The Clinical Value of Explainable Deep Learning for Diagnosing Fungal Keratitis Using in vivo Confocal Microscopy Images

Background: Artificial intelligence (AI) has great potential to detect fungal keratitis using in vivo confocal microscopy images, but its clinical value remains unclarified. A major limitation of its clinical utility is the lack of explainability and interpretability. Methods: An explainable AI (XAI) system based on Gradient-weighted Class Activation Mapping (Grad-CAM) and Guided Grad-CAM was established. In this randomized controlled trial, nine ophthalmologists (three expert ophthalmologists, three competent ophthalmologists, and three novice ophthalmologists) read images in each of the conditions: unassisted, AI-assisted, or XAI-assisted. In unassisted condition, only the original IVCM images were shown to the readers. AI assistance comprised a histogram of model prediction probability. For XAI assistance, explanatory maps were additionally shown. The accuracy, sensitivity, and specificity were calculated against an adjudicated reference standard. Moreover, the time spent was measured. Results: Both forms of algorithmic assistance increased the accuracy and sensitivity of competent and novice ophthalmologists significantly without reducing specificity. The improvement was more pronounced in XAI-assisted condition than that in AI-assisted condition. Time spent with XAI assistance was not significantly different from that without assistance. Conclusion: AI has shown great promise in improving the accuracy of ophthalmologists. The inexperienced readers are more likely to benefit from the XAI system. With better interpretability and explainability, XAI-assistance can boost ophthalmologist performance beyond what is achievable by the reader alone or with black-box AI assistance.

[1]  F. Stapleton The Epidemiology of Infectious Keratitis. , 2021, The ocular surface.

[2]  Rushi Lan,et al.  A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images , 2021, PloS one.

[3]  P. Gilligan,et al.  Practical Guidance for Clinical Microbiology Laboratories: Diagnosis of Ocular Infections , 2021, Clinical microbiology reviews.

[4]  C. Baudouin,et al.  Corneal Changes in Acanthamoeba Keratitis at Various Levels of Severity: An In Vivo Confocal Microscopic Study , 2021, Translational vision science & technology.

[5]  Qinghao Ye,et al.  Explainable AI for COVID-19 CT Classifiers: An Initial Comparison Study , 2021, 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS).

[6]  Qinghao Ye,et al.  Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond , 2021, Inf. Fusion.

[7]  Kai Zhang,et al.  Deep learning-based automated diagnosis of fungal keratitis with in vivo confocal microscopy images , 2020, Annals of translational medicine.

[8]  Scott Lundberg,et al.  Explaining Models by Propagating Shapley Values of Local Components , 2019, Explainable AI in Healthcare and Medicine.

[9]  Cuntai Guan,et al.  A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[10]  S. Sadda,et al.  Role of in vivo confocal microscopy in the diagnosis of infectious keratitis , 2019, International Ophthalmology.

[11]  M. Burton,et al.  Cellular morphological changes detected by laser scanning in vivo confocal microscopy associated with clinical outcome in fungal keratitis , 2019, Scientific Reports.

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

[13]  M. Harrison A Global Perspective , 2015, Bulletin of the history of medicine.

[14]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Alexander Binder,et al.  Explaining nonlinear classification decisions with deep Taylor decomposition , 2015, Pattern Recognit..

[16]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[17]  Q. Le,et al.  Early-Onset Candida glabrata Interface Keratitis after Deep Anterior Lamellar Keratoplasty , 2015, Optometry and vision science : official publication of the American Academy of Optometry.

[18]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[19]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[20]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[21]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[22]  Y. Ohashi,et al.  Effectiveness of In Vivo Confocal Microscopy in Detecting Filamentous Fungi During Clinical Course of Fungal Keratitis , 2010, Cornea.

[23]  D. Larkin,et al.  Diagnostic accuracy of microbial keratitis with in vivo scanning laser confocal microscopy , 2010, British Journal of Ophthalmology.

[24]  P. Garg,et al.  Role of Confocal Microscopy in Deep Fungal Keratitis , 2009, Cornea.

[25]  S. Yazdani,et al.  Sensitivity and Specificity of Confocal Scan in the Diagnosis of Infectious Keratitis , 2007, Cornea.

[26]  T. Naduvilath,et al.  Clinical outcomes of keratitis , 2007, Clinical & experimental ophthalmology.

[27]  Guang Yang,et al.  Exploring Uncertainty Measures in Bayesian Deep Attentive Neural Networks for Prostate Zonal Segmentation , 2020, IEEE Access.

[28]  Ramprasaath R. Selvaraju,et al.  Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization , 2016 .

[29]  Qiao Li-ping Acellular area in the corneal stroma long after LASIK:An in vivo confocal microscopic study , 2011 .

[30]  M. Labetoulle,et al.  Contribution of in vivo confocal microscopy to the diagnosis and management of infectious keratitis. , 2009, The ocular surface.

[31]  M. Srinivasan,et al.  Corneal blindness: a global perspective. , 2001, Bulletin of the World Health Organization.