Publications by authors named "Luis Serrador"
Knowledge distillation on individual vertebrae segmentation exploiting 3D U-Net.
Comput Med Imaging Graph
April 2024
Article Synopsis
- Recent advancements in medical imaging have led to the development of algorithms for segmenting individual vertebrae in CT scans, which are crucial for accurate diagnoses and treatment in fields like orthopaedics and neurosurgery.
- The research focuses on using knowledge distillation (KD) methods to train shallower neural networks that can efficiently segment vertebrae, ultimately reducing segmentation time and resource usage, especially for emergency cases.
- A two-step segmentation process was utilized, involving heatmap prediction for spine localization and iterative vertebra segmentation, achieving strong results from a teacher network with high performance metrics that were successfully distilled to a more efficient student network.
Objectives: To develop and validate a deep learning-based approach to automatically measure the patellofemoral instability (PFI) indices related to patellar height and trochlear dysplasia in knee magnetic resonance imaging (MRI) scans.
Methods: A total of 763 knee MRI slices from 95 patients were included in the study, and 3393 anatomical landmarks were annotated for measuring sulcus angle (SA), trochlear facet asymmetry (TFA), trochlear groove depth (TGD) and lateral trochlear inclination (LTI) to assess trochlear dysplasia, and Insall-Salvati index (ISI), modified Insall-Salvati index (MISI), Caton Deschamps index (CDI) and patellotrochlear index (PTI) to assess patellar height. A U-Net based network was implemented to predict the landmarks' locations.