no code implementations • 27 Apr 2023 • Han Liu, Zhoubing Xu, Riqiang Gao, Hao Li, Jianing Wang, Guillaume Chabin, Ipek Oguz, Sasa Grbic
In this paper, we empirically and systematically study the partial-label segmentation with in-depth analyses on the existing approaches and identify three distinct types of supervision signals, including two signals derived from ground truth and one from pseudo label.
no code implementations • 4 Jan 2022 • Florin C. Ghesu, Bogdan Georgescu, Awais Mansoor, Youngjin Yoo, Dominik Neumann, Pragneshkumar Patel, R. S. Vishwanath, James M. Balter, Yue Cao, Sasa Grbic, Dorin Comaniciu
Building accurate and robust artificial intelligence systems for medical image assessment requires not only the research and design of advanced deep learning models but also the creation of large and curated sets of annotated training examples.
no code implementations • 29 Sep 2021 • Riqiang Gao, Zhoubing Xu, Guillaume Chabin, Awais Mansoor, Florin-Cristian Ghesu, Bogdan Georgescu, Bennett A. Landman, Sasa Grbic
A Bad-GAN generates pseudo anomalies at the low-density area of inlier distribution, and thus the inlier/outlier distinction can be approximated.
no code implementations • 12 Apr 2021 • Sebastian Gündel, Arnaud A. A. Setio, Florin C. Ghesu, Sasa Grbic, Bogdan Georgescu, Andreas Maier, Dorin Comaniciu
Chest radiography is the most common radiographic examination performed in daily clinical practice for the detection of various heart and lung abnormalities.
no code implementations • 13 Aug 2020 • Eduardo Mortani Barbosa Jr., Warren B. Gefter, Rochelle Yang, Florin C. Ghesu, Si-Qi Liu, Boris Mailhe, Awais Mansoor, Sasa Grbic, Sebastian Piat, Guillaume Chabin, Vishwanath R S., Abishek Balachandran, Sebastian Vogt, Valentin Ziebandt, Steffen Kappler, Dorin Comaniciu
Purpose: To leverage volumetric quantification of airspace disease (AD) derived from a superior modality (CT) serving as ground truth, projected onto digitally reconstructed radiographs (DRRs) to: 1) train a convolutional neural network to quantify airspace disease on paired CXRs; and 2) compare the DRR-trained CNN to expert human readers in the CXR evaluation of patients with confirmed COVID-19.
no code implementations • 5 Aug 2020 • Sebastian Guendel, Arnaud Arindra Adiyoso Setio, Sasa Grbic, Andreas Maier, Dorin Comaniciu
However, because of the limited availability of scans containing nodules and the subtle properties of nodules in CXRs, state-of-the-art methods do not perform well on nodule classification.
no code implementations • 8 Jul 2020 • Florin C. Ghesu, Bogdan Georgescu, Awais Mansoor, Youngjin Yoo, Eli Gibson, R. S. Vishwanath, Abishek Balachandran, James M. Balter, Yue Cao, Ramandeep Singh, Subba R. Digumarthy, Mannudeep K. Kalra, Sasa Grbic, Dorin Comaniciu
In our experiments we demonstrate that sample rejection based on the predicted uncertainty can significantly improve the ROC-AUC for various tasks, e. g., by 8% to 0. 91 with an expected rejection rate of under 25% for the classification of different abnormalities in chest radiographs.
no code implementations • 9 Jun 2020 • Eduardo Jose Mortani Barbosa Jr., Bogdan Georgescu, Shikha Chaganti, Gorka Bastarrika Aleman, Jordi Broncano Cabrero, Guillaume Chabin, Thomas Flohr, Philippe Grenier, Sasa Grbic, Nakul Gupta, François Mellot, Savvas Nicolaou, Thomas Re, Pina Sanelli, Alexander W. Sauter, Youngjin Yoo, Valentin Ziebandt, Dorin Comaniciu
Training/testing cohorts included 927/100 COVID-19, 388/33 ILD, 189/33 other pneumonias, and 559/34 normal (no pathologies) CTs.
no code implementations • 5 May 2020 • Si-Qi Liu, Bogdan Georgescu, Zhoubing Xu, Youngjin Yoo, Guillaume Chabin, Shikha Chaganti, Sasa Grbic, Sebastian Piat, Brian Teixeira, Abishek Balachandran, Vishwanath RS, Thomas Re, Dorin Comaniciu
Additionally, we leverage location priors derived from manually labeled COVID-19 chest CTs patients to generate appropriate abnormality distributions.
no code implementations • 2 Apr 2020 • Shikha Chaganti, Abishek Balachandran, Guillaume Chabin, Stuart Cohen, Thomas Flohr, Bogdan Georgescu, Philippe Grenier, Sasa Grbic, Si-Qi Liu, François Mellot, Nicolas Murray, Savvas Nicolaou, William Parker, Thomas Re, Pina Sanelli, Alexander W. Sauter, Zhoubing Xu, Youngjin Yoo, Valentin Ziebandt, Dorin Comaniciu
Automated processing time to compute the severity scores was 10 seconds per case compared to 30 minutes required for manual annotations.
no code implementations • 18 Mar 2020 • Donghao Zhang, Si-Qi Liu, Shikha Chaganti, Eli Gibson, Zhoubing Xu, Sasa Grbic, Weidong Cai, Dorin Comaniciu
In this paper, we propose a framework for liver vessel morphology reconstruction using both a fully convolutional neural network and a graph attention network.
no code implementations • 8 Mar 2020 • Si-Qi Liu, Arnaud Arindra Adiyoso Setio, Florin C. Ghesu, Eli Gibson, Sasa Grbic, Bogdan Georgescu, Dorin Comaniciu
To make the network more robust to unanticipated noise perturbations, we use PGD to search for noise patterns that can trigger the network to give over-confident mistakes.
no code implementations • 18 Jun 2019 • Florin C. Ghesu, Bogdan Georgescu, Eli Gibson, Sebastian Guendel, Mannudeep K. Kalra, Ramandeep Singh, Subba R. Digumarthy, Sasa Grbic, Dorin Comaniciu
We argue that explicitly learning the classification uncertainty as an orthogonal measure to the predicted output, is essential to account for the inherent variability characteristic of this data.
no code implementations • 15 May 2019 • Sebastian Guendel, Florin C. Ghesu, Sasa Grbic, Eli Gibson, Bogdan Georgescu, Andreas Maier, Dorin Comaniciu
Chest X-ray (CXR) is the most common X-ray examination performed in daily clinical practice for the diagnosis of various heart and lung abnormalities.
no code implementations • 28 Dec 2018 • Jie Yang, Si-Qi Liu, Sasa Grbic, Arnaud Arindra Adiyoso Setio, Zhoubing Xu, Eli Gibson, Guillaume Chabin, Bogdan Georgescu, Andrew F. Laine, Dorin Comaniciu
Synthesizing the objects of interests, such as lung nodules, in medical images based on the distribution of annotated datasets can be helpful for improving the supervised learning tasks, especially when the datasets are limited by size and class balance.
no code implementations • 4 Dec 2018 • Si-Qi Liu, Eli Gibson, Sasa Grbic, Zhoubing Xu, Arnaud Arindra Adiyoso Setio, Jie Yang, Bogdan Georgescu, Dorin Comaniciu
The performance of medical image analysis systems is constrained by the quantity of high-quality image annotations.
no code implementations • 25 May 2018 • Zhoubing Xu, Yuankai Huo, Jin-Hyeong Park, Bennett Landman, Andy Milkowski, Sasa Grbic, Shaohua Zhou
However, this is a challenging problem given not only the inherent difficulties from the ultrasound modality, e. g., low contrast and large variations, but also the heterogeneity across tasks, i. e., one classification task for all views, and then one landmark detection task for each relevant view.
no code implementations • 14 Apr 2018 • Saeid Asgari Taghanaki, Aicha Bentaieb, Anmol Sharma, S. Kevin Zhou, Yefeng Zheng, Bogdan Georgescu, Puneet Sharma, Sasa Grbic, Zhoubing Xu, Dorin Comaniciu, Ghassan Hamarneh
Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients.
no code implementations • 12 Mar 2018 • Sebastian Guendel, Sasa Grbic, Bogdan Georgescu, Kevin Zhou, Ludwig Ritschl, Andreas Meier, Dorin Comaniciu
To foster future research we demonstrate the limitations of the current benchmarking setup and provide new reference patient-wise splits for the used data sets.
1 code implementation • 23 Nov 2017 • Si-Qi Liu, Daguang Xu, S. Kevin Zhou, Thomas Mertelmeier, Julia Wicklein, Anna Jerebko, Sasa Grbic, Olivier Pauly, Weidong Cai, Dorin Comaniciu
The focal loss is further utilized for more effective end-to-end learning.
no code implementations • 25 Jul 2017 • Dong Yang, Daguang Xu, S. Kevin Zhou, Bogdan Georgescu, Mingqing Chen, Sasa Grbic, Dimitris Metaxas, Dorin Comaniciu
Automatic liver segmentation in 3D medical images is essential in many clinical applications, such as pathological diagnosis of hepatic diseases, surgical planning, and postoperative assessment.
1 code implementation • 30 Nov 2016 • Rui Liao, Shun Miao, Pierre de Tournemire, Sasa Grbic, Ali Kamen, Tommaso Mansi, Dorin Comaniciu
The resulting registration approach inherently encodes both a data-driven matching metric and an optimal registration strategy (policy).