Mask R-CNN Outperforms U-Net in Instance Segmentation for Overlapping Cells

作者：Luca Rettenberger, Friedrich Rieken Münke, Roman Bruch, Markus Reischl · 发表于：Current Directions in Biomedical Engineering · 年份：2023 · DOI：10.1515/cdbme-2023-1084 · 被引用次数：15 · 研究领域：Digital Imaging for Blood Diseases、AI in cancer detection、Cell Image Analysis Techniques

Abstract U-Net is the go-to approach for biomedical segmentation applications. However, it is not designed to segment overlapping objects, a challenge Mask R-CNN has shown to have great potential in. Yet, Mask R-CNN receives little attention in biomedicine. Hence, we evaluate both approaches on a publicly available biomedical dataset. We find that Mask RCNN outperforms U-Net in segmenting overlapping cells and achieves comparable performance if they do not intersect. Our study provides valuable decision support to practitioners in selecting an appropriate method when solving instance segmentation tasks using deep learning, as well as important insights into enhancing the accuracy of such approaches in biomedical image analysis.