用生成模型增强甲状腺影像数据，提升疾病分类准确率
AI-Augmented Thyroid Scintigraphy for Robust Classification of Disease
- 采用流匹配与扩散模型进行高保真图像增广
- 流匹配方法使F1-score达0.78，AUC高达0.95
- 结合临床提示的生成模型更适配医疗场景
甲状腺显像对甲状腺疾病诊断至关重要，但深度学习模型常受限于数据少且不平衡。本研究评估了三种数据增强策略：稳定扩散（SD）、流匹配（FM）和传统增广（CA）对疾病分类的影响。基于来自9家医疗机构的2,954例患者的前位甲状腺显像图像，将疾病分为四类：弥漫性结节（DG）、结节性结节（NG）、正常（NL）和甲状腺炎（TI）。通过CA、多种SD与FM模型构建18种增广场景，每组用于训练ResNet18分类器。性能评估涵盖类别与平均精度、召回率、F1分数、AUC及图像保真度指标（FID与KID）。流匹配方法表现最优，原始数据+流匹配（O+FM）配置在微平均、宏平均与加权F1分数上分别达到0.78、0.77、0.78，AUC分别为0.95、0.93、0.94。尽管O+FM+CA也表现良好，但统计上优于单一方案，表明高保真生成增广可超越传统规则。此外，FM生成图像最真实，整体FID为0.66，KID为0.83。在各SD变体中，融合图像与医生提示的SD1效果最佳（宏平均F1: 0.76；FID: 4.17），说明临床提示提供关键上下文。整合流匹配与临床引导的扩散模型显著提升分类性能，凸显先进生成模型在有限数据下训练鲁棒模型的重要性。代码已开源：https://github.com/MaziarSabouri/Stable-Diffusion-Scintigraphy-Augmentation
原文摘要 · Abstract (English)
Thyroid scintigraphy is vital for diagnosing thyroid disorders, yet deep learning (DL) models in this domain often struggle with limited, imbalanced datasets. This study investigates the impact of three data augmentation strategies including Stable Diffusion (SD), Flow Matching (FM), and Conventional Augmentation (CA), on enhancing DL-based classification of disease. Anterior thyroid scintigraphy images from 2,954 patients across nine medical centers were classified into four categories: Diffuse Goiter (DG), Nodular Goiter (NG), Normal (NL), and Thyroiditis (TI). Data augmentation was performed using CA as well as various SD and FM models, creating 18 distinct scenarios. Each augmented dataset was used to train a ResNet18 DL-classifier. Model performance was assessed using class-wise and average precision, recall, F1-score, AUC, and image fidelity metrics (FID and KID). FM-based methods demonstrated top-tier performance, with the Original dataset combined with FM (O+FM) configuration achieving the highest micro, macro, and weighted F1-scores (0.78, 0.77, 0.78) and AUC values (0.95, 0.93, 0.94). While the O+FM+CA model also yielded excellent, balanced results, O+FM was statistically superior, indicating that high-fidelity generative augmentation can supersede conventional heuristics. FM also produced the most realistic images, achieving the lowest overall FID (0.66) and KID (0.83). Among the SD variants, SD1 combining image and prompt inputs was the most effective (macro F1: 0.76; FID: 4.17), showing that physician-generated prompts provide critical clinical context. Integrating FM and clinically-informed SD augmentation substantially improves thyroid scintigraphy classification, highlighting the importance of advanced generative models for robust training on limited datasets. The code is available at: https://github.com/MaziarSabouri/Stable-Diffusion-Scintigraphy-Augmentation
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。