COMPUTER AID FOR THE DECISION TO BIOPSY BREAST LESIONS

计算机辅助决定乳房病变活检

基本信息

批准号：
6174135
负责人：
CAREY E FLOYD
金额：
$ 15.2万
依托单位：
DUKE UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
1999
资助国家：
美国
起止时间：
1999-09-01 至 2001-08-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/6174135
关键词：
biopsy breast neoplasm /cancer diagnosis clinical research computer assisted diagnosis computer assisted medical decision making diagnosis design /evaluation female human data mammography

项目摘要

DESCRIPTION (Adapted from Applicant's Abstract): The applicants proposed to investigate the feasibility of developing a Case Based Reasoning (CBR) system to provide support for the clinical decision to perform breast biopsy. The system is designed to aid in the decision to biopsy those patients that have suspicious mammographic findings. The decision to biopsy is a two stage process: 1) mammographer views the mammogram and determines the presence or absence of image features such as calcifications and masses, 2) these features are merged to form a diagnosis. This work is motivated by a recent study which found that 52% of missed breast cancers are due to errors at the decision step and by the fact that about 80% of the biopsies that are performed are benign. The applicants proposed a system to significantly improve this performance by a CBR approach that utilizes a large database of cases with known outcomes. The innovative research would be the development and implementation of statistical measures for deciding which cases in the database come enough to matching the test case. The clinician reads a mammogram and enters the findings into a computer using a standard reporting lexicon (BI-RADS). The database is searched for similar cases and the fraction that were malignant is returned. This likelihood of malignancy is an intuitive response which the clinician can then include in the medical decision.

描述（根据申请人的摘要改编）：申请人提议研究开发基于案例推理（CBR）系统的可行性为进行乳房活检的临床决定提供支持。这系统旨在帮助决定那些患者可疑的乳房X线学发现。进行活检的决定是两个阶段过程：1）乳房X线照片观看乳房X线照片并确定存在或没有图像特征，例如钙化和质量，2）这些特征合并以形成诊断。这项工作是由最近的一项研究激发的发现52％的错过乳腺癌是由于决定步骤的错误而且，大约80％的活检是良性的。申请人提出了一个系统，以通过 CBR方法利用大量具有已知结果的病例数据库。这创新的研究将是统计的发展和实施确定数据库中哪些情况的措施足以与测试案例。临床医生阅读乳房X线照片，并将发现进入使用标准报告词典（BI-RADS）的计算机。搜索数据库对于类似的情况，返回了恶性的分数。这恶性肿瘤的可能性是临床医生可以的直观反应包括在医疗决定中。