Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:3044-3048. doi: 10.1109/EMBC46164.2021.9630134.
Joint effusion is a hallmark of osteoarthritis (OA) associated with stiffness, and may relate to pain, disability, and long-term outcomes. However, it is difficult to quantify accurately. We propose a new Deep Learning (DL) approach for automatic effusion assessment from Magnetic Resonance Imaging (MRI) using volumetric quantification measures (VQM). We developed a new multiplane ensemble convolutional neural network (CNN) approach for 1) localizing bony anatomy and 2) detecting effusion regions. CNNs were trained on femoral head and effusion regions manually segmented from 3856 images (63 patients). Upon validation on a non-overlapping set of 2040 images (34 patients) DL showed high agreement with ground-truth in terms of Dice score (0.85), sensitivity (0.86) and precision (0.83). Agreement of VQM per-patient was high for DL vs experts in term of Intraclass correlation coefficient (ICC)= 0.88[0.80,0.93]. We expect this technique to reduce inter-observer variability in effusion assessment, reducing expert time and potentially improving the quality of OA care.Clinical Relevance- Our technique for automatic assessment of hip MRI can be used for volumetric measurement of effusion. We expect this to reduce variability in OA biomarker assessment and provide more reliable indicators for disease progression.
关节积液是骨关节炎（OA）的一个标志，与僵硬有关，可能与疼痛、残疾和长期结果有关。然而，很难准确地量化。我们提出了一种新的深度学习（DL）方法，用于使用容积量化测量（VQM）从磁共振成像（MRI）自动评估积液。我们开发了一种新的多平面集成卷积神经网络（CNN）方法，用于 1）定位骨解剖结构，2）检测积液区域。从 3856 张图像（63 名患者）中手动分割股骨头和积液区域对 CNN 进行了训练。在对 2040 张非重叠图像（34 名患者）进行验证时，DL 在 Dice 评分（0.85）、灵敏度（0.86）和精度（0.83）方面与真实值高度一致。DL 与专家相比，每个患者的 VQM 协议的一致性很高，组内相关系数（ICC）=0.88[0.80，0.93]。我们期望这项技术能够减少积液评估中的观察者间变异性，减少专家时间，并有可能改善 OA 护理的质量。临床相关性-我们用于自动评估髋关节 MRI 的技术可用于积液的容积测量。我们期望这可以减少 OA 生物标志物评估的变异性，并为疾病进展提供更可靠的指标。
