Muhammad Moazzam Jawaid
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Muhammad Moazzam Jawaid has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- James M. Brown
University of Lincoln
3 shared publications - Sanam Narejo
Department of Computer System Engineering, Mehran University of Engineering and Technology, Indus Hwy, Jamshoro, Sindh 76062
3 shared publications - Rasneer Sonia Bains
Mary Lyon Centre, Medical Research Council Harwell Oxfordshire UK
2 shared publications - Sara Wells
The Mary Lyon Centre, MRC Harwell, Oxfordshire, United Kingdom
2 shared publications - Shafiya Qadeer Memon
Department of Software Engineering, Mehran University of Engineering & Technology, Jamshoro 76062, Pakistan
2 shared publications - Constantino Carlos Reyes-Aldasoro
City St. George’s, University of London
1 shared publication
Latest Publications
- Open Access
- 1 October 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (10) , 475
DWFAU-Net: A Clinically-Guided Dual-Window Fusion Attention U-Net for Coronary Artery Segmentation in CT Angiography
Coronary artery segmentation in coronary computed tomography angiography (CCTA) is challenging because the vessels are small, low in contrast and anatomically variable. We propose a Dual-Window Fusion Attention U-Net (DWFAU-Net) in which two Hounsfield Unit windows, selected on validation patients, are processed by parallel encoders, fused by learnable 1 × 1 convolutions and decoded by a shared attention-gated decoder. Each window input combines the normalized CT image with a Frangi vesselness map and a Gaussian-smoothed image, and training uses a topology-aware BCE, Soft-Dice and clDice loss. On 16 Rotterdam volumes, under a patient-level protocol and without a region of interest, centerline or seed points, DWFAU-Net achieved a Dice Similarity Coefficient (DSC) of 0.691 and an IoU of 0.580 on unseen patients, with a stable DSC of 0.697 ± 0.012 over five trainings. In five-fold patient-level cross-validation, it achieved the highest slice DSC in folds 1–4 and the lowest mean 95th-percentile Hausdorff distance (30.55 pixels), with overall overlap statistically comparable to single-window and concatenation models. Ablations showed a consistent gain from the Frangi channel (volumetric Dice 0.712 vs. 0.684) and identified a clDice weight of 0.5 as the best of the tested weights, preserving patient-level overlap. The model was robust to ±50 HU contrast-enhancement shifts (DSC change ≤ 0.040) and segmented a patient in 0.31 s. A slice-level split gave a DSC of 0.870, showing how strongly the data-splitting protocol affects reported accuracy.
- 1 October 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (10) , 475
Open AccessDWFAU-Net: A Clinically-Guided Dual-Window Fusion Attention U-Net for Coronary Artery Segmentation in CT Angiography
Coronary artery segmentation in coronary computed tomography angiography (CCTA) is challenging because the vessels are small, low in contrast and anatomically variable. We propose a Dual-Window Fusion Attention U-Net (DWFAU-Net) in which two Hounsfield Unit windows, selected on validation patients, are processed by parallel encoders, fused by learnable 1 × 1 convolutions and decoded by a shared attention-gated decoder. Each window input combines the normalized CT image with a Frangi vesselness map and a Gaussian-smoothed image, and training uses a topology-aware BCE, Soft-Dice and clDice loss. On 16 Rotterdam volumes, under a patient-level protocol and without a region of interest, centerline or seed points, DWFAU-Net achieved a Dice Similarity Coefficient (DSC) of 0.691 and an IoU of 0.580 on unseen patients, with a stable DSC of 0.697 ± 0.012 over five trainings. In five-fold patient-level cross-validation, it achieved the highest slice DSC in folds 1–4 and the lowest mean 95th-percentile Hausdorff distance (30.55 pixels), with overall overlap statistically comparable to single-window and concatenation models. Ablations showed a consistent gain from the Frangi channel (volumetric Dice 0.712 vs. 0.684) and identified a clDice weight of 0.5 as the best of the tested weights, preserving patient-level overlap. The model was robust to ±50 HU contrast-enhancement shifts (DSC change ≤ 0.040) and segmented a patient in 0.31 s. A slice-level split gave a DSC of 0.870, showing how strongly the data-splitting protocol affects reported accuracy.
- Open Access
- 20 July 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (7) , 328
Contrastive and Transfer Learning for Aligned Multimodal Neuroimaging Classification of Autism Spectrum Disorder
Autism Spectrum Disorder (ASD) assessment remains challenging because behavioural instruments are partly observer-dependent and neuroimaging data are heterogeneous. This paper presents FAA (Fuse After Aligned), which is a multimodal classification framework that combines transfer learning for structural MRI (sMRI) representation learning with a contrastive objective for the pre-fusion alignment of sMRI and resting-state functional MRI-derived functional connectivity (FC) features. Evaluation was restricted to the single-site ABIDE-I New York University subset comprising 75 participants with ASD and 98 typically developing controls. Under the reported five-fold internal cross-validation protocol, FAA achieved a mean accuracy of 92.6% compared with 87.4% for naive fusion and 90.9% for the sMRI-only baseline. Ablation analyses indicate that adding the contrastive objective is associated with improved classification performance and that ResNet-18 outperforms the evaluated ViT-16 configurations in this small-sample setting. These findings support the methodological value of pre-fusion feature alignment within the evaluated cohort. The framework offers a robust, computationally efficient, and clinically viable approach for objective ASD diagnosis with strong potential for generalisation to multi-site neuroimaging applications.
- 20 July 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (7) , 328
Open AccessContrastive and Transfer Learning for Aligned Multimodal Neuroimaging Classification of Autism Spectrum Disorder
Autism Spectrum Disorder (ASD) assessment remains challenging because behavioural instruments are partly observer-dependent and neuroimaging data are heterogeneous. This paper presents FAA (Fuse After Aligned), which is a multimodal classification framework that combines transfer learning for structural MRI (sMRI) representation learning with a contrastive objective for the pre-fusion alignment of sMRI and resting-state functional MRI-derived functional connectivity (FC) features. Evaluation was restricted to the single-site ABIDE-I New York University subset comprising 75 participants with ASD and 98 typically developing controls. Under the reported five-fold internal cross-validation protocol, FAA achieved a mean accuracy of 92.6% compared with 87.4% for naive fusion and 90.9% for the sMRI-only baseline. Ablation analyses indicate that adding the contrastive objective is associated with improved classification performance and that ResNet-18 outperforms the evaluated ViT-16 configurations in this small-sample setting. These findings support the methodological value of pre-fusion feature alignment within the evaluated cohort. The framework offers a robust, computationally efficient, and clinically viable approach for objective ASD diagnosis with strong potential for generalisation to multi-site neuroimaging applications.
- Open Access
- 10 November 2025
- Published by Ediciones Universidad de Salamanca in ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal
- Vol. 14, e32449
Explainable Machine Learning for Mental Health Detection Using NLP
Humans’ mental conditions are often revealed through their social media activity, facilitated by the anonymity of the internet. Early detection of psy- chiatric issues through these activities can lead to timely interventions, po- tentially preventing severe mental health disorders such as depression and anxiety. However, the complexity of state-of-the-art machine learning (ML) models has led to challenges in interpretability, often resulting in these models being viewed as «black boxes». This paper provides a comprehensive analysis of explainable AI (XAI) within the framework of Natural Language Processing (NLP) and ML. Thus, NLP techniques improve the performance of learning-based methods by incorporating the semantic and syntactic features of the text. The application of ML in healthcare is gaining traction, particularly in extracting novel scientific insights from observational or simulated data. Domain knowledge is crucial for achieving scientific consistency and explainability. In our study, we implemented Naïve Bayes and Random Forest algorithms, achieving accuracies of 92 % and 99 %, respectively. To further explore transparency, interpretability, and explainability, we applied explainable ML techniques, with LIME emerging as a popular tool. Our findings underscore the importance of integrating XAI methods to better understand and interpret the decisions made by complex ML models.
- 10 November 2025
- Published by Ediciones Universidad de Salamanca in ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal
- Vol. 14, e32449
Open AccessExplainable Machine Learning for Mental Health Detection Using NLP
Humans’ mental conditions are often revealed through their social media activity, facilitated by the anonymity of the internet. Early detection of psy- chiatric issues through these activities can lead to timely interventions, po- tentially preventing severe mental health disorders such as depression and anxiety. However, the complexity of state-of-the-art machine learning (ML) models has led to challenges in interpretability, often resulting in these models being viewed as «black boxes». This paper provides a comprehensive analysis of explainable AI (XAI) within the framework of Natural Language Processing (NLP) and ML. Thus, NLP techniques improve the performance of learning-based methods by incorporating the semantic and syntactic features of the text. The application of ML in healthcare is gaining traction, particularly in extracting novel scientific insights from observational or simulated data. Domain knowledge is crucial for achieving scientific consistency and explainability. In our study, we implemented Naïve Bayes and Random Forest algorithms, achieving accuracies of 92 % and 99 %, respectively. To further explore transparency, interpretability, and explainability, we applied explainable ML techniques, with LIME emerging as a popular tool. Our findings underscore the importance of integrating XAI methods to better understand and interpret the decisions made by complex ML models.
- Open Access
- 7 October 2025
- Published by MDPI AG in Journal of Imaging
- Vol. 11 (10) , 348
Hierarchical Deep Learning for Abnormality Classification in Mouse Skeleton Using Multiview X-Ray Images: Convolutional Autoencoders Versus ConvNeXt
Single-view-based anomaly detection approaches present challenges due to the lack of context, particularly for multi-label problems. In this work, we demonstrate the efficacy of using multiview image data for improved classification using a hierarchical learning approach. Using 170,958 images from the International Mouse Phenotyping Consortium (IMPC) repository, a specimen-wise multiview dataset comprising 54,046 specimens was curated. Next, two hierarchical classification frameworks were developed by customizing ConvNeXT and a convolutional autoencoder (CAE) as CNN backbones, respectively. The customized architectures were trained at three hierarchy levels with increasing anatomical granularity, enabling specialized layers to learn progressively more detailed features. At the top level (L1), multiview (MV) classification performed about the same as single views, with a high mean AUC of 0.95. However, using MV images in the hierarchical model greatly improved classification at levels 2 and 3. The model showed consistently higher average AUC scores with MV compared to single views such as dorsoventral or lateral. For example, at Level 2 (L2), the model divided abnormal cases into three subclasses, achieving AUCs of 0.65 for DV, 0.76 for LV, and 0.87 for MV. Then, at Level 3 (L3), it further divided these into ten specific abnormalities, with AUCs of 0.54 for DV, 0.59 for LV, and 0.82 for MV. A similar performance was achieved by the CAE-driven architecture, with mean AUCs of 0.87, 0.88, and 0.89 at Level 2 (L2) and 0.74, 0.78, and 0.81 at Level 3 (L3), respectively, for DV, LV, and MV views. The overall results demonstrate the advantage of multiview image data coupled with hierarchical learning for skeletal abnormality detection in a multi-label context.
- 7 October 2025
- Published by MDPI AG in Journal of Imaging
- Vol. 11 (10) , 348
Open AccessHierarchical Deep Learning for Abnormality Classification in Mouse Skeleton Using Multiview X-Ray Images: Convolutional Autoencoders Versus ConvNeXt
Single-view-based anomaly detection approaches present challenges due to the lack of context, particularly for multi-label problems. In this work, we demonstrate the efficacy of using multiview image data for improved classification using a hierarchical learning approach. Using 170,958 images from the International Mouse Phenotyping Consortium (IMPC) repository, a specimen-wise multiview dataset comprising 54,046 specimens was curated. Next, two hierarchical classification frameworks were developed by customizing ConvNeXT and a convolutional autoencoder (CAE) as CNN backbones, respectively. The customized architectures were trained at three hierarchy levels with increasing anatomical granularity, enabling specialized layers to learn progressively more detailed features. At the top level (L1), multiview (MV) classification performed about the same as single views, with a high mean AUC of 0.95. However, using MV images in the hierarchical model greatly improved classification at levels 2 and 3. The model showed consistently higher average AUC scores with MV compared to single views such as dorsoventral or lateral. For example, at Level 2 (L2), the model divided abnormal cases into three subclasses, achieving AUCs of 0.65 for DV, 0.76 for LV, and 0.87 for MV. Then, at Level 3 (L3), it further divided these into ten specific abnormalities, with AUCs of 0.54 for DV, 0.59 for LV, and 0.82 for MV. A similar performance was achieved by the CAE-driven architecture, with mean AUCs of 0.87, 0.88, and 0.89 at Level 2 (L2) and 0.74, 0.78, and 0.81 at Level 3 (L3), respectively, for DV, LV, and MV views. The overall results demonstrate the advantage of multiview image data coupled with hierarchical learning for skeletal abnormality detection in a multi-label context.
- 24 July 2024
- Published by Springer Nature
- p. 425-437
Hierarchical Multi-label Learning for Musculoskeletal Phenotyping in Mice
- 24 July 2024
- Published by Springer Nature
- p. 425-437
Hierarchical Multi-label Learning for Musculoskeletal Phenotyping in Mice
- Open Access
- 22 May 2024
- Published by IOP Publishing in Medical Engineering & Physics
- Vol. 129 (1) , 104182
Non-calcified plaque-based coronary stenosis grading in contrast enhanced CT
The high mortality rate associated with coronary heart disease has led to state-of-the-art non-invasive methods for cardiac diagnosis including computed tomography and magnetic resonance imaging. However, stenosis computation and clinical assessment of non-calcified plaques has been very challenging due to their ambiguous intensity response in CT i.e. a significant overlap with surrounding muscle tissues and blood. Accordingly, this research presents an approach for computation of coronary stenosis by investigating cross-sectional lumen behaviour along the length of 3D coronary segments. Non-calcified plaques are characterized by comparatively lower-intensity values with respect to the surrounding. Accordingly, segment-wise orthogonal volume was reconstructed in 3D space using the segmented coronary tree. Subsequently, the cross sectional volumetric data was investigated using proposed CNN-based plaque quantification model and subsequent stenosis grading in clinical context was performed. In the last step, plaque-affected orthogonal volume was further investigated by comparing vessel-wall thickness and lumen area obstruction w.r.t. expert-based annotations to validate the stenosis grading performance of model. The experimental data consists of clinical CT images obtained from the Rotterdam CT repository leading to 600 coronary segments and subsequent 15786 cross-sectional images. According to the results, the proposed method quantified coronary vessel stenosis i.e. severity of the non-calcified plaque with an overall accuracy of 83%. Moreover, for individual grading, the proposed model show promising results with accuracy equal to 86%, 90% and 79% respectively for severe, moderate and mild stenosis. The stenosis grading performance of the proposed model was further validated by performing lumen-area versus wall-thickness analysis as per annotations of manual experts. The statistical results for lumen area analysis precisely correlates with the quantification performance of the model with a mean deviation of 5% only. The overall results demonstrates capability of the proposed model to grade the vessel stenosis with reasonable accuracy and precision equivalent to human experts.
- 22 May 2024
- Published by IOP Publishing in Medical Engineering & Physics
- Vol. 129 (1) , 104182
Open AccessNon-calcified plaque-based coronary stenosis grading in contrast enhanced CT
The high mortality rate associated with coronary heart disease has led to state-of-the-art non-invasive methods for cardiac diagnosis including computed tomography and magnetic resonance imaging. However, stenosis computation and clinical assessment of non-calcified plaques has been very challenging due to their ambiguous intensity response in CT i.e. a significant overlap with surrounding muscle tissues and blood. Accordingly, this research presents an approach for computation of coronary stenosis by investigating cross-sectional lumen behaviour along the length of 3D coronary segments. Non-calcified plaques are characterized by comparatively lower-intensity values with respect to the surrounding. Accordingly, segment-wise orthogonal volume was reconstructed in 3D space using the segmented coronary tree. Subsequently, the cross sectional volumetric data was investigated using proposed CNN-based plaque quantification model and subsequent stenosis grading in clinical context was performed. In the last step, plaque-affected orthogonal volume was further investigated by comparing vessel-wall thickness and lumen area obstruction w.r.t. expert-based annotations to validate the stenosis grading performance of model. The experimental data consists of clinical CT images obtained from the Rotterdam CT repository leading to 600 coronary segments and subsequent 15786 cross-sectional images. According to the results, the proposed method quantified coronary vessel stenosis i.e. severity of the non-calcified plaque with an overall accuracy of 83%. Moreover, for individual grading, the proposed model show promising results with accuracy equal to 86%, 90% and 79% respectively for severe, moderate and mild stenosis. The stenosis grading performance of the proposed model was further validated by performing lumen-area versus wall-thickness analysis as per annotations of manual experts. The statistical results for lumen area analysis precisely correlates with the quantification performance of the model with a mean deviation of 5% only. The overall results demonstrates capability of the proposed model to grade the vessel stenosis with reasonable accuracy and precision equivalent to human experts.
- Open Access
- 1 January 2018
- Published by IACSIT Press in International Journal of Computer Theory and Engineering
- Vol. 10 (3) , 84-92
A Review of the State-of-the-Art Methods for Non-calcified Plaque Detection in Cardiac CT Angiography
- 1 January 2018
- Published by IACSIT Press in International Journal of Computer Theory and Engineering
- Vol. 10 (3) , 84-92
Open AccessA Review of the State-of-the-Art Methods for Non-calcified Plaque Detection in Cardiac CT Angiography