Two-Stage Hybrid Supervision Framework for Fast, Low-resource, and Accurate Organ and Pan-cancer Segmentation in Abdomen CT
This work addresses the need for accurate and efficient segmentation in clinical applications like organ quantification and disease diagnosis, but it is incremental as it builds on existing semi-supervised methods.
The paper tackles the problem of abdominal organ and tumor segmentation in CT scans by proposing a hybrid supervised framework that integrates self-training and mean teacher, achieving an average DSC score of 89.79% for organs and 45.55% for lesions on a validation set, with fast inference times and low GPU memory usage.
Abdominal organ and tumour segmentation has many important clinical applications, such as organ quantification, surgical planning, and disease diagnosis. However, manual assessment is inherently subjective with considerable inter- and intra-expert variability. In the paper, we propose a hybrid supervised framework, StMt, that integrates self-training and mean teacher for the segmentation of abdominal organs and tumors using partially labeled and unlabeled data. We introduce a two-stage segmentation pipeline and whole-volume-based input strategy to maximize segmentation accuracy while meeting the requirements of inference time and GPU memory usage. Experiments on the validation set of FLARE2023 demonstrate that our method achieves excellent segmentation performance as well as fast and low-resource model inference. Our method achieved an average DSC score of 89.79\% and 45.55 \% for the organs and lesions on the validation set and the average running time and area under GPU memory-time cure are 11.25s and 9627.82MB, respectively.