CISCA and CytoDArk0: a Cell Instance Segmentation and Classification method for histo(patho)logical image Analyses and a new, open, Nissl-stained dataset for brain cytoarchitecture studies

2024-09-06

arXiv.org

AI Summary

To address the challenge of jointly modeling instance segmentation and classification for cells in microscopic tissue images, this paper proposes CISCA: a framework featuring a lightweight three-head U-Net backbone that unifies boundary detection, cell-body semantic segmentation, background classification, and four-directional distance map regression. It introduces a novel instance generation algorithm fusing distance and boundary maps, enabling end-to-end joint inference for segmentation and type classification. We present CytoDArk0—the first large-scale, publicly available Nissl-stained brain tissue dataset—containing ~40,000 meticulously annotated neurons and glial cells. Additionally, we propose cross-stain (H&E/Nissl) and cross-tissue generalization training strategies. CISCA achieves state-of-the-art performance on CoNIC, PanNuke, MoNuSeg, and CytoDArk0, significantly improving accuracy and efficiency in digital pathology analysis and cytoarchitectural profiling across diverse tissues, magnifications, and staining protocols.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Delineating and classifying individual cells in microscopy tissue images is inherently challenging yet remains essential for advancements in medical and neuroscientific research. In this work, we propose a new deep learning framework, CISCA, for automatic cell instance segmentation and classification in histological slices. At the core of CISCA is a network architecture featuring a lightweight U-Net with three heads in the decoder. The first head classifies pixels into boundaries between neighboring cells, cell bodies, and background, while the second head regresses four distance maps along four directions. The outputs from the first and second heads are integrated through a tailored post-processing step, which ultimately produces the segmentation of individual cells. The third head enables the simultaneous classification of cells into relevant classes, if required. We demonstrate the effectiveness of our method using four datasets, including CoNIC, PanNuke, and MoNuSeg, which are publicly available H&Estained datasets that cover diverse tissue types and magnifications. In addition, we introduce CytoDArk0, the first annotated dataset of Nissl-stained histological images of the mammalian brain, containing nearly 40k annotated neurons and glia cells, aimed at facilitating advancements in digital neuropathology and brain cytoarchitecture studies. We evaluate CISCA against other state-of-the-art methods, demonstrating its versatility, robustness, and accuracy in segmenting and classifying cells across diverse tissue types, magnifications, and staining techniques. This makes CISCA well-suited for detailed analyses of cell morphology and efficient cell counting in both digital pathology workflows and brain cytoarchitecture research.

Problem

• Automates cell segmentation in histological images
• Classifies cells using deep learning techniques
• Introduces new dataset for brain cytoarchitecture studies

Innovation

• Deep learning framework CISCA
• Lightweight U-Net architecture
• CytoDArk0 Nissl-stained dataset