Automated 3D Tumor Segmentation using Temporal Cubic PatchGAN (TCuP-GAN)
This work addresses robust 3D segmentation for brain tumors in biomedical imaging, but it is incremental as it builds on existing GAN and LSTM techniques.
The authors tackled 3D tumor segmentation by introducing TCuP-GAN, a model combining generative adversarial networks with convolutional LSTMs, and demonstrated its performance on four BraTS Challenge datasets with metrics like LesionWise Dice and 95% Hausdorff Distance.
Development of robust general purpose 3D segmentation frameworks using the latest deep learning techniques is one of the active topics in various bio-medical domains. In this work, we introduce Temporal Cubic PatchGAN (TCuP-GAN), a volume-to-volume translational model that marries the concepts of a generative feature learning framework with Convolutional Long Short-Term Memory Networks (LSTMs), for the task of 3D segmentation. We demonstrate the capabilities of our TCuP-GAN on the data from four segmentation challenges (Adult Glioma, Meningioma, Pediatric Tumors, and Sub-Saharan Africa subset) featured within the 2023 Brain Tumor Segmentation (BraTS) Challenge and quantify its performance using LesionWise Dice similarity and $95\%$ Hausdorff Distance metrics. We demonstrate the successful learning of our framework to predict robust multi-class segmentation masks across all the challenges. This benchmarking work serves as a stepping stone for future efforts towards applying TCuP-GAN on other multi-class tasks such as multi-organelle segmentation in electron microscopy imaging.