Optimising Knee Injury Detection with Spatial Attention and Validating Localisation Ability

This work employs a pre-trained, multi-view Convolutional Neural Network (CNN) with a spatial attention block to optimise knee injury detection. An open-source Magnetic Resonance Imaging (MRI) data set with image-level labels was leveraged for this analysis. As MRI data is acquired from three planes, we compare our technique using data from a single-plane and multiple planes (multi-plane). For multi-plane, we investigate various methods of fusing the planes in the network. This analysis resulted in the novel ‘MPFuseNet’ network and state-of-the-art Area Under the Curve (AUC) scores for detecting Anterior Cruciate Ligament (ACL) tears and Abnormal MRIs, achieving AUC scores of 0.977 and 0.957 respectively. We then developed an objective metric, Penalised Localisation Accuracy (PLA), to validate the model’s localisation ability. This metric compares binary masks generated from Grad-Cam output and the radiologist’s annotations on a sample of MRIs. We also extracted explainability features in a model-agnostic approach that were then verified as clinically relevant by the radiologist.

[1]  N. Arun,et al.  Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging , 2020, medRxiv.

[2]  Simon See,et al.  Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention , 2019, MICCAI.

[3]  Nahum Kiryati,et al.  Knee Injury Detection using MRI with Efficiently-Layered Network (ELNet) , 2020, MIDL.

[4]  Karrar Hameed Abdulkareem,et al.  Efficient Detection of Knee Anterior Cruciate Ligament from Magnetic Resonance Imaging Using Deep Learning Approach , 2021, Diagnostics.

[5]  H. Tsuchiya,et al.  Oblique coronal and oblique sagittal MRI for diagnosis of anterior cruciate ligament tears and evaluation of anterior cruciate ligament remnant tissue. , 2014, The Knee.

[6]  Loïc Le Folgoc,et al.  Attention U-Net: Learning Where to Look for the Pancreas , 2018, ArXiv.

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Vincent Andrearczyk,et al.  Evaluation and comparison of CNN visual explanations for histopathology , 2021, AAAI 2021.

[9]  Subhransu Maji,et al.  Multi-view Convolutional Neural Networks for 3D Shape Recognition , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Andreas Holzinger,et al.  Measuring the Quality of Explanations: The System Causability Scale (SCS) , 2020, KI - Künstliche Intelligenz.

[11]  Martin Wattenberg,et al.  Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) , 2017, ICML.

[12]  A. Scott.  Measuring quality. , 1993, The New Zealand medical journal.

[13]  L G Nyúl,et al.  On standardizing the MR image intensity scale , 1999, Magnetic resonance in medicine.

[14]  Syed Muhammad Anwar,et al.  Deep Learning for Musculoskeletal Image Analysis , 2019, 2019 53rd Asilomar Conference on Signals, Systems, and Computers.

[15]  Evon M. O. Abu-Taieh,et al.  Comparative Study , 2020, Definitions.

[16]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[17]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[19]  Kris Sankaran,et al.  Interpretability of a deep learning model in the application of cardiac MRI segmentation with an ACDC challenge dataset , 2021, Medical Imaging.

[20]  A. Ng,et al.  Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet , 2018, PLoS medicine.

[21]  Martin Wattenberg,et al.  SmoothGrad: removing noise by adding noise , 2017, ArXiv.