Detection and Localization of Landmarks in the Lower Extremities Using an Automatically Learned Conditional Random Field

Mader, Alexander Oliver; Lorenz, Cristian; Bergtholdt, Martin; Berg, Jens von; Schramm, Hauke; Modersitzki, Jan; Meyer, Carsten

doi:10.1007/978-3-319-67675-3_7

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For automated screening, we envisage combining our vertebra-level fracture detection method with a vertebra localization method that automatically identifies and localizes each vertebra present in the image. Current state-of-the-art vertebra localization work reports identifying 91.6% of the vertebrae and localizing them with mean error 6.2±16.2 mm [9] on a challenging public dataset. We have used these localization error bounds to add noise to our ground truth centroid coordinates for simulating automated results.…”

Section: Aggregationmentioning

confidence: 99%

Detection of Vertebral Fractures in CT Using 3D Convolutional Neural Networks

Nicolaes

Raeymaeckers²,

Robben

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Osteoporosis induced fractures occur worldwide about every 3 seconds. Vertebral compression fractures are early signs of the disease and considered risk predictors for secondary osteoporotic fractures. We present a detection method to opportunistically screen spine-containing CT images for the presence of these vertebral fractures. Inspired by radiology practice, existing methods are based on 2D and 2.5D features but we present, to the best of our knowledge, the first method for detecting vertebral fractures in CT using automatically learned 3D feature maps. The presented method explicitly localizes these fractures allowing radiologists to interpret its results. We train a voxel-classification 3D Convolutional Neural Network (CNN) with a training database of 90 cases that has been semi-automatically generated using radiologist readings that are readily available in clinical practice. Our 3D method produces an Area Under the Curve (AUC) of 95% for patient-level fracture detection and an AUC of 93% for vertebra-level fracture detection in a five-fold cross-validation experiment.

show abstract

Section: Aggregationmentioning

confidence: 99%