ABSTRACT
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.
Subject(s)
Humans , Algorithms , Image Processing, Computer-Assisted , Neural Networks, Computer , Radiation Dosage , Tomography, X-Ray ComputedABSTRACT
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.
Subject(s)
Image Processing, Computer-Assisted , Radiotherapy/trends , Radiotherapy Planning, Computer-Assisted , Technology , Tomography, X-Ray ComputedABSTRACT
Objective To evaluate the geometric and dosimetric accuracy of autosegmentation software for contouring the organ-at-risk ( OAR) of esophageal cancer, and discuss its clinical feasibility. Methods A total of 10 patients were enrolled, and single and multi-template were adopted respectively to auto-delineate corresponding OARs on target CT images based on image registration. The geometric consistency including volume difference (ΔV) , dice similarity ( DSC) and position difference (Δx, Δy,Δz) between the two autosegmentation method and manual were compared using Wilcoxon signed-rank test. And the correlation between DSC and OAR volume was analyzed. In addition, to evaluate the clinical feasibility of autosegmentation, the dose distributions of all OARs were compared using Friedman test. Results The average DSC of all OARs obtained by single and multi-template were 0.82 ± 0.17 and 0.92 ± 0.54, respectively, with statistically significant difference (Z= -2.803- -2.497, P<0.05). A positive correlation between DSC of the autosegmentation and OAR volume was found by spearman analysis, and the single-template was not good enough for the spinal cord with smaller volume. The positional deviations of multi-template group were less than 0.5 cm in three directions, which were better than single-template group. The main dosimetric indexes of single-template and multiple-template were similar to manual coutours. V20 of whole lung were 23.2％, 22.4％ and 22.1％, Dmeanof whole lung were (11.3 ±4.0), (11.1 ±4.5) and (11.0 ±4.3) Gy, Dmaxof spinal cord were (40.3 ±4.8), (38.2 ±6.7) and (39.4 ± 5.3) Gy, respectively, and V30 of heart were 16.0％, 15.8％ and 15.5％, respectively. There was no statistical difference between the three methods (P>0.05), and all of the dosimetric indexes were in line with the requirements of clinical dose limits. Conclusions The autosegmentation software can achieve satisfactory precision for the OARs of the esophageal cancer patients, and the multi-template method is better than the single-template, which is more suitable for clinical application.
ABSTRACT
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.
ABSTRACT
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.
ABSTRACT
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.
ABSTRACT
PURPOSE: To evaluate the effect of repeated intravitreal injections of anti-vascular endothelial growth factor (anti-VEGF) on the thickness of the ganglion cell layer (GCL) in patients with retinal vein occlusion. METHODS: The present retrospective study included 60 patients with branch retinal vein occlusion and central retinal vein occlusion who received more than 3 anti-VEGF injections. GCL thickness was measured using spectral-domain optical coherence tomography. GCL thickness measurements were made at 9 Early Treatment Diabetic Retinopathy Study grid regions. We evaluated correlations between changes in the GCL thickness and other factors such as intraocular pressure, times of injection, and changes in central macular thickness (CMT). RESULTS: As a result of multiple intravitreal anti-VEGF treatments, GCL thickness was significantly decreased from 42.99 +/- 5.39 to 38.99 +/- 5.53 (p < 0.001). Changes in GCL thickness were correlated with CMT and the number of injections (p = 0.02 and p = 0.048, respectively). However, multivariate analysis showed the change in mean GCL thickness in the retinal vein occlusion (RVO) was strongly associated only with CMT (p < 0.001). CONCLUSIONS: As a result of multiple intravitreal injections of anti-VEGF, GCL thickness decreased significantly in RVO patients and changes in GCL thickness and CMT were correlated.
Subject(s)
Humans , Diabetic Retinopathy , Endothelial Growth Factors , Ganglion Cysts , Intraocular Pressure , Intravitreal Injections , Multivariate Analysis , Retinal Vein Occlusion , Retinal Vein , Retinaldehyde , Retrospective Studies , Tomography, Optical CoherenceABSTRACT
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.