School of Integrated Circuits, Shandong University, Jinan, 250101, China.
School of Integrated Circuits, Shandong University, Jinan, 250101, China; Shenzhen Research Institute of Shandong University, A301 Virtual University Park in South District of Shenzhen, China.
Comput Biol Med. 2024 Feb;169:107856. doi: 10.1016/j.compbiomed.2023.107856. Epub 2023 Dec 20.
Multiple cardiac diseases are closely associated with functional parameters of the left ventricle, but functional parameter quantification still requires manual involvement, a time-consuming and less reproducible task. We develop a joint attention network (JANet) and expand it into two versions (V1 and V2) that can be used to segment the left ventricular region in echocardiograms to assist physicians in diagnosis. V1 is a smaller model with a size of 56.3 MB, and V2 has a higher accuracy. The proposed JANet V1 and V2 achieve a mean dice score (DSC) of 93.59/93.69(V1/V2), respectively, outperforming the state-of-the-art models. We grade 1264 patients with 87.24/87.50 (V1/V2) accuracy when using the 2-level classification criteria and 83.62/84.18 (V1/V2) when using the 5-level classification criteria. The results of the consistency analysis show that the proposed method is comparable to that of clinicians.
多种心脏疾病与左心室的功能参数密切相关，但功能参数的量化仍然需要人工参与，这是一项耗时且重复性较差的任务。我们开发了一种联合注意网络（JANet），并将其扩展为两个版本（V1 和 V2），可用于分割超声心动图中的左心室区域，以协助医生进行诊断。V1 是一个较小的模型，大小为 56.3MB，V2 的准确性更高。所提出的 JANet V1 和 V2 的平均骰子得分（DSC）分别为 93.59/93.69（V1/V2），优于最先进的模型。当使用 2 级分类标准时，我们对 1264 名患者进行了分级，准确率为 87.24/87.50（V1/V2），当使用 5 级分类标准时，准确率为 83.62/84.18（V1/V2）。一致性分析的结果表明，该方法与临床医生的方法相当。
