Weakly supervised deep learning for diagnosis of multiple vertebral compression fractures in CT.
Researchers
Journal
Modalities
Models
Abstract
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 (nā=ā507, 62%) or VCFs (nā=ā308, 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 (nā=ā117, 52%) or VCFs (nā=ā110, 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 (pā=ā0.080), 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, pā=ā0.480), L3 (0.793 vs 0.586, pā<ā0.05), L4 (0.833 vs 0.667, pā=ā0.480), and L5 (0.600 vs 0.600, pā=ā1.000), 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, pā=ā0.617).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.ā¢ Our proposed weakly supervised method may have comparable or better performance than the supervised method for vertebral-level vertebral compression fracture classification. ā¢ 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. ā¢ Our proposed method could help reduce radiologists’ labour because it enables vertebral-level classification from image-level labels.Ā© 2023. The Author(s), under exclusive licence to European Society of Radiology.