The Quantitative Translational Imaging in Medicine Lab
Twitter FeedTweets by qtimlab
HST Virtual Lab Tour
Meet some of the lab and get a feel for some of our projects!
Our lab focuses on developing quantitative imaging biomarkers for cancer and other diseases using advanced imaging techniques and machine learning methods. We are comprised of computer science researchers, medical physicists, neuro-oncologists, and MRI technicians, and we are always looking to collaborate with experts outside of our field. We have recently worked to apply deep learning methods to a variety of diseases, and our goal is to unite the cutting edges of machine learning, medical oncology, and image analysis into practical clinical applications.
Read about our lab members on the People tab. Learn more about our specific research topics on the Research tab. See our recent publications on the Publications tab, job openings on the Jobs tab, and find a way to get in touch on the Contact tab. Last but not least, check the Fun tab to see some pictures of our lab members doing what we do best.
- 01/26/2023 - Katharina Höebel defends her thesis. The title: Domain and User-centered Machine Learning for Medical Image Analysis.
- 06/10/2022 - QTIM opens branch at the University of Colorado Denver | Anschutz Medical Campus!
- 02/01/2022 - Stay tuned for another of Kathi Hoebel's presentations: Is this good enough? On expert perception of brain tumor segmentation quality, which will be published in SPIE 2022 and is part of the SPIE Medical Imaging Conference! This is paper 12035-29.
- 02/01/2022 - Stay tuned for Kathi Hoebel's presentation: Do I know this? Segmentation uncertainty under domain shift, which will be published in SPIE 2022 and is part of the SPIE Medical Imaging Conference! This is paper 12032-27.
- 12/1/2021 - Shruti Raghavan's RSNA Abstract Automatic Detection Of Adrenal Nodules In Radiology Reports: Proof Of Concept For Using Recurrent Neural Networks For Cohort Creating Using Radiology reports was accepted and will be at 9:30am presented by Dr. Jayashree Kalpathy-Cramer.
- 11/29/2021 - Mishka Gidwani's RSNA Abstract Radiomic P-hacking: Corrupting The Training/validation/test/Split was accepted and will be at 12:45pm.
- 12/01/2021 - Jay Patel's RSNA Abstract Fully Automatic Segmentation And Treatment Response Assessment Of Brain Metastases On Magnetic Resonance Imaging was accepted and will be at 1:30-2:30pm.
- 12/01/2021 - Chris Bridge's RSNA Abstract A Fully Automated Pipeline For Multi‐vertebral Level Quantification And Characterization Of Muscle And Adipose Tissue On Chest Computed Tomography was accepted and will be at 3pm.
- 11/30/2021 - Charlie Lu's RSNA Abstract Subgroup Analysis Highlights Fairness Challenges For Deep Learning Algorithms In Breast Density Estimation was accepted and he presents at 12:15 - 12:45pm.
- 10/06/2021 - QTIM releases Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging! All eight saliency map techniques fail at least one of the criteria and were inferior in performance compared with localization networks.
- 12/16/2020 - QTIM releases Radiomics Repeatability Pitfalls in a Scan-Rescan MRI Study of Glioblastoma! This study uses a siamese neural network-based severity score that automatically measures radiographic COVID-19 pulmonary disease severity, which can be used to track disease change and predict subsequent intubation or death.
- 11/15/2020 - QTIM releases Towards Trainable Saliency Maps in Medical Imaging! Our results have implications for the clinical deployment of deep learning models, increasing their utility and explainability for clinicians.
- 7/22/2020 - QTIM releases Automated Assessment and Tracking of COVID-19 Pulmonary Disease Severity on Chest Radiographs using Convolutional Siamese Neural Networks! We developed an automated Siamese neural network-based pulmonary disease severity score for patients with COVID-19, with the potential to help with clinical triage and workflow optimization.
- 6/24/2020 - QTIM releases breast density classification algorithm in JACR! This article demonstrates the possible parameters that can influence the performance of the model and how crowdsourcing can be used for evaluation.
- 6/23/2020 - DeepNeuro: An Open-Source Deep Learning Toolbox for Neuroimaging was published in PebMed. DeepNeuro is a Python-based deep learning framework that puts deep neural networks for neuroimaging into practical usage with a minimum of friction during implementation.
- 5/15/2020 - QTIM's paper Assessing the validity of saliency maps for abnormality localization in medical imaging was published as part of MIDL Montréal 2020, a conference which brings deep learning and medical imaging researchers together for in-depth discussion and exchange of ideas.
- 3/10/2020 - Katharina Hoebel's paper An exploration of uncertainty information for segmentation quality assessment was published as part of SPIE medical imaging proceedings.
- 3/6/2020 - Siamese neural networks for evaluation of disease severity and change on a continuous spectrum in medical imaging accepted to npj Digital Medicine
- 11/13/2019 - Sean Ko's abstract Machine Learning Based Predictive Model of 5-Year Survival in Multiple Myeloma Autologous Transplant Patients is published in The American Society of Hematology
- 10/18/2019 - Post Doc Ikbeom Jang joined the lab
- 10/18/2019 - Masters student Bryan Chen joined the lab
- 10/17/2019 - Newly Published Literature: QTIM paper An exploration of uncertainty information for segmentation quality assessment has been accepted for oral presentation at SPIE Medical Imaging 2020!
- 10/07/2019 - Masters student Sean Ko joined the lab
- 10/01/2019 - Katharina Höbel's extended abstract Give me (un)certainty - An exploration of parameters that affect segmentation uncertainty was accepted to ML4H at NeurIPS 2019
- 9/26/2019 - Newly Published Literature: Bevacizumab reduces permeability and concurrent temozolomide delivery in a subset of patients with recurrent glioblastoma.
- 7/15/2019 - Data Scientist Ikbeom Jang joined the lab
- 7/9/2019 - Newly Published Literature: Machine Learning Models can Detect Aneurysm Rupture and Identify Clinical Features Associated with Rupture.
- 7/2019 - Newly Published Literature: Democratizing AI.
- 6/13/2019 - Postdoc Praveer Singh joined the lab