Shibutani Takayuki, Nakajima Kenichi, Wakabayashi Hiroshi, Mori Hiroshi, Matsuo Shinro, Yoneyama Hiroto, Konishi Takahiro, Okuda Koichi, Onoguchi Masahisa, Kinuya Seigo
Department of Quantum Medical Technology, Institute of Medical, Pharmaceutical and Health Sciences, Kanazawa University, 5-11-80, Kodatsuno, Kanazawa, Ishikawa, Japan.
Department of Nuclear Medicine, Kanazawa University Hospital, Kanazawa, Japan.
Ann Nucl Med. 2019 Feb;33(2):86-92. doi: 10.1007/s12149-018-1306-4. Epub 2018 Oct 9.
The patient-based diagnosis with an artificial neural network (ANN) has shown potential utility for the detection of coronary artery disease; however, the region-based accuracy of the detected regions has not been fully evaluated. The aim of this study was to demonstrate the accuracy of all detected regions compared with expert interpretation.
A total of 109 abnormal regions including 33 regions with stress defects and 76 regions with ischemia were examined, which were derived from 21 patients who underwent myocardial perfusion SPECT within 45 days of coronary angiography. The gray and color scale images, a polar map of stress, rest and difference, and left ventricular function were displayed on the monitor to score the extent and severity of stress defect and ischemia. Two experienced nuclear medicine physicians (Observers A and B) scored the abnormality with a 4-point scale and draw abnormal regions on a polar map. The gold standard was determined by the final judgment of normal or abnormal by the consensus of two other independent expert nuclear cardiologists, and was compared with the stress defect and ischemia derived from ANN.
The concordance rate of ANN to the gold standard was higher than that of two observers. Furthermore, the κ coefficient indicated moderate to substantial agreement for stress defect and slight to the fair agreement for ischemia. The area under the curve (AUC) of ANN was the highest for both stress defect and ischemia; in particular, the ANN of ischemia showed significantly higher AUC than Observer A (p = 0.005). The ANN of stress defect showed higher specificity compared with two observers, while the ANN of ischemia showed higher sensitivity. Consequently, the accuracy of ANN showed the highest in this study.
The ANN-based regional diagnosis showed a high concordance rate with the gold standard and comparable or even higher than the interpretation by nuclear medicine physicians.
基于患者的人工神经网络（ANN）诊断在冠状动脉疾病检测中已显示出潜在效用；然而，所检测区域的基于区域的准确性尚未得到充分评估。本研究的目的是证明与专家解读相比，所有检测区域的准确性。
共检查了109个异常区域，包括33个有应激缺损的区域和76个有缺血的区域，这些区域来自21例在冠状动脉造影后45天内接受心肌灌注SPECT检查的患者。在监视器上显示灰度和彩色图像、应激、静息和差值的极坐标图以及左心室功能，以对应激缺损和缺血的范围及严重程度进行评分。两名经验丰富的核医学医师（观察者A和B）用4分制对异常进行评分，并在极坐标图上画出异常区域。金标准由另外两名独立的专家核心脏病学家的共识确定的正常或异常的最终判断来确定，并与ANN得出的应激缺损和缺血进行比较。
ANN与金标准的一致性率高于两名观察者。此外，κ系数表明应激缺损为中度至高度一致，缺血为轻度至中度一致。ANN的曲线下面积（AUC）在应激缺损和缺血方面均最高；特别是，缺血的ANN显示AUC显著高于观察者A（p = 0.005）。应激缺损的ANN与两名观察者相比显示出更高的特异性，而缺血的ANN显示出更高的敏感性。因此，ANN的准确性在本研究中最高。
基于ANN的区域诊断与金标准显示出较高的一致性率，与核医学医师的解读相当甚至更高。
