Bogdan Georgescu

Bogdan Georgescu

Auto-generated profile, based on publicly available information

Bogdan Georgescu

Department of Digital Technology and Innovation, Siemens Healthineers , Princeton, NJ 08540

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2020 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
SCShikha Chaganti
Shikha Chaganti
Philippe A. GrenierPhilippe A. Grenier
Philippe A. Grenier
ABAbishek Balachandran
Abishek Balachandran
GCGuillaume Chabin
Guillaume Chabin
SCStuart Cohen
Stuart Cohen
DCDorin Comaniciu
Dorin Comaniciu
Purpose To present a method that automatically segments and quantifies abnormal CT patterns commonly present in coronavirus disease 2019 (COVID-19), namely ground glass opacities and consolidations...

1 May 2022 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
EGEli Gibson
Eli Gibson
BGBogdan Georgescu
Bogdan Georgescu
PCPascal Ceccaldi
Pascal Ceccaldi
PTPierre-Hugo Trigan
Pierre-Hugo Trigan
YYYoungjin Yoo
Youngjin Yoo
YLYvonne W. Lui
Yvonne W. Lui
Confidence scores from artificial intelligence (AI) software that detects, subtypes, and locates intracranial hemorrhage on noncontrast CT scans can improve AI-based worklist prioritization and str... Purpose To present a method that automatically detects, subtypes, and locates acute or subacute intracranial hemorrhage (ICH) on noncontrast CT (NCCT) head scans; generates detection confidence sco...


1 January 2013
Verified
Book Chapter
Closed access
PDF file
TMTommaso Mansi
Tommaso Mansi
BGBogdan Georgescu
Bogdan Georgescu
JHJagir Hussan
Jagir Hussan
PHPeter J. Hunter
Peter J. Hunter
AKAli Kamen
Ali Kamen
DCDorin Comaniciu
Dorin Comaniciu

2 January 2026 in Radiology Advances
Verified
Journal Article
Open access
EBEduardo J Mortani Barbosa
Eduardo J Mortani Barbosa
YKYohan Kim
Yohan Kim
YZYanbo Zhang
Yanbo Zhang
ASArnaud A A Setio
Arnaud A A Setio
FMFrancois Mellot
Francois Mellot
WGWarren B Gefter
Warren B Gefter
Background: Pulmonary nodules are commonly encountered in lung cancer screening. The risk of malignancy varies widely and is generally estimated using expert consensus guidelines (Lung CT Imaging Reporting and Data Systems [Lung-RADS]). Purpose: To assess the performance of a deep learning algorithm (Deep Pulmonary Nodule Profiler [DeepPNP]) for pulmonary nodule malignancy risk estimation in a lung cancer screening dataset and the effect of data enrichment in model training. Materials and Methods: A retrospective analysis was conducted using 3 datasets. DeepPNP is a 3D convolutional network (EfficientNet-B0-based) operating on nodule-centered 3D patches. For the DeepPNP model training and validation, the National Lung Screening Trial (NLST) dataset was combined with 2 independent malignant nodule-only datasets, resulting in a merged dataset of 28 057 nodules, including 2362 malignant nodules. An ablation model (DeepPNP-NLST) was trained on NLST only. The testing was conducted on a held-out dataset from the NLST dataset. Performance metrics, including sensitivity, specificity, precision, F1 score, and accuracy, were analyzed across 3 operating thresholds selected based on specificities of 0.80, 0.85, and 0.90 (selected on the validation set). Benchmarks included Lung-RADS v2022 and the PanCan model. Results: On the NLST test set (including 2597 nodules from 1243 CT scans), DeepPNP achieved an area under the receiver operating characteristic curve (ROC AUC) of 0.96 (95% confidence interval [CI], 0.95-0.97), outperforming Lung-RADS AUC = 0.91 (95% CI, 0.89-0.94; P < .001) and PanCan AUC = 0.93 (95% CI, 0.91-0.95; P < .001). DeepPNP-NLST had an AUC of 0.95 (95% CI, 0.93-0.97; P = .045 vs DeepPNP), indicating a modest gain from positive-only supplementation. Subgroup analyses showed consistent outperformance across nodule sizes and types. Operating-point metrics at 0.80/0.85/0.90 specificity are reported; at 0.80 specificity, DeepPNP achieved sensitivity of 0.94 (100/107; 95% CI, 0.88-0.98) and specificity of 0.88 (2196/2490; 95% CI, 0.87-0.90). Conclusion: DeepPNP outperformed established malignancy risk models in lung cancer screening. The inclusion of biopsy-confirmed malignant nodules from 2 external datasets provided a measurable performance gain, underscoring the importance of data enrichment during model training.

28 December 2018 in arXiv
Verified
Preprint
Open access
PDF file
JYJie Yang
Jie Yang
SLSiqi Liu
Siqi Liu
SGSasa Grbic
Sasa Grbic
ASArnaud Arindra Adiyoso Setio
Arnaud Arindra Adiyoso Setio
ZXZhoubing Xu
Zhoubing Xu
DCDorin Comaniciu
Dorin Comaniciu
Though large-scale datasets are essential for training deep learning systems, it is expensive to scale up the collection of medical imaging datasets. 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. In this paper, we propose the class-aware adversarial synthesis framework to synthesize lung nodules in CT images. The framework is built with a coarse-to-fine patch in-painter (generator) and two class-aware discriminators. By conditioning on the random latent variables and the target nodule labels, the trained networks are able to generate diverse nodules given the same context. By evaluating on the public LIDC-IDRI dataset, we demonstrate an example application of the proposed framework for improving the accuracy of the lung nodule malignancy estimation as a binary classification problem, which is important in the lung screening scenario. We show that combining the real image patches and the synthetic lung nodules in the training set can improve the mean AUC classification score across different network architectures by 2%.