Adversarial attacks on deep learning models for fatty liver disease classification by modification of ultrasound image reconstruction method

no code implementations • 7 Sep 2020 • Michal Byra, Grzegorz Styczynski, Cezary Szmigielski, Piotr Kalinowski, Lukasz Michalowski, Rafal Paluszkiewicz, Bogna Ziarkiewicz-Wroblewska, Krzysztof Zieniewicz, Andrzej Nowicki

In ultrasound (US) imaging, CNNs have been applied to object classification, image reconstruction and tissue characterization.

Adversarial Attack Image Reconstruction

Breast mass segmentation based on ultrasonic entropy maps and attention gated U-Net

no code implementations • 27 Jan 2020 • Michal Byra, Piotr Jarosik, Katarzyna Dobruch-Sobczak, Ziemowit Klimonda, Hanna Piotrzkowska-Wroblewska, Jerzy Litniewski, Andrzej Nowicki

In comparison to commonly applied segmentation methods, which use US images, our approach is based on quantitative entropy parametric maps.

Segmentation

Impact of ultrasound image reconstruction method on breast lesion classification with neural transfer learning

no code implementations • 6 Apr 2018 • Michal Byra, Tomasz Sznajder, Danijel Korzinek, Hanna Piotrzkowska-Wroblewska, Katarzyna Dobruch-Sobczak, Andrzej Nowicki, Krzysztof Marasek

We show that the augmentation of the training set with differently reconstructed B-mode images leads to a more robust and efficient classification.

Classification Data Augmentation +4

Added value of morphological features to breast lesion diagnosis in ultrasound

no code implementations • 6 Jun 2017 • Michał Byra, Katarzyna Dobruch-Sobczak, Hanna Piotrzkowska-Wróblewska, Andrzej Nowicki

The combination of the radiologist's experience related to the BI-RADS and the morphological features leads to a more effective breast lesion classification.

Breast Cancer Detection Classification +3