Colbert ZM, Ramachandran P. Auto-Segmentation of Thoracic Organs in CT Scans of Breast Cancer Patients using a 3D U-Net Cascaded into PatchGANs.
Biomed Phys Eng Express 2023. [PMID:
37433288 DOI:
10.1088/2057-1976/ace631]
[Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/13/2023]
Abstract
The quality of organ volume delineation significantly influences the efficacy of radiotherapy treatment for breast cancer patients. This study developed and tested a novel method for auto-segmentation of the breasts, lungs, and heart. The proposed pipeline leveraged a multi-class 3D U-Net with a pre-trained ResNet(2+1)D-18 encoder branch, cascaded with a 2D PatchGAN mask correction model for each class. This approach required a single 3D model, providing a relatively efficient solution. The models were trained and evaluated on 70 thoracic DICOM datasets belonging to breast cancer patients. The evaluation demonstrated state-of-the-art segmentation performance, with mean Dice similarity coefficient values ranging between 0.89 and 0.98; Hausdorff distance values ranging between 2.25 and 8.68 mm; and mean surface distance values ranging between 0.62 and 2.79 mm. These results underscore the pipeline's potential to enhance breast cancer diagnosis and treatment strategies, with possible applications in other medical sectors utilizing auto-segmentation.
Collapse