1
|
Salazar RM, Duryea JD, Leone AO, Nair SS, Mumme RP, De B, Corrigan KL, Rooney MK, Das P, Holliday EB, Court LE, Niedzielski JS. Random Forest Modeling of Acute Toxicity in Anal Cancer: Effects of Peritoneal Cavity Contouring Approaches on Model Performance. Int J Radiat Oncol Biol Phys 2024; 118:554-564. [PMID: 37619789 DOI: 10.1016/j.ijrobp.2023.08.042] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Revised: 08/04/2023] [Accepted: 08/13/2023] [Indexed: 08/26/2023]
Abstract
PURPOSE Our purpose was to analyze the effect on gastrointestinal (GI) toxicity models when their dose-volume metrics predictors are derived from segmentations of the peritoneal cavity after different contouring approaches. METHODS AND MATERIALS A random forest machine learning approach was used to predict acute grade ≥3 GI toxicity from dose-volume metrics and clinicopathologic factors for 246 patients (toxicity incidence = 9.5%) treated with definitive chemoradiation for squamous cell carcinoma of the anus. Three types of random forest models were constructed based on different bowel bag segmentation approaches: (1) physician-delineated after Radiation Therapy Oncology Group (RTOG) guidelines, (2) autosegmented by a deep learning model (nnU-Net) following RTOG guidelines, and (3) autosegmented but spanning the entire bowel space. Each model type was evaluated using repeated cross-validation (100 iterations; 50%/50% training/test split). The performance of the models was assessed using area under the precision-recall curve (AUPRC) and the receiver operating characteristic curve (AUROCC), as well as optimal F1 score. RESULTS When following RTOG guidelines, the models based on the nnU-Net auto segmentations (mean values: AUROCC, 0.71 ± 0.07; AUPRC, 0.42 ± 0.09; F1 score, 0.46 ± 0.08) significantly outperformed (P < .001) those based on the physician-delineated contours (mean values: AUROCC, 0.67 ± 0.07; AUPRC, 0.34 ± 0.08; F1 score, 0.36 ± 0.07). When spanning the entire bowel space, the performance of the autosegmentation models improved considerably (mean values: AUROCC, 0.87 ± 0.05; AUPRC, 0.70 ± 0.09; F1 score, 0.68 ± 0.09). CONCLUSIONS Random forest models were superior at predicting acute grade ≥3 GI toxicity when based on RTOG-defined bowel bag autosegmentations rather than physician-delineated contours. Models based on autosegmentations spanning the entire bowel space show further considerable improvement in model performance. The results of this study should be further validated using an external data set.
Collapse
Affiliation(s)
- Ramon M Salazar
- Department of Radiation Physics, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Jack D Duryea
- Department of Radiation Physics, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Alexandra O Leone
- Department of Radiation Physics, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Saurabh S Nair
- Department of Radiation Physics, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Raymond P Mumme
- Department of Radiation Physics, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Brian De
- Department of Radiation Oncology, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Kelsey L Corrigan
- Department of Radiation Oncology, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Michael K Rooney
- Department of Radiation Oncology, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Prajnan Das
- Department of Radiation Oncology, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Emma B Holliday
- Department of Radiation Oncology, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Laurence E Court
- Department of Radiation Physics, The University of Texas, MD Anderson Cancer Center, Houston, Texas
| | - Joshua S Niedzielski
- Department of Radiation Physics, The University of Texas, MD Anderson Cancer Center, Houston, Texas.
| |
Collapse
|
2
|
Zhang Z, Yu S, Peng F, Tan Z, Zhang L, Li D, Yang P, Peng Z, Li X, Fang C, Wang Y, Liu Y. Advantages and robustness of partial VMAT with prone position for neoadjuvant rectal cancer evaluated by CBCT-based offline adaptive radiotherapy. Radiat Oncol 2023; 18:102. [PMID: 37330508 DOI: 10.1186/s13014-023-02285-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2023] [Accepted: 05/18/2023] [Indexed: 06/19/2023] Open
Abstract
BACKGROUND AND PURPOSE This study aims to explore the advantages and robustness of the partial arc combined with prone position planning technique for radiotherapy in rectal cancer patients. Adaptive radiotherapy is recalculated and accumulated on the synthesis CT (sCT) obtained by deformable image registration between planning CT and cone beam CT (CBCT). Full and partial volume modulation arc therapy (VMAT) with the prone position on gastrointestinal and urogenital toxicity, based on the probability of normal tissue complications (NTCP) model in rectal cancer patients were evaluated. MATERIALS AND METHODS Thirty-one patients were studied retrospectively. The contours of different structures were outlined in 155 CBCT images. First, full VMAT (F-VMAT) and partial VMAT (P-VMAT) planning techniques were designed and calculated using the same optimization constraints for each individual patient. The Acuros XB (AXB) algorithm was used in order to generate more realistic dose distributions and DVH, considering the air cavities. Second, the Velocity 4.0 software was used to fuse the planning CT and CBCT to obtain the sCT. Then, the AXB algorithm was used in the Eclipse 15.6 software to conduct re-calculation based on the sCT to obtain the corresponding dose. Furthermore, the NTCP model was used to analyze its radiobiological side effects on the bladder and the bowel bag. RESULTS With a CTV coverage of 98%, when compared with F-VMAT, P-VMAT with the prone position technique can effectively reduce the mean dose of the bladder and the bowel bag. The NTCP model showed that the P-VMAT combined with the prone planning technique resulted in a significantly lower complication probability of the bladder (1.88 ± 2.08 vs 1.62 ± 1.41, P = 0.041) and the bowel bag (1.28 ± 1.70 vs 0.95 ± 1.52, P < 0.001) than the F-VMAT. In terms of robustness, P-VMAT was more robust than F-VMAT, considering that less dose and NTCP variation was observed in the CTV, bladder and bowel bag. CONCLUSION This study analyzed the advantages and robustness of the P-VMAT in the prone position from three aspects, based on the sCT fused by CBCT. Whether it is in regards to dosimetry, radiobiological effects or robustness, P-VMAT in the prone position has shown comparative advantages.
Collapse
Affiliation(s)
- Zhe Zhang
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China
| | - Shou Yu
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China
| | - Feng Peng
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China
| | - Zhibo Tan
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China
| | - Lei Zhang
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China
| | - Daming Li
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China
| | - Pengfei Yang
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China
| | - Zhaoming Peng
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China
| | - Xin Li
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China
- Shenzhen-Peking University, Hong Kong University of Science and Technology Medical Center, Shenzhen, China
| | - Chunfeng Fang
- Department of Radiation Oncology, Hebei Yizhou Cancer Hospital, Zhuozhou, China
| | - Yuenan Wang
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China.
| | - Yajie Liu
- Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen, China.
- Shenzhen-Peking University, Hong Kong University of Science and Technology Medical Center, Shenzhen, China.
| |
Collapse
|
3
|
Taylor S, Lim P, Cantwell J, D’Souza D, Moinuddin S, Chang YC, Gaze MN, Gains J, Veiga C. Image guidance and interfractional anatomical variation in paediatric abdominal radiotherapy. Br J Radiol 2023; 96:20230058. [PMID: 37102707 PMCID: PMC10230397 DOI: 10.1259/bjr.20230058] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2023] [Revised: 03/22/2023] [Accepted: 03/23/2023] [Indexed: 04/28/2023] Open
Abstract
OBJECTIVES To identify variables predicting interfractional anatomical variations measured with cone-beam CT (CBCT) throughout abdominal paediatric radiotherapy, and to assess the potential of surface-guided radiotherapy (SGRT) to monitor these changes. METHODS Metrics of variation in gastrointestinal (GI) gas volume and separation of the body contour and abdominal wall were calculated from 21 planning CTs and 77 weekly CBCTs for 21 abdominal neuroblastoma patients (median 4 years, range: 2 - 19 years). Age, sex, feeding tubes, and general anaesthesia (GA) were explored as predictive variables for anatomical variation. Furthermore, GI gas variation was correlated with changes in body and abdominal wall separation, as well as simulated SGRT metrics of translational and rotational corrections between CT/CBCT. RESULTS GI gas volumes varied 74 ± 54 ml across all scans, while body and abdominal wall separation varied 2.0 ± 0.7 mm and 4.1 ± 1.5 mm from planning, respectively. Patients < 3.5 years (p = 0.04) and treated under GA (p < 0.01) experienced greater GI gas variation; GA was the strongest predictor in multivariate analysis (p < 0.01). Absence of feeding tubes was linked to greater body contour variation (p = 0.03). GI gas variation correlated with body (R = 0.53) and abdominal wall (R = 0.63) changes. The strongest correlations with SGRT metrics were found for anterior-posterior translation (R = 0.65) and rotation of the left-right axis (R = -0.36). CONCLUSIONS Young age, GA, and absence of feeding tubes were linked to stronger interfractional anatomical variation and are likely indicative of patients benefiting from adaptive/robust planning pathways. Our data suggest a role for SGRT to inform the need for CBCT at each treatment fraction in this patient group. ADVANCES IN KNOWLEDGE This is the first study to suggest the potential role of SGRT for the management of internal interfractional anatomical variation in paediatric abdominal radiotherapy.
Collapse
Affiliation(s)
- Sabrina Taylor
- University College London, Centre for Medical Image Computing, London, United Kingdom
| | - Pei Lim
- Department of Oncology, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Jessica Cantwell
- Radiotherapy, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Derek D’Souza
- Radiotherapy, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Syed Moinuddin
- Radiotherapy, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Yen-Ching Chang
- Department of Oncology, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Mark N Gaze
- Department of Oncology, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Jennifer Gains
- Department of Oncology, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Catarina Veiga
- University College London, Centre for Medical Image Computing, London, United Kingdom
| |
Collapse
|
4
|
Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on Workflow. LIFE (BASEL, SWITZERLAND) 2022; 12:life12122088. [PMID: 36556455 PMCID: PMC9782080 DOI: 10.3390/life12122088] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/24/2022] [Revised: 11/30/2022] [Accepted: 12/09/2022] [Indexed: 12/14/2022]
Abstract
Proper delineation of both target volumes and organs at risk is a crucial step in the radiation therapy workflow. This process is normally carried out manually by medical doctors, hence demanding timewise. To improve efficiency, auto-contouring methods have been proposed. We assessed a specific commercial software to investigate its impact on the radiotherapy workflow on four specific disease sites: head and neck, prostate, breast, and rectum. For the present study, we used a commercial deep learning-based auto-segmentation software, namely Limbus Contour (LC), Version 1.5.0 (Limbus AI Inc., Regina, SK, Canada). The software uses deep convolutional neural network models based on a U-net architecture, specific for each structure. Manual and automatic segmentation were compared on disease-specific organs at risk. Contouring time, geometrical performance (volume variation, Dice Similarity Coefficient-DSC, and center of mass shift), and dosimetric impact (DVH differences) were evaluated. With respect to time savings, the maximum advantage was seen in the setting of head and neck cancer with a 65%-time reduction. The average DSC was 0.72. The best agreement was found for lungs. Good results were highlighted for bladder, heart, and femoral heads. The most relevant dosimetric difference was in the rectal cancer case, where the mean volume covered by the 45 Gy isodose was 10.4 cm3 for manual contouring and 289.4 cm3 for automatic segmentation. Automatic contouring was able to significantly reduce the time required in the procedure, simplifying the workflow, and reducing interobserver variability. Its implementation was able to improve the radiation therapy workflow in our department.
Collapse
|
5
|
Cheung MLM, Kan MWK, Yeung VTY, Poon DMC, Kam MKM, Lee LKY, Chan ATC. The radiobiological effect of using Acuros XB vs anisotropic analytical algorithm on hepatocellular carcinoma stereotactic body radiation therapy. Med Dosim 2022; 47:161-165. [PMID: 35241348 DOI: 10.1016/j.meddos.2022.01.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2021] [Revised: 01/23/2022] [Accepted: 01/31/2022] [Indexed: 11/26/2022]
Abstract
The purpose of this work was to study the radiobiological effect of using Acuros XB (AXB) vs Analytic Anisotropic Algorithm (AAA) on hepatocellular carcinoma (HCC) stereotactic body radiation therapy (SBRT). Seventy SBRT volumetric modulated arc therapy (VMAT) plans for HCC were calculated using AAA and AXB respectively with the same treatment parameters. Published tumor control probability (TCP) and normal tissue complication probability (NTCP) models were used to quantify the effect of dosimetric difference between AAA and AXB on TCP, NTCP and uncomplicated tumor control probability (UTCP). There was an average decrease of 2.5% in 6-month TCP. Normal liver has the largest average decrease in NTCP which was 59.7%. Bowels followed with 26.6% average decrease in NTCP. Duodenum, stomach and esophagus had 10.2%, 5.1%, and 4.3% average decrease in NTCP. There was an average decrease of 1.8% and up to 7.2% in 6-month UTCP. There was an overall decrease in TCP, NTCP, and UTCP for HCC SBRT plans calculated using AXB compared to AAA which could be clinically significant.
Collapse
Affiliation(s)
- Michael L M Cheung
- Department of Clinical Oncology, Prince of Wales Hospital, Hong Kong SAR, China; State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong SAR, China.
| | - Monica W K Kan
- Department of Clinical Oncology, Prince of Wales Hospital, Hong Kong SAR, China; State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Vanessa T Y Yeung
- Department of Clinical Oncology, Prince of Wales Hospital, Hong Kong SAR, China; State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Darren M C Poon
- State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Michael K M Kam
- State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Louis K Y Lee
- State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Anthony T C Chan
- Department of Clinical Oncology, Prince of Wales Hospital, Hong Kong SAR, China; State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong SAR, China
| |
Collapse
|