M
Michal Byra
Researcher at Polish Academy of Sciences
Publications - 54
Citations - 1001
Michal Byra is an academic researcher from Polish Academy of Sciences. The author has contributed to research in topics: Deep learning & Convolutional neural network. The author has an hindex of 11, co-authored 44 publications receiving 476 citations. Previous affiliations of Michal Byra include Veterans Health Administration & University of California, San Diego.
Papers
More filters
Journal ArticleDOI
Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images.
Michal Byra,Grzegorz Styczynski,Cezary Szmigielski,Piotr Kalinowski,Łukasz Michałowski,Rafał Paluszkiewicz,Bogna Ziarkiewicz-Wróblewska,Krzysztof Zieniewicz,Piotr Sobieraj,Andrzej Nowicki +9 more
TL;DR: A neural network-based approach for nonalcoholic fatty liver disease assessment in ultrasound that is efficient and in comparison with other methods does not require the sonographers to select the region of interest.
Journal ArticleDOI
Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversion
Michal Byra,Michal Byra,Michael Galperin,Haydee Ojeda-Fournier,Linda K. Olson,Mary O'Boyle,Christopher Comstock,Michael P. Andre +7 more
TL;DR: The concept of the matching layer is generalizable and can be used to improve the overall performance of the transfer learning techniques using deep convolutional neural networks.
Journal ArticleDOI
Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network.
Michal Byra,Michal Byra,Piotr Jarosik,Aleksandra Szubert,Michael Galperin,Haydee Ojeda-Fournier,Linda K. Olson,Mary O'Boyle,Christopher Comstock,Michael P. Andre +9 more
TL;DR: A selective kernel (SK) U-Net convolutional neural network to adjust network’s receptive fields via an attention mechanism, and fuse feature maps extracted with dilated and conventional convolutions for breast mass segmentation in ultrasound (US).
Journal ArticleDOI
Noninvasive Diagnosis of Nonalcoholic Fatty Liver Disease and Quantification of Liver Fat with Radiofrequency Ultrasound Data Using One-dimensional Convolutional Neural Networks.
Aiguo Han,Michal Byra,Elhamy Heba,Michael P. Andre,John W. Erdman,Rohit Loomba,Claude B. Sirlin,William D. O'Brien +7 more
TL;DR: Deep learning algorithms using radiofrequency ultrasound data are accurate for diagnosis of nonalcoholic fatty liver disease and hepatic fat fraction quantification when other causes of steatosis are excluded.
Journal ArticleDOI
Open access database of raw ultrasonic signals acquired from malignant and benign breast lesions
TL;DR: Access to a database consisting of the raw radio‐frequency ultrasonic echoes acquired from malignant and benign breast lesions of patients of the Institute of Oncology in Warsaw is provided to test quantitative ultrasound techniques and ultrasound image processing algorithms, or to develop computer‐aided diagnosis systems.