江西省HER2型乳腺癌辅助诊断模型训练数据

通过对样本的数据处理和数据加工，提供给辅助诊断人工智能模型进行训练，帮助人工智能模型更好地理解江西省样本场景下HER2型乳腺癌的情况，提取特征，发现规律，最终提高诊断人工智能模型的准确性、鲁棒性和泛化能力。1数据采集：通过正式合作协议，从医疗机构取得匿名化的样本临床数据，包括是否有术后病理结果，术后Her2情况，术后fish情况；2数据处理：对数据进行检查核对，确保所有数据去标识化，处于完全匿名化状态且不可还原的状态，将没有病理结果的数据去除，对异常数据进行清洗去除，对部分缺失数据进行生成式补充；3数据加工：基于原始数据以及算法规则HER2型乳腺癌的术后状态，生成阴性阳性分型标记，具体规则为：如果Her2满足3+或Her2满足2+且同时术后Fish为扩增则标记为阳性，其余标记为阴性。This dataset is subjected to sample data processing and curation, and provided for training auxiliary diagnostic artificial intelligence models. It aims to help the AI models better comprehend the scenario of HER2-positive breast cancer in samples from Jiangxi Province, extract features and discover patterns, ultimately enhancing the accuracy, robustness and generalization ability of the diagnostic AI models. 1. Data Collection: Obtain anonymized clinical sample data from medical institutions through formal cooperation agreements, including availability of post-operative pathological results, post-operative Her2 status and post-operative FISH results; 2. Data Processing: Perform inspection and verification on the data to ensure that all data is de-identified, fully anonymized and irreversibly unidentifiable; remove data without post-operative pathological results, clean and eliminate abnormal data, and conduct generative supplementation for partially missing data; 3. Data Curation: Generate negative and positive classification labels for the post-operative status of HER2-positive breast cancer based on the original data and algorithmic rules. The specific rules are: label as positive if Her2 is 3+, or Her2 is 2+ and post-operative FISH results show amplification; otherwise, label as negative.

搜集汇总

数据集介绍

特点

该数据集为江西省HER2型乳腺癌辅助诊断模型训练数据，包含150条样本数据，每年更新。数据来源于企业，经过匿名化处理，用于训练人工智能模型以提高诊断准确性。数据处理包括数据清洗、去标识化和生成式补充，最终生成阴性阳性分型标记。