As early detection and better treatment have increased cancer patient survival rates, the importance of protecting normal organs during radiation treatment is drawing more attention, which is critical in reducing long term toxicity of cancers. To avoid excessively high radiation doses to organs-at-risk (OARs), OARs need to be correctly segmented from simulation computed tomography (CT) scans during radiation treatment planning to get an accurate dose distribution. Despite tremendous effort in developing semi- or fully-automatic segmentation solutions, current automated segmentation software, mostly using the atlas-based methods, has not yet reached the level of accuracy and robustness required for clinical usage. Therefore, in current practice, significant manual efforts are still required in the OAR segmentation process. Manual contouring suffers from inter- and intra-observer variability, as well as institutional variability where different sites adopt distinct contouring atlases and labeling criteria, thus leading to inaccuracy and variability in OAR segmentation. When OARs are very close to the treatment target, segmentation errors as small as a few millimeters can have a statistically significant impact on dosimetry distribution and outcome. In addition, it is also costly and time consuming as it can take 1-2 hours of a clinicians? time to segment major thoracic organs due to the large number of axial slices required. In summary, an accurate and fast process for segmenting OARs in treatment planning using CT scans is needed for improving patient outcomes and reducing the cost of radiation therapy of cancers. In recent years, the rapid development of deep learning methods has revolutionized many computer-vision areas and the adoption of deep learning in medical applications has shown great success. Based on a deep-learning-based algorithm we developed that achieved better-than-human performance and ranked 1st in 2017 American Association of Physicist in Medicine Thoracic Auto-segmentation Challenge, an automatic OAR segmentation product will be developed in this project with the three aims: 1) further improve the performance and robustness of OAR segmentation algorithms, focusing on addressing the heterogeneity issue of different clinical environments; 2) further enrich the functionalities and enhance usability of the cloud- based software product; and 3) perform clinical validation study on the algorithm performance and software usability at collaborating sites. With this product, the segmentation accuracy can be improved, leading to more robust treatment plans in protecting normal organs and improved long term patient outcome. The time and cost of radiation treatment planning can be greatly reduced, contributing to a more affordable cancer treatment and reduced healthcare burden.
As early detection and better treatment have increased cancer patient survival rates, the importance of protecting normal organs during radiation treatment is drawing more attention. To avoid excessively high radiation doses to such organs-at-risk (OARs), they are required to be correctly segmented from simulation computed tomography (CT) scans. A deep-learning-based automatic OAR segmentation product developed in this project can improve the segmentation accuracy and reduce the time and cost of radiation treatment planning as compared with the current manual process, leading to improved long term patient outcome and reduced cancer treatment cost.
