KongNet: A Multi-headed Deep Learning Model for Detection and Classification of Nuclei in Histopathology Images

TL;DR

KongNet is a multi-headed deep learning model that effectively detects and classifies nuclei in histopathology images, achieving top performance in multiple challenges and datasets.

Contribution

The paper introduces KongNet, a novel multi-decoder architecture with attention modules, demonstrating superior nuclei detection and classification across diverse datasets.

Findings

Achieved first place in MONKEY Challenge track 1

Secured first place in MIDOG Challenge with KongNet-Det

Established state-of-the-art on PanNuke and CoNIC datasets

Abstract

Accurate detection and classification of nuclei in histopathology images are critical for diagnostic and research applications. We present KongNet, a multi-headed deep learning architecture featuring a shared encoder and parallel, cell-type-specialised decoders. Through multi-task learning, each decoder jointly predicts nuclei centroids, segmentation masks, and contours, aided by Spatial and Channel Squeeze-and-Excitation (SCSE) attention modules and a composite loss function. We validate KongNet in three Grand Challenges. The proposed model achieved first place on track 1 and second place on track 2 during the MONKEY Challenge. Its lightweight variant (KongNet-Det) secured first place in the 2025 MIDOG Challenge. KongNet pre-trained on the MONKEY dataset and fine-tuned on the PUMA dataset ranked among the top three in the PUMA Challenge without further optimisation. Furthermore, KongNet established state-of-the-art performance on the publicly available PanNuke and CoNIC datasets. Our results demonstrate that the specialised multi-decoder design is highly effective for nuclei detection and classification across diverse tissue and stain types. The pre-trained model weights along with the inference code have been publicly released to support future research.