Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, Matsuyama, 790-0024, Japan.
Department of Cardiology, Pulmonology, Hypertension & Nephrology, Ehime University Graduate School of Medicine, Toon, Japan.
J Nucl Cardiol. 2023 Apr;30(2):540-549. doi: 10.1007/s12350-022-03030-4. Epub 2022 Jul 8.
Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) plays a crucial role in the optimal treatment strategy for patients with coronary heart disease. We tested the feasibility of feature extraction from MPI using a deep convolutional autoencoder (CAE) model.
Eight hundred and forty-three pairs of stress and rest myocardial perfusion images were collected from consecutive patients who underwent cardiac scintigraphy in our hospital between December 2019 and February 2022. We trained a CAE model to reproduce the input paired image data, so as the encoder to output a 256-dimensional feature vector. The extracted feature vectors were further dimensionally reduced via principal component analysis (PCA) for data visualization. Content-based image retrieval (CBIR) was performed based on the cosine similarity of the feature vectors between the query and reference images. The agreement of the radiologist's finding between the query and retrieved MPI was evaluated using binary accuracy, precision, recall, and F1-score.
A three-dimensional scatter plot with PCA revealed that feature vectors retained clinical information such as percent summed difference score, presence of ischemia, and the location of scar reported by radiologists. When CBIR was used as a similarity-based diagnostic tool, the binary accuracy was 81.0%.
The results indicated the utility of unsupervised feature learning for CBIR in MPI.
单光子发射计算机断层扫描（SPECT）心肌灌注成像（MPI）在冠心病患者的最佳治疗策略中起着至关重要的作用。我们测试了使用深度卷积自动编码器（CAE）模型从 MPI 中提取特征的可行性。
从 2019 年 12 月至 2022 年 2 月在我院进行心脏闪烁成像的连续患者中收集了 843 对应激和静息心肌灌注图像。我们训练了一个 CAE 模型来复制输入的成对图像数据，作为编码器输出 256 维特征向量。通过主成分分析（PCA）进一步降低提取的特征向量的维度，以实现数据可视化。基于查询和参考图像之间特征向量的余弦相似度进行基于内容的图像检索（CBIR）。使用二进制准确性、精度、召回率和 F1 分数评估放射科医生在查询和检索 MPI 之间发现的一致性。
PCA 的三维散点图显示，特征向量保留了临床信息，如百分比总和差异评分、缺血的存在和放射科医生报告的疤痕位置。当使用 CBIR 作为基于相似性的诊断工具时，二进制准确性为 81.0%。
结果表明，无监督特征学习在 MPI 中的 CBIR 中具有实用性。
