Dr Javeria Amin

Dr. Javeria Amin

She received her degree in Classification Using Deep Learning from COMSATS University Islamabad, Pakistan. She is currently serving as an Assistant Professor in the Computer Science Department at Rawalpindi Women University, Pakistan. Her primary research interests in recent years include medical imaging, COVID-19, MRI analysis, video surveillance, human gait recognition, and agriculture plants using deep learning. She has published over 80 research papers with more than 6,067 citations, an overall impact factor of 320+, an H-index of 35, and an I-index of 59.

This research group's main goal is to create and test new image processing methods, algorithms, and software tools for medical image analysis. This includes extracting clinically useful characteristics and biomarkers from images that describe the appearance and function of organs. With a special focus on, but not limited to, the human brain, we hope to support clinical investigations and preclinical research, as well as develop and improve computer-aided diagnostics and patient-specific prediction models.

Predictive Analytics and Diagnostic Support

We're working on statistical and machine-learning models to make computer-aided diagnostic, treatment recommendations using real medical data and robotic, surveillances/ security based human videos analysis. Our efforts are focused on automating and improving components of model design in order to improve the accuracy and accessibility of this technology.

Generative Modeling

On the basis of medical pictures, we are developing unique statistically justified machine learning algorithms to assess and model form and appearance changes of anatomical and pathological structures (e.g., organs) on a subject-specific or population level. These models can then be used as clinical predictors, research exploratory tools, or prior information in sophisticated medical image analysis techniques

Medical Image Analysis

Innovative approaches are currently being developed to process, analyze, and leverage medical and biological images. These novel methods aim to enhance diagnostic accuracy, improve treatment strategies, and deepen our understanding of complex biological systems. The ongoing efforts signify a promising advancement in the field of medical imaging and bioinformatics.

Clinically acquired new challenging dataset for brain SOL segmentation: AJBDS-2023

Space-occupying lesions (SOL) brain detected on brain MRI are benign and malignant tumors. Several brain tumor segmentation algorithms have been developed but there is a need for a clinically acquired dataset that is used for real-time images. This research is done to facilitate reporting of MRI done for brain tumor detection by incorporating computer-aided detection. Another objective was to make reporting unbiased by decreasing inter-observer errors and expediting daily reporting sessions to decrease radiologists’ workload. This is an experimental study. The proposed dataset contains clinically acquired multiplanar, multi-sequential MRI slices (MPMSI) which are used as input to the segmentation model without any preprocessing. The proposed AJBDS-2023 consists of 10667 images of real patients imaging data with a size of 320*320*3. Acquired images have T1W, TW2, Flair, T1W contrast, ADC, and DWI sequences. Pixel-based ground-truth annotated images of the tumor core and edema of 6334 slices are made manually under the supervision of a radiologist. Quantitative assessment of AJBDS-2023 images is done by a novel U-network on 4333 MRI slices. The diagnostic accuracy of our algorithm U-Net trained on AJBDS-2023 was 77.4 precision, 82.3 DSC, 87.4 specificity, 93.8 sensitivity, and 90.4 confidence interval. An experimental analysis of AJBDS-2023 done by the U-Net segmentation model proves that the proposed AJBDS-2023 dataset has images without preprocessing, which is more challenging and provides a more realistic platform for evaluation and analysis of newly developed algorithms in this domain and helps radiologists in MRI brain reporting more realistically.

Training Dataset

Testing Dataset

Please cite these paper when using this dataset

1. Amin, J., Anjum, M. A., Gul, N., Sharif, M., & Kadry, S. (2023). Clinically Acquired New Challenging Dataset for Brain SOL Segmentation: AJBDS-2023. Data in Brief, 109915.

2. Amin, Javaria, Muhammad Almas Anjum, Nadia Gul, and Muhammad Sharif. "A secure two-qubit quantum model for segmentation and classification of brain tumor using MRI images based on blockchain." Neural Computing and Applications (2022): 1-14.

3. Amin, Javaria, Muhammad Almas Anjum, Nadia Gul, and Muhammad Sharif. "Detection of brain space-occupying lesions using quantum machine learning." Neural Computing and Applications (2023): 1-17.

Project Presentation at Asian-Oceanian Congress of Neurology 2023

Dr. Javeria Amin, Assistant Professor, Department of Computer Science-UW, presented two innovative projects titled "AI-Lung: A Deep Learning Approach for COVID-19 Lung Lobe Analysis and Grading" and "Deep Learning-Based Automated Detection of Space Occupying Lesions" at the 14th Asian Oceanian Congress of Neuroradiology held in Singapore from 16-18 August 2023. The congress was conducted with the SGCR-WIRES 2023, the 31st Annual Scientific Meeting of the Singapore Congress of Radiology, and the 13th Workshops in Interventional Radiology Education. These projects hold significant potential for revolutionizing the field of radiology and could pave the way for more effective diagnosis and treatment of various medical conditions.

Clinically acquired new challenging dataset for brain SOL segmentation: AJBDS-2023

Space-occupying lesions (SOL) brain detected on brain MRI are benign and malignant tumors. Several brain tumor segmentation algorithms have been developed but there is a need for a clinically acquired dataset that is used for real-time images. This research is done to facilitate reporting of MRI done for brain tumor detection by incorporating computer-aided detection. Another objective was to make reporting unbiased by decreasing inter-observer errors and expediting daily reporting sessions to decrease radiologists’ workload. This is an experimental study. The proposed dataset contains clinically acquired multiplanar, multi-sequential MRI slices (MPMSI) which are used as input to the segmentation model without any preprocessing.

Quantum AI for Psychiatric Diagnosis: Enhancing Dementia Classification with Quantum Machine Learning

Quantum AI for Psychiatric Diagnosis: Enhancing Dementia Classification with Quantum Machine Learning

Dr Javeria Amin October 02, 2025

📥 Download Project ZIP Aap neeche diye gaye button par click kar ke poora code ZIP file format mein download kar sakte hain: ⬇ Download Z…

Artificial Intelligence-Driven Deepfake Detection: Hybrid Self-Supervised Learning and Swin Transformer for Explainable Fake Image Classification

Artificial Intelligence-Driven Deepfake Detection: Hybrid Self-Supervised Learning and Swin Transformer for Explainable Fake Image Classification

Dr Javeria Amin May 07, 2025

Autoencoder with Squeeze-and-Excitation Blocks and SWIN Transformer for Image Classification This blog post presents a hybrid deep learning archite…

Validation of a COVID-19 grading system based on Harris Hawks optimization and a variational quantum classifier using JLDS-2024

Validation of a COVID-19 grading system based on Harris Hawks optimization and a variational quantum classifier using JLDS-2024

Dr Javeria Amin May 03, 2025

Lung Lobe-Based Scoring Criteria Score-level information was commonly used during the Severe Acute Respiratory Syndrome (SARS) epidemic. …

An optimized features selection approach based on Manta Ray Foraging Optimization (MRFO) method for parasite malaria classification

An optimized features selection approach based on Manta Ray Foraging Optimization (MRFO) method for parasite malaria classification

Dr Javeria Amin February 28, 2025

```html Malaria Cell Segmentation and Classification Introduction This Python implementation performs malaria cell segmentation and classificati…

Skin-Lesion Segmentation using Boundary-Aware Segmentation Network and Classification based on a Mixture of Convolutional and Transformer Neural Networks

Skin-Lesion Segmentation using Boundary-Aware Segmentation Network and Classification based on a Mixture of Convolutional and Transformer Neural Networks

Dr Javeria Amin February 23, 2025

Open in Google Colab import matplotlib.pyplot as plt import numpy as np import tensorflow as tf from tensorflow import keras from tensorflo…

Dual-Method for Semantic and Instance Brain Tumor Segmentation based on UNet and Mask R-CNN using MRI

Dual-Method for Semantic and Instance Brain Tumor Segmentation based on UNet and Mask R-CNN using MRI

Dr Javeria Amin October 04, 2024

DOWNLOAD CODE CLICK HERE TO DOWNLOAD PYTHON CODE CLICK HERE TO DOWNLOAD WEIGHT FILE

ALL Classification using QCNN and Segmentation based on SAM

ALL Classification using QCNN and Segmentation based on SAM

Dr Javeria Amin September 14, 2024

The ALL-IDB1, ALL-IDB2 and C-NMC 2019 datasets are publicly available on the following links “Acute Lymphoblastic Leukemia (ALL) image dataset (kagg…