Deep Adversarial Image Synthesis for Nuclei Segmentation of Histopathology Image

Cheng, Jijun; Wang, Zimin; Liu, Zhenbing; Feng, Zhengyun; Wang, Huadeng; Pan, Xipeng

doi:10.1109/accc54619.2021.00017

Cited by 2 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In histopathological image segmentation, Kurmi et al 23 proposed a content-based image retrieval algorithm for the recognition and extraction of cell nuclei, which is used for histopathological image segmentation and provides cell nucleus segmentation in three cascading stages. Jun et al 24 proposed a novel histopathological image data augmentation strategy, which assisted a deep attention feature fusion generative adversarial network (DAFF-GAN) to improve the effectiveness of cell nucleus segmentation. Sun et al 25 proposed a gastric histopathological image segmentation (GHIS) method based on a hierarchical conditional random field (HCRF) model, which can locate abnormal (cancerous) areas in gastric histopathological images to assist pathologists in their medical work.…”

Section: Histopathological Image Segmentationmentioning

confidence: 99%

A Two-stage Weakly Supervised Semantic Segmentation Model Based on Pathological Tissue Relationships

Huang

Liao

Peng

2023

Preprint

View full text Add to dashboard Cite

The segmentation of histopathological images is an important problem in the field of medical image processing. However, the high cost of manual annotation and the lack of large-scale annotated data are important factors that restrict the application of deep learning methods in this field. To overcome these challenges, we propose a two-stage weakly supervised semantic segmentation model based on pathological tissue relationships. Our framework leverages the potential relationships between various tissues in histopathological images through a similar Graph Parsing Attention Mechanism to improve segmentation performance. At the segmentation stage, we validate the effectiveness of our cyclic pseudo-mask strategy for denoising and segmentation, and further enhance segmentation performance through multi-resolution supervision. Our model exhibits advanced performance on both BCSS and LUAD histopathology datasets, demonstrating the superiority of our framework. The contribution of our paper lies in the introduction of prior knowledge about the potential relationships between tissues into the weakly supervised semantic segmentation domain, which realizes high-quality histopathological image segmentation on small sample datasets. Moreover, we propose novel strategies such as cyclic pseudo-masks and multi-resolution supervision to improve segmentation performance. Our framework has significant application value and theoretical significance, providing accurate diagnostic support for doctors.

show abstract

Section: Histopathological Image Segmentationmentioning

confidence: 99%

A Two-stage Weakly Supervised Semantic Segmentation Model Based on Pathological Tissue Relationships

Huang

Liao

Peng

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Besides the most common data augmentation ways like rotation, flipping and etc, we introduced our previously proposed GAN-based model for data augmentation [9]. This model used the masks from Lizard dataset as the input image and generated pseudo histopathology images.…”

Section: A Gan-based Data Augmentationmentioning

confidence: 99%

“…With the help of our previous works in digital pathology, we proposed a systematic and standardized pipeline for nuclei segmentation and classification by integrating several independent components, including data augmentation, stain normalization, CNN backbone and loss functions. First, we applied a GAN-based model [9] to generate paired pseudo masks and images to extend the training set. Next, we introduced a self-supervised stain normalization model [10] to make the color style consistent.…”

Section: Introductionmentioning

confidence: 99%

A Standardized Pipeline for Colon Nuclei Identification and Counting Challenge

Cheng¹,

Pan²,

Feihu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Nuclear segmentation and classification is an essential step for computational pathology. TIA lab from Warwick University organized a nuclear segmentation and classification challenge (CoNIC) [1] for H&E stained histopathology images in colorectal cancer with two highly correlated tasks, nuclei segmentation and classification task and cellular composition task. There are a few obstacles we have to address in this challenge, 1) limited training samples, 2) color variation, 3) imbalanced annotations, 4) similar morphological appearance among classes. To deal with these challenges, we proposed a standardized pipeline for nuclear segmentation and classification by integrating several pluggable components. First, we built a GAN-based model to automatically generate pseudo images for data augmentation. Then we trained a self-supervised stain normalization model to solve the color variation problem. Next we constructed a baseline model HoVer-Net with cost-sensitive loss to encourage the model pay more attention on the minority classes. According to the results of the leaderboard, our proposed pipeline achieves 0.40665 mPQ+ (Rank 49th) and 0.62199 r2 (Rank 10th) in the preliminary test phase.

show abstract

Deep Adversarial Image Synthesis for Nuclei Segmentation of Histopathology Image

Cited by 2 publications

References 19 publications

A Two-stage Weakly Supervised Semantic Segmentation Model Based on Pathological Tissue Relationships

A Two-stage Weakly Supervised Semantic Segmentation Model Based on Pathological Tissue Relationships

A Standardized Pipeline for Colon Nuclei Identification and Counting Challenge

Contact Info

Product

Resources

About