no code implementations • 7 Jul 2022 • Alireza Borjali, Soheil Ashkani-Esfahani, Rohan Bhimani, Daniel Guss, Orhun K. Muratoglu, Christopher W. DiGiovanni, Kartik Mangudi Varadarajan, Bart Lubberts
Model 3 outperformed Model 2 and achieved a nearly perfect performance, misclassifying only one case (F1-score = 0. 91) in the control group as unstable while being faster than Model 2.
no code implementations • 30 Nov 2020 • Gergo Merkely, Alireza Borjali, Molly Zgoda, Evan M. Farina, Simon Gortz, Orhun Muratoglu, Christian Lattermann, Kartik M. Varadarajan
Conclusion: CNN can be used to enhance the diagnostic performance of MRI in identifying isolated tibiofemoral cartilage defects and may replace diagnostic knee arthroscopy in certain cases in the future.
no code implementations • 27 Apr 2020 • Mohammad Amin Morid, Alireza Borjali, Guilherme Del Fiol
Inception models were the most commonly used in breast related studies (50%), while VGGNet was the common in eye (44%), skin (50%) and tooth (57%) studies.
no code implementations • 17 Apr 2020 • Alireza Borjali, Martin Magneli, David Shin, Henrik Malchau, Orhun K. Muratoglu, Kartik M. Varadarajan
In this study we proposed deep learning based NLP (DL-NLP) models for efficient and accurate hip dislocation AE detection following total hip replacement from standard (radiology notes) and non-standard (follow-up telephone notes) free-text medical narratives.
no code implementations • 2 Dec 2019 • Alireza Borjali, Antonia F. Chen, Orhun K. Muratoglu, Mohammad A. Morid, Kartik M. Varadarajan
To increase the confidence in the machine outcome, we also implemented saliency maps to visualize where the CNN looked at to make a diagnosis.
no code implementations • 27 Nov 2019 • Alireza Borjali, Antonia F. Chen, Orhun K. Muratoglu, Mohammad A. Morid, Kartik M. Varadarajan
Such CNN can be used to automatically identify the design of a failed THR implant preoperatively in just a few seconds, saving time and improving the identification accuracy.