Administrator, University of Gujrat · PhD, PIEAS
PhD in Computer Science | AI & Deep Learning Researcher
Medical AI·Computer Vision·Bioinformatics·Proteomics·Data Science
PhD-qualified data scientist and AI researcher specializing in deep learning, transformer-based architectures, vision-language models, and natural language processing. Her work focuses on multimodal and generative AI for healthcare, with particular attention to medical imaging, proteomics, cancer detection, and clinical decision-support systems. She designs end-to-end AI pipelines spanning supervised and unsupervised learning, model optimization, interpretability, and deployment, and is an experienced mentor, instructor, and academic trainer.
Deep learning systems for cancer detection and clinical decision support across dermatology, neuroimaging, haematology, thyroid, lung, liver, and breast imaging.
Classification, segmentation, and object detection on noisy, low-contrast, and multimodal medical images.
Residual-integrated, channel-boosted, and hybrid CNN–transformer architectures, including ARiViT, ReLViT, CBViT, and related models.
Protein-sequence analysis, multi-tissue protein expression classification, and computational approaches to leukaemia-related prediction.
GANs and related generative methods for medical image quality, augmentation, and channel-boosted transformer pipelines.
Interpretability for medical imaging models, including attention maps and XAI methods for breast ultrasound.
Dermatological diagnosis of skin cancer from lesion images, where visual inspection is labour-intensive and lesion appearance is complex.
PublishedClassification of noisy brain medical images, where overlapping intensities and image noise hinder reliable tumour analysis.
PublishedClassification and detection of acute myeloid leukemia on bone marrow images with complex structure and overlapping intensity.
PublishedFragmented evidence on skin cancer classification and segmentation using the ISIC datasets.
These contributions are listed with their current scholarly status. They are not presented as published papers.
A hospital-facing platform for brain tumour detection and classification, with CNN and transformer-inspired models.
DeployedLed design and deployment of the University of Gujrat learning management system, 2013–2014.
Project workDeep learning IDS comparing MLP, CNN, and transformer sequence models. Project work; not a CV-listed journal paper.
2014 – present
University of Gujrat, Pakistan
Nov 2023 – Feb 2024
International Certificate Center, Accra, Ghana
Sept 2019 – Oct 2023
Arid University, Rawalpindi, Pakistan
Madiha Hameed, Aneela Zameer, Muhammad Yousaf Hamza, Muhammad Asif Zahoor Raja
Applied Intelligence
doi:10.1007/s10489-026-07111-6Madiha Hameed, Kok Swee Sim
Frontiers in Digital Health, 8:1846763
doi:10.3389/fdgth.2026.1846763Madiha Hameed, Muhammad Asif Zahoor Raja, Aneela Zameer, Hafsa Shareef Dar, Ala Saleh Alluhaidan, Romana Aziz
Scientific Reports, 15, 32798
doi:10.1038/s41598-025-17891-5Time series · 28 August 2026
Amazon Chronos treats a series as tokens a language model can read. The original T5 models, Chronos-Bolt, and Chronos-2 differ in speed, context, and whether they can use related series and covariates.
RAG · 24 August 2026
RAG retrieves passages first, then generates. It is a method for reducing unsupported claims, not a guarantee of truth.
LLM · 23 August 2026
LLMs are strong at drafting and summarising. They are not a substitute for a trained medical-image model or for a cited clinical source.
Attia Noor
Comprehensive diagnostic strategies for thyroid cancer addressing class imbalance with advanced artificial intelligence learning techniques
MS · Completed · Co-supervised · 2025
Hamna Zubair
Advanced feature fusion for artificial intelligence driven breast cancer imaging
MS · Completed · Co-supervised · 2025
Khizra Noor
Deep learning empowered framework for improved diagnosis in thyroid carcinoma
MS · Completed · Co-supervised · 2025
Syeda Muntaha Bader
Explainable artificial intelligence for multimodel imaging in breast cancer diagnosis
MS · Completed · Co-supervised · 2025
Read the bibliography, the research portfolio, the services, the blog, or get in touch.