Parsimonious Dataset Construction for Laparoscopic Cholecystectomy Structure Segmentation
This work addresses the high labeling costs in medical imaging for surgeons and researchers, but it is incremental as it applies an existing active learning method to a specific surgical domain.
The paper tackles the problem of expensive labeling in medical deep learning by using active learning to select informative frames for constructing a laparoscopic cholecystectomy segmentation dataset, achieving a mean Intersection over Union (mIoU) of 0.4349 with half the data compared to 0.4374 with the full dataset.
Labeling has always been expensive in the medical context, which has hindered related deep learning application. Our work introduces active learning in surgical video frame selection to construct a high-quality, affordable Laparoscopic Cholecystectomy dataset for semantic segmentation. Active learning allows the Deep Neural Networks (DNNs) learning pipeline to include the dataset construction workflow, which means DNNs trained by existing dataset will identify the most informative data from the newly collected data. At the same time, DNNs' performance and generalization ability improve over time when the newly selected and annotated data are included in the training data. We assessed different data informativeness measurements and found the deep features distances select the most informative data in this task. Our experiments show that with half of the data selected by active learning, the DNNs achieve almost the same performance with 0.4349 mean Intersection over Union (mIoU) compared to the same DNNs trained on the full dataset (0.4374 mIoU) on the critical anatomies and surgical instruments.