Hussain Ahmad Madni

Mr. Hussain Ahmad Madni

COMSATS University Islamabad, Islamabad, Pakistan

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2021 in IEEE Access
Verified
Journal Article
Open access
FDFaizan Daud
Faizan Daud
RIRakhshanda Imtiaz
Rakhshanda Imtiaz
Hussain Ahmad MadniHussain Ahmad Madni
Hussain Ahmad Madni
HKHaroon Ahmed Khan
Haroon Ahmed Khan
TKTarqi Khan
Tarqi Khan
FAFaizan Abdullah
Faizan Abdullah
Glaucoma is an incurable eye disease that leads to slow progressive degeneration of the retina. It cannot be fully cured, however, its progression can be controlled in case of early diagnosis. Unfortunately, due to the absence of clear symptoms during the early stages, early diagnosis are rare. Glaucoma must be detected at early stages since late diagnosis can lead to permanent vision loss. Glaucoma affects the retina by damaging the Optic Nerve Head (ONH). Its diagnosis is dependent on the measurements of Optic Cup (OC) and Optic Disc (OD) in the retina. Computer vision techniques have been shown to diagnose glaucoma effectively and correctly with little overhead. These techniques measure OC and OC dimensions using machine learning based classification and segmentation algorithms. This article aims to provide a comprehensive overview of various existing techniques that use machine learning to detect and diagnose glaucoma based on fundus images. Readers would be able to understand the challenges glaucoma presents from an image processing and machine learning stand-point and will be able to identify gaps in current research.

12 January 2021 in Diagnostics
Verified
Journal Article
Open access
PDF file
Khuram NaveedKhuram Naveed
Khuram Naveed
FDFaizan Daud
Faizan Daud
Hussain Ahmad MadniHussain Ahmad Madni
Hussain Ahmad Madni
MKMohammad A.U. Khan
Mohammad A.U. Khan
TKTarqi Khan
Tarqi Khan
SNSyed Saud Naqvi
Syed Saud Naqvi
Automated detection of vision threatening eye disease based on high resolution retinal fundus images requires accurate segmentation of the blood vessels. In this regard, detection and segmentation of finer vessels, which are obscured by a considerable degree of noise and poor illumination, is particularly challenging. These noises include (systematic) additive noise and multiplicative (speckle) noise, which arise due to various practical limitations of the fundus imaging systems. To address this inherent issue, we present an efficient unsupervised vessel segmentation strategy as a step towards accurate classification of eye diseases from the noisy fundus images. To that end, an ensemble block matching 3D (BM3D) speckle filter is proposed for removal of unwanted noise leading to improved detection. The BM3D-speckle filter, despite its ability to recover finer details (i.e., vessels in fundus images), yields a pattern of checkerboard artifacts in the aftermath of multiplicative (speckle) noise removal. These artifacts are generally ignored in the case of satellite images; however, in the case of fundus images, these artifacts have a degenerating effect on the segmentation or detection of fine vessels. To counter that, an ensemble of BM3D-speckle filter is proposed to suppress these artifacts while further sharpening the recovered vessels. This is subsequently used to devise an improved unsupervised segmentation strategy that can detect fine vessels even in the presence of dominant noise and yields an overall much improved accuracy. Testing was carried out on three publicly available databases namely Structured Analysis of the Retina (STARE), Digital Retinal Images for Vessel Extraction (DRIVE) and CHASE_DB1. We have achieved a sensitivity of 82.88, 81.41 and 82.03 on DRIVE, SATARE, and CHASE_DB1, respectively. The accuracy is also boosted to 95.41, 95.70 and 95.61 on DRIVE, SATARE, and CHASE_DB1, respectively. The performance of the proposed methods on images with pathologies was observed to be more convincing than the performance of similar state-of-the-art methods.

16 February 2023 in IEEE Access
Verified
Journal Article
Open access
Hussain Ahmad MadniHussain Ahmad Madni
Hussain Ahmad Madni
RURao Muhammad Umer
Rao Muhammad Umer
GFGian Luca Foresti
Gian Luca Foresti
Federated Learning (FL) is a machine learning technique, where collaborative and distributed learning is performed, while the private data reside locally on the client. Rather than the data, only gradients are shared among all collaborative nodes with the help of a central server. To ensure the data privacy, the gradients are prone to the deformation, or the representation is perturbed before sharing, ultimately reducing the performance of the model. Recent studies show that the original data can still be recovered using latent space (i.e., gradient leakage problem) by Generative Adversarial Network and different optimization algorithms such as Bayesian and Covariance Matrix Adaptation Evolution Strategy. To address the issues of data privacy and gradient leakage, in this paper, we train deep neural networks by exploiting the blockchain-based Swarm Learning (SL) framework. In the SL scheme, instead of sharing perturbed or noisy gradients to the central server, we share the gradients among authenticated (i.e., blockchain-based smart contract) training nodes. To demonstrate the effectiveness of the SL approach, we evaluate the proposed approach using the standard CIFAR10 and MNIST benchmark datasets and compare it with the other existing methods.

23 January 2025 in International Journal of Medical Informatics
Verified
Journal Article
Open access
Hussain Ahmad MadniHussain Ahmad Madni
Hussain Ahmad Madni
RURao Muhammad Umer
Rao Muhammad Umer
SZSilvia Zottin
Silvia Zottin
CMCarsten Marr
Carsten Marr
GFGian Luca Foresti
Gian Luca Foresti
Segmentation models for clinical data experience severe performance degradation when trained on a single client from one domain and distributed to other clients from different domain. Federated Learning (FL) provides a solution by enabling multi-party collaborative learning without compromising the confidentiality of clients' private data. In this paper, we propose a cross-domain FL method for Weakly Supervised Semantic Segmentation (FL-W3S) of white blood cells in microscopic images. We perform model training on multiple clients with different data distributions to obtain a global aggregated model using only image-level class labels for semantic segmentation of white blood cells. A multi-class token transformer model learns the relationship between patch tokens and class tokens during collaborative learning and generates class-specific localization maps for mask predictions. To rectify the localization maps, we use patch-level pairwise affinity obtained from patch-to-patch transformer attention. We evaluate performance of the proposed semantic segmentation method on two different datasets of white blood cells from different domains. Our experimental results show that for two datasets, there is 2.56% and 1.39% increase in performance of the proposed method over existing state-of-the-art methods. The combination of federated learning for collaborative model training while preserving data privacy, alongside white blood cell segmentation techniques for precise cell identification, enhances diagnostic accuracy and personalized treatment strategies in clinical applications, particularly in hematology and pathology. More specifically, it involves isolating white blood cell from blood smear for further analysis such as automated blood cell counting, morphological analysis, cell classification, disease diagnosis and monitoring.

27 June 2025 in International Journal of Neural Systems
Verified
Journal Article
Closed access
Hussain Ahmad MadniHussain Ahmad Madni
Hussain Ahmad Madni
HSHafsa Shujat
Hafsa Shujat
ANAxel De Nardin
Axel De Nardin
SZSilvia Zottin
Silvia Zottin
GFGian Luca Foresti
Gian Luca Foresti

30 March 2026 in IEEE Access
Verified
Journal Article
Open access
Hussain Ahmad MadniHussain Ahmad Madni
Hussain Ahmad Madni
HSHafsa Shujat
Hafsa Shujat
SZSilvia Zottin
Silvia Zottin
ANAxel De Nardin
Axel De Nardin
GFGian Luca Foresti
Gian Luca Foresti
Clinical datasets are often limited in availability and subject to strict privacy regulations, posing significant challenges for the development of accurate classification models. Synthetic data generation offers a promising alternative, enabling the augmentation of training datasets while preserving patient privacy. However, generating high-fidelity synthetic images that effectively support model training remains a significant challenge. In this paper, we focus on the classification of colorectal and lung carcinoma as representative tasks in cancer clinical diagnostics. We utilize a stable diffusion model enhanced with Low-Rank Adaptation (LoRA) weights to generate synthetic images from a limited number of real images used for fine-tuning. This method results in a performance improvement of the DeiT-L (Data-efficient Image Transformer–Large) and CLIP (Contrastive Language–Image Pretraining) models for colon and lung datasets, respectively, when trained on excessive synthetic data and a few real samples. Synthetic data closely mirrors the real samples, mitigating the issues of data scarcity and privacy, while enhancing model generalization. These findings support the use of synthetic data as a viable tool in cancer disease classification and demonstrate its potential to strengthen deep learning applications in clinical diagnostics and medical research. Experimental results on colon and lung histopathology datasets demonstrate that augmenting limited real data with diffusion-generated synthetic images consistently improves classification accuracy and generalization across multiple deep learning architectures, particularly in low-data (few-shot) regimes. Notably, the hybrid configuration combining a small number of real samples with synthetic data yields the most practically significant performance gains, highlighting its relevance for real-world clinical settings where annotated data are scarce. Code is available at: https://github.com/h-ahmad/rare_disease_ classification.