Multi-task deep learning for automatic image segmentation and treatment response assessment in metastatic ovarian cancer.
Authors
Affiliations (12)
Affiliations (12)
- Department of Physics, University of Cambridge, Cambridge, United Kingdom.
- Department of Oncology, University of Cambridge, Cambridge, United Kingdom. [email protected].
- Early Cancer Institute, University of Cambridge, Cambridge, United Kingdom. [email protected].
- Department of Oncology, University of Cambridge, Cambridge, United Kingdom.
- Early Cancer Institute, University of Cambridge, Cambridge, United Kingdom.
- jung diagnostics GmbH, Hamburg, Germany.
- Cancer Research UK Cambridge Institute, Cambridge, United Kingdom.
- Cancer Research UK Cambridge Centre, Cambridge, United Kingdom.
- Cambridge University Hospitals NHS Foundation Trust, Cambridge, United Kingdom.
- Research Center for Medical Image Analysis and AI, Danube University, Krems an der Donau, Austria.
- Department of Radiology, Barts Health NHS Trust, London, United Kingdom.
- Department of Radiologic Sciences, Università Cattolica del Sacro Cuore, Milan, Italy.
Abstract
: High-grade serous ovarian carcinoma (HGSOC) is characterised by significant spatial and temporal heterogeneity, often presenting at an advanced metastatic stage. One of the most common treatment approaches involves neoadjuvant chemotherapy (NACT), followed by surgery. However, the multi-scale complexity of HGSOC poses a major challenge in evaluating response to NACT. : Here, we present a multi-task deep learning approach that facilitates simultaneous segmentation of pelvic/ovarian and omental lesions in contrast-enhanced computerised tomography (CE-CT) scans, as well as treatment response assessment in metastatic ovarian cancer. The model combines multi-scale feature representations from two identical U-Net architectures, allowing for an in-depth comparison of CE-CT scans acquired before and after treatment. The network was trained using 198 CE-CT images of 99 ovarian cancer patients for predicting segmentation masks and evaluating treatment response. : It achieves an AUC of 0.78 (95% CI [0.70-0.91]) in an independent cohort of 98 scans of 49 ovarian cancer patients from a different institution. In addition to the classification performance, the segmentation Dice scores are only slightly lower than the current state-of-the-art for HGSOC segmentation. : This work is the first to demonstrate the feasibility of a multi-task deep learning approach in assessing chemotherapy-induced tumour changes across the main disease burden of patients with complex multi-site HGSOC, which could be used for treatment response evaluation and disease monitoring.