paper-with-me

홈 › Papers

Improving Diagnostic Accuracy for Oral Cancer with inpainting Synthesis Lesions Generated Using Diffusion Models

2025-08-08 · Yong Oh Lee, JeeEun Kim, Jung Woo Lee arxiv

In oral cancer diagnostics, the limited availability of annotated datasets frequently constrains the performance of diagnostic models, particularly due to the variability and insufficiency of training data. To address these challenges, this study proposed a novel approach to enhance diagnostic accuracy by synthesizing realistic oral cancer lesions using an inpainting technique with a fine-tuned diffusion model. We compiled a comprehensive dataset from multiple sources, featuring a variety of oral cancer images. Our method generated synthetic lesions that exhibit a high degree of visual fidelity to actual lesions, thereby significantly enhancing the performance of diagnostic algorithms. The results show that our classification model achieved a diagnostic accuracy of 0.97 in differentiating between cancerous and non-cancerous tissues, while our detection model accurately identified lesion locations with 0.85 accuracy. This method validates the potential for synthetic image generation in medical diagnostics and paves the way for further research into extending these methods to other types of cancer diagnostics.

📄 PDF Abstract BibTeX arXiv:2508.06151

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Manipulation of oral cancer speech using neural articulatory synthesis

2022-03-31 · Bence Mark Halpern, Teja Rebernik, Thomas Tienkamp, Rob van Son 외

We present an articulatory synthesis framework for the synthesis and manipulation of oral cancer speech for clinical decision making and alleviation of patient stress. Objective and subjective evaluations demonstrate tha…

Decision Making

The DEVIL is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting

2021-05-11 · CVPR 2022 1 · Ryan Szeto, Jason J. Corso

Quantitative evaluation has increased dramatically among recent video inpainting work, but the video and mask content used to gauge performance has received relatively little attention. Although attributes such as camera…

AttributeDiagnosticVideo Inpainting

Let it shine: Autofluorescence of Papanicolaou-stain improves AI-based cytological oral cancer detection

2024-07-02 · Wenyi Lian, Joakim Lindblad, Christina Runow Stark, Jan-Michaél Hirsch 외

Oral cancer is a global health challenge. It is treatable if detected early, but it is often fatal in late stages. There is a shift from the invasive and time-consuming tissue sampling and histological examination, towar…

DiagnosticImage Registration

UniPaint: Unified Space-time Video Inpainting via Mixture-of-Experts

2024-12-09 · Zhen Wan, Yue Ma, Chenyang Qi, Zhiheng Liu 외

In this paper, we present UniPaint, a unified generative space-time video inpainting framework that enables spatial-temporal inpainting and interpolation. Different from existing methods that treat video inpainting and v…

Mixture-of-ExpertsVideo Inpainting

A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis

2025-12-15 · Xianchao Guan, Zhiyuan Fan, Yifeng Wang, Fuqiang Chen 외 arxiv

The development of clinical-grade artificial intelligence in pathology is limited by the scarcity of diverse, high-quality annotated datasets. Generative models offer a potential solution but suffer from semantic instabi…

Visual Question AnsweringSelf-Supervised LearningCross-Modal RetrievalNuclear Segmentation