Nuclei Segmentation with Recurrent Residual Convolutional Neural Networks based U-Net (R2U-Net)

TLDR

Biomedical image segmentation, particularly nuclei segmentation from high‑resolution histopathological images, is crucial for extracting detailed nuclear morphometric features, yet traditional methods like Otsu thresholding and watershed often fail, whereas deep‑learning models such as the Recurrent Residual U‑Net have achieved state‑of‑the‑art performance in various medical imaging tasks. This study applies the Recurrent Residual U‑Net to nuclei segmentation for the first time on the publicly available 2018 Data Science Bowl dataset. The authors implemented the Recurrent Residual U‑Net architecture—a convolutional neural network with recurrent residual blocks—on the 2018 Data Science Bowl nuclei segmentation dataset. The model achieved a 92.15 % Dice coefficient on the test set and qualitative results confirm its robust accuracy for nuclei segmentation.

Abstract

Bio-medical image segmentation is one of the promising sectors where nuclei segmentation from high-resolution histopathological images enables extraction of very high-quality features for nuclear morphometrics and other analysis metrics in the field of digital pathology. The traditional methods including Otsu thresholding and watershed methods do not work properly in different challenging cases. However, Deep Learning (DL) based approaches are showing tremendous success in different modalities of bio-medical imaging including computation pathology. Recently, the Recurrent Residual U-Net (R2U-Net) has been proposed, which has shown state-of-the-art (SOTA) performance in different modalities (retinal blood vessel, skin cancer, and lung segmentation) in medical image segmentation. However, in this implementation, the R2U-Net is applied to nuclei segmentation for the first time on a publicly available dataset that was collected from the Data Science Bowl Grand Challenge in 2018. The R2U-Net shows around 92.15% segmentation accuracy in terms of the Dice Coefficient (DC) during the testing phase. In addition, the qualitative results show accurate segmentation, which clearly demonstrates the robustness of the R2U-Net model for the nuclei segmentation task.