An open annotated dataset and baseline machine learning model for segmentation of vertebrae with metastatic bone lesions from CT

Abstract

Automatic analysis of pathologic vertebrae from computed tomography (CT) scans could significantly improve the diagnostic management of patients with metastatic spine disease. We provide the first publicly available annotated imaging dataset of cancerous CT spines to help develop artificial intelligence frameworks for automatic vertebrae segmentation and classification. This collection contains a dataset of 55 CT scans collected on patients with various types of primary cancers at two different institutions. In addition to raw images, data include manual segmentations and contours, vertebral level labeling, vertebral lesion-type classifications, and patient demographic details. Our automated segmentation model uses nnU-Net, a freely available open-source framework for deep learning in healthcare imaging, and is made publicly available. This data will facilitate the development and validation of models for predicting the mechanical response to loading and the resulting risk of fractures and spinal deformity.

Figure 1:

Example lesions and segmentations found in the dataset. Top row: Spine CTs with lytic, blastic, and mixed lesions and without lesions. Bottom row: Spine CTs with masks visualized as colored overlays.

Figure 2:

Illustrative example dataset of a patient with vertebral lesions with the raw CT, annotated segmentation and identification of vertebral levels, and lesion classification (Lytic, Blastic, and Mixed).

Figure 3:

Segmentation results on one patient using the trained nnU-Net model. From left to right: Axial, Coronal, Sagittal, and 3D views of the spine CT with segmentation masks; segmentation results overlaid with ground truth annotation of one vertebra with a blastic lesion.