Generating Progressive Images from Pathological Transitions via Diffusion Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zeyu, Zhang, Tianyi, He, Yufang, Feng, Yunlu, Zhao, Yu, Zhang, Guanglei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911792228204544
author Liu, Zeyu
Zhang, Tianyi
He, Yufang
Feng, Yunlu
Zhao, Yu
Zhang, Guanglei
author_facet Liu, Zeyu
Zhang, Tianyi
He, Yufang
Feng, Yunlu
Zhao, Yu
Zhang, Guanglei
contents Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis. However, most models generally require large-scale annotated data for training, which faces challenges due to the sampling and annotation scarcity in pathological images. The rapid developing generative models shows potential to generate more training samples from recent studies. However, they also struggle in generalization diversity with limited training data, incapable of generating effective samples. Inspired by the pathological transitions between different stages, we propose an adaptive depth-controlled diffusion (ADD) network to generate pathological progressive images for effective data augmentation. This novel approach roots in domain migration, where a hybrid attention strategy guides the bidirectional diffusion, blending local and global attention priorities. With feature measuring, the adaptive depth-controlled strategy ensures the migration and maintains locational similarity in simulating the pathological feature transition. Based on tiny training set (samples less than 500), the ADD yields cross-domain progressive images with corresponding soft-labels. Experiments on two datasets suggest significant improvements in generation diversity, and the effectiveness with generated progressive samples are highlighted in downstream classifications. The code is available at https://github.com/Rowerliu/ADD.
format Preprint
id arxiv_https___arxiv_org_abs_2311_12316
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generating Progressive Images from Pathological Transitions via Diffusion Model
Liu, Zeyu
Zhang, Tianyi
He, Yufang
Feng, Yunlu
Zhao, Yu
Zhang, Guanglei
Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis. However, most models generally require large-scale annotated data for training, which faces challenges due to the sampling and annotation scarcity in pathological images. The rapid developing generative models shows potential to generate more training samples from recent studies. However, they also struggle in generalization diversity with limited training data, incapable of generating effective samples. Inspired by the pathological transitions between different stages, we propose an adaptive depth-controlled diffusion (ADD) network to generate pathological progressive images for effective data augmentation. This novel approach roots in domain migration, where a hybrid attention strategy guides the bidirectional diffusion, blending local and global attention priorities. With feature measuring, the adaptive depth-controlled strategy ensures the migration and maintains locational similarity in simulating the pathological feature transition. Based on tiny training set (samples less than 500), the ADD yields cross-domain progressive images with corresponding soft-labels. Experiments on two datasets suggest significant improvements in generation diversity, and the effectiveness with generated progressive samples are highlighted in downstream classifications. The code is available at https://github.com/Rowerliu/ADD.
title Generating Progressive Images from Pathological Transitions via Diffusion Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
url https://arxiv.org/abs/2311.12316