Degenerative spinal pathologies are highly prevalent among the elderly
population. Timely diagnosis of osteoporotic fractures and other degenerative
deformities facilitates proactive measures to mitigate the risk of severe back
pain and disability. In this study, we specifically explore the use of shape
auto-encoders for vertebrae, taking advantage of advancements in automated
multi-label segmentation and the availability of large datasets for
unsupervised learning. Our shape auto-encoders are trained on a large set of
vertebrae surface patches, leveraging the vast amount of available data for
vertebra segmentation. This addresses the label scarcity problem faced when
learning shape information of vertebrae from image intensities. Based on the
learned shape features we train an MLP to detect vertebral body fractures.
Using segmentation masks that were automatically generated using the
TotalSegmentator, our proposed method achieves an AUC of 0.901 on the VerSe19
testset. This outperforms image-based and surface-based end-to-end trained
models. Additionally, our results demonstrate that pre-training the models in
an unsupervised manner enhances geometric methods like PointNet and DGCNN. Our
findings emphasise the advantages of explicitly learning shape features for
diagnosing osteoporotic vertebrae fractures. This approach improves the
reliability of classification results and reduces the need for annotated
labels. This study provides novel insights into the effectiveness of various
encoder-decoder models for shape analysis of vertebrae and proposes a new
decoder architecture: the point-based shape decoder.

使用形状自编码器和自动化的多标签分割方法，本研究探讨了骨质疏松性骨折的及时诊断，以及通过学习形状特征来改善骨骼退行性畸形的可靠性和减少标注的需求。