paper-with-me

Papers

Diverse Image Generation with Diffusion Models and Cross Class Label Learning for Polyp Classification

2025-02-08 · Vanshali Sharma, Debesh Jha, M. K. Bhuyan, Pradip K. Das, Ulas Bagci

Pathologic diagnosis is a critical phase in deciding the optimal treatment procedure for dealing with colorectal cancer (CRC). Colonic polyps, precursors to CRC, can pathologically be classified into two major types: adenomatous and hyperplastic. For precise classification and early diagnosis of such polyps, the medical procedure of colonoscopy has been widely adopted paired with various imaging techniques, including narrow band imaging and white light imaging. However, the existing classification techniques mainly rely on a single imaging modality and show limited performance due to data scarcity. Recently, generative artificial intelligence has been gaining prominence in overcoming such issues. Additionally, various generation-controlling mechanisms using text prompts and images have been introduced to obtain visually appealing and desired outcomes. However, such mechanisms require class labels to make the model respond efficiently to the provided control input. In the colonoscopy domain, such controlling mechanisms are rarely explored; specifically, the text prompt is a completely uninvestigated area. Moreover, the unavailability of expensive class-wise labels for diverse sets of images limits such explorations. Therefore, we develop a novel model, PathoPolyp-Diff, that generates text-controlled synthetic images with diverse characteristics in terms of pathology, imaging modalities, and quality. We introduce cross-class label learning to make the model learn features from other classes, reducing the burdensome task of data annotation. The experimental results report an improvement of up to 7.91% in balanced accuracy using a publicly available dataset. Moreover, cross-class label learning achieves a statistically significant improvement of up to 18.33% in balanced accuracy during video-level analysis. The code is available at https://github.com/Vanshali/PathoPolyp-Diff.

📄 PDF Abstract BibTeX arXiv:2502.05444

Code (1)

vanshali/pathopolyp-diff 공식 구현 pytorch

Tasks

Image GenerationMedical Procedure

Similar Papers 제목 키워드 기반

Towards Universal Dataset Distillation via Task-Driven Diffusion

2025-01-01 · CVPR 2025 1 · Ding Qi, Jian Li, Junyao Gao, Shuguang Dou 외

Dataset distillation (DD) condenses key information from large-scale datasets into smaller synthetic datasets, reducing storage and computational costs for training networks. However, recent research has primarily fo…

Dataset Distillationimage-classificationImage ClassificationImage Generation

FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 Classes

2024-02-28 · Ziying Pan, Kun Wang, Gang Li, Feihong He 외

The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 class…

Conditional Image GenerationImage Generationparameter-efficient fine-tuning

Diffusion Probe: Generated Image Result Prediction Using CNN Probes

2026-02-27 · Benlei Cui, Bukun Huang, Zhizeng Ye, Xuemei Dong 외 arxiv

Text-to-image (T2I) diffusion models lack an efficient mechanism for early quality assessment, leading to costly trial-and-error in multi-generation scenarios such as prompt iteration, agent-based generation, and flow-gr…

DiffX: Guide Your Layout to Cross-Modal Generative Modeling

2024-07-22 · Zeyu Wang, Jingyu Lin, Yifei Qian, Yi Huang 외

Diffusion models have made significant strides in language-driven and layout-driven image generation. However, most diffusion models are limited to visible RGB image generation. In fact, human perception of the world is …

DenoisingImage CaptioningImage Generation

DreamDA: Generative Data Augmentation with Diffusion Models

2024-03-19 · Yunxiang Fu, Chaoqi Chen, Yu Qiao, Yizhou Yu

The acquisition of large-scale, high-quality data is a resource-intensive and time-consuming endeavor. Compared to conventional Data Augmentation (DA) techniques (e.g. cropping and rotation), exploiting prevailing diffus…

Data AugmentationDiversity