Department of Artificial Intelligence, Yonsei University, Seoul, Republic of Korea.
School of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea.
Eur Radiol. 2024 Jun;34(6):3750-3760. doi: 10.1007/s00330-023-10394-9. Epub 2023 Nov 16.
This study aims to develop a weakly supervised deep learning (DL) model for vertebral-level vertebral compression fracture (VCF) classification using image-level labelled data.
The training set included 815 patients with normal (n = 507, 62%) or VCFs (n = 308, 38%). Our proposed model was trained on image-level labelled data for vertebral-level classification. Another supervised DL model was trained with vertebral-level labelled data to compare the performance of the proposed model.
The test set included 227 patients with normal (n = 117, 52%) or VCFs (n = 110, 48%). For a fair comparison of the two models, we compared sensitivities with the same specificities of the proposed model and the vertebral-level supervised model. The specificity for overall L1-L5 performance was 0.981. The proposed model may outperform the vertebral-level supervised model with sensitivities of 0.770 vs 0.705 (p = 0.080), respectively. For vertebral-level analysis, the specificities for each L1-L5 were 0.974, 0.973, 0.970, 0.991, and 0.995, respectively. The proposed model yielded the same or better sensitivity than the vertebral-level supervised model in L1 (0.750 vs 0.694, p = 0.480), L3 (0.793 vs 0.586, p < 0.05), L4 (0.833 vs 0.667, p = 0.480), and L5 (0.600 vs 0.600, p = 1.000), respectively. The proposed model showed lower sensitivity than the vertebral-level supervised model for L2, but there was no significant difference (0.775 vs 0.825, p = 0.617).
The proposed model may have a comparable or better performance than the supervised model in vertebral-level VCF classification.
Vertebral-level vertebral compression fracture classification aids in devising patient-specific treatment plans by identifying the precise vertebrae affected by compression fractures.
• Our proposed weakly supervised method may have comparable or better performance than the supervised method for vertebral-level vertebral compression fracture classification. • The weakly supervised model could have classified cases with multiple vertebral compression fractures at the vertebral-level, even if the model was trained with image-level labels. • Our proposed method could help reduce radiologists' labour because it enables vertebral-level classification from image-level labels.
本研究旨在利用图像级标记数据开发一种用于椎体压缩性骨折（VCF）分类的弱监督深度学习（DL）模型。
训练集包括 815 例正常（n=507，62%）或 VCF 患者（n=308，38%）。我们的模型在椎体级别的图像级标记数据上进行训练。另一个有监督的 DL 模型使用椎体级别的标记数据进行训练，以比较所提出模型的性能。
测试集包括 227 例正常（n=117，52%）或 VCF 患者（n=110，48%）。为了公平比较这两种模型，我们比较了具有相同特异性的两种模型的敏感性。总体 L1-L5 性能的特异性为 0.981。与椎体级别的有监督模型相比，该模型的敏感性可能分别为 0.770 对 0.705（p=0.080）。对于椎体水平分析，每个 L1-L5 的特异性分别为 0.974、0.973、0.970、0.991 和 0.995。在 L1（0.750 对 0.694，p=0.480）、L3（0.793 对 0.586，p<0.05）、L4（0.833 对 0.667，p=0.480）和 L5（0.600 对 0.600，p=1.000）中，该模型的敏感性均高于或等于椎体级别的有监督模型。与椎体级别的有监督模型相比，该模型在 L2 中的敏感性较低，但无统计学差异（0.775 对 0.825，p=0.617）。
与椎体级别的有监督模型相比，该模型在椎体 VCF 分类中具有相当或更好的性能。
椎体压缩性骨折分类有助于制定针对特定患者的治疗计划，通过识别受压缩骨折影响的确切椎体。
我们提出的弱监督方法在椎体压缩性骨折分类方面的性能可能与有监督方法相当或更好。
即使模型是使用图像级标签训练的，弱监督模型也可以对椎体水平的多个椎体压缩性骨折进行分类。
我们的方法可以帮助减少放射科医生的工作量，因为它可以从图像级标签中进行椎体水平的分类。
