Improving MRI-based Knee Disorder Diagnosis with Pyramidal Feature Details

Matteo Dunnhofer, Niki Martinel, Christian Micheloni
Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, PMLR 143:131-147, 2021.

Abstract

This paper presents MRPyrNet, a new convolutional neural network (CNN) architecture that improves the capabilities of CNN-based pipelines for knee injury detection via magnetic resonance imaging (MRI). Existing works showed that anomalies are localized in small-sized knee regions that appear in particular areas of MRI scans. Based on such facts, MRPyrNet exploits a Feature Pyramid Network to enhance small appearing features and Pyramidal Detail Pooling to capture such relevant information in a robust way. Experimental results on two publicly available datasets demonstrate that MRPyrNet improves the ACL tear and meniscal tear diagnosis capabilities of two state-of-the-art methodologies. Code is available at https://git.io/JtMPH.

Cite this Paper

BibTeX
@InProceedings{pmlr-v143-dunnhofer21a, title = {Improving {MRI}-based Knee Disorder Diagnosis with Pyramidal Feature Details}, author = {Dunnhofer, Matteo and Martinel, Niki and Micheloni, Christian}, booktitle = {Proceedings of the Fourth Conference on Medical Imaging with Deep Learning}, pages = {131--147}, year = {2021}, editor = {Heinrich, Mattias and Dou, Qi and de Bruijne, Marleen and Lellmann, Jan and Schläfer, Alexander and Ernst, Floris}, volume = {143}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v143/dunnhofer21a/dunnhofer21a.pdf}, url = {https://proceedings.mlr.press/v143/dunnhofer21a.html}, abstract = {This paper presents MRPyrNet, a new convolutional neural network (CNN) architecture that improves the capabilities of CNN-based pipelines for knee injury detection via magnetic resonance imaging (MRI). Existing works showed that anomalies are localized in small-sized knee regions that appear in particular areas of MRI scans. Based on such facts, MRPyrNet exploits a Feature Pyramid Network to enhance small appearing features and Pyramidal Detail Pooling to capture such relevant information in a robust way. Experimental results on two publicly available datasets demonstrate that MRPyrNet improves the ACL tear and meniscal tear diagnosis capabilities of two state-of-the-art methodologies. Code is available at https://git.io/JtMPH.} }
Endnote
%0 Conference Paper %T Improving MRI-based Knee Disorder Diagnosis with Pyramidal Feature Details %A Matteo Dunnhofer %A Niki Martinel %A Christian Micheloni %B Proceedings of the Fourth Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2021 %E Mattias Heinrich %E Qi Dou %E Marleen de Bruijne %E Jan Lellmann %E Alexander Schläfer %E Floris Ernst %F pmlr-v143-dunnhofer21a %I PMLR %P 131--147 %U https://proceedings.mlr.press/v143/dunnhofer21a.html %V 143 %X This paper presents MRPyrNet, a new convolutional neural network (CNN) architecture that improves the capabilities of CNN-based pipelines for knee injury detection via magnetic resonance imaging (MRI). Existing works showed that anomalies are localized in small-sized knee regions that appear in particular areas of MRI scans. Based on such facts, MRPyrNet exploits a Feature Pyramid Network to enhance small appearing features and Pyramidal Detail Pooling to capture such relevant information in a robust way. Experimental results on two publicly available datasets demonstrate that MRPyrNet improves the ACL tear and meniscal tear diagnosis capabilities of two state-of-the-art methodologies. Code is available at https://git.io/JtMPH.
APA
Dunnhofer, M., Martinel, N. & Micheloni, C.. (2021). Improving MRI-based Knee Disorder Diagnosis with Pyramidal Feature Details. Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 143:131-147 Available from https://proceedings.mlr.press/v143/dunnhofer21a.html.

Related Material