Information and Communication Engineering, Daegu Gyeongbuk Institute of Science and Technology, Daegu 42988, Korea.
The Department of Orthopedic Surgery, School of Medicine, Catholic University, Daegu 42472, Korea.
Sensors (Basel). 2021 Mar 22;21(6):2214. doi: 10.3390/s21062214.
A rotator cuff tear (RCT) is an injury in adults that causes difficulty in moving, weakness, and pain. Only limited diagnostic tools such as magnetic resonance imaging (MRI) and ultrasound Imaging (UI) systems can be utilized for an RCT diagnosis. Although UI offers comparable performance at a lower cost to other diagnostic instruments such as MRI, speckle noise can occur the degradation of the image resolution. Conventional vision-based algorithms exhibit inferior performance for the segmentation of diseased regions in UI. In order to achieve a better segmentation for diseased regions in UI, deep-learning-based diagnostic algorithms have been developed. However, it has not yet reached an acceptable level of performance for application in orthopedic surgeries. In this study, we developed a novel end-to-end fully convolutional neural network, denoted as Segmentation Model Adopting a pRe-trained Classification Architecture (SMART-CA), with a novel integrated on positive loss function (IPLF) to accurately diagnose the locations of RCT during an orthopedic examination using UI. Using the pre-trained network, SMART-CA can extract remarkably distinct features that cannot be extracted with a normal encoder. Therefore, it can improve the accuracy of segmentation. In addition, unlike other conventional loss functions, which are not suited for the optimization of deep learning models with an imbalanced dataset such as the RCT dataset, IPLF can efficiently optimize the SMART-CA. Experimental results have shown that SMART-CA offers an improved precision, recall, and dice coefficient of 0.604% (+38.4%), 0.942% (+14.0%) and 0.736% (+38.6%) respectively. The RCT segmentation from a normal ultrasound image offers the improved precision, recall, and dice coefficient of 0.337% (+22.5%), 0.860% (+15.8%) and 0.484% (+28.5%), respectively, in the RCT segmentation from an ultrasound image with severe speckle noise. The experimental results demonstrated the IPLF outperforms other conventional loss functions, and the proposed SMART-CA optimized with the IPLF showed better performance than other state-of-the-art networks for the RCT segmentation with high robustness to speckle noise.
肩袖撕裂（RCT）是一种成年人的损伤，会导致运动困难、无力和疼痛。只有磁共振成像（MRI）和超声成像（UI）系统等有限的诊断工具可用于 RCT 诊断。虽然 UI 的性能与 MRI 等其他诊断仪器相当，但成本更低，但可能会出现斑点噪声，从而降低图像分辨率。传统的基于视觉的算法在 UI 中对病变区域的分割表现不佳。为了在 UI 中实现更好的病变区域分割，已经开发了基于深度学习的诊断算法。然而，它在骨科手术中的应用尚未达到可接受的性能水平。在这项研究中，我们开发了一种新的端到端全卷积神经网络，称为采用预训练分类架构的分割模型（SMART-CA），并使用新的集成正损失函数（IPLF）来准确诊断使用 UI 进行骨科检查时的 RCT 位置。使用预训练网络，SMART-CA 可以提取出用普通编码器无法提取的非常明显的特征。因此，它可以提高分割的准确性。此外，与其他常规损失函数不同，后者不适合优化 RCT 数据集等不平衡数据集的深度学习模型，IPLF 可以有效地优化 SMART-CA。实验结果表明，SMART-CA 的精度、召回率和 Dice 系数分别提高了 0.604%（+38.4%）、0.942%（+14.0%）和 0.736%（+38.6%）。正常超声图像的 RCT 分割的精度、召回率和 Dice 系数分别提高了 0.337%（+22.5%）、0.860%（+15.8%）和 0.484%（+28.5%），在严重斑点噪声的超声图像中进行 RCT 分割时，分别提高了 0.337%（+22.5%）、0.860%（+15.8%）和 0.484%（+28.5%）。实验结果表明 IPLF 优于其他常规损失函数，并且使用 IPLF 优化的建议 SMART-CA 对具有高抗斑点噪声能力的 RCT 分割表现出优于其他最先进网络的性能。
