Automated detection of brain disease using quantum machine learning

Madhusudan Singh, Irish Singh, Dhananjay Singh

Sadia Nasrin Tisha, Mushfika Sharmin Rahman, Javier Orduz

Nancy Noella R S, Bhuvan Unhelkar, Siva Shankar Subramanian +1 more

Alzheimer’s is a progressive and degenerative brain disorder causing impairment in memory and cognitive function. It is the most common form of Dementia and the prevalence of Alzheimer’s disease (AD) increases with each decade of life. This usually starts in late middle age to old age resulting in progressive memory loss, impaired thinking, disorientation and changes in personality. Neurons are first lost in the hippocampus (the brain’s centre for memory and learning), and presence of neurofibrillary tangles and plaques containing beta-amyloid cells. Owing to the progressive nature of the disease and the complex structure of the brain, the exact causes, mechanisms and how Alzheimer’s spread is not completely understood thereby inhibiting in the production of a cure for the disease. Quantum Machine Learning (QML) is a promising area of research for the detection and diagnosis of Alzheimer’s disease. PET scan helps in diagnosing Alzheimer’s by detecting the amyloid plaques and tau tangles. It reveals areas with reduced metabolism, which helps differentiate Alzheimer’s from other conditions. Quantum computing provides a more efficient model for different disease classification tasks than classical machine learning approaches. In this study, we propose a model based on quantum machine learning classifiers to classify Alzheimer’s disease. This showcases the feasibility of Quantum enhanced classification and detection of AD for extremely limited medical datasets.

Siddhartha Kumar Arjaria, A. K. Gupta, Paritosh Mishra +3 more

Tayyaba Shahwar, Junaid Zafar, Ahmad Almogren +4 more

Deep Neural Networks have offered numerous innovative solutions to brain-related diseases including Alzheimer’s. However, there are still a few standpoints in terms of diagnosis and planning that can be transformed via quantum Machine Learning (QML). In this study, we present a hybrid classical–quantum machine learning model for the detection of Alzheimer’s using 6400 labeled MRI scans with two classes. Hybrid classical–quantum transfer learning is used, which makes it possible to optimally pre-process complex and high-dimensional data. Classical neural networks extract high-dimensional features and embed informative feature vectors into a quantum processor. We use resnet34 to extract features from the image and feed a 512-feature vector to our quantum variational circuit (QVC) to generate a four-feature vector for precise decision boundaries. Adam optimizer is used to exploit the adaptive learning rate corresponding to each parameter based on first- and second-order gradients. Furthermore, to validate the model, different quantum simulators (PennyLane, qiskit.aer and qiskit.basicaer) are used for the detection of the demented and non-demented images. The learning rate is set to 10−4 for and optimized quantum depth of six layers, resulting in a training accuracy of 99.1% and a classification accuracy of 97.2% for 20 epochs. The hybrid classical–quantum network significantly outperformed the classical network, as the classification accuracy achieved by the classical transfer learning model was 92%. Thus, a hybrid transfer-learning model is used for binary detection, in which a quantum circuit improves the performance of a pre-trained ResNet34 architecture. Therefore, this work offers a method for selecting an optimal approach for detecting Alzheimer’s disease. The proposed model not only allows for the automated detection of Alzheimer’s but would also speed up the process significantly in clinical settings.

Fazil A. Sheikh

Alzheimer's Disease (AD) first affects the brain parts that are associated with learning. It is one of the most prevalent forms of Dementia. Its early diagnosis is crucial for properly managing the disease treatment because it is chronic and irreversible. This paper introduces a holistic approach to achieve early detection of AD using the hippocampus and transfer learning. Here we have compared the results from the classical machine learning model – Support Vector Machine (SVM) and the Quantum Support Vector Machine (QSVM) model. QSVM - a quantum variant of standard SVM algorithm. It is developed using techniques such as quantum kernel estimation in quantum computing for more efficient processing of high-dimensional data than standard SVMs.. The most common symptoms of Alzheimer’s are loss of memory and cognitive impairment. This stems from the destruction and death of nerve cells in the brain related to memory. Mild Cognitive Impairment (MCI) is a condition between normal brain function and Alzheimer’s. From the prodromal MCI stage, it progresses gradually to dementia. Several studies show that Alzheimer’s develops at a rate of 10–15% per year from MCI. The early identification of patients with MCI may halt/delay the progression from MCI stage to Alzheimer’s. The results with the precision of 0.85 with the QSVM compared to the precision of 0.78 and recall of 1.00 compared to the 0.89 with the traditional SVM shows that our technique of Quantum Machine Learning (QML) is very useful in Alzheimer’s early diagnosis.