated, and the transformation matrix and deformation field are obtained. All the

delineated organs in the atlas will be deformed and mapped according to the same

transformation parameters, and the result of the mapping is the delineation result.

Jedoch, the single-atlas library delineation method may have a large difference

between the input patient images and the average atlas, resulting in unsatisfactory

delineation results.

The accuracy of the method based on a single atlas library depends heavily on the

accuracy of image registration. When the atlas used is very different from the image to

be delineated, it is difficult for the registration algorithm to achieve good results,

resulting in a significant reduction in delineation accuracy. In order to improve this

phenomenon, Aljabar et al. [46] proposed a multi-atlas method, which registered and

fused multiple sets of reference atlases with the images to be delineated, erhalten

multiple sets of alternative delineation schemes, and used an algorithm to synthesize

the alternative plans to form the final delineation. The performance of the multi-atlas

library is often more stable than that of the single-atlas library, because the poor

mapping results of some atlases in the multi-atlas will be corrected by other better-

performing atlases, so that each part can be relatively reasonable. While multi-map-

based methods improve the robustness of delineation compared to single-map-based

Methoden, they are prone to topological errors because voxel voting does not necessarily

result in closed surfaces. Such topological errors have a great impact on the formulation

of radiation therapy plans, and are also difficult to detect, requiring time-consuming

review and manual editing by clinicians [47].

3.2 Deep learning based automatic contouring

The atlas library is essentially the operation of registering the target image and the

template image through morphological features, das ist, the process of searching for the

most approximate shape in the atlas library. But if the shape difference of the template

image OARs is too large, the volume is too small or automatically delineated

inappropriate choice of deformation algorithm will affect the registration accuracy [48].

The multi-atlas library can improve the accuracy of delineation, but the amount of

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

calculation increases and the time-consuming increases, so a balance between accuracy

and speed must be balanced.

Automatic delineation based on deep learning does not require the above trade-offs.

Since the key advantage of deep learning is to automatically extract labelled features

through the learning of generalized features in training samples to identify new scenes,

the more input templates, the more accurate the learned features [49]. Dolz et al. [50] gebraucht

the support vector machine (SVM) algorithm to successfully achieve automatic

segmentation of the brainstem on the MRI image of brain tumors, and then used another

deep learning algorithm to segment the optic nerve, optic chiasm, pituitary and small

organs such as pituitary stalk are automatically segmented, and the similarity

coefficient reaches 76-83% [51]. They also used hand-extracted features, combined with

unsupervised stacked denoising autoencoders for brainstem segmentation, and the

classification speed was about 70 times faster than that based on SVM methods,

reducing segmentation time [52]. Liang et al. [53] performed automatic segmentation on

CT images based on deep learning, with a sensitivity of 0.997~1 for automatic

segmentation of most organs, which can effectively improve nasopharyngeal cancer

radiotherapy planning.

Currently, deep learning networks, especially convolutional neural networks

(CNN), have become a common method for medical image analysis [54]. CNN is capable

of processing multi-dimensional and multi-channel data, capturing complex nonlinear

mappings between input and output, with advantages for image processing and

classification. A Stanford University study used a CNN model to automatically segment

head and neck OARs for the first time. In the automatic segmentation of organs such as

bone, pharynx, larynx, eyeball and optic nerve, it is better than or equivalent to the

current best technology. But for organs such as parotid gland, submandibular gland and

optic chiasm whose boundaries are not easy to identify on CT images, the delineated

results are not satisfactory [55]. Lu et al. [56] used a 3D CNN to automatically segment

the liver, combined with a graph cut algorithm to refine the segmentation. Der

advantage is that no manual initialization is required, and the segmentation process can

be performed by non-professionals. Also using 3D CNN for liver segmentation, Hu et

al. [57] combined deep learning with global and local shape prior information, Und

evaluated on the same dataset, and all error indicators were significantly reduced. In einem

follow-up study, the target was extended to abdominal multi-organ segmentation, verwenden

3D CNN to perform pixel-to-pixel dense prediction with higher accuracy and shorter

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

segmentation time [58].

daher, the outline processing of OARs is a complex project, and it is often

difficult to use a set of models to achieve the expected accuracy for different parts of

the body or different modalities. In actual situations, it is necessary to combine specific

factors to make certain improvements to deep neural networks.

4. Therapeutic target segmentation based on deep learning

4.1 GTV automatic delineation

As with normal tissue delineation, deep learning-assisted tumor target delineation

helps improve execution efficiency. Jedoch, since it is often difficult to distinguish

the boundary between the tumor and the surrounding tissue, the clinical information,

pathological sections, and images of the patient will become the reference data for GTV

delineation. Various techniques are used to aid in identification. In the Multimodal

Brain Tumor Image Segmentation Challenge (BraTS) In 2013, Pereira et al. [59] gebraucht

CNN to automatically segment brain tumor MRI images, which improved the network

accuracy and ranked first. Since then, Kamnitsas et al. [60] proposed a dual-channel 3D

CNN network for brain injury (including traumatic brain injury, brain tumor, ischemic

stroke) segmentation, the first time to use fully connected conditional randomization on

medical data. Both of the above studies used neural networks with small convolution

kernels to make the network structure deeper without increasing the computational cost.

Men et al. [61] used big data to train deep dilated residual network (DD-ResNet) für

breast tumor segmentation, and the results were better than deep dilated convolutional

neural networks (DDCNN) and distributed deep neural networks (DDNN), similar to

Dice The dice similarity coefficient (DSC) War 91%, which was higher than the result

hand-drawn by experts [62].

Zusätzlich, for the above-mentioned basic network types, studies have also shown

that the improved network in [63] can improve the accuracy of network segmentation

and has stronger robustness. Lin et al. [64] trained a 3D CNN to delineate the GTV of

nasopharyngeal carcinoma on MRI images, and the similarity with the GTV delineated

by experts was high, with the DSC reaching 79%. With the help of machine learning,

doctors reduced their time by 39.4% and improved their accuracy. 3D CNN not only

utilizes the CT image information of each layer extracted by traditional CNN, but also

utilizes the information between layers, the information utilization rate is high, und das

accuracy is improved to a certain extent. Qi et al. [65] used convolutional neural networks

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

to delineate the target volume of nasopharyngeal carcinoma based on multimodal

Bildgebung (CT and MRI). The results show that the target area is delineated with high

precision. Li et al. [66] used the U-Net to automatically delineate the target volume of

nasopharyngeal carcinoma based on CT images. The results showed that the

segmentation accuracy of the automatically delineated target volume was high. Li et al.

[67] based on the four-dimensional computed tomography data of patients with non-

small cell lung cancer, used transfer learning to automatically delineate the tumor area,

which improved the accuracy and shortened the retraining time of the network. Wann

the breathing range was 5-10 mm, the matching index improved by 36.1% on average

compared with the comprehensive elastic deformation registration technique. In a

recent study [68], the authors used fuzzy c-means clustering (FCM), artificial neural

network（ANN）, and SVM algorithms to automatically segment GTV of solid, Boden-

glass, and mixed lung cancer lesions, jeweils. It is considered that the results of

the FCM model are more accurate and efficient, and can be reliably applied to SBRT.

Delineating GTV based on deep learning can improve the work efficiency of

clinicians, but this method cannot completely replace manual delineation. On the basis

of automatic delineation, manual correction is still required to achieve accurate

delineation effects [69].

4.2 CTV automatic delineation

CTV should be given a certain dose of radiation to the subclinical foci formed by

infiltration around the primary tumor and the path of regional lymph node metastasis

according to the requirements of radiobiology and the factors of tumor occurrence and

metastasis. It is the basis for tumor regional radiotherapy to control recurrence and

metastasis. The delineation needs to be judged in combination with the specific

pathological conditions and the possible invasion or metastasis range of the diseased

tissue, and the delineation results of different types of tumors and different stages are

completely different.

Speziell, Men et al. [70] used a DDCNN model to attempt automatic

segmentation of CTV and OARs in 218 rectal cancer patients, and the results were

accurate and efficient. Among them, the DSC of CTV reaches 87.7%, the DSC of

bladder and bilateral femoral head is more than 90%, and the delineation of small

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

intestine and colon is not accurate enough, and the DSC is 65.3% Und 61.8%,

jeweils. It is possibly related with that they are both air-containing hollow organs.

Based on deep learning with Area-aware reweight strategy and Recursive refinement

strategy, called RA-CTVNet, Shi et al. [71] segment the CTV from cervical cancer CT

Bilder. Their experimental results show that RA-CTVNet improves DSC compared

with different network architectures. Compared with three clinical experts, RA-

CTVNet performed better than the two experts while comparably to the third expert.

Shen et al. [72] modified the U-net model by incorporating the contours of gross tumor

volume of lymph node (GTVnd) and designed the DiUnet model for the automatic

delineation of lung cancer CTV. The results showed that the DSC of most lymph node

regions was up to 70%, which was not significantly different from manual delineation.

Zusätzlich, our team [73] collected CT images of 53 cervical cancer patients. Von

modifying the U-net model and the training process according to the task, the automatic

segmentation of images of cervical cancer CTV region and normal tissue is realized.

By testing the prediction accuracy of the model and the number of required dialogue

rounds, the recall rate, accuracy rate, DSC, Intersection over Union (IoU), usw. of the

results were evaluated. The results show that the proposed model has good performance

in all the indicators outlined in the target area. And compared with commonly used deep

learning neural network models such as mask region-based convolution neural network

(Mask R-CNN), speech enhancement generative adversarial network (SegAN), and U-

net, the segmentation boundary of the proposed model is clearer and smoother, und das

recall rate is obviously better than that of other models. Darüber hinaus, because of its very

light weight, it can be adapted to the dataset size-limited case.

Due to the involvement of subclinical lesions and lymph node drainage areas, CTV

automatic delineation is relatively more difficult, and the performance of deep learning

delineation is still far from that of experts [74-76]. In the future, relying on the disease-

specific big data platform to integrate multimodal radiotherapy data, Bildgebung, genetic

and other multi-omics data, as well as the experience data of senior radiotherapy

physicians, physicists, and technicians, it is expected to be useful in the prediction of

efficacy and complication risk. Guided by the results, individualized CTV range

decisions are provided.

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

5. Abschluss

The research of machine learning methods in the field of radiotherapy has been

fully rolled out and achieved phased results, among which the automatic delineation of

normal tissues and tumor target areas has always been a research hotspot [77-79]. Most

of the existing deep learning models are based on natural images, and there is a lack of

deep learning models dedicated to medical, especially radiation oncology-related

Bilder. The difference between medical images and natural images is that medical

images are grayscale images and generally have continuity [80-81]. In image

segmentation, not only the regional structure of an image, but also the spatial structure

of 3D data must be considered [82]. Zusätzlich, local and global prior information needs

to be considered before it can further contribute to the segmentation of OARs and

therapeutic target volume [83]. Darüber hinaus, multimodal image registration is often

required to further identify the extent of tumor invasion [84-85].

Besides, radiotherapy is one of the links in tumor treatment. How to determine the

appropriate radiotherapy target range and irradiation dose is a complex issue that

requires system integration, such as disease characteristics and overall treatment mode,

even the cross-scale issues from molecular cells to tissues and organs, and the spatio-

temporal relationship of biomolecules and other factors need to be comprehensively

analyzed. So that the radiotherapy plan obtained in this way is more in line with the

principle of precise individualized treatment. The integration of automatic radiotherapy

target delineation with artificial intelligence knowledge maps and causal analysis may

play an important role in the formulation of clinical radiotherapy targets[86].

At present, most of the current applications are in the preclinical research stage, Aber

there are still some problems in clinical application. Erste, high-quality clinical data is

the basis for artificial intelligence to learn and judge, but the current standardization of

relevant medical data for automatic target area delineation is not high. The quality of

labeling is uneven, and the data of major medical centers lack a joint construction and

sharing mechanism. There are data barriers, which seriously hinder the effective use of

data and product development. Zweitens, it is still difficult to accurately define the

treatment target area. Based on the current CT, MRT, PET-CT and other means, es ist

generally not difficult to determine the GTV, but some lesions are still difficult to

identify, such as soft tissue invasion, bone destruction degree and scope, usw. The doses

of CTV are different according to the risk of recurrence and metastasis. There is no

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

relevant research on how to determine high-, medium-, and low-risk CTV. Zusätzlich,

the clinical application of artificial intelligence is directly related to life and health, Und

faces many ethical and legal challenges. Jedoch, the automatic delineation of

radiotherapy target volume based on machine learning will be an important

development direction of artificial intelligence in the medical field in the future.

Danksagungen

This work was financially supported by

1. Scientific Research Project of Anhui Provincial Health Commission (NEIN.

AHWJ2022b058)

2. Joint Fund for Medical Artificial Intelligence of the First Afﬁliated Hospital of

USTC (NEIN. MAI2022Q009)

3. Student Innovation and Entrepreneurship Fund of USTC (NEIN. WK5290000003)

4. China Scholarship Council (NEIN. 202206340057)

Autorenbeiträge

Zhenchao Tao

(zctao@mail.ustc.edu.cn, 0000-0001-8142-9164): Methodik,

Writing – original draft preparation, Akquise von Fördermitteln.

Shengfei Lyu (shengfei.lyu@ntu.edu.sg, 0000-0002-1843-6836): Writing – original

draft preparation, Writing – review and editing.

Reference

1. Sung, H., Ferlay, J,, Siegel, R.L., et al.:. Global Cancer Statistics 2020:

GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in

185 Countries. CA: A Cancer Journal for Clinicians 71(3), 209-249 (2021).

2. Devita, V.T.Jr., Rosenberg, S.A.: Two hundred years of cancer research. The New

England Journal of Medicine 366 (23), 2207-14 (2012).

3. Avanzo, M., Stancanello, J., Pirrone, G., et al.: Radiomics and deep learning in lung

cancer. Strahlentherapie und Onkologie 196(10), 879-887 (2020).

4. Howard, F.M., Kochanny, S., Koshy, M., et al.: Machine Learning-Guided

Adjuvant Treatment of Head and Neck Cancer. JAMA Network Open 3 (11),

e2025881 (2020).

5. Xingyu, W., Zhenchao, T., Bingbing, J., et al.: Domain knowledge-enhanced

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

variable selection for biomedical data analysis, Information Sciences 606, 469-488

(2022).

6. Yang, Z., Olszewski, D., Er, C., et al.: Machine learning and statistical prediction

of patient quality-of-life after prostate radiation therapy. Computers in Biology and

Medicine 129(Feb), 104127 (2021).

7. Schmied, A.G., Petersen, J., Terrones-Campos, C., et al.: RootPainter3D: Interactive-

machine-learning enables rapid and accurate contouring for radiotherapy. Medical

Physik 49(1), 461-473 (2022).

8. Baskar, R., Lee, K.A., Yeo, R., et al.: Cancer and radiation therapy: current

advances and future directions. International Journal of Medical Sciences 9(3), 193-

9 (2012).

9. Zhenchao, T., Jun, Q., Yangyang, Z., et al.: Endostar plus chemoradiotherapy

versus chemoradiotherapy alone for patients with advanced nonsmall cell lung

cancer: A systematic review and meta-analysis. International Journal of Radiation

Forschung 19(1), 1-12 (2021).

10. Coutard, H. Principles of X-ray therapy of malignant disease. The Lancet 224

(5784), 1-4 (1934).

11. Thariat, J., Hannoun-Levi, J.M., Sun-Myint, A., et al.: Past, present, and future of

radiotherapy for the benefit of patients. Nature Reviews Clinical Oncology 10(1),

52-60 (2013).

12. Takahashi, S.: Conformation radiotherapy. Rotation techniques as applied to

radiography and radiotherapy of cancer. Acta Radiologica Diagnosis 242, 11-17

(1965).

13. Chang, J.Y., Senan, S., Paul, M.A. et al.: Stereotactic ablative radiotherapy versus

lobectomy for operable stage I non-small-cell lung cancer: a pooled analysis of two

randomised trials. The Lancet Oncology 16(6), 630-637 (2015).

14. Basson, L., Jarraya, H., Escande, A., et al.: Chest Magnetic Resonance Imaging

Decreases Inter-observer Variability of Gross Target Volume for Lung Tumors.

Frontiers in Oncology 9:690 (2019).

15. Sun, Y., Shi, H., Zhang, S., et al.: Accurate and rapid CT image segmentation of the

eyes and surrounding organs for precise radiotherapy. Medical Physics 46(5), 2214-

2222 (2019).

16. Batra, R., Kuecuekkaya, A., Zeevi, T., et al.: Proof-Of-Concept Use Of Machine

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

Learning To Predict Tumor Recurrence Of Early-Stage Hepatocellular Carcinoma

Before Therapy Using Baseline Magnetic Resonance Imaging. Transplantation

104(S3), S43-S44 (2020).

17. Wong, J., Fong, A., McVicar, N., et al.: Comparing deep learning-based auto-

segmentation of organs at risk and clinical target volumes to expert inter-observer

variability in radiotherapy planning. Radiotherapy And Oncology 144, 152-158

(2020).

18. Men, K., Geng, H., Cheng, C., et al.: Technical Note: More accurate and efficient

segmentation of organs-at-risk in radiotherapy with convolutional neural networks

cascades. Medical Physics 46(1), 286-292 (2019).

19. Fu, Y., Mazur, T.R., Wu, X., et al.: A novel MRI segmentation method using CNN-

based correction network for MRI-guided adaptive radiotherapy. Medical Physics

45(11), 5129-5137 (2018).

20. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Natur 521(7553), 436-444

(2015).

21. Jiang, B., Wu, X., Zhou, X., et al.: Semi-Supervised Multiview Feature Selection

With Adaptive Graph Learning. IEEE Transactions Neural Networks and Learning

Systeme, PP (2022).

22. Li, L., Yan, M., Tao, Z., et al.: Semi-Supervised Graph Pattern Matching and

Rematching for Expert Community Location. ACM Transactions on Knowledge

Discovery from Data (TKDD), (2022).

23. Valdes, G., Simone, C.B., Chen, J., et al.: Clinical decision support of radiotherapy

treatment planning: A data-driven machine learning strategy for patient-specific

dosimetric decision making. Radiother Oncol 125(3), 392-397 (2017).

24. Guo, H.Y., Wang, D.Z.: A Multilevel Optimal Feature Selection and Ensemble

Learning for a Specific CAD System-Pulmonary Nodule Detection. Applied

Mechanics and Materials & Materials 380, 1593-1599 (2013).

25. Zhenyu, L., Chaohong, L., Haiwei, H., et al.: Hierarchical Multi-Granularity

Attention-Based Hybrid Neural Network for Text Classification. IEEE Access

2020(8), 149362-149371 (2020).

26. Zhao, X., Chen, H., Xing, Z., et al.: Brain-Inspired Search Engine Assistant Based

on Knowledge Graph. IEEE Transactions on Neural Networks and Learning

Systeme, PP (2021).

27. Huang, B., Zhu, Y., Usman, M., et al.: Graph Neural Networks for Missing Value

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

Classification in a Task-driven Metric Space. IEEE Transactions on Knowledge and

Data Engineering, (2022).

28. Zhao, X., Chen, L., Chen, H.: A Weighted Heterogeneous Graph-Based Dialog

System. IEEE Trans Neural Netw Learn Syst, PP (2021).

29. Yuan, B., Chen, H., Yao, X.: Toward efficient design space exploration for fault-

tolerant multiprocessor systems. IEEE Transactions on Evolutionary Computation

24(1), 157-169 (2019).

30. Lyu, S., Tian, X., Li, Y., et al.: Multiclass probabilistic classification vector machine.

IEEE Transactions on Neural Networks and Learning Systems 31(10), 3906-3919

(2019).

31. Yu, K., Liu, L., Li, J., et al.: Mining Markov Blankets Without Causal Sufficiency.

IEEE Transactions on Neural Networks and Learning Systems 29(12), 6333-6347

(2018).

32. Rahunathan, S., Stredney, D., Schmalbrock, P., et al.: Image registration using rigid

registration and maximization of mutual information. The 13th Annual Medicine

Meets Virtual Reality Conference, (2005).

33. Viergever, M.A., Maintz, J.B.A., Klein, S., et al.: A survey of medical image

registration – under review. Medical Image Analysis 33, 140-144 (2016).

34. Oliveira, F.P., Tavares, J.M.: Medical image registration: a review. Computer

Methods in Biomechanics & Biomedizintechnik 17(2), 73-93 (2014).

35. Mahapatra, D., Antony, B., Sedai, S., et al.: Deformable medical image registration

using generative adversarial networks. 2018 IEEE 15th International Symposium

on Biomedical Imaging (ISBI 2018). IEEE, 1449-1453 (2018).

36. Kearney, V., Haaf, S., Sudhyadhom, A., et al.: An unsupervised convolutional

neural network-based algorithm for deformable image registration. Physics in

Medicine and Biology 63(18), 185017 (2018).

37. Gu, S., Meng, X., Sciurba, F.C., et al.: Bidirectional elastic image registration using

B-spline affine transformation. Computerized Medical Imaging and Graphics 38(4),

306-314 (2014).

38. Pradhan, S., Patra, D.: RMI based non-rigid image registration using BF-QPSO

optimization and P-spline. AEU-International Journal of Electronics and

Kommunikation 69(3): 609-621 (2015).

39. Wodzinski, M., Skalski, A., Ciepiela, ICH., et al.: Application of demons image

registration algorithms in resected breast cancer lodge localization. 2017 Signal

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

Processing: Algorithms, Architectures, Arrangements, and Applications (SPA),

400-405 (2017).

40. Sokooti, H., Vos, B., Berendsen, F., et al.: Nonrigid image registration using multi-

scale 3D convolutional neural networks. International conference on medical image

computing and computer-assisted intervention. Springer, Cham, 232-239 (2017).

41. Hongming, L., Yong, F.: Non-Rigid Image Registration Using Self-Supervised

Fully Convolutional Networks Without Training Data. IEEE 15th International

Symposium on Biomedical Imaging, 1075-1078 (2018).

42. Rong, Y., Rosu-Bubulac, M., Benedict, SH., et al.: Rigid and Deformable Image

Registration for Radiation Therapy: A Self-Study Evaluation Guide for NRG

Oncology Clinical Trial Participation. Practical Radiation Oncology 11(4), 282-298

(2021).

43. Zhang, T., Yang, Y., Wang, J., et al.: Comparison between atlas and convolutional

neural network based automatic segmentation of multiple organs at risk in non-

small cell lung cancer. Medicine (Baltimore) 99(34), e21800 (2020).

44. Lustberg, T., Soest, J.V., Gooding, M., et al.: Clinical evaluation of atlas and deep

learning based automatic contouring for lung cancer. Radiotherapy and Oncology

126(2), 312-317 (2018).

45. Cabezas, M., Oliver, A., Lladó, X., et al.: A review of atlas-based segmentation for

magnetic resonance brain

Bilder. Computer Methods and Programs

Biomedicine 104(3), e158-77 (2011).

46. Aljabar, P., Heckemann, R.A., Hammers, A., et al.: Multi-atlas based segmentation

of brain images: atlas selection and its effect on accuracy. Neurobild 46(3), 726-

738 (2009).

47. Sharp, G., Fritscher, K.D., Pekar, V., et al.: Vision 20/20: perspectives on automated

image segmentation for radiotherapy. Medical Physics 41(5), 050902 (2014).

48. Valerio, F., René, F.V., Fedde, V.D.L, et al.: Tissue segmentation of head and neck

CT images for treatment planning: a multiatlas approach combined with intensity

modeling. Medical Physics 40(7), 071905 (2013).

49. Li, Y., Zhang, H., Xue, X., et al.: Deep learning for remote sensing image

classification: A survey. Wiley Interdisciplinary Reviews: Data Mining and

Knowledge Discovery 8(6), e1264 (2018).

50. Dolz, J., Laprie, A., Ken, S., et al.: Supervised machine learning-based

classification scheme to segment the brainstem on MRI in multicenter brain tumor

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

treatment context. International Journal of Computer Assisted Radiology Surgery

11(1), 43-51 (2016).

51. Dolz, J., Reyns, N., Betrouni, N., et al.: A deep learning classification scheme based

on augmented-enhanced features to segment organs at risk on the optic region in

brain cancer patients. arXiv preprint arXiv:1703.10480 (2017).

52. Dolz, J., Betrouni, N., Quidet, M., et al.: Stacking denoising auto-encoders in a deep

network to segment the brainstem on MRI in brain cancer patients: A clinical study.

Computerized Medical Imaging and Graphics 52, 8-18 (2016).

53. Liang, S., Tang, F., Huang, X., et al.: Deep-learning-based detection and

segmentation of organs at risk in nasopharyngeal carcinoma computed tomographic

images for radiotherapy planning. European Radiology 29(4), 1961-1967 (2019).

54. Litjens, G., Kooi, T., Bejnordi, B.E., et al.: A survey on deep learning in medical

image analysis. Medical Image Analysis 42, 60-88 (2017).

55. Ibragimov, B., Xing, L.: Segmentation of organs-at-risks in head and neck CT

images using convolutional neural networks. Medical Physics 44(2), 547-557

(2017).

56. Lu, F., Wu, F., Hu, P., et al.: Automatic 3D liver location and segmentation via

convolutional neural network and graph cut. International Journal of Computer

Assisted Radiology Surgery 12(2), 171-182 (2017).

57. Hu, P., Wu, F., Peng, J., et al.: Automatic 3D liver segmentation based on deep

learning and globally optimized surface evolution. Physics in Medicine and Biology

61(24), 8676-8698 (2016).

58. Hu, P., Wu, F., Peng, J., et al.: Automatic abdominal multi-organ segmentation

using deep convolutional neural network and time-implicit level sets. International

Journal of Computer Assisted Radiology Surgery 12(3), 399-411 (2017).

59. Pereira, S., Pinto, A., Alves, V., et al.: Brain Tumor Segmentation Using

Convolutional Neural Networks in MRI Images. IEEE Transactions on Medical

Imaging 35(5), 1240-1251 (2016).

60. Kamnitsas, K., Ledig, C., Newcombe, V.F.J., et al.: Efficient multi-scale 3D CNN

with fully connected CRF for accurate brain lesion segmentation. Medical Image

Analyse 36, 61-78 (2017).

61. Men, K., Zhang, T., Chen, X., et al.: Fully automatic and robust segmentation of

the clinical target volume for radiotherapy of breast cancer using big data and deep

learning. Physica Medica 50, 13-19 (2018).

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

62. Mourik, A.M.V, Elkhuizen, P.H.M., Minkema, D., et al.: Multiinstitutional study

on target volume delineation variation in breast radiotherapy in the presence of

guidelines. Radiotherapy & Oncology 94(3), 286-91 (2010).

63. Oktay, O., Ferrante, E., Kamnitsas, K., et al.: Anatomically Constrained Neural

Netzwerke (ACNNs): Application to Cardiac Image Enhancement and Segmentation.

IEEE Transactions on Medical Imaging 37(2), 384-395 (2018).

64. Lin, L., Dou, Q., Jin, Y.M., et al.: Deep Learning for Automated Contouring of

Primary Tumor Volumes by MRI for Nasopharyngeal Carcinoma. Radiology

291(3), 677-686 (2019).

65. Qi, Y., Li, J., Chen, H., et al.: Computer-aided diagnosis and regional segmentation

of nasopharyngeal carcinoma based on multi-modality medical

Bilder.

International Journal of Computer Assisted Radiology Surgery 16(6), 871-882

(2021).

66. Li, S., Xiao, J., Er, L., et al.: The Tumor Target Segmentation of Nasopharyngeal

Cancer in CT Images Based on Deep Learning Methods. Technology in Cancer

Forschung & Treatment 18:1533033819884561 (2019).

67. Xiadong, L., Ziheng, D., Qinghua, D., et al.: A novel deep learning framework for

internal gross target volume definition from 4D computed tomography of lung

cancer patients. IEEE Access 6, 37775-37783 (2018).

68. Kawata, Y., Arimura, H., Ikushima, K., et al.: Impact of pixel-based machine-

learning techniques on automated frameworks for delineation of gross tumor

volume regions for stereotactic body radiation therapy. Physica Medica 42, 141-

149 (2017).

69. Chen, M., Wu, S., Zhao, W., et al.: Application of deep learning to auto-delineation

of target volumes and organs at risk in radiotherapy. Cancer Radiotherapie 26(3),

494-501 (2022).

70. Men, Kuo., Dai, Jianrong., Li, Yexiong.: Automatic segmentation of the clinical

target volume and organs at risk in the planning CT for rectal cancer using deep

dilated convolutional neural networks. Medical Physics 44(12), 6377-6389 (2017).

71. Shi, J., Ding, X., Liu, X., et al.: Automatic clinical target volume delineation for

cervical cancer in CT images using deep learning. Medical Physics 48(7), 3968-

3981 (2021).

72. Shen, J., Zhang, F., Aus, M., et al.: Clinical target volume automatic segmentation

based on lymph node stations for lung cancer with bulky lump lymph nodes.

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

Thoracic Cancer 13(20), 2897-2903 (2022).

73. Yizhan, F., Zhenchao, T., Jun, L., et al.: An Encoder-Decoder Network for

Automatic Clinical Target Volume Target Segmentation of Cervical Cancer in CT

Images. International Journal of Crowd Science 6(3), 111-116 (2022).

74. Chen, X., Sun, S., Bai, N., et al.: A deep learning-based auto-segmentation system

for organs-at-risk on whole-body computed tomography images for radiation

therapy. Radiotherapy and Oncology 160, 175-184 (2021).

75. Ju, Z., Guo, W., Gu, S., et al.: CT based automatic clinical target volume delineation

using a dense-fully connected convolution network for cervical Cancer radiation

therapy. BMC Cancer 21(1), 1-10 (2021).

76. Unkelbach, J., Bortfeld, T., Cardenas, C.E., et al.: The role of computational

methods for automating and improving clinical target volume definition.

Radiotherapy and Oncology 153, 15-25 (2020).

77. Min, H., Dowling, J., Jameson, M.G., et al.: Automatic radiotherapy delineation

quality assurance on prostate MRI with deep learning in a multicentre clinical trial.

Physics in Medicine Biology 66(19), 195008 (2021).

78. Robert, C., Munoz, A., Moreau, D., et al.: Clinical implementation of deep-learning

based auto-contouring tools-Experience of three French radiotherapy centers.

Cancer Radiotherapie 25(6-7), 607-616 (2021).

79. Piazzese, C., Evans, E., Thomas, B., et al.: FIELDRT: an open-source platform for

the assessment of target volume delineation in radiation therapy. British Journal of

Radiology 94(1126), 20210356 (2021).

80. Ogura, A., Kamakura, A., Kaneko, Y., et al.: Comparison of grayscale and color-

scale renderings of digital medical

images for diagnostic

Deutung.

Radiological Physics and Technology 10(3), 359-363 (2017).

81. Huang, Y., Hu, G., Ji, C., et al.: Glass-cutting medical images via a mechanical

image segmentation method based on crack propagation. Nature Communications

11(1), 5669 (2020).

82. Pizer, S.M., Fletcher, P.T., Joshi, S., et al.: Deformable M-Reps for 3D Medical

Image Segmentation. International Journal of Computer Vision 55(2-3), 85-106

(2003).

83. Mansoor, A., Bagci, U., Foster, B., et al.: Segmentation and Image Analysis of

Abnormal Lungs at CT: Current Approaches, Challenges, and Future Trends.

Radiographics 35(4), 1056-1076 (2015).

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00204

84. Perkuhn, M., Stavrinou, P., Thiele, F., et al.: Clinical Evaluation of a

Multiparametric Deep Learning Model for Glioblastoma Segmentation Using

Heterogeneous Magnetic Resonance Imaging Data From Clinical Routine.

Investigative Radiology 53(11), 647-654 (2018).

85. Li, L., Zhao, X., Lu, W., et al.: Deep Learning for Variational Multimodality Tumor

Segmentation in PET/CT. Neurocomputing 392, 277-295 (2020).

86. Lei, L., Xun, Du., Zan, Zhang., et al.: Fuzzy-Constrained Graph Pattern Matching

in Medical Knowledge Graphs. Datenintelligenz 4(3), 599–619 (2022).

Author biography

Zhenchao Tao received the M.M. degree in oncology from Anhui

Medical University, In 2012, and he is currently pursuing the Ph.D.

degree with University of Science and Technology of China, Hefei. Er

is the deputy chief physician of the Department of Radiation Oncology

at the First Affiliated Hospital of the University of Science and Technology of China.

His research interests mainly include clinical tumor radiation therapy, medical artificial

intelligence, materials science and other directions.

Shengfei Lyu is now a research fellow of Nanyang Technological

Universität (NTU). He received the Ph.D. degree with the School of

Computer Science and Technology, University of Science and

Technology of China (USTC) In 2020. He received the B.Sc. degree in

Information Management and Information Systems from Hefei University of

Technologie (HFUT) In 2015. His research interests include relation extraction, Daten

mining and machine learning.

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
4
2
1
2
9
4
4
2
D
N
_
A
_
0
0
2
0
4
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3 Data Intelligence Just Accepted MS. Bild

PDF Herunterladen