Callum Altham

Callum Altham

BSc. (Hons), MSc, FHEA

PhD Candidate in Computer Informatics and Graduate Teaching Assistant at Edge Hill University

Publications

You can also find my articles on my Google Scholar profile.

Machine learning for the detection and diagnosis of cognitive impairment in Parkinson’s Disease: A systematic review

Published in PLOS ONE, 2024

Parkinson’s Disease is the second most common neurological disease in over 60s. Cognitive impairment is a major clinical symptom, with risk of severe dysfunction up to 20 years post-diagnosis. Processes for detection and diagnosis of cognitive impairments are not sufficient to predict decline at an early stage for significant impact. Ageing populations, neurologist shortages and subjective interpretations reduce the effectiveness of decisions and diagnoses. Researchers are now utilising machine learning for detection and diagnosis of cognitive impairment based on symptom presentation and clinical investigation. This work aims to provide an overview of published studies applying machine learning to detecting and diagnosing cognitive impairment, evaluate the feasibility of implemented methods, their impacts, and provide suitable recommendations for methods, modalities and outcomes.

Recommended citation: Altham C, Zhang H, Pereira E (2024) Machine learning for the detection and diagnosis of cognitive impairment in Parkinson’s Disease: A systematic review. PLOS ONE 19(5): e0303644. https://doi.org/10.1371/journal.pone.0303644 https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0303644

Early Detection of Parkinson’s Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN)

Published in Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022), 2023

Detecting the potential for Parkinson’s Disease Dementia (PDD) as early as possible is crucial to ensure that quality of life can be maintained. However, the full origins of this condition are unknown and analysing potential causes such as the influence of the Cholinergic Basal Forebrain (cBF) can be challenging due to variation in brain tissue as well as low scan resolution. Additionally, the structure and function of the cBF can span both brain hemispheres, and therefore prove difficult to analyse using a singular deep learning method. In this paper, we propose a multi-scale, dual-sided approach to analysis of regions with low surface area such as the cBF. Initially, images are parsed using super-resolution to increase resolution and contrast. Then, a dual sided multi-scale convolutional neural network (DSMS-CNN) model is proposed to classify subjects as either normal cognition or PDD based on both hemispheres of the cBF together. Ablation studies and comparison experiments with state-of-the-art CNN models show that DSMS-CNN can achieve promising and superior performance.

Recommended citation: Altham, C. et al. (2023). Early Detection of Parkinson’s Disease Dementia Using Dual-Sided Multi-scale Convolutional Neural Networks (DSMS-CNN). In: Su, R., Zhang, Y., Liu, H., F Frangi, A. (eds) Medical Imaging and Computer-Aided Diagnosis. MICAD 2022. Lecture Notes in Electrical Engineering, vol 810. Springer, Singapore. https://doi.org/10.1007/978-981-16-6775-6_17 https://link.springer.com/chapter/10.1007/978-981-16-6775-6_17

Adaptive Multiscale Superpixel Embedding Convolutional Neural Network for Land Use Classification

Published in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022

Currently, a large number of remote sensing images with different resolutions are available for Earth observation and land monitoring, which are inevitably demanding intelligent analysis techniques for accurately identifying and classifying land use (LU). This article proposes an adaptive multiscale superpixel embedding convolutional neural network architecture (AMUSE-CNN) for tackling LU classification. Initially, the images are parsed via the superpixel representation so that the object-based analysis (via a superpixel embedding convolutional neural network scheme) can be carried out with the pixel context and neighborhood information. Then, a multiscale convolutional neural network (MS-CNN) is proposed to classify the superpixel-based images by identifying object features across a variety of scales simultaneously, in which multiple window sizes are used to fit to the various geometries of different LU classes. Furthermore, a proposed adaptive strategy is applied to best exert the classification capability of the MS-CNN. Subsequently, two modules are developed to fully implement the AMUSE-CNN architecture. More specifically, Module I is to determine the most suitable classes for each window size (scale) by applying majority voting to a series of MS-CNNs Module II carries out the classification of the classes identified in Module I for the given scale used in the MS-CNN and, therefore, complete the LU classification of the entire classes. The proposed AMUSE-CNN architecture is both quantitatively and qualitatively validated using remote sensing data collected from two cities, Kano and Lagos in Nigeria, due to the spatially complex LU distribution. Experimental results show the superior performance of our approach against several state-of-the-art techniques.

Recommended citation: H. Zhang et al., "Adaptive Multiscale Superpixel Embedding Convolutional Neural Network for Land Use Classification," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 7631-7642, 2022, doi: 10.1109/JSTARS.2022.3203234. https://ieeexplore.ieee.org/document/9875975