Floyd C E, Lo J Y, Yun A J, Sullivan D C, Kornguth P J
Department of Radiology, Duke University Medical Center, Durham, NC 27710.
Cancer. 1994 Dec 1;74(11):2944-8. doi: 10.1002/1097-0142(19941201)74:11<2944::aid-cncr2820741109>3.0.co;2-f.
An artificial neural network (ANN) was developed to predict breast cancer from mammographic findings. This network was evaluated in a retrospective study.
For a set of patients who were scheduled for biopsy, radiologists interpreted the mammograms and provided data on eight mammographic findings as part of the standard mammographic workup. These findings were encoded as features for an ANN. Results of biopsies were taken as truth in the diagnosis of malignancy. The ANN was trained and evaluated using a jackknife sampling on a set of 260 patient records. Performance of the network was evaluated in terms of sensitivity and specificity over a range of decision thresholds and was expressed as a receiver operating characteristic curve.
The ANN performed more accurately than the radiologists (P < 0.08) with a relative sensitivity of 1.0 and specificity of 0.59.
An ANN can be trained to predict malignancy from mammographic findings with a high degree of accuracy.
开发了一种人工神经网络（ANN），用于根据乳房X光检查结果预测乳腺癌。该网络在一项回顾性研究中进行了评估。
对于一组计划进行活检的患者，放射科医生解读乳房X光片，并提供八项乳房X光检查结果的数据，作为标准乳房X光检查流程的一部分。这些结果被编码为ANN的特征。活检结果被用作恶性肿瘤诊断的真实情况。使用留一法抽样在一组260例患者记录上对ANN进行训练和评估。在一系列决策阈值范围内，根据敏感性和特异性评估网络性能，并表示为受试者工作特征曲线。
ANN的表现比放射科医生更准确（P < 0.08），相对敏感性为1.0，特异性为0.59。
可以训练ANN根据乳房X光检查结果高度准确地预测恶性肿瘤。
