Research on multi-Atlas segmentation based on feature clustering / 中华放射肿瘤学杂志

Objective:To study the improvement of normal tissue region of interest (ROI) segmentation based on clustering-based multi-Atlas segmentation method, thereby achieving better delineation of organs at risk.Methods:CT images of 100 patients with cervical cancer who had completed treatment in Zhejiang Cancer Hospital during 2019-2020 were selected as the Atlas database. According to the volume characteristic parameters of the organs at risk (bladder, rectum and outer contour), the Atlas database was divided into several subsets by k-means clustering algorithm. The image to be segmented was matched to the corresponding Atlas library for multi-Atlas segmentation. The dice similarity coefficient (DSC) was used to evaluate the segmentation results.Results:Using 30 patients as the test set, the sub-Atlas generated by different clustering methods were compared for the improvement of image segmentation results. Compared with general multi-Atlas segmentation methods, clustering-based multi-Atlas segmentation method significantly improve the segmentation accuracy for the bladder (DSC=0.83±0.09 vs. 0.69±0.15, P<0.001) and the rectum (0.7±0.07 vs. 0.56±0.16, P<0.001), but no statistical significance was observed for left and right femoral head (0.92±0.04, 0.91±0.02) and bone marrow (0.91±0.06). The average segmentation time of clustering-based multi-Atlas segmentation method was shorter than that of the general multi-Atlas segmentation method (2.7 min vs. 6.3 min). Conclusion:The clustering-based multi-Atlas segmentation method can not only reduce the number of Atlas images registered with the image to be segmented, but also can be expected to improve the segmentation effect and obtain higher accuracy.

Automatic-delineation model construction for prostate cancer target volume of postoperative radiotherapy based on artificial intelligence / 中华放射肿瘤学杂志

Objective:To explore the method of constructing automatic delineation model for clinical target volume (CTV) and partially organs at risk (OAR) of postoperative radiotherapy for prostate cancer based on convolutional neural network, aiming to improve the clinical work efficiency and the unity of target area delineation.Methods:Postoperative CT data of 117 prostate cancer patients manually delineated by one experienced clinician were retrospectively analyzed. A multi-class auto-delineation model was designed based on 3D UNet. Dice similarity coefficient (DSC), 95% Hausdorf distance (95%HD), and average surface distance (ASD) were used to evaluate the segmentation ability of the model. In addition, the segmentation results in the test set were evaluated by two senior physicians. And the CT data of 78 patients treated by other physicians were also collected for external validation of the model. The automatic segmentation of these 78 patients by CTV-UNet model was also evaluated by two physicians.Results:The mean DSC for tumor bed area (CTV1), pelvic lymph node drainage area (CTV2), bladder and rectum of CVT-UNet auto-segmentation model in the test set were 0.74, 0.82, 0.94 and 0.79, respectively. Both physicians' scoring results of the test set and the external validation showed more consensus on the delineation of CTV2 and OAR. However, the consensus of CTV1 delineation was less.Conclusions:The automatic delineation model based on convolutional neural network is feasible for CTV and related OAR of postoperative radiotherapy for prostate cancer. The automatic segmentation ability of tumor bed area still needs to be improved.

Application of 3D ResSE-Unet-based intelligent delineation of clinical target volume in postoperative radiotherapy for breast cancer / 中华放射医学与防护杂志

Objective:To evaluate the effectiveness and feasibility of 3D ResSE-Unet-based intelligent delineation of clinical target volume (CTV) in postoperative adjuvant radiotherapy for breast cancer.Methods:A total of 974 cases of breast cancer treated in the Cancer Diagnosis and Treatment Center of the Fourth Affiliated Hospital of Guangxi Medical University from September 2018 to June 2022 were enrolled in this study, including 614 cases receiving total mastectomy and 360 cases treated with breast-conserving surgery. They were divided into a training set, a validation set, and a testing set. The training set consisted of 874 cases and was used to build a model of 3D ResSE-Unet-based intelligent CTV delineation. The validation set comprised 40 cases and was used to evaluate the feasibility and effectiveness of the clinical application of AI-based CTV design in the radiotherapy for breast cancer. The testing set was composed of 60 cases and was used to test the accuracy of intelligent CTV. The Wilcoxon rank test was used to compare the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) obtained using the intelligent delineation model.Results:The intelligent delineation model showed high precision. The CTV of cases treated with total mastectomy (CTV cw) and the CTV of cases treated with breast-conserving surgery (CTV b) had DSCs greater than 0.80 and greater than 0.88, respectively. Therefore, compared with CTV cw, CTV b had a higher DSC (0.91 ± 0.03 vs.0.83 ± 0.05, t = 7.11, P < 0.05). Both CTV cw and CTV b had lower HD 95 [(7.56 ± 3.42) mm vs.(8.77 ± 5.89) mm] and ASD [(1.85 ± 0.71) mm vs.(1.86 ± 0.83)mm], without statistically significant difference ( P > 0.05). The left/right supraclavicular and infraclavicular CTV (CTV2) had DSCs greater than 0.8. CTV2 also had low average HD95 and ASD, without statistically significant difference ( P > 0.05). Conclusions:The 3D ResSE-Unet-based intelligent CTV delineation has better consistency and feasibility in postoperative adjuvant radiotherapy for breast cancer, especially the CTVs after breast-conserving surgery.

Application of artificial intelligence in the target delineation of radiotherapy / 国际肿瘤学杂志

Artificial intelligence is the use of computer algorithms to copy or simulate human behavior, giving machines human-like ability. With the rapid development of radiotherapy technology, artificial intelligence has great potential value in all stages of radiotherapy. Image segmentation is the premise of target delineation using artificial intelligence. The commonly used methods in clinic mainly include automatic segmentation based on deep learning and atlas library. The technology of artificial intelligence in organs at risk delineation is relatively mature, which can significantly shorten the delineation time and improve the efficiency. The delineation of tumor targets has achieved some success, the accuracy still needs to be further improved. Artificial intelligence technology makes the target delineation more and more efficient, and the consistency and repeatability have been significantly improved. It is expected to provide more accurate and individualized treatment for patients.

Advances in application of CT/MR and PET/MR for target delineation in glioma / 中华放射肿瘤学杂志

Glioma is the most common central nervous system tumor, mainly derived from the interstitial cells of the nervous system, showing diffuse and infiltrative growth, with the characteristics of high morbidity, high postoperative recurrence, high mortality and low cure rate. Currently, radical resection followed by radiotherapy and chemotherapy is the first choice of treatment. Accurate delineation of GTV-T is of significance for precision radiotherapy after surgery. In addition, CT/MR fusion imaging has been commonly used in the delineation of tumor targets in glioma. In recent years, PET/MR has been more and more widely applied in tumors. In this article, the application and differences between PET/MR and CT/MR for target delineation in glioma were reviewed.

Progress on delineation of clinical target volume of primary tumour of nasopharyngeal carcinoma / 中华放射肿瘤学杂志

Accurate delineation of clinical target volume (CTV) of nasopharyngeal carcinoma is of significance to prevent local recurrence and improve the survival rate of patients. When intensity-modulated radiotherapy (IMRT) was first introduced, CTV was delineated based on two-dimensional radiotherapy experience. The local recurrence-free survival is high, but the adverse reactions induced by radiotherapy are severe and the patients’ quality of life is poor. How to reduce CTV to alleviate acute and late radiotherapy-induced adverse reactions without deteriorating therapeutic effect has currently become a research hotspot. Despite the 2010 Chinese Nasopharyngeal Carcinoma IMRT Target and Dose Design Guideline Expert Consensus and the International Guideline for the Delineation of the CTV for Nasopharyngeal Carcinoma as references, the optimal individualized and standardized delineation of CTV remains controversial. This review summarizes the progress on the delineation of CTV of primary tumour of nasopharyngeal carcinoma, aiming to provide practical reference for clinicians.

Study of level Ⅴmetastasis of nasopharyngeal carcinoma based on 2013 updated consensus guidelines of the neck node levels / 中华放射肿瘤学杂志

Objective:According to 2013 updated consensus guidelines of neck node levels, the distribution characteristics of cervical lymph nodes of nasopharyngeal carcinoma (NPC) were analyzed, aiming to provide preliminary reference for the clinical target volume (CTV) delineation of level Ⅴ in NPC.Methods:A total of 1110 patients pathologically diagnosed with NPC from 2012 to 2020 were retrospectively recruited for further analysis. All patients’ MRI and contrast-enhanced CT simulation scan imageswere retrospectively reviewed, metastatic lymph nodes were mapped using the 2013 International Consensus Guidelines. Then, the correlation between Ⅴa, Ⅴb and Ⅴc metastatic lymph nodes and other lymph nodes was analyzed. An NPC case diagnosed with T 1N 0M 0 was selected as the baseline standard for the normal anatomical structure and proportion of Ⅴc area. The metastatic lymph nodes in Vc were delineated on the CT simulation scan image of sample case, and the distribution characteristics of the metastatic lymph nodes inⅤc were analyzed. Results:Among the 1110 patients, 1004(90.5%) patients had lymph node metastases. The most common area of metastatic lymph node levels were level Ⅶa (74.7%) and level Ⅱb(70.7%), and the skip metastasis of lymph nodes was rare (1.0%). The multivariate analysis showed lymph node metastasis in level Va was correlated with levels Ⅱb, Ⅲ, Ⅳa, Ⅴb, and Ⅷ region ( P=0.010, 0.001, 0.001, 0.001, 0.037). Lymph node metastasis in level Ⅴb was correlated with levels Ⅲ, Ⅳa, Ⅴa and Ⅴc region ( P=0.006, 0.001, 0.001, 0.001). Lymph node metastasis in level Ⅴc was correlated with levels Ⅳb and Ⅴb region ( P=0.008, 0.001). There were 28 cases of lymph node metastasis in levelⅤc. A total of 38 metastatic lymph nodes were counted in level Vc. Among them, 33(86.8%) lymph nodes were located in the medial of the omohyoid muscle (Ⅴc-1 region), and 5(13.2%) were located in the lateral of the omohyoid muscle (Ⅴc-2 region). Conclusions:This study reflects the principle of individualized CTV delineation, which is based on the levels of nodal spread in NPC patients. When correlation is observed among different level V, V should be delineated as the moderate risk lymphatic drainage (CTV n2). It is recommended to individualized delineate level Vc when the CTV n2 covers Vc. The Ⅴc-2 region should be delineated as CTV n2 only when there is nodal spread in the ipsilateral Ⅴc-1 region.

Chemotherapeutic nanomaterials in tumor boundary delineation: Prospects for effective tumor treatment

Accurately delineating tumor boundaries is key to predicting survival rates of cancer patients and assessing response of tumor microenvironment to various therapeutic techniques such as chemotherapy and radiotherapy. This review discusses various strategies that have been deployed to accurately delineate tumor boundaries with particular emphasis on the potential of chemotherapeutic nanomaterials in tumor boundary delineation. It also compiles the types of tumors that have been successfully delineated by currently available strategies. Finally, the challenges that still abound in accurate tumor boundary delineation are presented alongside possible perspective strategies to either ameliorate or solve the problems. It is expected that the information communicated herein will form the first compendious baseline information on tumor boundary delineation with chemotherapeutic nanomaterials and provide useful insights into future possible paths to advancing current available tumor boundary delineation approaches to achieve efficacious tumor therapy.

Research on automatic delineation of nasopharyngeal carcinoma target area based on generative adversarial network / 中华放射肿瘤学杂志

Objective:To propose a deep learning network model 2D-PE-GAN to automatically delineate the target area of nasopharyngeal carcinoma and improve the efficiency of target area delineation.Methods:The model adopted the architecture of generative adversarial networks which used a UNet similar structure as the generator, and 2D-PE-block was added after each layer of convolution operation of the generator to improve the accuracy of delineation. The experimental data included CT images from 130 cases of nasopharyngeal carcinoma. The images were preprocessed before model training. In addition, three models of UNet, GAN, and GAN with an attention mechanism were compared, and Dice similarity coefficient, Hausdorff distance, accuracy, Matthews correlation coefficient, Jaccard distance were employed to evaluate network performance.Results:Compared with UNet, GAN and GAN with the attention mechanism, the average Dice similarity coefficient of 2D-PE-GAN network segmentation of CTV was increased by 26%, 4% and 2%. The average Dice similarity coefficient of GTV segmentation was increased by 21%, 4%, 2%, respectively. Compared with the GAN network with the attention mechanism, the parameters and time of 2D-PE-GAN were reduced by 0.16% and 18%, respectively.Conclusions:Compared with the above three networks, 2D-PE-GAN network can increase the segmentation accuracy of nasopharyngeal carcinoma target area delineation. At the same time, compared with the attention mechanism with similar reasons, 2D-PE-GAN network can reduce the occupation of computing resources when the segmentation accuracy is not much different.

Comparison of different delineation methods of clinical target volume of internal mammary lymph node for patients after internal mammary lymph node dissection / 中华放射肿瘤学杂志

Objective:To compare the differences of postoperative clinical target volume of internal mammary lymph node (CTV ImlN) by different delineation methods, and to explore the reasonable method of CTV ImlN delineation after internal mammary lymph node dissection (ImlND). Methods:A total of 20 breast cancer patients who had undergone modified radical mastectomy (MRM) with ImlND on the affected side and had complete preoperative and postoperative CT images were selected. The CTV (CTV pr-I, CTV pr-a) of both sides of ImlN were delineated on preoperative CT images according to RTOG guideline. On postoperative CT images, three different methods including deformation image registration (DIR) method, visual contrast method and precise measurement method, were employed to delineate the postoperative CTV ImlN of the affected side. The targets were named as CTV DIR, CTV V and CTV M, respectively. The central displacement, target volume, degree of inclusion (DI) and conformity index (CI) of CTV pr-a, CTV V, CTV M and CTV DIR were compared. Results:The central displacement of CTV V, CTV M and CTV DIR from CTV pr-a was 2.17 cm, 1.44 cm and 1.25 cm, respectively. The target volume of CTV pr-a, CTV pr-I, CTV V, CTV M and CTV DIR was 2.10 cm 3, 2.17 cm 3, 2.04 cm 3, 1.88 cm 3 and 2.07 cm 3 respectively. There was no significant difference in the target volume (all P>0.05). The CI values of CTV V-CTV pr-a and CTV M-CTV pr-a were both 0.16, and that of CTV DIR-CTV pr-a was 0.43. The CI value of CTV DIR was significantly higher than those of CTV V and CTV M (both P<0.01). The DI values of CTV V-CTV pr-a, CTV M-CTV pr-a and CTV DIR-CTV pr-a were 0.26, 0.24 and 0.58, respectively. The DI value of CTV DIR was significantly higher than those of CTV V and CTV M (both P<0.01). Conclusions:It is difficult to accurately delineate the CTV ImlN for patients after ImlND. However, the spatial position fitness of the target region delineated by DIR method is better than those by visual contrast and precise measurement methods.

Value of MRI T 2WI-TSE-BLADE sequence in accurately delineating the gross tumor volume of esophageal carcinoma based on pathological specimens / 中华放射肿瘤学杂志

Objective:To explore the value of BLADE sequence in determining the target range of esophageal cancer radiotherapy through the correlation and consistency between measured esophageal cancer length on the MRI-BLADE sequence and the surgical pathological specimens.Methods:Clinical data of 36 patients who were pathologically diagnosed with esophageal carcinoma and received preoperative esophageal MRI in the Affiliated Cancer Hospital of Zhengzhou University between January 2016 to June 2019 were collected. The CT, DWI and BLADE sequence images of all participants were collected and imported into the Monaco system, by which the correlation and consistency between the tumor length measured based on these three imaging methods were statistically compared. Furthermore, the differences in gross tumor volume (GTV) delineated by different physicians in different images were compared.Results:The correlation coefficients of the tumor length measured by CT, DWI and BLADE and pathological specimen length were 0.467, 0.723 and 0.896, respectively. The consistency analysis indicated that all the differences between the BLADE sequence and pathological specimen length were within the 95% consistency limit. The consistency and correlation between the BLADE sequence and actual tumor length were significantly better than those between the DWI sequence and CT images (both P<0.05). The volume of DWI and BLADE images obtained by four physicians was significantly smaller than that of CT images (both P<0.05). The differences in GTV delineated by different physicians by these three imaging methods were insignificant (all P>0.05), but the GTV delineated by the four physicians on the BLADE sequence were more similar (all P>0.05). Conclusions:BLADE sequence can help physicians to determine the upper and lower boundaries of esophageal tumors more accurately and reduce the differences in GTV delineation among different physicians. And it can effectively improve the unity of individual′s understanding of the scope of target area delineation, and improve the objectivity of clinicians′ judgment of GTV. BLADE sequence can be used as an important imaging tool for accurate target delineation in radiotherapy.

Advances in bowel delineation and dose-volume constraint in intensity modulated radiation therapy and 3D conformal radiation therapy for pelvic tumors / 中华放射医学与防护杂志

Intestinal injury is an important toxic response during radiation therapy of pelvic tumors. With the widespread use of precision radiotherapy techniques such as intensity modulated radiation therapy (IMRT), the dose exposed to normal tissues and organs has been significantly reduced. However, the toxic response of the bowel still limits the increase of the dose to the target volume. Therefore, the protection of important organs at risk (OAR), such as the bowel, becomes more and more important while giving adequate irradiated dose to the target volume. Most current studies used loop to contour bowel. For patients who underwent IMRT, the meaningful dose-volume predictors of grade 2 acute intestinal adverse events using bowel loop (small loop + big bowel) delineation included V45 Gy < 50 cm 3,V50 Gy < 13 cm 3, and V55 Gy < 3 cm 3, and the corresponding predicators using bowel bag delineation were V40 Gy < 170 cm 3,V45 Gy < 100 cm 3, and V50 Gy < 33 cm 3.

Comparison of the automatic delineation of two kinds of stomach by the AccuContour software for patients with thoracic and abdominal tumors / 中国辐射卫生

Objective To delineate the normal stomach and thoracic stomach structure of patients with thoracic and abdominal tumor automatically using the AccuContour software based on deep learning in order to evaluate and compare the results. Methods Thirty-six patients with choracic and abdominal tumors were chosen for this study, and were divided into two groups. Group A included 18 patients with normal stomach, and group B included the other 18 patients undergoing esophageal carcinoma operation with thoracic stomach. The stomach structures were automatically delineated by the AccuContour software in the simulation CT series. Statistical analysis was carried out to data of the differences in volume, position and shape between the automatic and manual delineations, and data of the two kinds of stomach were compared. Results For group A, the differences in volume (ΔV%) between the automatic and manual delineations was (−1.82 ± 9.65)%, the total position difference (ΔL) was (0.51 ± 0.37) cm, the values of dice similarity coefficient (DSC) was 0.89 ± 0.04. There were significant differences in values of ΔV%、ΔL and DSC (P < 0.05). Conclusion The used version of AccuContour software in this study had a satisfactory result of automatic delineation of the normal stomach structure larger than certain volume, but could not delineate the thoracic stomach structures effectively for patients undergoing esophageal carcinoma operation.

A fusion network model based on limited training samples for the automatic segmentation of pelvic endangered organs / 生物医学工程学杂志

When applying deep learning to the automatic segmentation of organs at risk in medical images, we combine two network models of Dense Net and V-Net to develop a Dense V-network for automatic segmentation of three-dimensional computed tomography (CT) images, in order to solve the problems of degradation and gradient disappearance of three-dimensional convolutional neural networks optimization as training samples are insufficient. This algorithm is applied to the delineation of pelvic endangered organs and we take three representative evaluation parameters to quantitatively evaluate the segmentation effect. The clinical result showed that the Dice similarity coefficient values of the bladder, small intestine, rectum, femoral head and spinal cord were all above 0.87 (average was 0.9); Jaccard distance of these were within 2.3 (average was 0.18). Except for the small intestine, the Hausdorff distance of other organs were less than 0.9 cm (average was 0.62 cm). The Dense V-Network has been proven to achieve the accurate segmentation of pelvic endangered organs.

Application and Development Trend of Medical Image Automatic Segmentation Technology in Radiation Therapy / 中国医疗器械杂志

The development of medical image segmentation technology has been briefly reviewed. The applications of auto-segmentation of organs at risk and target volumes based on Atlas and deep learning in the field of radiotherapy have been introduced in detail, respectively. Then the development direction and product model for general automatic sketching tools or systems based on solid clinical data are discussed.

Automated Pre-delineation of CTV in Patients with Cervical Cancer Using Dense V-Net / 中国医疗器械杂志

We use a dense and fully connected convolutional network with good feature learning in small samples, to automatically pre-deline CTV of cervical cancer patients based on CT images and evaluate the effect. The CT data of stage IB and IIA postoperative cervical cancer with similar delineation scope were selected to be used to evaluate the pre-sketching accuracy from three aspects:sketching similarity, sketching offset and sketching volume difference. It has been proved that the 8 most representative parameters are superior to those with single network and reported internationally before. Dense V-Net can accurately predict CTV pre-delineation of cervical cancer patients, which can be used clinically after simple modification by doctors.

Delineation of groundwater potential zones utilising geospatial techniques in Kadiri watershed of Anantapur district, Andhra Pradesh, India

Aim: The objective of the study was to analyse and to identify the groundwater prospect zones (GWPZ) by developing groundwater potential zone map for Kadiri watershed of Anantapur district in Andhra Pradesh, India. Methodology: Nine thematic layers were generated, i.e., geology, geomorphology, soil texture, soil depth, drainage density, slope, rainfall, lineament density and land use land cover of the study area, and based on multi criteria analysis (MCA) method revised ratings and weights were computed from interrelationship among the influencing layers. Integration of all thematic layers was done through weighted overlay technique (WOT) for developing groundwater potential zone map of the study area using GIS software. Results: Five groundwater potential zones (GWPZ) were identified in the study area ranging from very poor to very good. According to the classification of GWPZ, 7.14% (36.95 sq.km) and 39.88 % (206.31 sq.km) of the study area falls under 'very good' and 'good' groundwater potential zone whereas 30.81 % of study area, i.e., 159.35 sq.km accounts for moderate groundwater prospect. It was also observed that 17.77% (91.9 sq.km) and 4.40% (22.77 sq.km) accounts for 'poor' and 'very poor' groundwater potential zone in the study area, respectively. The major portion of good groundwater potential zone was found in the eastern part of the study area. Interpretation: The research outcome of the present study on status of groundwater availability will be helpful to the stake holders, local administration and policy makers in framing the guidelines for better planning, utilization and rejuvenation of depleting groundwater resources for sustainable development in the study area.

Research on modes and methods of radiotherapy teaching centering on target delineation / 中华医学教育探索杂志

Target delineation is the key and difficult point in radiation oncology teaching. Combined with the teaching experience in department of cancer radio-chemotherapy, Zhongnan hospital of Wuhan university, this study focused on target delineation to explore the teaching mode and method of radiation oncology. Self-directed learning was combined with teacher's lecturing and guiding. By enhancing tumor imaging teaching and basic theory of tumor radiotherapy, students can grasp the essence and detail of target delineation and build individualized and precise radiotherapy. Finally, a new teaching mode combining students' autonomous learning with teachers' teaching and guide is established. Taking the radiation therapy of breast cancer as an example, We briefly described the concrete application of this teaching system.

Research progress on target delineation for radiotherapy in hepatocellular carcinoma with / 中华放射肿瘤学杂志

Modern medical imaging techniques,such as computed tomorgraphy (CT),magnetic resonance imaging (MRI) and position emission tomorgraphy/computed tomorgraphy (PET-CT) can accurately delineate the gross target volume (GTV) of hepatocellular carcinoma (HCC).Comparison of postoperative pathological subclinical lesions,imaging and clinical parameters contributes to the precise delineation of clinical target volume (CTV).Moreover,radiotherapy-assisted techniques,such as fourdimensional computed tomography (4DCT),compression of abdomen,active breathing control and respiratory gating,can minimize the internal target volume (ITV).In addition,immobilization with vacuum cushion and body membrane can reduce the set-up error,minimize the planning target volume (PTV) and avoid or decrease the irradiation error or missing irradiation.All these approach can minimize the target volume,elevate the dose and reduce the complications during radiotherapy for HCC.In this article,the research progress on the target delineation for external beam radiotherapy in HCC patients was reviewed.

The role of magnetic resonance imaging in radiation therapy for breast cancer / 中华放射肿瘤学杂志

In recent years,along with the clinical exploration and application of magnetic resonance simulation localization and radiotherapy equipment,more and more studies have been performed to focus on the excellent ability of MRI in identifying soft tissues,aiming to explore the potential application value of magnetic resonance imaging (MRI) in radiotherapy for breast cancer patients.In this article,the research progress on MRI in radiotherapy after breast-conserving surgery was reviewed to provide certain ideas and references for subsequent research.