The importance of data domain on self-supervised learning for brain metastasis detection and segmentation

Youngjin Yoo, Gengyan Zhao, Andreea Sandu, Thomas J. Re, Jyotipriya Das, Hesheng Wang, Michelle Kim, Colette Shen, Yueh Lee, Douglas Kondziolka, Mohannad Ibrahim, Jun Lian, Rajan Jain, Tong Zhu, Hemant Parmar, James M. Balter, Yue Cao, Eli Gibson, Dorin Comaniciu

Abstract: Brain metastases are the most common malignant form of tumors and occur in 10%-30% of adult patients with systematic cancer. With recent advances in treatment options, there is an increasing evidence that automated detection and segmentation from MRI can assist clinicians for diagnosis and therapy planning. In this study, we investigate the impact of data domain on self-supervised learning (SSL) for pretraining a deep learning network to detect and segment brain metastases on 3D post-contrast T1-weighted images. We performed pretraining a 3D patch-based U-Net using the Model Genesis framework on three subject cohorts that have different data domain. The pretrained networks were then finetuned on brain MR scans from patients with metastases as a downstream task dataset. We analyzed the impact of data domain on SSL by examining validation metric evolution, FROC analyses and testing performance of early-trained models and best-validated models. Our results suggested that, in the early stage of finetuning for the target task, SSL is crucial for faster training convergence and similar data domain on SSL could be helpful to attain improved detection and segmentation performance earlier. However, we observed that the importance of data domain similarity for SSL progressively diminished as training continued with sufficient amount of iterations in our relatively large data regime. After training convergence, the best-validated models pretrained with SSL provided enhanced detection performance over the model without pretraining regardless of data domain.