Development and evaluation of radiotherapy deep learning dose prediction models for breast cancer
| Autor: | Jacqueline Theuws, Hanneke Bluemink, Coen W. Hurkmans, Nienke Bakx, Maurice J.C. van der Sangen, E. Hagelaar |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
lcsh:Medical physics. Medical radiology. Nuclear medicine
medicine.medical_specialty Intensity-modulated radiotherapy medicine.medical_treatment lcsh:R895-920 Planning target volume Dose distribution Dose prediction lcsh:RC254-282 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Breast cancer Machine learning medicine Radiology Nuclear Medicine and imaging Medical physics Original Research Article Radiation treatment planning Radiation business.industry Deep learning medicine.disease lcsh:Neoplasms. Tumors. Oncology. Including cancer and carcinogens Radiation therapy 030220 oncology & carcinogenesis Convolutional neural networks Artificial intelligence business Regression forest |
| Zdroj: | Physics and Imaging in Radiation Oncology, Vol 17, Iss, Pp 65-70 (2021) Physics and Imaging in Radiation Oncology |
| ISSN: | 2405-6316 |
| Popis: | Background and purpose: Treatment planning of radiotherapy is a time-consuming and planner dependent process that can be automated by dose prediction models. The purpose of this study was to evaluate the performance of two machine learning models for breast cancer radiotherapy before possible clinical implementation. Materials and methods: An in-house developed model, based on U-net architecture, and a contextual atlas regression forest (cARF) model integrated in the treatment planning software were trained. Obtained dose distributions were mimicked to create clinically deliverable plans. For training and validation, 90 patients were used, 15 patients were used for testing. Treatment plans were scored on predefined evaluation criteria and percent errors with respect to clinical dose were calculated for doses to planning target volume (PTV) and organs at risk (OARs). Results: The U-net plans before mimicking met all criteria for all patients, both models failed one evaluation criterion in three patients after mimicking. No significant differences (p |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|