Nahid Ul Islam
Nahid Ul Islam

Nahid Ul Islam, Ph.D.

Artificial Intelligence · Deep Learning · Computer Vision
Ph.D. in Computer Science · Arizona State University
About

Summary

I hold a Ph.D. in Computer Science from Arizona State University, where I developed foundation models for large-scale image analysis in collaboration with Mayo Clinic. My work focuses on Computer Vision and Deep Learning, with expertise in foundation model pretraining, multi-task learning, Vision Transformers (ViT), and Swin Transformers, building models that unify classification, detection, and segmentation within a single end-to-end framework.

I have published 6 conference and 2 journal papers with 180+ citations and h-index 7, and hold 3 granted and 5+ pending U.S. patents in AI and Deep Learning. I am a recipient of the prestigious President's Award for Innovation at Arizona State University (Dec'2024) and the SUN Award for invited research talk and subject matter expertise (Apr'2026).

Beyond academia, I completed two industry internships at Intel Corporation in Machine Learning and Computer Vision. I am experienced in large-scale experiment design, benchmarking, and optimization across diverse imaging tasks, and proficient in Python, PyTorch, and TensorFlow, with hands-on experience in distributed training on HPC/GPU clusters, large-scale data pipelines, and end-to-end model development.

Career

Experience

Aug 2018 – May 2026Tempe, AZ

Research Assistant

ASU-Mayo Clinic Joint Research Collaboration
  • Published 8 peer-reviewed papers (6 conference, 2 journal) on Deep Learning, Computer Vision, and Image Analysis.
  • Inventor of 3 granted and 5 pending U.S. patents in AI and Deep Learning, developed in collaboration with Mayo Clinic.
  • Built scalable AI/ML frameworks on High-Performance Computing (HPC) GPU infrastructure using distributed training, Linux/SLURM-based remote computing, workflow orchestration, and large-scale data pipelines to support model training.
  • Developed a systematic benchmark comparing 12 CNN architectures, Vision/Swin Transformers, and 19 self-supervised models for image classification; proposed Embedding-based ViT (EViT), a two-stage framework that aggregates image-level representations across variable-length image sequences for volume-level prediction, improving AUC by 2.22% over prior state-of-the-art; achieved 94.3% average AUC in zero-shot transfer, with model attention verified against ground-truth regions.
  • Designed Foundation X/X+, an end-to-end multi-task foundation model framework integrating image classification, object detection, and segmentation; pretrained on 11 datasets (~826k images) spanning 11 classification, 6 detection, and 3 segmentation tasks; introduced Lock-Release Pretraining to reduce task-specific overfitting; outperformed single-task baselines across all datasets, with average gains of +1.0% AUC, +8.4% mAP, +3.7% Dice, and strong cross-task/cross-dataset generalization.
  • Developed Foundation CTPA, a unified 3D foundation model integrating image-level classification, volume-level classification, detection, and segmentation in one framework; pretrained on over 1.5 million image slices from 3D volumes; introduced Region-Guided ROI Alignment to transfer detection cues to segmentation; achieved gains over single-task baselines, averaging +6.7% image AUC, +2.6% volume AUC, +16.5% mAP, and +5.8% Dice, with strong generalization and cross-domain transferability.
May 2017 – Aug 2017Hillsboro, OR

Graduate Technical Intern

Client Computing Group
  • Benchmarked R-CNN, Fast R-CNN, Faster R-CNN, and Mask R-CNN for real-time obstacle detection, classification, and collision prediction for moving objects.
  • Presented experimental findings and actionable recommendations to the team, contributing to pathfinding and technical readiness decisions.
Feb 2017 – May 2017Hillsboro, OR

Graduate Software Engineering Intern

Client Computing Group
  • Researched deep learning approaches for human activity recognition from videos to enable smart home applications.
  • Developed an activity recognition system combining CNNs and optical flow for temporal modeling; conducted iterative experiments to improve model accuracy and robustness.
Background

Education

2018 – 2026

Ph.D. in Computer Science

Research Area: Computer Vision, Deep Learning, Foundation Models
Ph.D. Dissertation

Maximizing the Utility of Expert Annotations for Medical Image Analysis

Developing foundation models for image analysis through large-scale pretraining across multiple datasets and tasks, unifying classification, localization, and segmentation in a single end-to-end framework to maximize the utility of diverse expert annotations and improve cross-task learning.

2015 – 2017

M.Sc. in Computer Science

Research Area: Computer Vision, Machine Learning, Image Processing
M.Sc. Thesis

Human Face Detection Followed by Gender and Age Estimation Using Patch-Based DCT and Histogram of Oriented Gradients

Improved algorithms for face detection, gender classification, and age estimation using Discrete Cosine Transform (DCT) and Histogram of Oriented Gradients (HOG) for feature extraction, with Convolutional Neural Networks and Support Vector Machines for classification.

2010 – 2014

B.Sc. in Computer Science

Research Area: Image Processing
B.Sc. Thesis

Automated Parking Lot Management for Bengali License Plates Using Hough Transformation and Image Segmentation

Built an automated parking lot management system for Bengali license plates. Plates were localized with connected component labeling, bounding boxes, Canny edge detection, and the Hough transform, then recognized with OCR, with records stored and managed in a database.

Toolbox

Technical Skills

Programming Languages
PythonC/C++JavaMATLAB
ML Frameworks & Libraries
PyTorchTensorFlowScikit-LearnOpenCVMatplotlibNumPyWeights & BiasesGit/GitHub
Core AI & Machine Learning
Deep LearningFoundation ModelsLarge-scale PretrainingTransfer LearningFine-tuningMultitask LearningSupervised/Self-Supervised LearningCNNsLarge Language Models (LLMs)Transformer Architectures (Vision/Swin)
Data & Experimentation
Dataset CurationAnnotation IntegrationExperiment DesignBenchmarkingDistributed TrainingHPC / Linux Cluster Workflows
Model Analysis & Interpretability
Explainable AIGrad-CAMt-SNE Embedding AnalysisModel Monitoring / DebuggingQuantitative / Qualitative Evaluation
Operating System
WindowsLinux
Research output

Publications

Journal Articles

  • 2026Islam, N. U., Ma, D., Gotway, M. B., & Liang, J. Foundation Chest CT-CTPA: Maximizing the Utility of Heterogeneous Expert Annotations via a Unified Slice-Based 2D-3D Foundation Model. Medical Image Analysis. [under review].
  • 2026Islam, N. U., Ma, D., Pang, J., Gotway, M. B., & Liang, J. Foundation X⁺: Enhanced Knowledge Sharing for Integrated Classification, Localization, and Segmentation with Lock-Release Pretraining and Region-Guided ROI Alignment in Chest X-ray Analysis. Medical Image Analysis. [under review].
  • 2024Islam, N. U., Zhou, Z., Gehlot, S., Gotway, M. B., & Liang, J. Seeking an optimal approach for Computer-aided Diagnosis of Pulmonary Embolism. Medical Image Analysis (Impact Factor 14.0), 91, 102988.
  • 2024Guo, Z., Islam, N. U., Gotway, M. B., & Liang, J. Stepwise incremental pretraining for integrating discriminative, restorative, and adversarial learning. Medical Image Analysis (Impact Factor 14.0), 95, 103159.

Conference Papers

  • 2026Islam, N. U., Ma, D., Gotway, M. B., & Liang, J. A Generic 3D Foundation Model Utilizing 2D and 3D Annotations for Classification, Localization, and Segmentation in CT Pulmonary Angiography. Large Foundation Models in Biology and Biomedicine (LFMBio 2026), in conjunction with IEEE/CVF WACV 2026.
  • 2025Islam, N. U., Ma, D., Pang, J., Senthil Velan, S., Gotway, M. B., & Liang, J. Foundation X: Integrating Classification, Localization, and Segmentation through Lock-Release Pretraining Strategy for Chest X-ray Analysis. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
  • 2022Guo, Z., Islam, N. U., Gotway, M. B., & Liang, J. Discriminative, restorative, and adversarial learning: Stepwise incremental pretraining. Domain Adaptation and Representation Transfer, in conjunction with MICCAI 2022.
  • 2022Pang, J., Haghighi, F., Ma, D., Islam, N. U., Hosseinzadeh Taher, M. R., Gotway, M. B., & Liang, J. POPAR: Patch Order Prediction and Appearance Recovery for Self-supervised Medical Image Analysis. In conjunction with MICCAI 2022.
  • 2022Ma, D., Hosseinzadeh Taher, M. R., Pang, J., Islam, N. U., Haghighi, F., Gotway, M. B., & Liang, J. Benchmarking and boosting transformers for medical image classification. In conjunction with MICCAI 2022.
  • 2021Islam, N. U., Gehlot, S., Zhou, Z., Gotway, M. B., & Liang, J. Seeking an optimal approach for computer-aided pulmonary embolism detection. Machine Learning in Medical Imaging (MLMI), in conjunction with MICCAI 2021.

See research highlights →

Intellectual property

Patents

Granted

  • 2026Zuwei Guo, Nahid Ul Islam, Jianming Liang. U.S. Patent No. 12,572,813, “Systems, methods, and apparatuses for implementing discriminative, restorative, and adversarial (DiRA) learning using stepwise incremental pre-training for medical image analysis” issued Mar 10, 2026.
  • 2025DongAo Ma, Jiaxuan Pang, Nahid Ul Islam, Mohammad Reza Hosseinzadeh Taher, Fatemeh Haghighi, Jianming Liang. U.S. Patent No. 12,394,186, “Systems, methods, and apparatuses for implementing self-supervised domain-adaptive pre-training via a transformer for use with medical image classification” issued Aug 19, 2025.
  • 2025Nahid Ul Islam, Shiv Gehlot, Zongwei Zhou, Jianming Liang. U.S. Patent No. 12,236,592, “Systems, methods, and apparatuses for systematically determining an optimal approach for the computer-aided diagnosis of a pulmonary embolism” issued Feb 25, 2025.

Pending (Selected)

  • 2026Nahid Ul Islam, DongAo Ma, Jiaxuan Pang, Jianming Liang. U.S. Patent Application No. 19/447,985, “Method and Apparatus for Integrating Classification, Localization, and Segmentation Through Lock-Release Pretraining Strategy for Chest X-Ray Analysis,” filed Jan 13, 2026 (patent pending).
  • 2024Nahid Ul Islam, Zongwei Zhou, Shiv Gehlot, Jianming Liang. U.S. Patent Application No. 18/904,995, “Systems, Methods and Apparatuses for Computer-Aided Diagnosis of Pulmonary Embolism,” filed Oct 2, 2024 (patent pending).
  • 2024Zuwei Guo, Nahid Ul Islam, Jianming Liang. U.S. Patent Application No. 18/776,010, “Systems, methods, and apparatuses for implementing stepwise incremental pre-training for integrating discriminative, restorative, and adversarial learning into an AI model,” filed Jul 17, 2024 (patent pending).
  • 2023Jiaxuan Pang, Fatemeh Haghighi, DongAo Ma, Nahid Ul Islam, Mohammad Reza Hosseinzadeh Taher, Jianming Liang. U.S. Patent Application No. 18/241,809, “Systems, methods, and apparatuses for implementing patch order prediction and appearance recovery (popar) based image processing for self-supervised learning medical image analysis,” filed Sept 1, 2023 (patent pending).
Open source

Publicly Released Software

  • Foundation X/X+: An end-to-end model integrating classification, localization, and segmentation tasksGitHub
  • Foundation CTPA: A slice-based 3D foundation model integrating classification, detection, and segmentationGitHub
  • Stepwise Incremental Pretraining: Achieving discriminative, restorative, and adversarial learningGitHub
  • Benchmarking Transformers: Benchmarking and boosting transformers for image classificationGitHub
  • POPAR: Restoring patch order and appearance for self-supervised image analysisGitHub
  • EViT and Benchmark: Benchmarking CNNs, Vision/Swin Transformers, and self-supervised models, plus the EViT framework for volume-level predictionGitHub
Recognition

Awards and Honors

  • Apr 2026SUN Award, Arizona State University, for invited research talk and providing subject matter expert feedback.View certificate
  • Dec 2024President’s Award for Innovation, Arizona State University. Project: “Annotation-efficient Deep Learning for Computer-aided Diagnosis in Medical Imaging.”View certificate
  • Aug 2018Doctoral Fellowship, Arizona State University.View letter
  • Dec 2014VC’s List Award, BRAC University, for securing the highest GPA (4.0 out of 4.0) in the last semester.
Sharing knowledge

Talks and Presentations

Research seminar

Learning Unified Chest Radiograph Representations from Heterogeneous Expert Models and Annotations

BIDS Seminar (ASU–Mayo)

Research seminar

Foundation X: Leveraging Annotations for Comprehensive Multi-Task Learning in Chest X-ray Analysis

Graduate-level seminar · WACV 2025 paper

Research seminar

Seeking an Optimal Approach for Computer-aided Diagnosis of Pulmonary Embolism

Graduate-level seminar · Medical Image Analysis, 2024

Technical talk

GPU Utilization for Deep Learning and Computer Vision

Guided peers on workflows for large-scale training.

Peer learning

State-of-the-art Deep Learning Frameworks in Image Analysis

Facilitated peer learning and discussions on their applications.

Milestones

Timeline

  • May 2026Successfully defended Ph.D. Dissertation and graduated from Arizona State University.
  • Apr 2026Earned SUN Award, Arizona State University, for invited research talk and providing subject matter expert feedback.
  • Dec 2024Received the prestigious President’s Award for Innovation, Arizona State University . Project: “Annotation-efficient Deep Learning for Computer-aided Diagnosis in Medical Imaging.”
  • May 2024Certificate of GPSA Travel Grant Reviewer, Arizona State University.
  • May 2023Certificate of GPSA Travel Grant Reviewer, Arizona State University.
  • Aug 2022Travel Grant, MICCAI 2022, awarded by the GPSA (Arizona State University).
  • Apr 2022Travel Grant, CVPR 2022, awarded by the GPSA (Arizona State University).
  • Aug 2018Started Ph.D in Computer Science at Arizona State University.
  • May 2018Received prestigious CIDSE Doctoral Fellowship from the School of Computing, Informatics, and Decision Systems Engineering at Arizona State University.
  • Mar 2018Got admission into Ph.D program in Computer Science at Arizona State University.
  • Dec 2017Completed M.Sc. in Computer Science from University of Texas at San Antonio, USA.
  • Nov 2017Successfully defended Masters Thesis at University of Texas at San Antonio.
  • May 2017Joined Intel Corporation for the summer'17 semester as Graduate Technical Intern.
  • Feb 2017Joined Intel Corporation for the spring'17 semester as Graduate Software Engineering Intern.
  • Aug 2015Started M.Sc. in Computer Science at University of Texas at San Antonio, USA.
  • Nov 2014Completed B.Sc. in Computer Science from BRAC University, Bangladesh.