Deep Learning-Based Regression and Classification for Automatic Landmark Localization in Medical Images
| Autor: | Richard A.P. Takx, Max A. Viergever, Elbrich M. Postma, Bob D. de Vos, Jelmer M. Wolterink, Tim Leiner, Ivana Išgum, Julia M. H. Noothout, Paul A.M. Smeets |
|---|---|
| Přispěvatelé: | Biomedical Engineering and Physics, Graduate School, ACS - Atherosclerosis & ischemic syndromes, Radiology and Nuclear Medicine, ANS - Brain Imaging, ACS - Heart failure & arrhythmias, Applied Analysis |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition FOS: Physical sciences convolutional neural network cardiac CT Convolutional neural network Displacement (vector) 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine cephalometric X-ray FOS: Electrical engineering electronic engineering information engineering Electrical and Electronic Engineering Sensory Science and Eating Behaviour VLAG Landmark Radiological and Ultrasound Technology Artificial neural network business.industry Deep learning Image and Video Processing (eess.IV) 22/2 OA procedure Reproducibility of Results deep learning Pattern recognition Electrical Engineering and Systems Science - Image and Video Processing Physics - Medical Physics Regression Computer Science Applications Sensoriek en eetgedrag Kernel (image processing) classification olfactory MR Landmark localization regression Artificial intelligence Medical Physics (physics.med-ph) Neural Networks Computer Anatomic Landmarks business Software Algorithms |
| Zdroj: | IEEE Transactions on Medical Imaging, 39(12), 4011-4022 IEEE transactions on medical imaging, 39(12):9139480, 4011-4022. Institute of Electrical and Electronics Engineers Inc. IEEE Transactions on Medical Imaging 39 (2020) 12 IEEE transactions on medical imaging, 39(12):9139480, 4011-4022. IEEE |
| ISSN: | 0278-0062 |
| DOI: | 10.1109/tmi.2020.3009002 |
| Popis: | In this study, we propose a fast and accurate method to automatically localize anatomical landmarks in medical images. We employ a global-to-local localization approach using fully convolutional neural networks (FCNNs). First, a global FCNN localizes multiple landmarks through the analysis of image patches, performing regression and classification simultaneously. In regression, displacement vectors pointing from the center of image patches towards landmark locations are determined. In classification, presence of landmarks of interest in the patch is established. Global landmark locations are obtained by averaging the predicted displacement vectors, where the contribution of each displacement vector is weighted by the posterior classification probability of the patch that it is pointing from. Subsequently, for each landmark localized with global localization, local analysis is performed. Specialized FCNNs refine the global landmark locations by analyzing local sub-images in a similar manner, i.e. by performing regression and classification simultaneously and combining the results. Evaluation was performed through localization of 8 anatomical landmarks in CCTA scans, 2 landmarks in olfactory MR scans, and 19 landmarks in cephalometric X-rays. We demonstrate that the method performs similarly to a second observer and is able to localize landmarks in a diverse set of medical images, differing in image modality, image dimensionality, and anatomical coverage. Comment: 12 pages, accepted at IEEE transactions in Medical Imaging |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|