1
|
Apte AP, Iyer A, Thor M, Pandya R, Haq R, Jiang J, LoCastro E, Shukla-Dave A, Sasankan N, Xiao Y, Hu YC, Elguindi S, Veeraraghavan H, Oh JH, Jackson A, Deasy JO. Library of deep-learning image segmentation and outcomes model-implementations. Phys Med 2020; 73:190-196. [PMID: 32371142 PMCID: PMC8474066 DOI: 10.1016/j.ejmp.2020.04.011] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/11/2019] [Revised: 04/09/2020] [Accepted: 04/12/2020] [Indexed: 12/14/2022] Open
Abstract
An open-source library of implementations for deep-learning-based image segmentation and outcomes models based on radiotherapy and radiomics is presented. As oncology treatment planning becomes increasingly driven by automation, such a library of model implementations is crucial to (i) validate existing models on datasets collected at different institutions, (ii) automate segmentation, (iii) create ensembles for improving performance and (iv) incorporate validated models in the clinical workflow. Inclusion of deep-learning-based image segmentation and outcomes models in the same library provides a fully automated and reproduceable pipeline to estimate prognosis. The library was developed with the Computational Environment for Radiological Research (CERR) software platform. Centralizing model implementations in CERR builds upon its rich set of radiotherapy and radiomics tools and caters to the world-wide user base. CERR provides well-validated feature extraction pipelines for radiotherapy dosimetry and radiomics with fine control over the calculation settings, allowing users to select appropriate parameters used in model derivation. Models for automatic image segmentation are distributed via containers, allowing them to be deployed with a variety of scientific computing architectures. The library includes implementations of popular DVH-based models outlined in the Quantitative Analysis of Normal Tissue Effects in the Clinic effort and recently published literature. Radiomics models include features from the Image Biomarker Standardization Initiative and application-specific features found to be relevant across multiple sites and image modalities. The library is distributed as a module within CERR at https://www.github.com/cerr/CERR under the GNU-GPL copyleft with additional restrictions on clinical and commercial use and provision to dual license in future.
Collapse
Affiliation(s)
- Aditya P Apte
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA.
| | - Aditi Iyer
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Maria Thor
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Rutu Pandya
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Rabia Haq
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Jue Jiang
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Eve LoCastro
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Amita Shukla-Dave
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Nishanth Sasankan
- Department of Radiation Oncology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Ying Xiao
- Department of Radiation Oncology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Yu-Chi Hu
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Sharif Elguindi
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Harini Veeraraghavan
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Jung Hun Oh
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Andrew Jackson
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Joseph O Deasy
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| |
Collapse
|
2
|
Vasiljevic D, Arnold C, Neuman D, Fink K, Popovscaia M, Kvitsaridze I, Nevinny-Stickel M, Glatzer M, Lukas P, Seppi T. Occurrence of pneumonitis following radiotherapy of breast cancer - A prospective study. Strahlenther Onkol 2018; 194:520-32. [PMID: 29450591 DOI: 10.1007/s00066-017-1257-z] [Citation(s) in RCA: 34] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2017] [Accepted: 12/22/2017] [Indexed: 01/17/2023]
Abstract
AIM of this study is to determine the temporal resolution of therapy-induced pneumonitis, and to assess promoting factors in adjuvant treated patients with unilateral mammacarcinoma. PATIENTS AND METHODS A total of 100 post-surgery patients were recruited. The cohort was treated by 2 field radiotherapy (2FRT; breast and chest wall, N = 75), 3 field radiotherapy (3FRT; + supraclavicular lymphatic region, N = 8), or with 4 field radiotherapy (4FRT; + parasternal lymphatic region, N = 17). Ninety-one patients received various systemic treatments prior to irradiation. Following an initial screening visit post-RT, two additional visits after 12 and 25 weeks were conducted including radiographic examination. In addition, general anamnesis and the co-medication were recorded. The endpoint was reached as soon as a pneumonitis was developed or at maximum of six months post-treatment. RESULTS A pneumonitis incidence of 13% was determined. Of 91 patients with prior systemic therapy, 11 patients developed pneumonitis. Smoking history and chronic obstructive pulmonary disease (COPD) appeared to be positive predictors, whereas past pneumonia clearly promoted pneumonitis. Further pneumonitis-promoting predictors are represented by the applied field extensions (2 field radiotherapy [2FRT] < 3 field radiotherapy [3FRT] < 4 field radiotherapy [4FRT]) and the type of combined initial systemic therapies. As a consequence, all of the three patients in the study cohort treated with 4FRT and initial chemotherapy combined with anti-hormone and antibody protocols developed pneumonitis. A combination of the hormone antagonists tamoxifen and goserelin might enhance the risk for pneumonitis. Remarkably, none of the 11 patients co-medicated with statins suffered from pneumonitis. CONCLUSIONS The rapidly increasing use of novel systemic therapy schedules combined with radiotherapy (RT) needs more prospective studies with larger cohorts. Our results indicate that contribution to pneumonitis occurrence of various (neo)adjuvant therapy approaches followed by RT is of minor relevance, whereas mean total lung doses of >10 Gy escalate the risk of lung tissue complications. The validity of potential inhibitors of therapy-induced pneumonitis as observed for statin co-medication should further be investigated in future trials.
Collapse
|