Trialect

Active

ON HOLD: DO NOT APPLY Artificial Intelligence, Machine Learning in Neuroimaging

Harvard Medical School
(5/5) - 1 reviews

University of Southern California

Main Areas of Interest

Lecturing and Teaching:

This Traineeship is designed for anyone who are interested in or working in neuroscience, computer science, biomedical engineering, electric engineering or equivalent research fields and especially for medical students, M.D. physician researchers, undergraduate juniors/seniors or Master students who look for a certificate useful for their career path or their applications for a PhD program in the aforementioned fields.

My research spans an interdisciplinary cross-section of Medical Image Processing, Machine learning, and Neuroscience covering clinical neurology and neuropsychiatry. In the fields of medical image processing and analysis, I have studied on multi-contrast image registration and segmentation, surface modeling of cortical/subcortical structures which are the prerequisite techniques to proceed with the analysis of structural and functional brain imaging studies.

My projects that have been recently launched at USC-INI and USC-LONI include mainly three domains of the research field: 1) Prediction of neurodevelopmental outcome in neonates with various clinical conditions such as preterm birth, hypoxia-ischemia, and congenital heart disease: This project expands in line with my team's expertise in neurodevelopment, neuroimaging, computational imaging feature modeling and machine learning (particularly DEEP learning); 2) Neuroimaging data quality controls (image QC): My team dedicates its efforts to implementation of online-based LONI-QC system that allows the public to evaluate their own data as well as to automated QC feature that will ultimately predict the accuracy of brain image post-processing and the sensitivity in the subsequently biological/clinical analysis to given target pathophysiology, and 3) Prediction of brain age and accelerated aging due to neurodegeneration: combination of brain imaging data and convolutional neural network-based deep-learning can estimate the brain age for individual images. extending this model with a statistical hazard model, we aim to determine risk scores for aging subjects who potentially develop a neurodegenerative disease.
In other clinical/neuroscientific applications, my team has applied various advanced analytic frameworks, including cortical morphometry, voxel-based morphometry, deformation-based morphometry, and structural network analysis, to the assessment of brain structure in healthy conditions as well as pathological conditions, which often present anatomical variations beyond the range of normal structures.

My team continues to expand the aforementioned techniques to the analysis of BIG DATA of brain imaging data to better understand mechanisms involved in various diseases and disorders such as stroke, epilepsy, dementia, sleep disorders, as well as long-term deafness, and sudden hearing loss.

Techniques You Will Learn

Learning and Teaching Resources

These will be provided separately by the instructor as a form of ppt, exercise coding scripts and related data

other materials/resources for self learning outside the training session (web links, YouTube links, etc.):

Curriculum

Topics/Class Activities: Readings and Homework: Deliverable/Assignment

Part I: Introduction and Fundamentals

Class 1:

Topic 1: Overview and Introduction

Neuroimaging science
Machine learning in clinicalneuroimaging studies
University admission in USA

References:

https://www.sciencedirect.com/science/article/pii/S2352872918300447

Machine learning of neuroimaging for the assisted diagnosis of cognitive impairment and dementia: A systematic review

Class 2

Topic 2: Statistics for neuroimaging data analysis - Normal distributions, t-tests, and linear regressions

Normal distributions
Student’s t-tests
Linear regressions (a.k.a. general linear model)

Hands-on Software: matlab

References:

https://www.sciencedirect.com/science/article/abs/pii/S1053811905024900

Aging of cortical thickness in healthy young adults with surface-based methods

Class 3

Topic 3. Basics in Pattern learning

Lecture:

Unsupervised learning
Supervised learning
Brain tissue classification

Hands-on Software: matlab

References:

Zhang, IEEE TMI 2001, 20(1):45-57

Run a tissue classification using a clustering algorithm

Assignment 1

Given a structural MRI, find a solution to segment brain tissues.

Class 4

Topic 4: a pipeline for brain image processing and analysis

Understanding of brain imaging
FSL
FreeSurfer
Machine learning techniques

References:

https://surfer.nmr.mgh.harvard.edu/fswiki/FreeSurferAnalysisPipelineOverview#TheSurface-basedStream
https://www.youtube.com/watch?v=Y6Mu_09ou5E&list=PLvgasosJnUVnSoMl3rsWDIaFuZQu_rtyT&index=2

Class 5

Topic 5: Deep learning for medical image analysis application I

Lecture:

Installation of python, TensorFlow
Image segmentation using deep learning

Hands-on Software: python, TensorFlow

References:

https://www.youtube.com/watch?v=M3EZS__Z_XE
towardsdatascience.com

Assignment 2

open matlab python and tensorflow on your computer, test the demo code. Mentor walks through with you.

convolutional-networks

segment it using convolutional neural network as a deep learning approach.

Class 6

Topic 6: Deep learning for medical image analysis application II

Lecture:

image classification & labeling – concept & exercise
Summary of the course and possibleinternship opportunity

Hands on Software: matlab or python, TensorFlow

References:

https://arxiv.org/pdf/1612. 02572.pdf

https://openreview.net/pd f?id=rJlhd1S0FE

Accommodation

Fully online course due to COVID-19

Fees and Program Logistics

This program has the following durations available:

Duration	Fee

Who Can Apply

Host Details

Host Name: Steven M. Dubinett

Affiliation: Harvard Medical School

Address: University of Southern California; 2025 Zonal Ave; Los Angeles,;CA 90033;United States

Website URL: https://sites.google.com/usc.edu/nidll/members?authuser=0

Disclaimer:It is mandatory that all applicants carry workplace liability insurance, e.g., https://www.protrip-world-liability.com (Erasmus students use this package and typically costs around 5 € per month - please check) in addition to health insurance when you join any of the onsite Trialect partnered fellowships.

Legal & Affiliation Disclaimer

Affiliation Disclaimer: Trialect operates independently and is not affiliated with, endorsed by, or supported by any sponsors or organizations posting on the GrantsBoard platform. As an independent aggregator of publicly available funding opportunities, Trialect provides equal access to information for all users without endorsing any specific funding source, content, organization, or sponsor. Trialect assumes no responsibility for the content posted by sponsors or third parties.

Subscription Disclaimer: Upon logging into Trialect, you may choose to SUBSCRIBE to GrantsBoard for timely notifications of funding opportunities and to access exclusive benefits, such as priority alerts, reminders, personalized recommendations, and additional application support. However, users are advised to contact sponsors directly for any questions and are not required to subscribe to engage with funding opportunities.

Content Ownership and Copyright Disclaimer: Trialect respects the intellectual property rights of all organizations and individuals. All content posted on GrantsBoard is provided solely for informational purposes and remains the property of the original owners. Trialect does not claim ownership of, nor does it have any proprietary interest in, content provided by third-party sponsors. Users are encouraged to verify content and ownership directly with the posting sponsor.

Fair Use Disclaimer: The information and content available on GrantsBoard are compiled from publicly accessible sources in alignment with fair use principles under U.S. copyright law. Trialect serves as an aggregator of this content, offering it to users in good faith and with the understanding that it is available for public dissemination. Any organization or individual who believes their intellectual property rights have been violated is encouraged to contact us for prompt resolution.

Third-Party Posting Responsibility Disclaimer: Trialect is a neutral platform that allows third-party sponsors to post funding opportunities for informational purposes only. Sponsors are solely responsible for ensuring that their postings comply with copyright, trademark, and other intellectual property laws. Trialect assumes no liability for any copyright or intellectual property infringements in third-party content and will take appropriate action to address any substantiated claims.

Accuracy and Verification Disclaimer: Trialect makes no warranties regarding the accuracy, completeness, or reliability of the information provided by sponsors. Users are advised to verify the details of any funding opportunity directly with the sponsor before taking action. Trialect cannot be held liable for any discrepancies, omissions, or inaccuracies in third-party postings.

Notice and Takedown Policy: Trialect is committed to upholding copyright law and protecting the rights of intellectual property owners. If you believe that content on GrantsBoard infringes your copyright or intellectual property rights, please contact us with detailed information about the claim. Upon receipt of a valid notice, Trialect will promptly investigate and, where appropriate, remove or disable access to the infringing content.

Onsite/On-Campus Program

Traineeship

United States

Application Review Deadline:

Mar 15th, 2026

Apply Now

Featured Reviews

5

1 reviews

Excellent

Very good

Average

Poor

Terrible

Kaona Suksuchano 4 years ago

(5/5)

Summary

The lecture, presentation and examples are quite appreciated. Some slow pace of teaching especially in technical terms and Matlab will be nice.

Highlights
Although the course is intensive with deep knowledge, the mentor allows me a slow pace of learning with example to understand the key concepts of each session.

Program Logistics and Administrative Fees

This program has the following durations available:

Duration	Fee

Questions and Answers

Commonly asked questions about this program from the host and other attendees.

I am from a country outside US. Am I eligible for the program?

Yes, as long as the time zone is not an issue because this is a fully online course. The instructor is available 9am-12pm or 5pm-10pm Pacific Time and available Monday, Tuesday, Wednesday, Thursday, and Saturday.

I am highly interested in machine learning, deep learning or Artificial intelligence but have no computation background and am not familiar with coding. Am I still elligible?

Yes, you definitely are. This program is designed for anyone with non-computer science background. You will need commitment to learning new but basic computer languages (like Matlab coding) and a strong motivation to dare new knowledge :).

how is the program composed of?

It comsists of a half of lecture in theoretical background and the other half of coding exercise. The lecture will be given as in a video recording to students after each class such that you can walk through the video by yourself to repeat exercises or learn any missing part of the fundamental theory.