安徽省Luminal类型判断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安徽省样本场景下的Luminal类型情况，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，包括术后Ki67增殖指数，同时还要获取系统内乳腺癌类型数据；2数据处理：对数据进行检查核对，确保所有数据去标志化，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，生成乳腺癌的Luminal类型标记，具体判断规则为：如果乳腺癌类型为Luminal型， 同时Ki67增殖指数小于14，则肿瘤类型标记为Luminal A型，反之为Luminal B型。

This dataset, following sample data processing and curation, is intended for training auxiliary diagnostic artificial intelligence (AI) models. It aims to enable the models to better grasp Luminal subtype scenarios in Anhui Province-based samples, extract features and identify underlying patterns, thereby ultimately enhancing the accuracy, robustness and generalization ability of the diagnostic AI models.
1. Data Collection: Anonymized clinical sample data is acquired from medical institutions through formal cooperation agreements, including postoperative Ki67 proliferation index and breast cancer subtype data from the institutional system;
2. Data Processing: Data verification and validation are performed to ensure all data is de-identified, fully anonymized and irreversibly non-reidentifiable. Entries without pathological results are removed, abnormal data is cleaned and eliminated, and generative imputation is conducted for partially missing data;
3. Data Curation: Luminal subtype labels for breast cancer are generated based on raw data and predefined algorithmic rules. The specific judgment criteria are: if the breast cancer subtype is Luminal type and the Ki67 proliferation index is less than 14, the tumor is labeled as Luminal A subtype; otherwise, it is labeled as Luminal B subtype.

搜集汇总

数据集介绍

特点

该数据集包含150条安徽省Luminal类型乳腺癌的样本数据，用于训练辅助诊断人工智能模型。数据经过匿名化处理，包含术后Ki67增殖指数和乳腺癌类型等关键信息，并通过特定算法规则标记Luminal类型，以提高模型的诊断准确性和泛化能力。