scholarly journals The Dosimetric Impact of Deep Learning-Based Auto-Segmentation of Organs at Risk on Nasopharyngeal and Rectal Cancer

Author(s):  
Hongbo Guo ◽  
Jiazhou Wang ◽  
Xiang Xia ◽  
Yang Zhong ◽  
Jiayuan Peng ◽  
...  

Abstract PurposeTo investigate the dosimetric impact of deep learning-based auto-segmentation of organs at risk (OARs) on nasopharyngeal and rectal cancer.Methods and MaterialsTwenty patients, including ten nasopharyngeal carcinoma (NPC) patients and ten rectal cancer patients, who received radiotherapy in our department were enrolled in this study. Two deep learning-based auto-segmentation systems, including an in-house developed system (FD) and a commercial product (UIH), were used to generate two auto-segmented OARs sets (OAR_FD and OAR_UIH). Treatment plans based on auto-segmented OARs and following our clinical requirements were generated for each patient on each OARs set (Plan_FD and Plan_UIH). Geometric metrics (Hausdorff distance (HD), mean distance to agreement (MDA), the Dice similarity coefficient (DICE) and the Jaccard index) were calculated for geometric evaluation. The dosimetric impact was evaluated by comparing Plan_FD and Plan_UIH to original clinically approved plans (Plan_Manual) with dose-volume indices and 3D gamma pass rates. Spearman’s correlation analysis was performed to investigate the correlation between dosimetric deviation and geometric metrics.ResultsFD and UIH could provide similar geometric performance in parotids, temporal lobes, lens, and eyes (DICE, p > 0.05). OAR_FD had better geometric performance in the optic nerves, oral cavity, larynx, and femoral heads (DICE, p < 0.05). OAR_UIH had better geometric performance in the bladder (DICE, p < 0.05). In dosimetric analysis, both Plan_FD and Plan_UIH had nonsignificant dosimetric differences compared to Plan_Manual for most PTV and OARs dose-volume indices. The only significant dosimetric difference was the Dmax of the left temporal lobe for Plan_FD vs. Plan_Manual (p = 0.05). Only one significant correlation was found between the mean dose of the femoral head and its HD index (R = 0.4, p = 0.01).ConclusionsDeep learning-based OARs auto-segmentation for NPC and rectal cancer has a nonsignificant impact on most PTV and OARs dose-volume indices. Correlations between the auto-segmentation geometric metric and dosimetric difference were not observed for most OARs.

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Hongbo Guo ◽  
Jiazhou Wang ◽  
Xiang Xia ◽  
Yang Zhong ◽  
Jiayuan Peng ◽  
...  

Abstract Purpose To investigate the dosimetric impact of deep learning-based auto-segmentation of organs at risk (OARs) on nasopharyngeal and rectal cancer. Methods and materials Twenty patients, including ten nasopharyngeal carcinoma (NPC) patients and ten rectal cancer patients, who received radiotherapy in our department were enrolled in this study. Two deep learning-based auto-segmentation systems, including an in-house developed system (FD) and a commercial product (UIH), were used to generate two auto-segmented OARs sets (OAR_FD and OAR_UIH). Treatment plans based on auto-segmented OARs and following our clinical requirements were generated for each patient on each OARs sets (Plan_FD and Plan_UIH). Geometric metrics (Hausdorff distance (HD), mean distance to agreement (MDA), the Dice similarity coefficient (DICE) and the Jaccard index) were calculated for geometric evaluation. The dosimetric impact was evaluated by comparing Plan_FD and Plan_UIH to original clinically approved plans (Plan_Manual) with dose-volume metrics and 3D gamma analysis. Spearman’s correlation analysis was performed to investigate the correlation between dosimetric difference and geometric metrics. Results FD and UIH could provide similar geometric performance in parotids, temporal lobes, lens, and eyes (DICE, p > 0.05). OAR_FD had better geometric performance in the optic nerves, oral cavity, larynx, and femoral heads (DICE, p < 0.05). OAR_UIH had better geometric performance in the bladder (DICE, p < 0.05). In dosimetric analysis, both Plan_FD and Plan_UIH had nonsignificant dosimetric differences compared to Plan_Manual for most PTV and OARs dose-volume metrics. The only significant dosimetric difference was the max dose of the left temporal lobe for Plan_FD vs. Plan_Manual (p = 0.05). Only one significant correlation was found between the mean dose of the femoral head and its HD index (R = 0.4, p = 0.01), there is no OARs showed strong correlation between its dosimetric difference and all of four geometric metrics. Conclusions Deep learning-based OARs auto-segmentation for NPC and rectal cancer has a nonsignificant impact on most PTV and OARs dose-volume metrics. Correlations between the auto-segmentation geometric metric and dosimetric difference were not observed for most OARs.


2020 ◽  
Vol 47 (11) ◽  
pp. 5467-5481
Author(s):  
Zhiqiang Liu ◽  
Xinyuan Chen ◽  
Kuo Men ◽  
Junlin Yi ◽  
Jianrong Dai

2022 ◽  
Author(s):  
Jing Shen ◽  
Yinjie TAO ◽  
Hui GUAN ◽  
Hongnan ZHEN ◽  
Lei HE ◽  
...  

Abstract Purpose Clinical target volumes (CTV) and organs at risk (OAR) could be auto-contoured to save workload. The goal of this study was to assess a convolutional neural network (CNN) for totally automatic and accurate CTV and OAR in prostate cancer, while also comparing anticipated treatment plans based on auto-contouring CTV to clinical plans. Methods From January 2013 to January 2019, 217 computed tomography (CT) scans of patients with locally advanced prostate cancer treated at our hospital were collected and analyzed. CTV and OAR were delineated with a deep learning based method, which named CUNet. The performance of this strategy was evaluated using the mean Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD), and subjective evaluation. Treatment plans were graded using predetermined evaluation criteria, and % errors for clinical doses to the planned target volume (PTV) and organs at risk(OARs) were calculated. Results The defined CTVs had mean DSC and 95HD values of 0.84 and 5.04 mm, respectively. For one patient's CT scans, the average delineation time was less than 15 seconds. When CTV outlines from CUNetwere blindly chosen and compared to GT, the overall positive rate in clinicians A and B was 53.15% vs 46.85%, and 54.05% vs 45.95%, respectively (P>0.05), demonstrating that our deep machine learning model performed as good as or better than human demarcation Furthermore, 8 testing patients were chosen at random to design the predicted plan based on the auto-courtoring CTV and OAR, demonstrating acceptable agreement with the clinical plan: average absolute dose differences of D2, D50, D98, Dmean for PTV are within 0.74%, and average absolute volume differences of V45, V50 for OARs are within 3.4%. Without statistical significance (p>0.05), the projected findings are comparable to clinical truth. Conclusion The experimental results show that the CTV and OARs defined by CUNet for prostate cancer were quite close to the ground reality.CUNet has the potential to cut radiation oncologists' contouring time in half. When compared to clinical plans, the differences between estimated doses to CTV and OAR based on auto-courtoring were small, with no statistical significance, indicating that treatment planning for prostate cancer based on auto-courtoring has potential.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Weijun Chen ◽  
Cheng Wang ◽  
Wenming Zhan ◽  
Yongshi Jia ◽  
Fangfang Ruan ◽  
...  

AbstractRadiotherapy requires the target area and the organs at risk to be contoured on the CT image of the patient. During the process of organs-at-Risk (OAR) of the chest and abdomen, the doctor needs to contour at each CT image. The delineations of large and varied shapes are time-consuming and laborious. This study aims to evaluate the results of two automatic contouring softwares on OARs definition of CT images of lung cancer and rectal cancer patients. The CT images of 15 patients with rectal cancer and 15 patients with lung cancer were selected separately, and the organs at risk were manually contoured by experienced physicians as reference structures. And then the same datasets were automatically contoured based on AiContour (version 3.1.8.0, Manufactured by Linking MED, Beijing, China) and Raystation (version 4.7.5.4, Manufactured by Raysearch, Stockholm, Sweden) respectively. Deep learning auto-segmentations and Atlas were respectively performed with AiContour and Raystation. Overlap index (OI), Dice similarity index (DSC) and Volume difference (Dv) were evaluated based on the auto-contours, and independent-sample t-test analysis is applied to the results. The results of deep learning auto-segmentations on OI and DSC were better than that of Atlas with statistical difference. There was no significant difference in Dv between the results of two software. With deep learning auto-segmentations, auto-contouring results of most organs in the chest and abdomen are good, and with slight modification, it can meet the clinical requirements for planning. With Atlas, auto-contouring results in most OAR is not as good as deep learning auto-segmentations, and only the auto-contouring results of some organs can be used clinically after modification.


2015 ◽  
Vol 18 (3) ◽  
pp. 93-100
Author(s):  
Tu Thi Cam Nguyen ◽  
Nhon Van Mai ◽  
Binh Thai Nguyen

Nowadays, traditional radiation therapy using x-rays is still the most common type of external exposure in curing cancer. However, the persisting problem is that significant dose delivered to normal tissues because of the characteristics of interaction of photons with matter even with the most advanced delivery techniques such as IMRT, IGRT, etc. Proton therapy is not only the technique producing better conformity to target but also better sparing to organs at risk. In this work, intensity modulated proton therapy (IMPT) and intensity modulated photon therapy (IMRT) plans are generated for a prostate patient. The evaluation and comparison of the two treatment plans were performed in term of physical quantity based on Dose Volume Histogram (DVH) and dose statistics for both target and organs at risk. The results of our study show that IMPT could be beneficial compared to IMRT with 5 fields. The doses to intestine and bladder are low resulting in possibly reducing side effects and second malignancies


2021 ◽  
Vol 10 ◽  
Author(s):  
Xiang Xia ◽  
Jiazhou Wang ◽  
Yujiao Li ◽  
Jiayuan Peng ◽  
Jiawei Fan ◽  
...  

Background and PurposeTo develop an artificial intelligence-based full-process solution for rectal cancer radiotherapy.Materials and MethodsA full-process solution that integrates autosegmentation and automatic treatment planning was developed under a single deep-learning framework. A convolutional neural network (CNN) was used to generate segmentations of the target and the organs at risk (OAR) as well as dose distribution. A script in Pinnacle that simulates the treatment planning process was used to execute plan optimization. A total of 172 rectal cancer patients were used for model training, and 18 patients were used for model validation. Another 40 rectal cancer patients were used for an end-to-end evaluation for both autosegmentation and treatment planning. The PTV and OAR segmentation was compared with manual segmentation. The planning results was evaluated by both objective and subjective assessment.ResultsThe total time for full-process planning without contour modification was 7 min, and an additional 15 min may require for contour modification and re-optimization. The PTV DICE similarity coefficient was greater than 0.85 for all 40 patients in the evaluation dataset while the DICE indices of the OARs also indicated good performance. There were no significant differences between the auto plans and manual plans. The physician accepted 80% of the auto plans without any further operation.ConclusionWe developed a deep learning-based automatic solution for rectal cancer treatment that can improve the efficiency of treatment planning.


2021 ◽  
Vol 9 ◽  
Author(s):  
Wei Wang ◽  
Qingxin Wang ◽  
Mengyu Jia ◽  
Zhongqiu Wang ◽  
Chengwen Yang ◽  
...  

Purpose: A novel deep learning model, Siamese Ensemble Boundary Network (SEB-Net) was developed to improve the accuracy of automatic organs-at-risk (OARs) segmentation in CT images for head and neck (HaN) as well as small organs, which was verified for use in radiation oncology practice and is therefore proposed.Methods: SEB-Net was designed to transfer CT slices into probability maps for the HaN OARs segmentation purpose. Dual key contributions were made to the network design to improve the accuracy and reliability of automatic segmentation toward the specific organs (e.g., relatively tiny or irregularly shaped) without sacrificing the field of view. The first implements an ensemble of learning strategies with shared weights that aggregates the pixel-probability transfer at three orthogonal CT planes to ameliorate 3D information integrity; the second exploits the boundary loss that takes the form of a distance metric on the space of contours to mitigate the challenges of conventional region-based regularization, when applied to highly unbalanced segmentation scenarios. By combining the two techniques, enhanced segmentation could be expected by comprehensively maximizing inter- and intra-CT slice information. In total, 188 patients with HaN cancer were included in the study, of which 133 patients were randomly selected for training and 55 for validation. An additional 50 untreated cases were used for clinical evaluation.Results: With the proposed method, the average volumetric Dice similarity coefficient (DSC) of HaN OARs (and small organs) was 0.871 (0.900), which was significantly higher than the results from Ua-Net, Anatomy-Net, and SRM by 4.94% (26.05%), 7.80% (24.65%), and 12.97% (40.19%), respectively. By contrast, the average 95% Hausdorff distance (95% HD) of HaN OARs (and small organs) was 2.87 mm (0.81 mm), which improves the other three methods by 50.94% (75.45%), 88.41% (79.07%), and 5.59% (67.98%), respectively. After delineation by SEB-Net, 81.92% of all organs in 50 HaN cancer untreated cases did not require modification for clinical evaluation.Conclusions: In comparison to several cutting-edge methods, including Ua-Net, Anatomy-Net, and SRM, the proposed method is capable of substantially improving segmentation accuracy for HaN and small organs from CT imaging in terms of efficiency, feasibility, and applicability.


2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Seung Yeun Chung ◽  
Jee Suk Chang ◽  
Min Seo Choi ◽  
Yongjin Chang ◽  
Byong Su Choi ◽  
...  

Abstract Background In breast cancer patients receiving radiotherapy (RT), accurate target delineation and reduction of radiation doses to the nearby normal organs is important. However, manual clinical target volume (CTV) and organs-at-risk (OARs) segmentation for treatment planning increases physicians’ workload and inter-physician variability considerably. In this study, we evaluated the potential benefits of deep learning-based auto-segmented contours by comparing them to manually delineated contours for breast cancer patients. Methods CTVs for bilateral breasts, regional lymph nodes, and OARs (including the heart, lungs, esophagus, spinal cord, and thyroid) were manually delineated on planning computed tomography scans of 111 breast cancer patients who received breast-conserving surgery. Subsequently, a two-stage convolutional neural network algorithm was used. Quantitative metrics, including the Dice similarity coefficient (DSC) and 95% Hausdorff distance, and qualitative scoring by two panels from 10 institutions were used for analysis. Inter-observer variability and delineation time were assessed; furthermore, dose-volume histograms and dosimetric parameters were also analyzed using another set of patient data. Results The correlation between the auto-segmented and manual contours was acceptable for OARs, with a mean DSC higher than 0.80 for all OARs. In addition, the CTVs showed favorable results, with mean DSCs higher than 0.70 for all breast and regional lymph node CTVs. Furthermore, qualitative subjective scoring showed that the results were acceptable for all CTVs and OARs, with a median score of at least 8 (possible range: 0–10) for (1) the differences between manual and auto-segmented contours and (2) the extent to which auto-segmentation would assist physicians in clinical practice. The differences in dosimetric parameters between the auto-segmented and manual contours were minimal. Conclusions The feasibility of deep learning-based auto-segmentation in breast RT planning was demonstrated. Although deep learning-based auto-segmentation cannot be a substitute for radiation oncologists, it is a useful tool with excellent potential in assisting radiation oncologists in the future. Trial registration Retrospectively registered.


Cancers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 702
Author(s):  
Nalee Kim ◽  
Jaehee Chun ◽  
Jee Suk Chang ◽  
Chang Geol Lee ◽  
Ki Chang Keum ◽  
...  

This study investigated the feasibility of deep learning-based segmentation (DLS) and continual training for adaptive radiotherapy (RT) of head and neck (H&N) cancer. One-hundred patients treated with definitive RT were included. Based on 23 organs-at-risk (OARs) manually segmented in initial planning computed tomography (CT), modified FC-DenseNet was trained for DLS: (i) using data obtained from 60 patients, with 20 matched patients in the test set (DLSm); (ii) using data obtained from 60 identical patients with 20 unmatched patients in the test set (DLSu). Manually contoured OARs in adaptive planning CT for independent 20 patients were provided as test sets. Deformable image registration (DIR) was also performed. All 23 OARs were compared using quantitative measurements, and nine OARs were also evaluated via subjective assessment from 26 observers using the Turing test. DLSm achieved better performance than both DLSu and DIR (mean Dice similarity coefficient; 0.83 vs. 0.80 vs. 0.70), mainly for glandular structures, whose volume significantly reduced during RT. Based on subjective measurements, DLS is often perceived as a human (49.2%). Furthermore, DLSm is preferred over DLSu (67.2%) and DIR (96.7%), with a similar rate of required revision to that of manual segmentation (28.0% vs. 29.7%). In conclusion, DLS was effective and preferred over DIR. Additionally, continual DLS training is required for an effective optimization and robustness in personalized adaptive RT.


Sign in / Sign up

Export Citation Format

Share Document