We develop the theory and application of deep learning to improve diagnoses, prognoses and therapy decision making. We move the boundaries of what predictive models can achieve by developing new methods and tools for machine learning and deep learning and improve their applicability and performance on information rich, biomedical problems. Our applications of machine learning focus on building predictive models for neurodegenerative diseases, neurodevelopmental disorders and mental disorders. To achieve these aims, we employ the latest, most advanced, non-invasive neuroimaging acquisitions techniques and develop optimized post-processing for: multi-contrast MRI, EEG/MEG, PET/SPECT.
How can deep learning models be optimally tailored to each new problem to maximize prediction performance? How can domain expertise from clinicians be embedded into deep learning models? How can causal information be extracted in longitudinal deep learning data analyses to avoid reliance on purely correlation based information? We are tackling these problems with a combination of innovative algorithmic development for automated hyperparameter optimization, Bayesian Probability theory, and Information theory. Our focus is on making customized deep learning solutions available to any researcher, including those without machine learning expertise. Our approaches optimize the use of limited labeled training data and provide detailed information about what the models have learned to reveal how predictions are made.
How can we improve our currently subjective diagnoses of subtypes brain disorders and diseases that have overlapping symptoms? How can we identify new gene targets for spectrum disorders using the exquisite phenotypes provided by functional neuroimaging? How do we identify pre-treatment biomarkers of therapy response so that optimal patient management decisions can be made before therapy starts? We are addressing these questions by building deep learning predictive models that combine quantitative, multimodal neuroimaging data with multi-omic data and clinical information to reduce uncertainty and improve patient care. This facilitates getting patients the correct treatment sooner, when it can do the most good. Working together with our clinical collaborators, our models are used to cluster disease subtypes and identify the best treatment for each individual patient.
The lab is an active part of the Lyda Hill Department of Bioinformatics. We are also affiliated with the Research Division of the Radiology Department and the Advanced Imaging Research Center. We are also affiliated with the Biomedical Engineering Program, the Computational and Systems Biology Track and the Neuroscience Dept.
Son has obtained a Ph.D. in Electrical Engineering with a focus on machine learning from the University of Texas at Arlington. He has developed advanced extensions to the backpropagation algorithms using second order training methods to substantially improve their convergence speed. He has adapted and demonstrated his approaches for both feed forward neural networks and for convolutional neural networks. His expertise includes Tensorflow, PyTorch, Matlab, scientific programing and cloud computing. His postdoctoral research focuses on additional improvements to machine learning methodology as well as their clinical applications including oncological applications and the quantitative analysis of diagnostic MRI.
Kevin earned his BS in Biomedical Engineering in 2016 at Yale University, where he developed an interest in computer vision, medical image analysis, and machine learning. He is currently pursuing MD and PhD degrees in the Medical Scientist Training Program at UT Southwestern. His research interests include creating automated tools for treatment planning and prognosis in psychiatric and neurological diseases such as depression and Parkinson’s Disease. He also hopes to develop techniques to overcome the "big data" requirement in deep learning, allowing deep learning models to train and perform well in data-limited situations, as is the case in most medical imaging problems. In his future career, Kevin plans to become an academic physician-scientist, an educator, and an advocate for the use of machine learning in medicine.
Clinical Research Coordinator
Jana is a Certified Clinical Research Coordinator who has a passion for clinical research and whose mission is to achieve excellence in patient-centered care. Before clinical research was a career option to consider, Jana obtained her Masters in Biology with a concentration in applied statistics. She is a highly capable, detail-oriented, and seasoned professional with 20 years combined clinical research, bench research, lab management, and teaching experience. Jana has extensive research study coordination having served in this capacity at UTSW in the Simmons Comprehensive Cancer Center, Cognition and Memory Disorders research, and in Movement Disorders research. She has successfully managed a variety of clinical research studies from Observational clinical studies to Interventional/ Experimental Phase I through Phase III clinical trials. As a study coordinator, Jana facilitates in patient recruitment, consenting, eligibility, quality data acquisition, and communicating with patients and other research staff. When not coordinating research studies, you might find Jana zip-lining in a rain forest, escaping Escape Rooms, singing in the Praise Band, or double two-stepping around a dance floor. However, she treasures most her time spent with family and friends, especially when this involves playing a mean game of dominoes or Pandemic!
Alex majored in Physics with concentrations in chemistry and mathematics and graduated in 2014 from the University of North Texas. Alex’s undergraduate research focused on quantitative simulations of anti-matter to optimize experimental parameters describing the effect of gravity on anti-matter. Subsequently he developed computational algorithms for the analysis of mass-spectral lipidomics data working closely with Jeff McDonald at UT Southwestern. Since 2017 Alex has been perusing a PhD at UTSW. In Dr. Montillo's lab, Alex’s research focus on the development of methods to automatically optimize deep learning models to inform prognosis and diagnosis in neurodevelopmental and neurodegenerative diseases. Through his work, Alex is generating clinically viable tools to aid in the treatment of Parkinson’s and elucidating deeper understanding of the molecular underpinnings of neurological disease mechanisms.
Cooper triple majored in Physics: Biophysics, Computational Neurobiology, and Biochemistry at the University of Washington. Since 2016, he has been pursuing an MD-PhD combined degree at the University of Texas Southwestern Medical Center. He is pursuing a PhD degree in Biomedical Engineering on the Imaging track. His undergraduate research focused on signal processing and causal analysis of Brain-Computer interfaces. Current research focuses on using a combination of neuroimaging, deep learning, and causal inference to develop diagnostic and prognostic algorithms. The overarching goal is to both develop clinically useful tools as well as identify regions of importance in the pathophysiology of neurodevelopmental and neurodegenerative disease. Specifically, he is interested in prior-informed measures of causal connectivity derived from functional imaging and how these connectivity measures are changed in disease state and with treatment. Outside of the lab, Cooper enjoys cooking, hiking, and has been becoming more involved with Search and Rescue.
Dr. Zhiguo Shang is a Computational Scientist specializing in image analysis. He is currently developing novel approaches to inform diagnoses and prognoses using multi-contrast MRI and PET/CT medical images with diverse machine learning methodologies. He also developing methods to combine genetic sequencing with medical image processing to address challenges in cancer diagnosis and prognosis. >
Krishna has formal training in medical image analysis, deep learning and computer vision with special emphasis in the physics and clinical applications of Magnetic Resonance Imaging. He has experience in methods for detecting and quantitating structures/lesions in MRI datasets, Fluorescent microscopy images and colonoscopy. He is developing machine learning algorithms including advanced convolutional neural networks to solve image analysis challenges involving multi-modal medical imaging.
Vyom is currently pursuing his bachelor's degree in Neuroscience at the University of Texas at Dallas. His research has focused on creating prognostic models for Parkinson's Disease and developing motion correction algorithms for functional MRI analysis. He has also previously engaged in developmental neurolinguistics research using EEG and on the 3D printing and characterization of liquid crystal elastomer materials. He is interested in using machine learning to confront neurological dysfunctions and to uncover principles of neural function. He aims to pursue an MD-PhD and engage deeply in translational research.
Our PI, Albert Montillo is an Assistant Professor in the Lyda Hill Department of Bioinformatics with secondary appointments in the Department of Radiology, the Advanced Imaging Research Center, and Biomedical Engineering within the Graduate School of Biomedical Sciences. He also directs the research of the Deep Learning for Precision Health lab. He is also an Adjunct Professor at UT Dallas in the School of Engineering in Computer Science and in Biomedical Engineering.
Dr. Montillo received bachelor of science and master of science degrees in Computer Science from RPI and minor concentrations in Electrical Engineering and Cognitive science/Psychology. He obtained his PhD in Computer Science from the University of Pennsylvania where he studied automated image analysis of 4D cardiac MRI and neuroimage co-registration and parcellation (automated quantitative neuroanatomical structure volumetry) with applications to Alzheimer’s. During his studies, Dr. Montillo developed a core neuroanatomical structure labeling algorithm which has been adopted into FreeSurfer, while at Harvard/MIT Martinos Center for Biomedical Imaging, and is now used worldwide. A variant of the algorithm has received FDA approval the first brain parcellation algorithm to do so. After his studies, Dr. Montillo developed a deep learning approach for the decision forest, known as entanglement, which improves prediction accuracy and increases prediction speed while a researcher at the Machine Intelligence and Perception group of Microsoft Research in Cambridge, United Kingdom. Subsequently he joined as a Lead Scientist at General Electric Research Center in upstate New York where he led the development of machine learning based methods for analyzing high volume neuroimaging data. His efforts led to automated methods for brain parcellation (patented), brain lesion quantification, and automated brain-connectivity based prognoses for mild traumatic brain injury (mTBI) – all using advanced multi-contrast MRI. His efforts also led to machine learning algorithms that rank features in imaging genomics studies of Alzheimer’s for automated individualized disease progression prediction. His efforts led to fully automated, machine learning based identification of the content of a imaging scan which prepares a wide range of clinical image data for automated analyses and enables radiation dosage reduction in computed tomography via scout-scans.
The laboratory of Albert Montillo in the Bioinformatics Department at the UT Southwestern Medical Center is an interactive and collaborative team conducting cutting-edge research to advance the theory and application of machine learning for medical image analysis. We address unmet clinical needs by forming predictive models that make diagnoses and prognoses more precise and advance neuroscience by furthering the understanding of mechanisms in disease and intervention. Medical image analysis software the lab has developed include machine learning-based methods for labeling structures throughout the brain (parcellation), versions of which are used worldwide and FDA approved. The lab has built deep learning methods to label networks in resting state fMRI and detect artifacts in MEG. The lab has pioneered deep learning decision forests that increase prediction accuracy while reducing prediction time and outcome prediction methods using structural and functional connectomics. Building off these capabilities, we plan to develop novel modeling and outcome prediction tools for mental & neurodevelopmental disorders, and neurodegenerative diseases.
The lab is co-located within the Bioinformatics Department on UT Southwestern’s south campus and embedded in the Radiology Department on north campus. We are an integral part of the Advanced Imaging Research Center, and work closely with research groups within Neuroscience, Neurology, Psychiatry, Radiation Oncology, and Surgery. Lab members have access to extensive computational resources, including the >6,800-core cluster with >8 Petabyte of storage available through UTSW’s high-performance infrastructure ( BioHPC ). Members have access to multiple research-dedicated scanners (such as 7T and 3T MRI) and the opportunity to work on a range of image analysis, machine learning and modeling projects on interdisciplinary teams, and participate in all aspects of method development and data analysis with collaborators.
UT Southwestern Medical Center is an Affirmative Action/Equal Opportunity Employer. Women, minorities, veterans and individuals with disabilities are encouraged to apply.
Current students (Ph.D. students at UT Southwestern, UTD, UTA, SMU and MSTP MD/Ph.D. students) are welcome to join our team by emailing me at Albert.Montillo@UTSouthwestern.edu to arrange a meeting. The research experience in our lab provides a great opportunity to supplement your background in computer science, engineering, applied math, physics or neuroscience with robust training in scientific algorithm development and computational modeling while conducting cutting-edge research to advance the theory and application of machine learning for medical image analysis.Prospective students looking to apply for UTSW graduate school admission must apply by the university’s December 1st deadline, and preferably by November 1st. Be sure to explicitly indicate your interest in my lab in your application. For prospective Ph.D. students, the Ph.D. program in Biomedical Engineering, and in particular the Imaging Track is one often pursued by students in our lab. For M.D./Ph.D. applicants, the MSTP admission deadline is November 1st.
Two postdoctoral positions are available in the Deep Learning for Precision Health lab. Applications are invited for a 2 to 3-year computational postdoctoral research position. The researchers will develop novel deep learning models to predict diagnoses and outcomes from patient data including imaging (fMRI, diffusion MRI, MEG/EEG, PET/SPECT) and corresponding genomic, metabolic and clinical data. Potential projects include theoretical or applied method development. Theoretical projects target the development of 1) improved visualization of network learned abstractions, and 2) streamlined network parameter optimization. Applied projects include advancing the state-of-the-art in methods for: 1) discovering image-based biomarkers, including advanced brain connectivity measures, and differentially expressed metabolic markers and genes for disease diagnosis, and treatment outcome prediction in mental & neurodevelopmental disorders and neurodegenerative diseases. And 2) optimizing non-invasive brain stimulation therapies. Ideal applicants will have: - Ph.D. degree in Computer Science, Electrical or Biomedical Engineering, or related field. - Experience in medical image analysis including familiarity with at least 1 image data type: MRI, PET, CT, MEG/EEG. - Machine learning experience in one or more of the following: deep learning: neural nets (RNN,CNN,DNN), DCGAN, deep RL, transfer learning, autoencoders; classical or shallow learning methods; probabilistic graphical models; optimization; image recognition, registration & segmentation. - Strong programming skills including experience with at least 1 ML Python library: Keras, scikit-learn, TensorFlow, PyTorch, Nilearn. - At least 2 first author papers published and writing skills in English. To apply, email to Dr. Montillo [Albert.Montillo@UTSouthwestern.edu] and include your CV, names and addresses of three references, statement of research accomplishments and future goals, preferably as one single PDF-document. Use the subject line “PostdocApplicant: ”. For additional details download Postdoctoral research position (PDF).
The laboratory of Albert Montillo ( http://www.utsouthwestern.edu/labs/montillo ) in the Bioinformatics Department of UT Southwestern Medical Center is seeking a full time Scientific Programmer for studies of mental & neurodevelopmental disorders and neurodegenerative diseases. The Scientific Programmer will use multimodal MRI, and MEG/EEG data to study structural and functional circuit changes, and PET/SPECT, CT to study metabolic and pathophysiological changes associated with diagnosis and prognoses. The main responsibilities of the position include: implementing and optimizing image processing, computational and analyses pipelines for large-scale multimodal brain imaging data and corresponding clinical data. The lab is an interactive and collaborative team directed by Albert Montillo, Ph.D., conducting cutting-edge research to advance the theory and application of machine learning for the analysis of medical images. The lab addresses unmet clinical needs by forming predictive models that make diagnoses and prognoses more precise and advance neuroscience by furthering the understanding of mechanisms in disease and intervention. You will work directly with him and an array of principle investigators, collaborators and trainees. Ideal applicants will have: - B.A. or B.S. Degree in Computer Science, Electrical Engineering, Biomedical Engineering or a related field with three (3) years scientific software development; Master’s or Ph.D. preferred. Software development experience on high performance compute clusters or GPU-based machine learning is a strong plus. Will consider record of success in publishing computational results in lieu of experience. - Familiarity with at least 1 image data type: MRI, PET/SPECT, CT, MEG/EEG & format: NIFTI, DICOM. - Experience in at least 1 neuroimage analysis pipeline: NiPype, SPM, FSL, AFNI, FreeSurfer; for diffusion MRI: Camino, DTI-TK, DiPy, TrackVis, DTI/DSI studio, ExploreDTI; for MEG/EEG: Brainstorm, EEGLAB, FieldTrip, MNE, NUTMEG. - At least 2 years of experience in Linux, Python and 1 other language (Matlab, R, C/C++). - Optional but helpful: Practical experience in machine learning, Git, and C++/cMake software development. To apply, email to Dr. Montillo [Albert.Montillo@UTSouthwestern.edu] and include your CV and names and addresses of three references, preferably as one single PDF-document. Use the subject line “ScientificProgrammer: ”. For additional details download Scientific programmer position (PDF).
New website goes live! Thank you for visiting! Albert gives invited conference talk at Brain Informatics conference.
Bioinformatics Dept Hackathon 2018 is a super success; congrats Alex for winning an award!
Welcome new MSTP graduate student Cooper! Welcome rotation student Paul!
Welcome new MSTP graduate student Kevin!
Welcome new graduate student Alex!
Albert gives invited talk, Deep learning for artifact detection in MEG, at the 2018 International Workshop on Interactive and Spatial Computing (IWISC).
Albert joins program committee of the SPIE Medical Imaging conference.
Behrouz and Gowtham deliver oral presentations at SPIE Medical Imaging conference in Houston, TX. A team of bioinformatics researchers (Drs. Montillo, Rajaram and Cobanoglu) develop and teach a new nanocourse, Machine Learning I, to researchers (grad students, postdocs, faculty) from across the UTSW. Highly positive reviews! Plans underway for subsequent offerings. Welcome to our new scientific programmer Danni!
Albert gives invited talk, Deep learning: a new tool for analyzing Big Neuroimaging Datasets at the jointly (UTD, UTSW) sponsored symposium, Neuroimaging is a team sport.
Albert receives appointment in the newly formed Bioinformatics Department at UTSW Albert trains researchers in neuroimage analysis with SPM.
Albert is interviewed for research contributions in machine learning for radiology at RSNA.
2 papers presented at the International conference, Medical Image Computing and Computer Assisted Intervention (MICCAI) including Convolutional Neural Networks for artifact detection in MEG, and deep neural networks for quantifying the association between type-2 diabetes management and brain perfusion measured via ASL MRI.
2 abstracts accepted to American Society for Functional Neuroradiology (ASFNR). Congratulations Behrouz and Gowtham!
2 papers presented at Pattern Recognition for Neuro Imaging (PRNI) on 3D convolutional neural networks for resting state network labeling for rs-fMRI and deep convolutional neural networks for MEG cardiac artifact detection.1 paper presented at Human Brain Mapping conference on machine learning that uses resting state fMRI to accurately predict head impact exposure in youths playing a single season of football.
Albert joins the Research Committee of American Society of Neuroradiology. Albert teaches Mathematics for Medicine to medical students at UTSW including topics of Bayesian Decision Theory and Deep Learning.
Afarin Famili successfully defends master’s thesis using machine learning to detect functional connectivity changes in epilepsy & diabetes. Congrats Afarin! Albert gives invited conference talk: Machine Learning in functional Neuroimaging at the American Society of Neuroradiology in Los Angeles. 4 papers presented at UTSW Radiology Research Day by Prabhat Garg, Gowtham Murugesan, Afarin Famili! Gowtham Murugesan presents 2 papers at IEEE International Symposium on Biomedical Imaging (ISBI) in Melbourne, Australia
Abstract accepted to Organization for Human Brain Mapping (OHBM) conference
Two papers Accepted to IEEE International Symposium on Biomedical Imaging (ISBI) Meeting Conference! Albert attends annual mtg of American clinical MEG society (ACMEGS).
Welcome to our new postdoc, Behrouz and research scientist, Anand to the lab!
Welcome aboard new trainee, Gowtham!
Welcome aboard graduate student, Afarin to the lab!
King Foundation grant awarded to Drs. Montillo and Moore.
Albert gives invited conference talk at American Society of Neuroradiology (ASNR) in Washington DC: Machine Learning for Neuroimaging.
Albert gives seminar talks to Mathematics Dept at UT Dallas and Statistics Dept at Southern Methodist University.
Albert attends MEG training at McGill.
Senior Research Associate
Graduate Research Assistant
St. Mark's School of Texas
The Department of Bioinformatics is located in the E building at 5323 Harry Hines Blvd., Dallas, Texas. From Harry Hines Blvd., turn southwest onto Sen. Kay Bailey Hutchison Drive. Take the first right onto a drive that leads to Lot 7, Visitor Parking. See Rebekah Craig during your visit for a parking pass. From Visitor Parking, cross the street to the Donald Seldin Plaza. Walk across the plaza to the right, across the area marked D building, which is underground. At the right side to the E building, take an external stairwell down one level to a garden/koi pond area. Enter through the grey double doors and take the elevator to 4th floor. The Department of Bioinformatics entrance is the glass door at the end of the hallway. Please proceed straight thru to the admin team area and a member of the admin team will escort you to your meeting.
UT Southwestern has full information on parking.
We are accessible by public transportation.
We are an 8 minute walk from the Southwestern Medical District/Parkland Station on the DART green and orange rail lines and 5 min walk from the Medical/Market Station on the Trinity Railway Express.