Dr. Geoffrey D. Rubin Profile

Dr. Geoffrey D. Rubin

at Duke Univ

SPIE Involvement:

Author

Profile Summary

Geoffrey D. Rubin, MD, MBA is the George B. Geller Distinguished Professor for Research in Cardiovascular Diseases and former chair of the Department of Radiology at Duke University. Previously, he was Professor of Radiology at Stanford University where he co-founded the Stanford 3-D Medical Imaging Laboratory in 1996 and served as its Medical Director until 2010, establishing the first scalable clinical service facility for applying computer graphics and vision tools to medical imaging data and training hundreds of physicians and technologists to emulate the model worldwide. His research focuses on applications of machine learning to medical image analysis, human perception in the interpretation of volumetric medical images, and the application of CT and MRI for assessing the cardiovascular and respiratory systems.
He is past president of the North American Society for Cardiovascular Imagers, the Society for Advanced Body Imaging, and the Fleischner Society. He has authored over 220 peer-reviewed manuscripts and edited six books, including the acclaimed textbook, CT and MR Angiography: Comprehensive Vascular Assessment.

Publications (20)

Proceedings Article | 4 April 2022 Paper

Paper

Co-occurring diseases heavily influence the performance of weakly supervised learning models for classification of chest CT

Fakrul Islam Tushar, Vincent D'Anniballe, Geoffrey Rubin, Ehsan Samei, Joseph Lo

Proceedings Volume 12033, 120332J (2022) https://doi.org/10.1117/12.2612700

KEYWORDS: Binary data, Emphysema, Performance modeling, Machine learning, Computed tomography, Solid modeling, Lung, Data modeling, Computer aided diagnosis and therapy, Chest

Read Abstract +

SPIE Journal Paper | 9 January 2021 Open Access

Open Access

Task-dependent estimability index to assess the quality of cardiac computed tomography angiography for quantifying coronary stenosis

Ehsan Samei, Taylor Richards, William Segars, Melissa Daubert, Alex Ivanov, Geoffrey Rubin, Pamela Douglas, Udo Hoffmann

JMI, Vol. 8, Issue 01, 013501, (January 2021) https://doi.org/10.1117/12.10.1117/1.JMI.8.1.013501

KEYWORDS: Computed tomography, Image quality, Scanners, Motion models, Stochastic processes, Angiography, Clinical trials, Calcium, Statistical analysis, Imaging systems

Read Abstract +

Purpose: Quantifying stenosis in cardiac computed tomography angiography (CTA) images remains a difficult task, as image noise and cardiac motion can degrade image quality and distort underlying anatomic information. The purpose of this study was to develop a computational framework to objectively assess the precision of quantifying coronary stenosis in cardiac CTA. Approach: The framework used models of coronary vessels and plaques, asymmetric motion point spread functions, CT image blur (task-based modulation transfer functions) and noise (noise-power spectrums), and an automated maximum-likelihood estimator implemented as a matched template squared-difference operator. These factors were integrated into an estimability index (e ′ ) as a task-based measure of image quality in cardiac CTA. The e ′ index was applied to assess how well it can to predict the quality of 132 clinical cases selected from the Prospective Multicenter Imaging Study for Evaluation of Chest Pain trial. The cases were divided into two cohorts, high quality and low quality, based on clinical scores and the concordance of clinical evaluations of cases by experienced cardiac imagers. The framework was also used to ascertain protocol factors for CTA Biomarker initiative of the Quantitative Imaging Biomarker Alliance (QIBA). Results: The e ′ index categorized the patient datasets with an area under the curve of 0.985, an accuracy of 0.977, and an optimal e ′ threshold of 25.58 corresponding to a stenosis estimation precision (standard deviation) of 3.91%. Data resampling and training–test validation methods demonstrated stable classifier thresholds and receiver operating curve performance. The framework was successfully applicable to the QIBA objective. Conclusions: A computational framework to objectively quantify stenosis estimation task performance was successfully implemented and was reflective of clinical results in the context of a prominent clinical trial with diverse sites, readers, scanners, acquisition protocols, and patients. It also demonstrated the potential for prospective optimization of imaging protocols toward targeted precision and measurement consistency in cardiac CT images.

Proceedings Article | 16 March 2020 Presentation + Paper

Presentation + Paper

Weakly supervised 3D classification of chest CT using aggregated multi-resolution deep segmentation features

Anindo Saha, Fakrul Tushar, Khrystyna Faryna, Vincent D'Anniballe, Rui Hou, Maciej Mazurowski, Geoffrey Rubin, Joseph Lo

Proceedings Volume 11314, 1131408 (2020) https://doi.org/10.1117/12.2550857

KEYWORDS: Convolutional neural networks, Feature selection, Computer aided diagnosis and therapy, Radiology, 3D modeling, Computed tomography, Lung, Classification systems, Chest, Binary data, Data modeling, Emphysema, Feature extraction, Image segmentation

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Presentation + Paper

Attention-guided classification of abnormalities in semi-structured computed tomography reports

Khrystyna Faryna, Fakrul Tushar, Vincent D'Anniballe, Rui Hou, Geoffrey Rubin, Joseph Lo

Proceedings Volume 11314, 113141P (2020) https://doi.org/10.1117/12.2551370

KEYWORDS: Lung, Liver, Kidney, Radiology, Computed tomography, Neural networks, Binary data

Read Abstract +

SPIE Journal Paper | 25 January 2020

Influence of background lung characteristics on nodule detection with computed tomography

Boning Li, Taylor Smith, Kingshuk Roy Choudhury, Brian Harrawood, Lukas Ebner, Justus Roos, Geoffrey Rubin

JMI, Vol. 7, Issue 02, 022409, (January 2020) https://doi.org/10.1117/12.10.1117/1.JMI.7.2.022409

KEYWORDS: Lung, Computed tomography, Performance modeling, Statistical analysis, Statistical modeling, Blood vessels, Chest, Lung cancer, Data modeling, Feature selection

Read Abstract +

Proceedings Article | 15 March 2019 Paper

Paper

Deep learning of 3D computed tomography (CT) images for organ segmentation using 2D multi-channel SegNet model

Yingzhou Liu, Wanyi Fu, Vignesh Selvakumaran, Matthew Phelan, W. Paul Segars, Ehsan Samei, Maciej Mazurowski, Joseph Lo, Geoffrey Rubin, Ricardo Henao

Proceedings Volume 10954, 109541D (2019) https://doi.org/10.1117/12.2512887

KEYWORDS: Image segmentation, Data modeling, 3D modeling, Computed tomography, Kidney, 3D image processing, Medical imaging, Machine learning

Read Abstract +

Proceedings Article | 13 March 2019 Presentation + Paper

Presentation + Paper

Classification of chest CT using case-level weak supervision

Ruixiang Tang, Fakrul Islam Tushar, Songyue Han, Rui Hou, Geoffrey Rubin, Joseph Lo

Proceedings Volume 10950, 1095017 (2019) https://doi.org/10.1117/12.2513576

KEYWORDS: Lung, Chest, Radiology, Image classification, Convolution, Neural networks, Computer aided diagnosis and therapy, Machine learning

Read Abstract +

Proceedings Article | 13 March 2019 Paper

Paper

Classifying abnormalities in computed tomography radiology reports with rule-based and natural language processing models

Songyue Han, James Tian, Mark Kelly, Vignesh Selvakumaran, Ricardo Henao, Geoffrey Rubin, Joseph Lo

Proceedings Volume 10950, 109504H (2019) https://doi.org/10.1117/12.2513577

KEYWORDS: Computed tomography, Lung, Radiology, Machine learning, Rule based systems, Kidney, Liver, Medical imaging, Performance modeling, Data modeling

Read Abstract +

Purpose: When conducting machine learning algorithms on classification and detection of abnormalities for medical imaging, many researchers are faced with the problem that it is hard to get enough labeled data. This is especially difficult for modalities such as computed tomography (CT) with potentially 1000 or more slice images per case. To solve this problem, we plan to use machine learning algorithms to identify abnormalities within existing radiologist reports, thus creating case-level labels that may be used for weakly supervised training on the image data. We used a two-stage procedure to label the CT reports. In the first stage, a rule-based system labeled a smaller set of cases automatically with high accuracy. In the second stage, we developed machine learing algorithms using the labels from the rule-based system and word vectors learned without supervision from unlabeled CT reports. Method: In this study, we used approximately 24,000 CT reports from Duke University Health System. We initially focused on three organs, the lungs, liver/gallbladder, and kidneys. We first developed a rule-based system that can quickly identify certain types of abnormalities within CT reports with high accuracy. For each organ and disease combination, we produced several hundred cases with rule-based labels. These labels were combined with word vectors generated using word2vec from all the unlabeled reports to train two different machine learning algorithms: (a) average of word vectors merged by logistic regression, and (b) recurrent neural network (RNN). Result: Performance was evaluated by receiver operating characteristic (ROC) area under the curve (AUC) over an independent test set of 440 reports for which those organs were manually labeled as normal or abnormal by clinical experts. For lungs, the performance was 0.796 for average word vector and 0.827 for RNN. Liver performance was 0.683 for average word vector and 0.791 for RNN. For kidneys, it was 0.786 for average word vector and 0.928 for RNN. Conclusion: It is possible to label large numbers of cases automatically. These rule-based labels can then be used to build a classification model for large numbers of medical reports. With word2vec and other transfer learning techniques, we can get a good generalization performance.

Proceedings Article | 13 March 2019 Presentation + Paper

Presentation + Paper

Combining deep learning methods and human knowledge to identify abnormalities in computed tomography (CT) reports

Matias Benitez, James Tian, Mark Kelly, Vignesh Selvakumaran, Matthew Phelan, Maciej Mazurowski, Joseph Lo, Geoffrey Rubin, Ricardo Henao

Proceedings Volume 10950, 109500V (2019) https://doi.org/10.1117/12.2512886

KEYWORDS: Computed tomography, Kidney, Lung, Performance modeling, Machine learning, Statistical modeling, Medicine

Read Abstract +

Proceedings Article | 13 March 2019 Paper

Paper

2.5D CNN model for detecting lung disease using weak supervision

Yue Geng, Yinhao Ren, Rui Hou, Songyue Han, Geoffrey Rubin, Joseph Lo

Proceedings Volume 10950, 109503O (2019) https://doi.org/10.1117/12.2513631

KEYWORDS: Lung, Computed tomography, 3D modeling, Radiology, Data modeling, Convolution, Solid modeling, Computer aided diagnosis and therapy, Image segmentation, Network architectures

Read Abstract +

Our goal is to develop a 2.5D CNN model to detect multiple diseases in multiple organs in CT scans. In this study we investigated detection of 4 common diseases in the lungs, which are atelectasis, edema, pneumonia and nodule. Most existing algorithms for computer-aided diagnosis (CAD) of CT use 2D models for the axial slices. Our hypothesis is that by using information from all of the three views (coronal, sagittal and axial), we may achieve a better classification result, because some diseases may be more obvious from a different view or from the combination of multi-views. Our data consisted of 1089 CT scans, which contains 288 normal cases, 224 atelectasis cases, 156 edema cases, 225 pneumonia cases and 196 nodule cases. The cases were selected from approximately 5,000 chest CTs from Duke University Health System, and case-level labels were automatically extracted by simple rule-based filtering of the unstructured text from the radiology report. Each of these 5 categories excluded the others, which indicates that cases from each category will have either only one of the four diseases or no disease. To create 2.5D volume patches, we combined together three channels representing parallel slices in each of the three intersecting, orthogonal directions, resulting in sparsely sampled cubes of 20.2 x 20.2 x 20.2 mm. For each CT scan, the volume containing the lungs was identified with thresholding, and 30 patches were randomly sampled within that volume. Then three 3-channel images in each patch representing those 3 different directions were entered into 3 independent CNN paths separately, which were finally fused by a fully connected layer. We used a 4 fold cross-validation and evaluated our results using receiver operating characteristic (ROC) area under the curve (AUC). We achieved an average AUC of 0.891 for classifying normal vs. atelectasis disease, 0.940 for edema disease, 0.869 for pneumonia disease and 0.784 for nodule disease. We also implemented a train-validation-test process for each disease to evaluate the generalization of our model and again got comparable test results, 0.818 for atelectasis, 0.963 for edema, 0.878 for pneumonia and 0.784 for nodule. Despite the limitation of the small dataset scale, we demonstrated that we developed a generalizable 2.5D CNN model for detection of multiple lung diseases.

Proceedings Article | 1 March 2019 Paper

Paper

Multi-organ segmentation in clinical-computed tomography for patient-specific image quality and dose metrology

Wanyi Fu, Shobhit Sharma, Taylor Smith, Rui Hou, Ehsan Abadi, Vignesh Selvakumaran, Ruixiang Tang, Joseph Lo, W. Paul Segars, Anuj Kapadia, Justin Solomon, Geoffrey Rubin, Ehsan Samei

Proceedings Volume 10948, 1094829 (2019) https://doi.org/10.1117/12.2512883

KEYWORDS: Image segmentation, Image quality, Computed tomography, 3D modeling, Machine learning, Monte Carlo methods, Imaging systems, Safety

Read Abstract +

The purpose of this study was to develop a robust, automated multi-organ segmentation model for clinical adult and pediatric CT and implement the model as part of a patient-specific safety and quality monitoring system. 3D convolutional neural network (Unet) models were setup to segment 30 different organs and structures at the diagnostic image resolution. For each organ, 200 manually-labeled cases were used to train the network, fitting it to different clinical imaging resolutions and contrast enhancement stages. The dataset was randomly shuffled, and divided with 6/2/2 train/validation/test set split. The model was deployed to automatically segment 1200 clinical CT images as a demonstration of the utility of the method. Each case was made into a patient-specific phantom based on the segmentation masks, with unsegmented organs and structures filled in by deforming a template XCAT phantom of similar anatomy. The organ doses were then estimated using a validated scanner-specific MC-GPU package using the actual scan information. The segmented organ information was likewise used to assess contrast, noise, and detectability index within each organ. The neural network segmentation model showed dice similarity coefficients (DSC) above 0.85 for the majority of organs. Notably, the lungs and liver showed a DSC of 0.95 and 0.94, respectively. The segmentation results produced patient-specific dose and quality values across the tested 1200 patients with representative the histogram distributions. The measurements were compared in global-to-organ (e.g. CTDvol vs. liver dose) and organ-to-organ (e.g. liver dose vs. spleen dose) manner. The global-to-organ measurements (liver dose vs. CTDIvol: 𝑅 = 0.62; liver vs. global d’: 𝑅 = 0.78; liver vs. global noise: 𝑅 = 0.55) were less correlated compared to the organ-to-organ measurements (liver vs. spleen dose: 𝑅 = 0.93; liver vs. spleen d’: 𝑅 = 0.82; liver vs. spleen noise: 𝑅 = 0.78). This variation of measurement is more prominent for iterative reconstruction kernel compared to the filtered back projection kernel (liver vs. global noise: 𝑅𝐼𝑅 = 0.47 vs. 𝑅𝐹𝐵𝑃 = 0.75; liver vs. global d’: 𝑅𝐼𝑅 = 0.74 vs. 𝑅𝐹𝐵𝑃 = 0.83). The results can help derive meaningful relationships between image quality, organ doses, and patient attributes.

SPIE Journal Paper | 22 November 2018

Local complexity metrics to quantify the effect of anatomical noise on detectability of lung nodules in chest CT imaging

Taylor Brunton Smith, Geoffrey Rubin, Justin Solomon, Brian Harrawood, Kingshuk Roy Choudhury, Ehsan Samei

JMI, Vol. 5, Issue 04, 045502, (November 2018) https://doi.org/10.1117/12.10.1117/1.JMI.5.4.045502

KEYWORDS: Lung, 3D image processing, Computed tomography, Binary data, Statistical analysis, Chest, 3D acquisition, Data modeling, 3D modeling, 3D image enhancement

Read Abstract +

SPIE Journal Paper | 17 January 2018

Quantification of uncertainty in the assessment of coronary plaque in CCTA through a dynamic cardiac phantom and 3D-printed plaque model

Taylor Richards, Gregory Sturgeon, Juan Carlos Ramirez-Giraldo, Geoffrey Rubin, Lynne Hurwitz Koweek, William Paul Segars, Ehsan Samei

JMI, Vol. 5, Issue 01, 013501, (January 2018) https://doi.org/10.1117/12.10.1117/1.JMI.5.1.013501

KEYWORDS: Heart, Beam propagation method, 3D modeling, Image segmentation, Motion models, Electrocardiography, Computed tomography, Image quality, Motion measurement, Reconstruction algorithms

Read Abstract +

Proceedings Article | 10 March 2017 Presentation + Paper

Presentation + Paper

Development of local complexity metrics to quantify the effect of anatomical noise on detectability of lung nodules in chest CT imaging

Justin Solomon, Geoffrey Rubin, Taylor Smith, Brian Harrawood, Kingshuk Roy Choudhury, Ehsan Samei

Proceedings Volume 10136, 101360X (2017) https://doi.org/10.1117/12.2254044

KEYWORDS: Lung, Computed tomography, Image enhancement, Chest, Chest imaging, Statistical analysis, Data modeling, Image analysis, Statistical modeling, Lung cancer, Binary data

Read Abstract +

Proceedings Article | 9 March 2017 Paper

Paper

Quantification of the uncertainty in coronary CTA plaque measurements using dynamic cardiac phantom and 3D-printed plaque models

Taylor Richards, Gregory Sturgeon, Juan Carlos Ramirez-Giraldo, Geoffrey Rubin, Paul Segars, Ehsan Samei

Proceedings Volume 10132, 101325E (2017) https://doi.org/10.1117/12.2255592

KEYWORDS: Accuracy assessment, Image quality, Reliability, 3D modeling, Motion models, Heart, Electrocardiography, Computed tomography, Image segmentation, Tissues, Iodine, Temporal resolution

Read Abstract +

Proceedings Article | 28 February 2009 Paper

Paper

Automated coronary CT angiography plaque-lumen segmentation

Harvey Cline, Karthik Krishnan, Sandy Napel, Geoffrey Rubin, Wesley Turner, Ricardo Avila

Proceedings Volume 7260, 726003 (2009) https://doi.org/10.1117/12.811328

KEYWORDS: Angiography, Arteries, Point spread functions, Blood, Image segmentation, Computed tomography, Blood vessels, 3D modeling, Algorithm development, Blood circulation

Read Abstract +

Proceedings Article | 16 May 2002 Paper

Paper

Automated creation of radiology teaching modules: demonstration of PACS integration and distribution

Bhargav Raman, Raghav Raman, Lalithakala Raman, Geoffrey Rubin, Christopher Beaulieu

Proceedings Volume 4685, (2002) https://doi.org/10.1117/12.467030

KEYWORDS: Picture Archiving and Communication System, Databases, Radiology, Internet, Image processing, System integration, Medical imaging, Information security, Network security, Receivers

Read Abstract +

Proceedings Article | 15 April 1996 Paper

Paper

Semiautomated editing of computed tomography sections for visualization of vasculature

Smadar Shiffman, Geoffrey Rubin, Sandy Napel

Proceedings Volume 2707, (1996) https://doi.org/10.1117/12.238441

KEYWORDS: Image segmentation, Neural networks, Blood vessels, Computed tomography, Arteries, Spine, Angiography, Visualization, 3D modeling, Tissues

Read Abstract +

Proceedings Article | 15 April 1996 Paper

Paper

Perspective volume rendering of cross-sectional images for simulated endoscopy and intraparenchymal viewing

Sandy Napel, Geoffrey Rubin, Christopher Beaulieu, R. Brooke Jeffrey, Vincent Argiro

Proceedings Volume 2707, (1996) https://doi.org/10.1117/12.238498

KEYWORDS: Endoscopy, Volume rendering, Opacity, Colon, Computed tomography, Cameras, Data acquisition, Collimation, Visualization, Tissues

Read Abstract +

Proceedings Article | 1 May 1994 Paper

Paper

Volumetric applications for spiral CT in the thorax

Geoffrey Rubin, Sandy Napel, Ann Leung

Proceedings Volume 2168, (1994) https://doi.org/10.1117/12.174409

KEYWORDS: Computed tomography, Collimation, Angiography, Arteries, Lung, Collimators, Veins, X-ray computed tomography, Signal attenuation, Diagnostics

Read Abstract +

Showing 5 of 20 publications

SIGN IN TO:

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Advertisement

Advertisement