DeGPR

DEGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting

Abstract

Multi-class cell detection and counting is an essential task for many pathological diagnoses. Manual counting is tedious and often leads to inter-observer variations among pathologists. While there exist multiple, general-purpose, deep learning-based object detection and counting methods, they may not readily transfer to detecting and counting cells in medical images, due to the limited data, presence of tiny overlapping objects, multiple cell types, severe class-imbalance, minute differences in size/shape of cells, etc. In response, we propose guided posterior regularization DeGPR, which assists an object detector by guiding it to exploit discriminative features among cells. The features may be pathologist-provided or inferred directly from visual data. We validate our model on two publicly available datasets (CoNSeP and MoNuSAC), and on MuCeD, a novel dataset that we contribute. MuCeD consists of 55 biopsy images of the human duodenum for predicting celiac disease. We perform extensive experimentation with three object detection baselines on three datasets to show that DeGPR is model-agnostic, and consistently improves baselines obtaining up to 9% (absolute) mAP gains.

Model Details

Yolov5 is trained on MuCeD dataset with Posterior Regularization.

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: [https://github.com/dair-iitd/DeGPR]
• Paper : here

Training Details

Training Data

Training dataset can be found here

Results

Citation

@inproceedings{tyagi2023degpr,
  title={DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting},
  author={Tyagi, Aayush Kumar and Mohapatra, Chirag and Das, Prasenjit and Makharia, Govind and Mehra, Lalita and AP, Prathosh and others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={23913--23923},
  year={2023}
}