<br>深度学习辅助识别肩关节MR关节造影上盂唇前后病变的初步探索,International Orthopaedics

当前位置： X-MOL 学术 › Int. Orthop. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

深度学习辅助识别肩关节MR关节造影上盂唇前后病变的初步探索
International Orthopaedics ( IF 2.0 ) Pub Date : 2023-09-20 , DOI: 10.1007/s00264-023-05987-4
Ming Ni ₁ , Lixiang Gao ₁ , Wen Chen ₁ , Qiang Zhao ₁ , Yuqing Zhao ₁ , Chenyu Jiang ₁ , Huishu Yuan ₁

Affiliation

目的

磁共振关节造影（MRA）是术前诊断上盂唇前后（SLAP）病变最准确的方法，但由于经验等因素，诊断结果可能有很大差异。在本研究中，利用深度学习来促进SLAP病变的初步识别，并与不同资历的放射科医生进行比较。

方法

回顾性收集636例患者的MRA数据，根据肩关节镜检查将所有患者分为有/无SLAP病变。 SLAP-Net 模型是在 514 名患者（数据集 1）上构建和测试的，并根据来自其他两台 MRI 设备的数据（122 名患者，数据集 2）进行了独立测试。手动诊断由三名不同资历的放射科医生进行，并与 SLAP-Net 的输出进行比较。通过受试者工作特征（ROC）曲线、ROC曲线下面积（AUC）等评估模型性能。麦克尼马尔检验用于比较模型之间以及放射科医生模型之间的性能。组内相关系数（ICC）用于评估放射科医生的可靠性。 p < 0.05 被认为具有统计显着性。

结果

SLAP-Net 在数据集 1 中的分类 AUC = 0.98 和准确度 = 0.96，在数据集 2 中 AUC = 0.92 和准确度 = 0.85。在数据集 1 中，SLAP-Net 的诊断性能与高级放射科医生相似 ( p = 0.055)，但高于职业生涯早期和中期的放射科医生（ p = 0.025 和 0.011）。在数据集 2 中，SLAP-Net 与所有三个资历级别的放射科医生具有相似的诊断性能（分别为p = 0.468、0.289 和 0.495）。

结论

深度学习可用于在初次 MR 关节造影检查时识别 SLAP 病变。 SLAP-Net 的性能与高级放射科医生相当。

"点击查看英文标题和摘要"

Preliminary exploration of deep learning-assisted recognition of superior labrum anterior and posterior lesions in shoulder MR arthrography

Purpose

MR arthrography (MRA) is the most accurate method for preoperatively diagnosing superior labrum anterior–posterior (SLAP) lesions, but diagnostic results can vary considerably due to factors such as experience. In this study, deep learning was used to facilitate the preliminary identification of SLAP lesions and compared with radiologists of different seniority.

Methods

MRA data from 636 patients were retrospectively collected, and all patients were classified as having/not having SLAP lesions according to shoulder arthroscopy. The SLAP-Net model was built and tested on 514 patients (dataset 1) and independently tested on data from two other MRI devices (122 patients, dataset 2). Manual diagnosis was performed by three radiologists with different seniority levels and compared with SLAP-Net outputs. Model performance was evaluated by the receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), etc. McNemar’s test was used to compare performance among models and between radiologists’ models. The intraclass correlation coefficient (ICC) was used to assess the radiologists’ reliability. p < 0.05 was considered statistically significant.

Results

SLAP-Net had AUC = 0.98 and accuracy = 0.96 for classification in dataset 1 and AUC = 0.92 and accuracy = 0.85 in dataset 2. In dataset 1, SLAP-Net had diagnostic performance similar to that of senior radiologists (p = 0.055) but higher than that of early- and mid-career radiologists (p = 0.025 and 0.011). In dataset 2, SLAP-Net had similar diagnostic performance to radiologists of all three seniority levels (p = 0.468, 0.289, and 0.495, respectively).