Accurate auto-labeling of chest X-ray images based on quantitative similarity to an explainable AI model

Doyun Kim,  Joowon Chung,  Jongmun Choi,  Marc D. Succi,  John Conklin,  Maria Gabriela Figueiro Longo,  Jeanne B. Ackman,  Brent P. Little,  Milena Petranovic,  Mannudeep K. Kalra,  Michael H. Lev &  Synho Do

Prediction of oxygen requirement in patients with COVID-19 using a pre-trained chest radiograph xAI model: efficient development of auditable risk prediction models via a fine-tuning approach

Joowon Chung,  Doyun Kim,  Jongmun Choi,  Sehyo Yune,  Kyoung Doo Song,  Seonkyoung Kim,  Michelle Chua,  Marc D. Succi,  John Conklin,  Maria G. Figueiro Longo,  Jeanne B. Ackman,  Milena Petranovic,  Michael H. Lev &  Synho Do 

Intracranial Hemorrhage (ICH) Detection @ AuntMinnie

AuntMinnie reports (Dec 17, 2018, Ridley) “Researchers have developed a new artificial intelligence (AI) algorithm designed to address two of the biggest challenges in imaging AI: its “black box” nature and the need for large amounts of image data to train the models, according to a study published online December 17 in Nature Biomedical Engineering.”

“An Explainable Deep-learning Algorithm for the Detection of Acute Intracranial Haemorrhage from Small Datasets” Published in Nature Biomedical Engineering

“An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets (Hyunkwang Lee, Sehyo Yune, Mohammad Mansouri, Myeongchan Kim, Shahein H. Tajmir, Claude E. Guerrier, Sarah A. Ebert, Stuart R. Pomerantz, Javier M. Romero, Shahmir Kamalian, Ramon G. Gonzalez, Michael H. Lev & Synho Do)“ is published in Nature Biomedical Engineering. The article is available here.

“Practical Window Setting Optimization for Medical Image Deep Learning” Accepted by ML4H Workshop at NeurIPS 2018

“Practical Window Setting Optimization for Medical Image Deep Learning (Hyunkwang Lee, Myeongchan Kim, Synho Do)” is accepted by Machine Learning for Health (ML4H) Workshop at NeurIPS 2018. (Link) The article is available here.

“Beyond Human Perception: Sexual Dimorphism in Hand and Wrist Radiographs Is Discernible by a Deep Learning Model” Published in Journal of Digital Imaging

“Beyond Human Perception: Sexual Dimorphism in Hand and Wrist Radiographs Is Discernible by a Deep Learning Model (Sehyo Yune, Hyunkwang Lee, Myeongchan Kim, Shahein H. Tajmir, Michael S. Gee, Synho Do)“ is published in Journal of Digital Imaging. The article is available here.

3D Convolutional Neural Network for Voxel-level Prediction of Radiation Absorption (CMIMI 2018 Presentation)

Myeongchan Kim (MD) gave a presentation on his paper “3D Convolutional Neural Network for Voxel-level Prediction of Radiation Absorption” at 2018 SIIM Conference on Machine Intelligence in Medical Imaging (CMIMI). Kim, M., Li, X., Yune, S., Lee, H., Liu, B., Do, S., 2018. 3D Convolutional Neural Network for Voxel-level Prediction of Radiation Absorption. The risk of diagnostic imaging procedures such…

Continue Reading

Real-World Performance of Deep-Learning-based Automated Detection System for Intracranial Hemorrhage (CMIMI 2018 Presentation)

Sehyo Yune (MD, MPH, MBA) gave a presentation on her paper “Real-World Performance of Deep-Learning-based Automated Detection System for Intracranial Hemorrhage” at 2018 SIIM Conference on Machine Intelligence in Medical Imaging (CMIMI). Yune, S., Lee, H., Pomerantz, S., Romero, J., Kamalian, S., Gonzalez, R., Lev, M., Do, S., 2018. Real-World Performance of Deep-Learning-based Automated Detection System for Intracranial Hemorrhage….

Continue Reading

Fall 2018 Harvard Undergraduate Research Spotlight

Our intern, Allison Welton (Harvard College Class of 2018) will give a presentation on her research “Extraction of Findings in Chest X-Ray Reports for Medical AI Development” (mentored by Dr. Synho Do) at Fall 2018 Undergraduate Research Spotlight. Fall 2018 Undergraduate Research Spotlight October 10, 2018 12PM -1:30PM Cabot Library Discovery Bar on the first…

Continue Reading