← Back to cohort

Abdul Rehman

NUST · 2026
Email
abrehman4163@gmail.com
Phone
923024917963
LinkedIn
https://www.linkedin.com/in/abrehman41
GitHub

Academic

Program
BS Computer Science
CGPA
3.75
Year
2026
Education
SEECS
Address
Okara, Pakistan
DOB

Career

Current role
Target role
Skills
Machine Learning, Deep Learning, Supervised Learning, Unsupervised Learning, CNNs, GANs, Deep Neural Networks, Medical Imaging, MRI Segmentation, Cardiac CINE MRI Analysis, Retinal Disease Classification, Dental Implant Detection, Explainable AI, LLM Bias

Verbatim text

The exact text the LLM saw on the page (or the booklet text from the old import). This is what powers semantic search.
Abdul Rehman
Cell: 923024917963 |  Email: abrehman4163@gmail.com
LinkedIn: https://www.linkedin.com/in/abrehman41
Address: HOUSE NO 41 STREET NO 2 DAR-UL-EHSAN TOWN OKARA , Okara , Pakistan
PROFESSIONAL PROFILE
Undergraduate researcher specializing in deep learning for medical imaging, with experience in MRI
segmentation, retinal disease classification, and dental implant detection using explainable AI
EDUCATION
BS Computer Science
SEECS , Islamabad , 3.75/4.0 (2026)
INTERNSHIP EXPERIENCE
Gengini
01-Jun-2025 - 31-Aug-2025
Machine Learning Intern
Deep Learning Lab, National Center of Artificial Intelligence (NCAI)
01-Jun-2025 - 31-May-2026
Research Assistant
Brain Vision Lab
23-Jan-2026 - 23-Jan-2026
Research based project on identification of LLM Bias
FINAL YEAR PROJECT
AI-Based Automatic Frequency Offset Selection for bSSFP CINE MRI at 3.0 Tesla
Balanced Steady State Precision (bSSFP) CMR sequence provides high contrast but is sensitive to off-resonance effects, requiring
frequency scouting to minimize banding artifacts. Manual selection is time-consuming and subjective, warranting an AI-driven
solution. Objective: To develop and validate an AI-based algorithm for automatic frequency offset selection in bSSFP CMR. Methods:
• Study Design: Study in 100 patients at 3T. • AI Model: A deep learning algorithm trained on bSSFP scout data to predict optimal
frequency offsets. • Comparison: AI-selected vs. manually selected offsets assessed for artifact reduction, image quality, and efficiency. • Outcomes: Primary: Optimal banding suppression. Secondary: Time efficiency and agreement with experts. Expected Impact: AI-driven frequency selection could improve image quality, standardize CMR workflows, and reduce scan time.
TECHNICAL EXPERTISE
Machine Learning & Deep Learning
Hands-on experience in machine learning and deep learning techniques, including supervised and unsupervised learning, CNNs,
GANs, and deep neural networks. Applied these methods to real-world research problems with strong performance across
classification and segmentation tasks.
Medical Imaging & Healthcare AI
Specialized in AI-driven medical imaging, with experience in MRI segmentation, cardiac CINE MRI analysis, retinal disease classification, and dental implant detection. Developed and evaluated clinically relevant models using healthcare datasets and research-grade benchmarks.

AI enrichment

Abdul Rehman is a BS Computer Science undergraduate with a 3.75 CGPA, specializing in deep learning for medical imaging and healthcare AI. He has research experience in MRI segmentation, retinal disease classification, and LLM bias identification through internships and academic projects.
Skills (AI)
["Deep Learning", "Machine Learning", "CNNs", "GANs", "Medical Imaging", "MRI Segmentation", "Retinal Disease Classification", "Explainable AI", "Python", "Research"]
Status: ai_done
Provenance
Source file: SEECS - Computer Science-2026.pdf
From job #258 page 77
Created: 1778167261