M. Moein Shariatnia

prof_pic.jpg

I’m passionate about practical applications of ML in medical imaging. I’ve developed SOTA models for medical image segmentation and recently for accurate bone age estimation from hand X-rays, which could save patients from unnecessary costs and radiation exposure.

I’ve also been involved in core ML research, with two works on contrastive learning and transfer learning accepted for poster presentations at workshops in ICML’22 and ICLR’23.

Currently, I’m leading AI research projects in collaboration with the AI team at Hospital for Special Surgery (HSS) under the supervision of Dr. Ayoosh Pareek where our focus is to automate morphology parameter measurement from MSK imaging and save orthopedists the time required to manually annotate images for surgery planning and bone age assessment.

I graduated with my MD degree from Tehran University of Medical Sciences and have been doing ML research/development since 2019.

selected publications

  1. transdeeplab.png
    Transdeeplab: Convolution-free transformer-based deeplab v3+ for medical image segmentation
    Reza Azad, Moein Heidari, Moein Shariatnia, Ehsan Khodapanah Aghdam, and 3 more authors
    In PRIME workshop, MICCAI 2022, 2022
  2. hands.jpg
    Determination of Skeletal Age From Hand Radiographs Using Deep Learning
    Joshua T Bram, Ayoosh Pareek, Samuel A Beber, Ruth H Jones, and 5 more authors
    The American Journal of Sports Medicine, 2025
  3. iclr.png
    The role of pre-training data in transfer learning
    Rahim Entezari, Mitchell Wortsman, Olga Saukh, Moein Shariatnia, and 2 more authors
    MRL workshop, ICLR 2023, 2023
  4. shoulder-ai.jpg
    Deep learning model for measurement of shoulder critical angle and acromion index on shoulder radiographs
    Moein Shariatnia, Taghi Ramazanian, Joaquin Sanchez-Sotelo, and Hilal Maradit Kremers
    JSES reviews, reports, and techniques, 2022