Medical Imaging Datasets for Multimodal Disease Detection and Diagnosis Research

This collection of medical image datasets is a valuable resource for anyone involved in medical imaging and disease research. It includes a variety of images from different medical fields, all designed to support research in diagnosis and treatment. The datasets cover chest CT-scans, lung radiography, brain MRI, retinal imaging, and gastrointestinal tract imaging. The chest CT-scan dataset includes 867 images of normal lungs and three types of lung cancer—adenocarcinoma, large cell carcinoma, and squamous cell carcinoma—providing essential data for understanding lung cancer. The lung radiography dataset offers 1,198 X-ray images that include normal lungs and conditions like COVID-19, lung opacity, and viral pneumonia, making it useful for comparing COVID-19 with other respiratory diseases. The brain MRI dataset contains 253 scans of both normal brains and those with tumors, ideal for studying brain tumor detection. The retinal imaging dataset features 2,757 images covering normal retinas and seven types of retinal conditions, such as diabetic retinopathy and glaucoma, offering a comprehensive resource for eye disease research. Lastly, the gastrointestinal tract dataset contains 2,000 images of normal and diseased colons, including conditions like esophagitis, polyps, and ulcerative colitis, important for studying gastrointestinal health. Each dataset is carefully curated and resampled to ensure accuracy and prevent data leakage, making them reliable tools for research and machine learning.

本医疗图像数据集集合是医学影像和疾病研究领域的重要资源。该集合汇聚了来自不同医学领域的多种图像，旨在为诊断和治疗研究提供支持。数据集涵盖了胸部CT扫描、肺X光摄影、脑部MRI、视网膜成像以及胃肠道成像等多种类型。胸部CT扫描数据集包含867张正常肺部图像及三种类型的肺癌图像——腺癌、大细胞癌和鳞状细胞癌，为理解肺癌提供了关键数据。肺X光摄影数据集提供了1,198张X光图像，包括正常肺部以及COVID-19、肺不透光和病毒性肺炎等状况，有助于比较COVID-19与其他呼吸系统疾病。脑部MRI数据集包含253次扫描，包括正常大脑和肿瘤大脑，是研究脑肿瘤检测的理想选择。视网膜成像数据集展示了2,757张图像，涵盖正常视网膜和七种视网膜状况，如糖尿病视网膜病变和青光眼，为眼科疾病研究提供了全面资源。最后，胃肠道数据集包含了2,000张正常和病变结肠图像，包括食管炎、息肉和溃疡性结肠炎等状况，对研究胃肠道健康具有重要意义。每个数据集均经过精心整理和重采样，以确保数据的准确性并防止数据泄露，从而成为研究和机器学习的可靠工具。