scholarly journals Geometric and Dosimetric Evaluation of Deep Learning-Based Automatic Delineation on CBCT-Synthesized CT and Planning CT for Breast Cancer Adaptive Radiotherapy: A Multi-Institutional Study

2021 ◽  
Vol 11 ◽  
Author(s):  
Zhenhui Dai ◽  
Yiwen Zhang ◽  
Lin Zhu ◽  
Junwen Tan ◽  
Geng Yang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Organs At Risk ◽  
Clinical Impact ◽  
Pass Rate ◽  
Breath Hold ◽  
Dice Similarity Coefficient ◽  
Breast Cancer Radiotherapy ◽  
The Mean ◽  
Planning Ct

PurposeWe developed a deep learning model to achieve automatic multitarget delineation on planning CT (pCT) and synthetic CT (sCT) images generated from cone-beam CT (CBCT) images. The geometric and dosimetric impact of the model was evaluated for breast cancer adaptive radiation therapy.MethodsWe retrospectively analyzed 1,127 patients treated with radiotherapy after breast-conserving surgery from two medical institutions. The CBCT images for patient setup acquired utilizing breath-hold guided by optical surface monitoring system were used to generate sCT with a generative adversarial network. Organs at risk (OARs), clinical target volume (CTV), and tumor bed (TB) were delineated automatically with a 3D U-Net model on pCT and sCT images. The geometric accuracy of the model was evaluated with metrics, including Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95). Dosimetric evaluation was performed by quick dose recalculation on sCT images relying on gamma analysis and dose-volume histogram (DVH) parameters. The relationship between ΔD95, ΔV95 and DSC-CTV was assessed to quantify the clinical impact of the geometric changes of CTV.ResultsThe ranges of DSC and HD95 were 0.73–0.97 and 2.22–9.36 mm for pCT, 0.63–0.95 and 2.30–19.57 mm for sCT from institution A, 0.70–0.97 and 2.10–11.43 mm for pCT from institution B, respectively. The quality of sCT was excellent with an average mean absolute error (MAE) of 71.58 ± 8.78 HU. The mean gamma pass rate (3%/3 mm criterion) was 91.46 ± 4.63%. DSC-CTV down to 0.65 accounted for a variation of more than 6% of V95 and 3 Gy of D95. DSC-CTV up to 0.80 accounted for a variation of less than 4% of V95 and 2 Gy of D95. The mean ΔD90/ΔD95 of CTV and TB were less than 2Gy/4Gy, 4Gy/5Gy for all the patients. The cardiac dose difference in left breast cancer cases was larger than that in right breast cancer cases.ConclusionsThe accurate multitarget delineation is achievable on pCT and sCT via deep learning. The results show that dose distribution needs to be considered to evaluate the clinical impact of geometric variations during breast cancer radiotherapy.

scholarly journals Evaluation of deep learning-based autosegmentation in breast cancer radiotherapy

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Hwa Kyung Byun ◽  
Jee Suk Chang ◽  
Min Seo Choi ◽  
Jaehee Chun ◽  
Jinhong Jung ◽  
...  
Keyword(s):  
Deep Learning ◽  
User Satisfaction ◽  
Organs At Risk ◽  
Breast Conserving Surgery ◽  
Dice Similarity Coefficient ◽  
Expert Committee ◽  
Breast Radiotherapy ◽  
Breast Cancer Radiotherapy ◽  
Independent Expert ◽  
Manual Contour

Abstract Purpose To study the performance of a proposed deep learning-based autocontouring system in delineating organs at risk (OARs) in breast radiotherapy with a group of experts. Methods Eleven experts from two institutions delineated nine OARs in 10 cases of adjuvant radiotherapy after breast-conserving surgery. Autocontours were then provided to the experts for correction. Overall, 110 manual contours, 110 corrected autocontours, and 10 autocontours of each type of OAR were analyzed. The Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to compare the degree of agreement between the best manual contour (chosen by an independent expert committee) and each autocontour, corrected autocontour, and manual contour. Higher DSCs and lower HDs indicated a better geometric overlap. The amount of time reduction using the autocontouring system was examined. User satisfaction was evaluated using a survey. Results Manual contours, corrected autocontours, and autocontours had a similar accuracy in the average DSC value (0.88 vs. 0.90 vs. 0.90). The accuracy of autocontours ranked the second place, based on DSCs, and the first place, based on HDs among the manual contours. Interphysician variations among the experts were reduced in corrected autocontours, compared to variations in manual contours (DSC: 0.89–0.90 vs. 0.87–0.90; HD: 4.3–5.8 mm vs. 5.3–7.6 mm). Among the manual delineations, the breast contours had the largest variations, which improved most significantly with the autocontouring system. The total mean times for nine OARs were 37 min for manual contours and 6 min for corrected autocontours. The results of the survey revealed good user satisfaction. Conclusions The autocontouring system had a similar performance in OARs as that of the experts’ manual contouring. This system can be valuable in improving the quality of breast radiotherapy and reducing interphysician variability in clinical practice.

scholarly journals Automatic Segmentation of Clinical Target Volume and Organs-At-Risk for Breast Conservative Radiotherapy Using a Convolutional Neural Network

2021 ◽  
Author(s):  
Zhikai Liu ◽  
Fangjie Liu ◽  
Wanqi Chen ◽  
Yinjie Tao ◽  
Xia Liu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Spinal Cord ◽  
At Risk ◽  
Clinical Target Volume ◽  
Organs At Risk ◽  
Target Volume ◽  
Contralateral Breast ◽  
Dice Similarity Coefficient ◽  
Proposed Model ◽  
The Mean

Abstract Background and Objective: Delineation of the clinical target volume (CTV) and organs at risk (OARs) is very important for radiotherapy but is time-consuming and prone to inter- and intra-observer variation. We trained and evaluated a U-Net-based model to provide fast and consistent auto-segmentation for breast cancer radiotherapy. Methods: We collected 160 patients’ computed tomography (CT) scans with early-stage breast cancer who underwent breast-conserving surgery (BCS) and were treated with radiotherapy in our center. CTV and OARs (contralateral breast, heart, lungs and spinal cord) were delineated manually by two experienced radiation oncologists. The data were used for model training and testing. The dice similarity coefficient (DSC) and 95th Hausdorff distance (95HD) were used to assess the performance of our model. CTV and OARs were randomly selected as ground truth (GT) masks, and artificial intelligence (AI) masks were generated by the proposed model. The contours were randomly distributed to two clinicians to compare CTV score differences. The consistency between two clinicians was tested. We also evaluated time cost for auto-delineation. Results: The mean DSC values of the proposed method were 0.94, 0.95, 0.94, 0.96, 0.96 and 0.93 for breast CTV, contralateral breast, heart, right lung, left lung and spinal cord, respectively. The mean 95HD values were 4.31 mm, 3.59 mm, 4.86 mm, 3.18 mm, 2.79 mm and 4.37 mm for the above structures respectively. The average CTV scores for AI and GT were 2.92 versus 2.89 when evaluated by oncologist A (P=.612), and 2.75 versus 2.83 by oncologist B (P=.213), with no statistically significant differences. The consistency between two clinicians was poor (Kappa=0.282). The times for auto-segmentation of CTV and OARs were 3.88 s and 6.15 s. Conclusions: Our proposed model can improve the speed and accuracy of delineation compared with U-Net, while it performed equally well with the segmentation generated by oncologists.

scholarly journals Clinical feasibility of deep learning-based auto-segmentation of target volumes and organs-at-risk in breast cancer patients after breast-conserving surgery

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Seung Yeun Chung ◽  
Jee Suk Chang ◽  
Min Seo Choi ◽  
Yongjin Chang ◽  
Byong Su Choi ◽  
...  
Keyword(s):  
Breast Cancer ◽  
At Risk ◽  
Deep Learning ◽  
Cancer Patients ◽  
Organs At Risk ◽  
Breast Conserving Surgery ◽  
Dice Similarity Coefficient ◽  
Breast Cancer Patients ◽  
Dose Volume Histograms ◽  
Radiation Oncologists

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.

scholarly journals Deep-inspirational breath-hold (DIBH) technique in left-sided breast cancer: various aspects of clinical utility

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Szilvia Gaál ◽  
Zsuzsanna Kahán ◽  
Viktor Paczona ◽  
Renáta Kószó ◽  
Rita Drencsényi ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Side Effects ◽  
Clinical Utility ◽  
Prospective Trial ◽  
Conformal Radiotherapy ◽  
Free Breathing ◽  
Left Breast ◽  
Breath Hold ◽  
Ipsilateral Lung ◽  
Breast Cancer Radiotherapy

Abstract Background Studying the clinical utility of deep-inspirational breath-hold (DIBH) in left breast cancer radiotherapy (RT) was aimed at focusing on dosimetry and feasibility aspects. Methods In this prospective trial all enrolled patients went through planning CT in supine position under both DIBH and free breathing (FB); in whole breast irradiation (WBI) cases prone CT was also taken. In 3-dimensional conformal radiotherapy (3DCRT) plans heart, left anterior descending coronary artery (LAD), ipsilateral lung and contralateral breast doses were analyzed. The acceptance of DIBH technique as reported by the patients and the staff was analyzed; post-RT side-effects including radiation lung changes (visual scores and lung density measurements) were collected. Results Among 130 enrolled patients 26 were not suitable for the technique while in 16, heart or LAD dose constraints were not met in the DIBH plans. Among 54 and 34 patients receiving WBI and postmastectomy/nodal RT, respectively with DIBH, mean heart dose (MHD) was reduced to < 50%, the heart V25 Gy to < 20%, the LAD mean dose to < 40% and the LAD maximum dose to about 50% as compared to that under FB; the magnitude of benefit was related to the relative increase of the ipsilateral lung volume at DIBH. Nevertheless, heart and LAD dose differences (DIBH vs. FB) individually varied. Among the WBI cases at least one heart/LAD dose parameter was more favorable in the prone or in the supine FB plan in 15 and 4 cases, respectively; differences were numerically small. All DIBH patients completed the RT, inter-fraction repositioning accuracy and radiation side-effects were similar to that of other breast RT techniques. Both the patients and radiographers were satisfied with the technique. Conclusions DIBH is an excellent heart sparing technique in breast RT, but about one-third of the patients do not benefit from that otherwise laborious procedure or benefit less than from an alternative method. Trial registration: retrospectively registered under ISRCTN14360721 (February 12, 2021)

scholarly journals Feasibility of Continual Deep Learning-Based Segmentation for Personalized Adaptive Radiation Therapy in Head and Neck Area

Cancers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 702
Author(s):  
Nalee Kim ◽  
Jaehee Chun ◽  
Jee Suk Chang ◽  
Chang Geol Lee ◽  
Ki Chang Keum ◽  
...  
Keyword(s):  
Deep Learning ◽  
Head And Neck ◽  
Organs At Risk ◽  
Subjective Assessment ◽  
Turing Test ◽  
Similar Rate ◽  
Dice Similarity Coefficient ◽  
Adaptive Planning ◽  
Test Set ◽  
Using Data

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.

scholarly journals Lesion-Based Bone Metastasis Detection in Chest Bone Scintigraphy Images of Prostate Cancer Patients Using Pre-Train, Negative Mining, and Deep Learning

Diagnostics ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 518
Author(s):  
Da-Chuan Cheng ◽  
Te-Chun Hsieh ◽  
Kuo-Yang Yen ◽  
Chia-Hung Kao
Keyword(s):  
Breast Cancer ◽  
Prostate Cancer ◽  
Deep Learning ◽  
Bone Metastasis ◽  
Cancer Patients ◽  
Bone Scintigraphy ◽  
Breast Cancer Patients ◽  
Location Detection ◽  
The Mean ◽  
Mean Sensitivity

This study aimed to explore efficient ways to diagnose bone metastasis early using bone scintigraphy images through negative mining, pre-training, the convolutional neural network, and deep learning. We studied 205 prostate cancer patients and 371 breast cancer patients and used bone scintigraphy data from breast cancer patients to pre-train a YOLO v4 with a false-positive reduction strategy. With the pre-trained model, transferred learning was applied to prostate cancer patients to build a model to detect and identify metastasis locations using bone scintigraphy. Ten-fold cross validation was conducted. The mean sensitivity and precision rates for bone metastasis location detection and classification (lesion-based) in the chests of prostate patients were 0.72 ± 0.04 and 0.90 ± 0.04, respectively. The mean sensitivity and specificity rates for bone metastasis classification (patient-based) in the chests of prostate patients were 0.94 ± 0.09 and 0.92 ± 0.09, respectively. The developed system has the potential to provide pre-diagnostic reports to aid in physicians’ final decisions.

Deep-inspiration breath hold radiotherapy in patients with left-sided breast cancer after partial mastectomy

2021 ◽  
Vol 100 (4) ◽  
Keyword(s):  
Breast Cancer ◽  
Radiation Dose ◽  
Organs At Risk ◽  
Left Lung ◽  
Free Breathing ◽  
Partial Mastectomy ◽  
Breath Hold ◽  
Deep Inspiration ◽  
Deep Inspiration Breath Hold ◽  
Dose Volume Histograms

Introduction: The purpose of this study was to compare the radiation dose to organs at risk for deep-inspiration breath hold (DIBH) and free-breathing (FB) radiotherapy in patients with lef-sided breast cancer undergoing adjuvant radiotherapy after partial mastectomy. Methods: One hundred patients with left-sided breast cancer underwent DIBH and FB planning computed tomography scans, and the 2 techniques were compared. Dose-volume histograms were analyzed for heart, left anterior descending coronary artery (LAD), and left lung. Results: Radiation dose to heart, LAD, and left lung was significantly lower for DIBH than for free breathing plans. The median mean heart dose for DIBH technique in comparison with FB was 1.21 Gy, and 3.22 Gy respectively; for LAD, 4.67 versus 24.71 Gy; and for left lung 8.32 Gy versus 9.99 Gy. Conclusion: DIBH is an effective technique to reduce cardiac and lung radiation exposure.

Deep inspiration breath-hold for patients with left-sided breast cancer – A one fits all approach? A prospective analysis of patient selection using dosimetrical and practical aspects

2021 ◽  
pp. 20210295
Author(s):  
Christina Schröder ◽  
Sebastian Kirschke ◽  
Eyck Blank ◽  
Sophia Rohrberg ◽  
Robert Förster ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Left Lung ◽  
Free Breathing ◽  
Lymphatic Drainage ◽  
Breath Hold ◽  
Deep Inspiration ◽  
Deep Inspiration Breath Hold ◽  
Patient Preparation ◽  
Treatment Plans ◽  
Planning Ct

Objective: To prospectively analyze the feasibility of an algorithm for patient preparation, treatment planning and selection for deep inspiration breath-hold (DIBH) treatment of left-sided breast cancer. Methods: From 02/2017 to 07/2019, 135 patients with left-sided breast cancer were selected and prepared for radiotherapy in DIBH. 99 received radiotherapy for the breast alone and 36 for the breast including the lymphatic drainage (RNI). Treatment plans DIBH and free breathing (FB) were calculated. Dosimetrical analyses were performed and criteria were defined to assess whether a patient would dosimetrically profit from DIBH. Results: Of the 135 patients, 97 received a DIBH planning CT and 72 were selected for treatment in DIBH according to predefined criteria. When using DIBH there was a mean reduction of the DmeanHeart of 2.8 Gy and DmeanLAD of 4.2 Gy. seven patients did not benefit from DIBH regarding DmeanHeart, 23 regarding DmeanLAD. For the left lung the V20Gy was reduced by 4.9%, the V30Gy by 2.7% with 15 and 29 patients not benefitting from DIBH, respectively. In the 25 patients treated in FB, the benefit of DIBH would have been lower than for patients treated with DIBH (ΔDmeanHeart0.7 Gy vs 3.4 Gy). Conclusion: Dosimetrically, DIBH is no “one fits all” approach. However, there is a statistically significant benefit when looking at a larger patient population. DIBH should be used for treatment of left-sided breast cancer in patients fit for DIBH. Advances in knowledge: This analysis offers a well-designed dosimetrical analysis in patients treated with DIBH radiotherapy in an “every day” cohort.

Sign in / Sign up

Export Citation Format

Share Document