Color Space-based HoVer-Net for Nuclei Instance Segmentation and Classification

2022-03-03 · Hussam Azzuni, Muhammad Ridzuan, Min Xu, Mohammad Yaqub

Nuclei segmentation and classification is the first and most crucial step that is utilized for many different microscopy medical analysis applications. However, it suffers from many issues such as the segmentation of small objects, imbalance, and fine-grained differences between types of nuclei. In this paper, multiple different contributions were done tackling these problems present. Firstly, the recently released "ConvNeXt" was used as the encoder for HoVer-Net model since it leverages the key components of transformers that make them perform well. Secondly, to enhance the visual differences between nuclei, a multi-channel color space-based approach is used to aid the model in extracting distinguishing features. Thirdly, Unified Focal loss (UFL) was used to tackle the background-foreground imbalance. Finally, Sharpness-Aware Minimization (SAM) was used to ensure generalizability of the model. Overall, we were able to outperform the current state-of-the-art (SOTA), HoVer-Net, on the preliminary test set of the CoNiC Challenge 2022 by 12.489% mPQ+.

📄 PDF Abstract BibTeX arXiv:2203.01940

Code (0)

등록된 구현이 없습니다.

Tasks

Instance Segmentation Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Focal Loss A Focal Loss function addresses class imbalance during training in tasks like object detection. Focal loss applies a modulating term to the cross entropy loss in order to…

Sharpness-Aware Minimization Sharpness-Aware Minimization, or SAM, is a procedure that improves model generalization by simultaneously minimizing loss value and loss sharpness. SAM functions by…

HoVer-UNet: Accelerating HoVerNet with UNet-based multi-class nuclei segmentation via knowledge distillation

2023-11-21 · Cristian Tommasino, Cristiano Russo, Antonio Maria Rinaldi, Francesco Ciompi

We present HoVer-UNet, an approach to distill the knowledge of the multi-branch HoVerNet framework for nuclei instance segmentation and classification in histopathology. We propose a compact, streamlined single UNet netw…

Instance Segmentation Knowledge Distillation Semantic Segmentation

Separable-HoverNet and Instance-YOLO for Colon Nuclei Identification and Counting

2022-03-01 · Chunhui Lin, Liukun Zhang, Lijian Mao, Min Wu 외

Nuclear segmentation, classification and quantification within Haematoxylin & Eosin stained histology images enables the extraction of interpretable cell-based features that can be used in downstream explainable models i…

Classification Explainable Models Nuclear Segmentation Segmentation

Cellular Segmentation and Composition in Routine Histology Images using Deep Learning

2022-03-04 · Muhammad Dawood, Raja Muhammad Saad Bashir, Srijay Deshpande, Manahil Raza 외

Identification and quantification of nuclei in colorectal cancer haematoxylin \& eosin (H\&E) stained histology images is crucial to prognosis and patient management. In computational pathology these tasks are referred t…

Management Nuclear Segmentation Prognosis Segmentation

HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images

2018-12-16 · Simon Graham, Quoc Dang Vu, Shan E Ahmed Raza, Ayesha Azam 외

Nuclear segmentation and classification within Haematoxylin & Eosin stained histology images is a fundamental prerequisite in the digital pathology work-flow. The development of automated methods for nuclear segmentation…

Classification General Classification Multi-tissue Nucleus Segmentation Nuclear Segmentation+1

Panoptic segmentation with highly imbalanced semantic labels

2022-03-03 · Josef Lorenz Rumberger, Elias Baumann, Peter Hirsch, Andrew Janowczyk 외

We describe here the panoptic segmentation method we devised for our participation in the CoNIC: Colon Nuclei Identification and Counting Challenge at ISBI 2022. Key features of our method are a weighted loss specificall…

Instance Segmentation Panoptic Segmentation Segmentation Semantic Segmentation