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.
Dr. Albert Montillo's formal training is through a Ph.D. in Computer Science with a focus on Medical Image Analysis from the University of Pennsylvania, Philadelphia, PA through training in departments of Computer and Information Science and Radiology. There his research focuses on medical image analysis in MRI including applications in neuroradiology and cardiology. Additional extensive training stems from his experience as a research scientist leading neuroimaging analysis efforts at the General Electric Research Center in New York and research at the Machine Intelligence and Perception Laboratory of Microsoft Research in Cambridge, United Kingdom, as well as machine learning based medical image analysis research at the Harvard-MIT Martinos Center for Biomedical Imaging, Boston, MA and Rutgers University in New Jersey.
Dr. Montillo's research focus is advancing the theory and application of deep learning. He develops de novo machine learning algorithms that increase the accuracy and precision of quantitative, integrative analyses of multi-modal brain images. His approaches combine data-driven training & clinician/scientist expert prior knowledge and have both clinical and neuroscience applications. Clinical applications include automating image interpretation for diagnoses and prognoses (assistive second reader), optimizing non-invasive treatments (e.g. tDCS, TMS), automatic clean-up of data, and automatic feature extraction from images. Basic science applications include understanding brain activity in health and in neurological disorders.
Researchers in Dr. Montillo’s group focus their efforts on four areas. (1) Discovering the significant assoicaitons between non-invasive functional and structural connectomics features (from fMRI, MEG/EEG and diffusion MRI) and disease severity and treatment outcomes in pediatric radiology, TBI, epilepsy, autism, diabetes, schizophrenia and Alzheimer’s. (2) Uncovering associations between radiological imaging signatures (such as anatomical and structural connectomics from MRI) and gene expression and optimizing their combined use in prognostics. (3) Developing novel machine learning methods (such as deep learning neural networks) for personalized medicine. (4) Developing multi-parametric MRI for improved cancer diagnostics and prognostics.
Dr. Montillo is actively engaged in supervising, teaching and training of students spanning UT Southwestern, UT Dallas, and UT Arlington. He teaches Machine Learning at UTSW and at UT Dallas through an adjunct appointment there, serves on Ph.D. thesis committees at UT Arlington and UT Southwestern.
- Rensselaer Polytechnic Inst (1992), Computer Sciences
- Graduate School
- Rensselaer Polytechnic Inst (1993), Computer Sciences
- Graduate School
- University of Pennsylvania (2004), Medical Imaging
- Developing statistical, machine learning approaches that extract radiological imaging (MEG/EEG, functional, diffusion, perfusion, metabolic MRI) and imaging-genomic biomarkers and that engender personalized diagnostics and prognostics in clinical neuroscience and oncological applications.
- Testing novel candidate therapies with such biomarkers for improved patient care. Developing novel algorithmic methods to stratify patients through retrospective data analyses that guide prospective patient care.
- MEGnet: Automatic ICA-based artifact removal for MEG using spatiotemporal convolutional neural networks.
- Treacher AH, Garg P, Davenport E, Godwin R, Proskovec A, Bezerra LG, Murugesan G, Wagner B, Whitlow CT, Stitzel JD, Maldjian JA, Montillo AA, Neuroimage 2021 Jul 241 118402
- Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures.
- Nguyen KP, Raval V, Treacher A, Mellema C, Yu FF, Pinho MC, Subramaniam RM, Dewey RB, Montillo AA, Parkinsonism Relat Disord 2021 Apr 85 44-51
- Preoperative Prediction of Lymph Node Metastasis from Clinical DCE MRI of the Primary Breast Tumor Using a 4D CNN.
- Nguyen S, Polat D, Karbasi P, Moser D, Wang L, Hulsey K, Çobanoglu MC, Dogan B, Montillo A, Med Image Comput Comput Assist Interv 2020 Oct 12262 326-334
- Prediction of Individual Progression Rate in Parkinson's Disease Using Clinical Measures and Biomechanical Measures of Gait and Postural Stability.
- Raval V, Nguyen KP, Gerald A, Dewey RB, Montillo A, Proc IEEE Int Conf Acoust Speech Signal Process 2020 May 2020 1319-1323
- Improved motion correction for functional MRI using an omnibus regression model.
- Raval V, Nguyen KP, Mellema C, Montillo A, Proc IEEE Int Symp Biomed Imaging 2020 Apr 2020 1044-1047
- Architectural configurations, atlas granularity and functional connectivity with diagnostic value in Autism Spectrum Disorder.
- Mellema CJ, Treacher A, Nguyen KP, Montillo A, Proc IEEE Int Symp Biomed Imaging 2020 Apr 2020 1022-1025
- Predicting response to the antidepressant bupropion using pretreatment fMRI
- Nguyen KP, Fatt CC, Treacher A, Mellema C, Trivedi MH, Montillo A Medical Image Computing and Computer-Assisted Intervention 2019
- Deep Learning Architectures Achieve Superior Performance Diagnosing Autism Spectrum Disorder Using Features Previously Extracted from Structural and Functional MRI
- Mellema C, Treacher A, Nguyen KP, Montillo A IEEE International Symposium on Biomedical Imaging 2019 1 1891-1895
- Deep Fully Connected Neural Network for Estimation of Caudate Perfusion from Clinical Parameters in African Americans with Type 2 Diabetes
- Behrouz Saghafi, Benjamin C. Wagner, S. Carrie Smith, Jianzhao Xu, Jasmin Divers, Ananth Madhuranthakam, Barry I. Freedman, Joseph A. Maldjian, and Albert A. Montillo MICCAI 2017
- Automatic Multiple MEG Artifact Detection using 1-D Convolutional Neural Networks without Electrooculography or Electrocardiography
- Prabhat Garg, Elizabeth Davenport, Gowtham Murugesan, Ben Wagner, Christopher Whitlow, Joseph Maldjian, Albert Montillo PRNI 2017
Entanglement and Differentiable Information Gain Maximization. In Decision Forests for Computer Vision and Medical Image Analysis
Albert Montillo, Jilin Tu, Jamie Shotton, John Winn, J. Eugenio Iglesias, Dimitris Metaxas, and Antonio Criminisi (2013). Springer
Medical Computer Vision: Algorithms for Big Data, Fourth International MICCAI Workshop
Bjoern H. Menze, Georg Langs, Albert Montillo, Michael Kelm, Henning Muller, Shaoting Zhang, Weidong Cai, Dimitri Metaxas (Ed.) (2015). Springer
Medical Computer Vision: Large Data in Medical Imaging, Third International MICCAI Workshop
Bjoern Menze, Georg Langs, Albert Montillo, Henning Muller, Zhuowen Tu (2014). Springer
Medical Computer Vision: Recognition Techniques and Applications in Medical Imaging, Second International MICCAI Workshop
Bjoern Menze, Georg Langs, Le Lu, Albert Montillo, Zhuowen Tu, Antonio Criminisi (Ed.) (2013). Springer
- Organization for Human Brain Mapping (OHBM) (2012)
- American Society of Neuroradiology (ASNR) (2011)
- IEEE (senior member) (2002)
- Medical Image Computing and Computer assisted intervention (MICCAI) (2002)