Auto-segmentation of target areas and organs-at-risk for total marrow and lymphoid irradiation in children / 中国医学物理学杂志

Objective To investigate the feasibility of AccuLearning system for the auto-segmentation of target areas and organs-at-risk(OAR)for total marrow and lymphoid irradiation(TMLI)in children.Methods Thirty pediatric patients who underwent TMLI since 2018 to 2022 were selected.The patients were immobilized in the supine position,and their CT images were acquired on the Philips Brilliance Big Bore CT scanner.After the target areas and OAR were manually delineated and modified,the CT images and manually delineated contours were imported into AccuLearning system for training,validation,and testing of the auto-segmentation model.The auto-segmentation results in 6 TMLI patients in the test set were evaluated in terms of Dice similarity coefficient(DSC),95%Hausdorff distance and average surface distance.Results On the test set with 6 cases,except for the lens that was difficult to be delineated automatically,the DSC values was above 0.70 for all other target areas and OAR,with only one patient having a DSC value of 0.59 for the stomach.The average DSC value for the stomach in all 6 patients was 0.76,and the average DSC values for the other organs were above 0.80.Conclusion The target areas and OAR automatically delineated with the model can meet the requirements of clinical planning after simple modifications.

The Effects of Different Adaptive Statistical Iterative Reconstruction-V and Convolution Kernel Parameters on Auto-Segmentation Stability in CT Images / 中国医疗器械杂志

Objective The study aims to investigate the effects of different adaptive statistical iterative reconstruction-V（ ASiR-V） and convolution kernel parameters on stability of CT auto-segmentation which is based on deep learning. Method Twenty patients who have received pelvic radiotherapy were selected and different reconstruction parameters were used to establish CT images dataset. Then structures including three soft tissue organs (bladder, bowelbag, small intestine) and five bone organs (left and right femoral head, left and right femur, pelvic) were segmented automatically by deep learning neural network. Performance was evaluated by dice similarity coefficient（ DSC） and Hausdorff distance, using filter back projection(FBP) as the reference. Results Auto-segmentation of deep learning is greatly affected by ASIR-V, but less affected by convolution kernel, especially in soft tissues. Conclusion The stability of auto-segmentation is affected by parameter selection of reconstruction algorithm. In practical application, it is necessary to find a balance between image quality and segmentation quality, or improve segmentation network to enhance the stability of auto-segmentation.

Segmentation of organs at risk in nasopharyngeal cancer for radiotherapy using a self-adaptive Unet network / 南方医科大学学报

OBJECTIVE@#To investigate the accuracy of automatic segmentation of organs at risk (OARs) in radiotherapy for nasopharyngeal carcinoma (NPC).@*METHODS@#The CT image data of 147 NPC patients with manual segmentation of the OARs were randomized into the training set (115 cases), validation set (12 cases), and the test set (20 cases). An improved network based on three-dimensional (3D) Unet was established (named as AUnet) and its efficiency was improved through end-to-end training. Organ size was introduced as a priori knowledge to improve the performance of the model in convolution kernel size design, which enabled the network to better extract the features of different organs of different sizes. The adaptive histogram equalization algorithm was used to preprocess the input CT images to facilitate contour recognition. The similarity evaluation indexes, including Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD), were calculated to verify the validity of segmentation.@*RESULTS@#DSC and HD of the test dataset were 0.86±0.02 and 4.0±2.0 mm, respectively. No significant difference was found between the results of AUnet and manual segmentation of the OARs (@*CONCLUSIONS@#AUnet, an improved deep learning neural network, is capable of automatic segmentation of the OARs in radiotherapy for NPC based on CT images, and for most organs, the results are comparable to those of manual segmentation.

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.

A dosimetric evaluation of treatment planning based on optimal auto-segmentation / 中华放射肿瘤学杂志

Objective To evaluate the dosimetric errors of organs-at-risk (OARs) induced by the optimal auto-segmentation using Mim Maestro based on dose calculation and measurement.Methods The Mim atlas library composed of 240 nasopharyngeal carcinoma,breast cancer,and rectal cancer patients that were retrospectively selected was used for the auto-segmentation of OARs on the CT images of corresponding regions in 76 patients.Relative to the manual contouring,one optimal case was selected from each site based on conformity index (CI),mean distance to conformity (MDC),relative volume difference (Dv％),DICE,sensitivity index (Se.Idx),and inclusion index (Inc.Idx).Treatment plans were made to satisfy the DVH constraints of OARs based on auto-contours,and then the dose errors to the actual organs were evaluated in terms of calculation and measurement.The paired t-test (normal distribution) or rank sum test (non-normal distribution).Results Significant differences were observed in the 76 patients between the manual and automated segmentation (P＜0.05).For the optimal cases,the DICE index of various OARs ranged from 0.43 to O.98,and 73％(16/22) of DICE values were higher than 0.70.The calculated dose errors to various OARs were (-1.15±15.94)％(95％ CI:-8.21％ to 5.92％) (mean dose) and (-6.53±21.13)％ (95％ CI:-15.90％ to 2.84％) (maximum dose).The measured dose errors were (-2.43± 24.52)％ (95％ CI:-13.30％ to 8.44％)(mean dose) and (-3.38±20.87)％(95％ CI:-12.63％ to 5.87％)(maximum dose).Conclusion Without human interference,even the optimal auto-segmentation results are not clinically acceptable for treatment planning.

Clinical feasibility of atlas-based auto-segmentation software in radiotherapy for cervical cancer / 中华放射肿瘤学杂志

Objective To investigate the time efficiency and accuracy of atlas-based auto-segmentation ( ABAS ) software with different atlas template numbers and layers of computed tomography ( CT ) scans in delineation of the target tissues of cervical cancer patients receiving radiotherapy . Methods The CT images from 20, 40, 60, 80, 100, and 120 patients with cervical cancer were separately selected as atlas templates for MIM auto-segmentation software, and the CT-based tumor volumes of another 20 patients with cervical cancer were manually contoured by physicians. The quality of contours obtained automatically from the software and manual contouring was compared by one-way analysis of variance ( ANOVA ) , randomized block ANOVA, and least significant difference t test. The impact of atlas template numbers and layers of CT scans on the accuracy and time efficiency of MIM software was analyzed based on the time spent in delineation, dice similarity coefficient, and overlap index. Results Taking manual contouring as the reference, no significant differences were observed in the accuracy and time efficiency of auto-contouring when atlas template numbers ranged from 20 to 120(all P>005). The ABAS auto-contouring significantly shortened the time for target contours when the layers of CT scans were less than 65 ( all P>005 ) , but reduced the accuracy of rectal contours (P=0000), while CT scans with 67 layers achieved the highest accuracy of rectal contours ( P= 0037 ) . Conclusions The ABAS software shows an advantage in delineation of the target tissues of cervical cancer patients receiving radiotherapy, and 20 templates are suggested to construct this atlas. The CT scans with 65 layers are recommended for patients when target tissues include the bladder, femur, and spinal cord, and CT scans with 67 layers are recommended for patients when target tissues include the rectum.

Clinical feasibility of atlas-based auto-segmentation software in radiotherapy for cervical cancer / 中华放射肿瘤学杂志

Objective To investigate the time efficiency and accuracy of atlas-based auto-segmentation ( ABAS ) software with different atlas template numbers and layers of computed tomography ( CT ) scans in delineation of the target tissues of cervical cancer patients receiving radiotherapy . Methods The CT images from 20, 40, 60, 80, 100, and 120 patients with cervical cancer were separately selected as atlas templates for MIM auto-segmentation software, and the CT-based tumor volumes of another 20 patients with cervical cancer were manually contoured by physicians. The quality of contours obtained automatically from the software and manual contouring was compared by one-way analysis of variance ( ANOVA ) , randomized block ANOVA, and least significant difference t test. The impact of atlas template numbers and layers of CT scans on the accuracy and time efficiency of MIM software was analyzed based on the time spent in delineation, dice similarity coefficient, and overlap index. Results Taking manual contouring as the reference, no significant differences were observed in the accuracy and time efficiency of auto-contouring when atlas template numbers ranged from 20 to 120(all P>005). The ABAS auto-contouring significantly shortened the time for target contours when the layers of CT scans were less than 65 ( all P>005 ) , but reduced the accuracy of rectal contours (P=0000), while CT scans with 67 layers achieved the highest accuracy of rectal contours ( P= 0037 ) . Conclusions The ABAS software shows an advantage in delineation of the target tissues of cervical cancer patients receiving radiotherapy, and 20 templates are suggested to construct this atlas. The CT scans with 65 layers are recommended for patients when target tissues include the bladder, femur, and spinal cord, and CT scans with 67 layers are recommended for patients when target tissues include the rectum.

Commissioning of an atlas-based auto-segmentation software for application in organ contouring of radiotherapy planning / 中华放射肿瘤学杂志

Objective To perform a preclinical test of a delineation software based on atlas-based auto-segmentation (ABAS),to evaluate its accuracy in the delineation of organs at risk (OARs) in radiotherapy planning for nasopharyngeal carcinoma (NPC),and to provide a basis for its clinical application.Methods Using OARs manually contoured by physicians on planning-CT images of 22 patients with NPC as the standard,the automatic delineation using two different algorithms (general and head/neck) of the ABAS software were applied to the following tests:(1) to evaluate the restoration of the atlas by the software,automatic delineation was performed on copied images from each patient using the contours of OARs manually delineated on the original images as atlases;(2) to evaluate the accuracy of automatic delineation on images from various patients using a single atlas,the contours manually delineated on images from one patients were used as atlases for automatic delineation of OARs on images from other patients.Dice similarity coefficient (DSC),volume difference (Vdiff),correlation between the DSC and the volume of OARs,and efficiency difference between manual delineation and automatic delineation plus manual modification were used as indices for evaluation.Wilcoxon signed rank test and Spearman correlation analysis were used.Results The head/neck algorithm had superior restoration of the atlas over the general algorithm.The DSC was positively correlated with the volume of OARs and was higher than 0.8 for OARs larger than 1 cc in volume in the restoration test.For automatic delineation with the head/neck algorithm using a single atlas,the mean DSC and Vdiff were 0.81-0.90 and 2.73％-16.02％,respectively,for the brain stem,temporal lobes,parotids,and mandible,while the mean DSC was 0.45-0.49 for the temporomandibular joint and optic chiasm.Compared with manual delineation,automatic delineation plus manual modification saved 68％ of the time.Conclusions A preclinical test is able to determine the accuracy and conditions of the ABAS software in specific clinical application.The tested software can help to improve the efficiency of OAR delineation in radiotherapy planning for NPC.However,it is not suitable for delineation of OAR with a relatively small volume.