Boosting Liver and Lesion Segmentation from CT Scans By Mask Mining

We propose a novel procedure to improve liver and lesion segmentation from CT scans for U-Net based models. Our method extends standard segmentation pipelines to focus on higher target recall or reduction of noisy false-positive predictions, by including segmentation errors into a new learning process appended to the main training setup. This allows the model to find features which explain away previous errors. We evaluate on semantically distinct architectures on liver and lesion segmentation data are provided by the Liver Tumor Segmentation challenge (LiTS), with an increase in dice score of up to 2 points.