Aliasghar Mortazi

My academic background includes a postdoctoral research fellow in Medical Image Processing Group (MIPG) at University of Pennsylvania working with Dr. Udupa which I worked on developing new methods for disease quantification from whole body PET/CT images. I got my Ph.D from Center for Research in Computer Vision (CRCV) at computer science department of University of Central Florida (UCF) which i was working on developing and optimizing deep learning-based algorithms for medical image processing and analysis.

My name is Ali and I am currently sr scientist in computer vision and image analytics at Volastra therapeutic. In my current role I took the lead in designing and constructing the company’s pipelines from scratch for assessing chromosomal instability (CIN) across diverse image modalities, facilitating target identification and prioritization, early validation, and biomarker discovery.

I have 8+ experience in designing and implementing end-to-end multi-stage deep learning-based pipelines/products for medical image analysis and processing consist of SOTA segmentation, classification, and detection algorithms incorporating domain adaptation, VAE, ViT, and GAN techniques. These pipelines developed in collaboration with cross-functional teams (radiology, biology, immunology, software engineer) and utilized for tumor quantification, cardiac analysis, facilitate drug discovery and biomarkers discovery, patient outcomes predictions, organ detection, etc across various image modalities such as MRI, CT, PET, microscopic images (H&E, DAPI, live images), and more for real clinic environment applications.

News (last update 09/01/2023):

Paper accepted to Frontier in Nuclear Medicine 2023 : "A Post-Acquisition Standardization Method for Positron Emission Tomography Images",(pdf)

Paper accepted to Frontier in Radiology 2023: "Selecting the Best Optimizers for Deep Learning based Medical Image Segmentation",( pdf, final version will publish soon)

IP filed to the U.S. Patent and Trademark Office: "Standardization Of Positron Emission Tomography Based Images" (pdf)

Paper accepted to SPIE 2020: "A Post-Acquisition Standardization Method for Positron Emission Tomography Images",( pdf will be available soon)

Paper accepted to MLMI 2019 for Oral Presentation: "Weakly Supervised Segmentation by A Deep Geodesic Prior",(pdf)

Paper accepted to MICCAI 2019: "PAN: Projective Adversarial Network for Medical Image Segmentation",( pdf)

Research Specialist at MIPG in University of Pennsylvania(Summer 2019 till now)

Paper accepted to MedIA 2019: "Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge",( pdf)

Oral educational exhibition in RSNA 2018: Cardiac Image Analysis with Deep Learning Methods (Presentation)

Oral educational exhibition in RSNA 2018: Virtual Radiologists: Current Status of Deep Learning in Radiology and Its Future Trends

Visiting Scholar Intern at MIPG in University of Pennsylvania(Fall 2018, Spring 2019)

Paper accepted to MLMI 2018 for Oral Presentation: "Automatically Designing CNN Architectures for Medical Image Segmentation",(pdf)

Intern researcher at CRL in Harvard Medical School and Boston Children's Hospital (Summer 2018)

A deep-learning review paper for breast cancer is published in the British Journal of Radiology 2018 (pdf)

Paper accepted to STACOM 2017: "Multi-View Deep Segmentation Networks for Cardiac Structures from MRI and CT",(pdf)

Abstract accepted to RSNA 2017 for oral presentation: "Deep Learning for Cardiac MRI: Automatically Segmenting Left Atrium Expert Human Level Performance"

Merit Award for presentation in RSNA 2017 : "Deep Learning Applications in Radiology, Recent Developments, Challenges and Potential Solutions"

Abstract accepted as one of the American Heart Association(AHA) CVRI Young Investigator Award finalists at NASCI 2017 : "MACHINE LEARNING FOR CARDIAC MRI: AUTOMATED MAPPING OF LEFT ATRIUM AND PULMONARY VEINS WITH HUMAN LEVEL PERFORMANCE"

Paper accepted to MICCAI 2017: "CardiacNET: Segmentation of Left Atrium and Proximal Pulmonary Veins from MRI Using Multi-View CNN",( pdf)

Google Sites

Report abuse