ExplainabilityTransparencyAccountabilityeess.IV
Using a Convolutional Neural Network and Explainable AI to Diagnose Dementia Based on MRI Scans
Tyler Morris, Ziming Liu, Longjian Liu, Xiaopeng Zhao
May 26, 2024
arXiv.org
4 citations
Key Takeaways
-
High accuracy with transparency: The AI system achieved 98% validation accuracy in classifying dementia types from MRI scans while using explainable AI techniques to show which brain regions influenced each diagnosis, addressing the "black box" problem that typically makes AI decisions untrustworthy in medical settings.
-
Visualization builds trust and accountability: By visualizing which parts of MRI scans the AI focused on when making diagnoses, the system allows doctors, patients, and other stakeholders to understand why a particular dementia classification was recommended, rather than simply accepting an unexplained algorithmic output.
-
Potential to reduce human error: The paper suggests this AI-assisted approach could improve upon current diagnostic methods that "rely on human input, which can be inaccurate," though clinical validation with real patients would be needed to confirm this benefit in practice.
-
Explainability is essential for medical AI adoption: The authors demonstrate that combining high-performing algorithms with explainable AI techniques isn't just a nice feature—it's necessary for responsible deployment in healthcare, where clinicians need to understand and verify AI recommendations before using them with patients.
Abstract
As the number of dementia patients rises, the need for accurate diagnostic procedures rises as well. Current methods, like using an MRI scan, rely on human input, which can be inaccurate. However, the decision logic behind machine learning algorithms and their outputs cannot be explained, as most operate in black-box models. Therefore, to increase the accuracy of diagnosing dementia through MRIs, a convolution neural network has been developed and trained using an open-source database of 6400 MRI scans divided into 4 dementia classes. The model, which attained a 98 percent validation accuracy, was shown to be well fit and able to generalize to new data. Furthermore, to aid in the visualization of the model output, an explainable AI algorithm was developed by visualizing the outputs of individual filters in each convolution layer, which highlighted regions of interest in the scan. These outputs do a great job of identifying the image features that contribute most to the model classification, thus allowing users to visualize and understand the results. Altogether, this combination of the convolution neural network and explainable AI algorithm creates a system that can be used in the medical field to not only aid in the proper classification of dementia but also allow everyone involved to visualize and understand the results.