Improving breast cancer diagnosis with computer-aided diagnosis
Improving breast cancer diagnosis with computer-aided diagnosis
复制标题
DOI：
10.1016/s1076-6332(99)80058-0
复制
发表时间：
1999-01-01
影响因子：
4.8
通讯作者：
Doi, K
中科院分区：
文献类型：
--
作者：
Jiang, YL;Nishikawa, RM;Doi, K
理由和目标。本研究的目的是测试计算机辅助诊断（CAD）是否可以提高放射科医师在乳腺癌诊断中的表现。的;本研究中使用的计算机澄清方案基于从标准视图乳房X线照片获得的8个计算机提取特征来估计簇状微钙化的恶性可能性;本研究中使用了近连续活检系列中的104个经组织学验证的微钙化病例（46个恶性，58个良性）。观察员的表现进行了测量，10名放射科医生阅读原始的标准和放大视图的乳房X线照片。计算机辅助提供了恶性肿瘤可能性的百分比估计。结果计算机辅助下的平均ROC曲线面积（A（z））从无辅助时的0.61增加到有辅助时的0.75（P <0.0001）。平均而言，在计算机辅助下，每个观察者建议恶性病变病例增加6.4次活检（P = 0.0006），良性病变病例减少6.0次活检（P = 0.003）。这种改善对应于敏感性（从73.5%到87.4%）、特异性（从31.6%到41.9%）和假设阳性活检率（从46%到55%）的增加。计算机辅助诊断可用于提高放射科医生在癌症诊断中的表现。
Rationale and Objectives. The purpose of this study was to test whether computer-aided diagnosis (CAD) can improve radiologists' performance in breast cancer diagnosis.Materials and Methods. The; computer clarification scheme used in this study estimates the likelihood of malignancy for clustered microcalcifications based on eight computer-extracted features obtained from standard-view mammograms; One hundred four histologically verified cases of microcalcifications (46 malignant, 58 benign) in a near-consecutive biopsy series were used in this study. Observer performance was measured on 10 radiologists who read the original standard- and magnification-view mammograms. The computer aid provided a percentage estimate of the likelihood of malignancy. Comparison if was made between computer-aided performance and unaided (routine clinical) performance by using receiver operating characteristic (ROC) analysis and by comparing biopsy recommendations.Results The average ROC curve area (A(z)) increased 0.61 without aid to 0.75 with the computer aid (P < .0001). On average, with the computer aid, each observer recommended 6.4 additional biopsies for cases with malignant lesions (P =.0006) and 6.0 fewer biopsies for cases with benign lesions (P =.003). This improvement corresponded to increases in sensitivity (from 73.5% to 87.4% ), specificity (from 31.6% to 41.9%), and hypothetical positive biopsy yield (from 46% to 55%).Conclusion. CAD can be used to improve radiologists' performance in boast cancer diagnosis.