Machine Learning for Image-Based Radiotherapy Outcome Prediction
Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review
Medical images represent the main source of information for radiotherapy (RT) planning. Historically, medical images have been utilized to qualitatively and quantitatively access the location and size of the tumor, the shape and positions of the surrounding healthy organs, and the spatial relationships between these organs and the tumor. The images, however, contain much more information than it is usually extracted during RT planning. The appearance of the tumor and healthy organs can potentially give insights about the cancer aggressiveness, risks associated with the treatment, and most likely treatment outcomes. The challenge remains to correctly identify such predictive image biomarkers, and map their predictive powers to the RT outcomes of interest. This book chapter summarizes the existing machine learning solutions for image-based RT outcome prediction. The chapter critically access different aspects of existing solutions, including the type of utilized imaging modality, biomarker extraction protocol, machine learning algorithm, and algorithm performance evaluation. This chapter also critically summarizes the conclusions of the existing studies, and highlights the promising directions for future research.
Original language | English |
---|---|
Title of host publication | Artificial Intelligence in Radiation Oncology and Biomedical Physics |
Editors | Gilmer Valdes, Lei Xing |
Number of pages | 28 |
Publisher | CRC Press |
Publication date | 2023 |
Pages | 25-52 |
Chapter | 2 |
ISBN (Print) | 9780367538101, 9780367556198 |
ISBN (Electronic) | 9781003094333 |
DOIs | |
Publication status | Published - 2023 |
ID: 390359192