Compact network improves joint nuclei segmentation and classification accuracy

TME-ContextNet: Class-Conditioned Spatial Supervision and Grouped Decoding for Joint Nuclei Instance Segmentation and Classification

Computer Vision and Pattern Recognition

Summary

Distinguishing and classifying different cell nuclei in microscope images is important but challenging because many cells look alike and are tightly packed. The authors present TME-ContextNet, a new model that uses detailed spatial information based on distance maps from existing labels and groups decoding tasks to better separate and identify nuclei. Their method includes modules that combine local and global image context and reduces extra computations, resulting in good accuracy on several pathology datasets while using fewer parameters than previous models. This means it can analyze cells more efficiently and accurately without needing extra annotation work.

What this means in practice

  • For medical image analysts: Improve automated analysis of tissue samples by jointly segmenting and classifying nuclei with precise boundaries and spatial context.
  • For digital pathology software developers: Integrate efficient and compact models for joint nuclei segmentation and classification to speed up pathology workflows and reduce computational needs.$Commercial implications: Enables development of improved diagnostic tools for pathology labs that handle large histology slide datasets, offering faster and more accurate cell analysis.

Authors

Rukang Ma, Bingxue Wang, Liwen Zou, Yingying Cao, Zhenghua Cai, Yu Li, Dong Wang, Huiyu Zhou, Luying Gui

Abstract

Joint nuclei instance segmentation and classification requires precise boundaries and neighborhood information that helps distinguish morphologically similar cell types. We present TME-ContextNet, a multi-task framework that learns class-conditioned spatial context from existing nuclear annotations and organizes decoding into geometry-related and semantic task groups. Class-conditioned spatial supervision extends nuclear labels into a dense target using Euclidean distance transforms, requiring no additional tissue-region annotation. We derive its nearest-region interpretation and characterize its stability to small annotation perturbations. A local--global context module combines dilated convolution and self-attention, while a grouped task decoder reduces redundant computation. The spatial head supplies training supervision and is omitted during inference. Experiments on PanMix, CoNSeP, and PanNuke yield Dice scores of 80.23%, 65.32%, and 79.13%, and mean multi-class panoptic quality (mPQ+) scores of 67.62%, 35.50%, and 43.74%, respectively. PanNuke results are averaged across three test folds. Target and decoder controls support the combination of distance-based supervision and grouped decoding while identifying their dependence on task configuration. The framework uses 36.40 million parameters, compared with 54.74 million for HoVer-Net. These findings support a compact, context-aware formulation for joint nuclei analysis in computational pathology.
View PDFOpen arXiv