Lung Cancer Detection - Dataset.zip

This dataset comprises medical images categorized into four distinct classes: Adenocarcinoma, Large Cell Carcinoma, Squamous Cell Carcinoma, and Normal. The dataset includes a total of 1,000 images, with 338 images labeled as Adenocarcinoma, 187 as Large Cell Carcinoma, 260 as Squamous Cell Carcinoma, and 215 as Normal. The images are primarily in PNG format (988 images) with a small fraction in JPG format (12 images). The average image dimensions are 258 pixels in height and 356 pixels in width.The dataset is structured into three subsets: training, validation, and test sets, ensuring proper evaluation and model generalization. Additionally, a separate category, referred to as "bad images," stores non-readable or corrupted images that are unsuitable for processing. The dataset provides a valuable resource for developing and evaluating deep learning models for lung cancer detection and classification.本数据集包含四类医学图像，分别为腺癌（Adenocarcinoma）、大细胞癌（Large Cell Carcinoma）、鳞状细胞癌（Squamous Cell Carcinoma）与正常样本。数据集总计包含1000张图像，其中标注为腺癌的图像338张、大细胞癌187张、鳞状细胞癌260张，正常样本图像215张。图像格式以PNG为主（共988张），仅少量为JPG格式（12张），平均图像尺寸为高258像素、宽356像素。数据集划分为训练集、验证集与测试集三个子集，以保障模型得到合理评估并具备良好泛化能力。此外，数据集还设有单独的坏图像（bad images）类别，用于存储无法读取或已损坏、不适用于模型处理的图像。本数据集可为肺癌检测与分类相关深度学习模型的开发与评估提供宝贵的研究资源。