Dr. J. Michael O'Connor Profile

Dr. J. Michael O'Connor

Adjunct Instructor

SPIE Involvement:

Author

Publications (17)

Proceedings Article | 16 March 2020 Presentation + Paper

Using “Reader Disagreement Index” as a predictive reviewer performance monitoring tool for timely intervention

Manish Sharma, J. Michael O'Connor, Anitha Singareddy, Madhuri Madasu, Nicholas Enus, Kassel Fotinos-Hoyer, Yibin Shao

Proceedings Volume 11316, 113160A (2020) https://doi.org/10.1117/12.2549980

KEYWORDS: Oncology, Clinical trials, Statistical analysis, Analytical research

Read Abstract +

Purpose: Blinded Independent Central Review (BICR) is a well-accepted method employed in many oncology registration trials. Ongoing monitoring radiologist “reader” performance is both good clinical trial practice and a requirement by regulatory authorities. We continue to use Reader Disagreement Index (RDI) as an important measure in BICR. In this work we studied RDI as an early indicator to identify an outlier reader during the monitoring of reader performance in BICR. Early indication would enable early intervention and thus possibly improve trial outcomes.
Methods: We performed a retrospective analysis of readers’ RDIs in nineteen different clinical trials. Ninety-two reader performances were examined at five intervals in each trial. These individual trial reviews were conducted by forty-three board-certified radiologist readers using several established imaging assessment trial criteria. The objective was to see how well RDI performance above a threshold at progressive monitoring intervals would “flag” a potential overall end-point performance “issue” for that specific reader.
Results: We present results for the prediction of exceeding threshold (one standard deviation above a study mean RDI). Sensitivity, Specificity, Positive Predictive Value (PPV) and Negative Predictive Value (NPV) were determined for the predicted performance outcomes. We explored interpreting multiple “flags” for each trial to improve the aforementioned metrics.
Conclusions: One would expect that a “flag” of RDI exceeding threshold at an early-stage would likely give a useful prediction of end-point reader performance. We refined our methods to use multiple flags which enable statistically improved Specificity and PPV. Improved predictive capability at early stage intervals coupled with persistent monitoring across subsequent intervals will enable trial managers to focus on specific readers. An earlier indication of possible reader performance issues can permit proactive intervention and enhance good trial practices.

Proceedings Article | 4 March 2019 Presentation + Paper

Reader disagreement index: a better measure of overall review quality monitoring in an oncology trial compared to adjudication rate

Manish Sharma, J. Michael O'Connor, Anitha Singareddy

Proceedings Volume 10952, 109520Q (2019) https://doi.org/10.1117/12.2512611

KEYWORDS: Oncology, Clinical trials, Tumors, Analytical research, Image registration, Tumor growth modeling, Data acquisition, Image acquisition, Performance modeling

Read Abstract +

Proceedings Article | 4 March 2019 Presentation + Paper

Development of methods to evaluate probability of reviewer’s assessment bias in Blinded Independent Central Review (BICR) imaging studies

J. Michael O'Connor, Manish Sharma, Anitha Singareddy

Proceedings Volume 10952, 109520P (2019) https://doi.org/10.1117/12.2512603

KEYWORDS: Clinical trials, Statistical analysis, Analytical research, Solids, Tumors, Image processing, Matrices, Data analysis, Clinical research, Computer programming

Read Abstract +

Proceedings Article | 10 March 2017 Presentation + Paper

Development of discordant likelihood metrics for use in evaluation of 'double reviewer' performance in blinded independent central review (BICR) RECIST imaging studies

J. Michael O'Connor, Manish Sharma, Anitha Singareddy, Annette Schmid

Proceedings Volume 10136, 1013609 (2017) https://doi.org/10.1117/12.2255753

KEYWORDS: Diagnostics, Data analysis, Analytical research, Clinical research, Performance modeling, Image analysis, Clinical trials, Tumors, Matrices, Chromium, Statistical analysis, Oncology

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Machine-learning model observer for detection and localization tasks in clinical SPECT-MPI

Felipe Parages, J. Michael O'Connor, P. Hendrik Pretorius, Jovan Brankov

Proceedings Volume 9787, 97870W (2016) https://doi.org/10.1117/12.2217124

KEYWORDS: Image quality, Machine learning, Diagnostics, Single photon emission computed tomography, 3D image reconstruction, Bayesian inference, Image segmentation, Feature extraction, Image classification, Ions, Neodymium

Read Abstract +

In this work we propose a machine-learning MO based on Naive-Bayes classification (NB-MO) for the diagnostic tasks of detection, localization and assessment of perfusion defects in clinical SPECT Myocardial Perfusion Imaging (MPI), with the goal of evaluating several image reconstruction methods used in clinical practice. NB-MO uses image features extracted from polar-maps in order to predict lesion detection, localization and severity scores given by human readers in a series of 3D SPECT-MPI. The population used to tune (i.e. train) the NB-MO consisted of simulated SPECT-MPI cases – divided into normals or with lesions in variable sizes and locations – reconstructed using filtered backprojection (FBP) method. An ensemble of five human specialists (physicians) read a subset of simulated reconstructed images, and assigned a perfusion score for each region of the left-ventricle (LV). Polar-maps generated from the simulated volumes along with their corresponding human scores were used to train five NB-MOs (one per human reader), which are subsequently applied (i.e. tested) on three sets of clinical SPECT-MPI polar maps, in order to predict human detection and localization scores. The clinical “testing” population comprises healthy individuals and patients suffering from coronary artery disease (CAD) in three possible regions, namely: LAD, LcX and RCA. Each clinical case was reconstructed using three reconstruction strategies, namely: FBP with no SC (i.e. scatter compensation), OSEM with Triple Energy Window (TEW) SC method, and OSEM with Effective Source Scatter Estimation (ESSE) SC. Alternative Free-Response (AFROC) analysis of perfusion scores shows that NB-MO predicts a higher human performance for scatter-compensated reconstructions, in agreement with what has been reported in published literature. These results suggest that NB-MO has good potential to generalize well to reconstruction methods not used during training, even for reasonably dissimilar datasets (i.e. simulated vs. clinical).

Proceedings Article | 21 March 2014 Paper

Enhancement of 3D modeling and classification of microcalcifications in breast computed tomography (BCT)

Hiam Alquran, Eman Shaheen, J. Michael O'Connor, Mufeed Mahd

Proceedings Volume 9034, 903436 (2014) https://doi.org/10.1117/12.2043277

KEYWORDS: 3D modeling, Breast, Computer aided diagnosis and therapy, Radon transform, 3D image processing, Image classification, Mammography, Computed tomography, Cancer, Breast cancer

Read Abstract +

Proceedings Article | 11 March 2014 Paper

A Naive-Bayes model observer for detection and localization of perfusion defects in cardiac SPECT-MPI

Felipe Parages, J. Michael O’Connor, P. Hendrik Pretorius, Jovan Brankov

Proceedings Volume 9037, 90370N (2014) https://doi.org/10.1117/12.2044441

KEYWORDS: Image segmentation, Single photon emission computed tomography, Molybdenum, Medical imaging, Image quality, Reconstruction algorithms, Optimization (mathematics), Statistical analysis, 3D image processing, Feature extraction

Read Abstract +

Proceedings Article | 29 February 2012 Paper

Creation of an ensemble of simulated cardiac cases and a human observer study: tools for the development of numerical observers for SPECT myocardial perfusion imaging

J. Michael O'Connor, P. Hendrik Pretorius, Howard Gifford, Robert Licho, Samuel Joffe, Matthew McGuiness, Shannon Mehurg, Michael Zacharias, Jovan Brankov

Proceedings Volume 8318, 83180R (2012) https://doi.org/10.1117/12.911502

KEYWORDS: Monte Carlo methods, Single photon emission computed tomography, Image segmentation, Arteries, NOx, Computer simulations, Heart, Neodymium, Cardiology, Statistical analysis

Read Abstract +

Proceedings Article | 29 February 2012 Paper

Combined collimator/reconstruction optimization for myocardial perfusion SPECT imaging using polar map-based LROC numerical observer

Souleymane Konate, P. Hendrik Pretorius, Howard Gifford, J. Michael O'Connor, Arda Konik, Mohammed Salman Shazeeb, Michael King

Proceedings Volume 8318, 83181L (2012) https://doi.org/10.1117/12.911479

KEYWORDS: Collimators, Single photon emission computed tomography, Computer aided design, Spatial resolution, Optimization (mathematics), Gaussian filters, 3D image reconstruction, Defect detection, Solid modeling, Signal attenuation

Read Abstract +

Polar maps have been used to assist clinicians diagnose coronary artery diseases (CAD) in single photon emission computed tomography (SPECT) myocardial perfusion imaging. Herein, we investigate the optimization of collimator design for perfusion defect detection in SPECT imaging when reconstruction includes modeling of the collimator. The optimization employs an LROC clinical model observer (CMO), which emulates the clinical task of polar map detection of CAD. By utilizing a CMO, which better mimics the clinical perfusion-defect detection task than previous SKE based observers, our objective is to optimize collimator design for SPECT myocardial perfusion imaging when reconstruction includes compensation for collimator spatial resolution. Comparison of lesion detection accuracy will then be employed to determine if a lower spatial resolution hence higher sensitivity collimator design than currently recommended could be utilized to reduce the radiation dose to the patient, imaging time, or a combination of both. As the first step in this investigation, we report herein on the optimization of the three-dimensional (3D) post-reconstruction Gaussian filtering of and the number of iterations used to reconstruct the SPECT slices of projections acquired by a low-energy generalpurpose (LEGP) collimator. The optimization was in terms of detection accuracy as determined by our CMO and four human observers. Both the human and all four CMO variants agreed that the optimal post-filtering was with sigma of the Gaussian in the range of 0.75 to 1.0 pixels. In terms of number of iterations, the human observers showed a preference for 5 iterations; however, only one of the variants of the CMO agreed with this selection. The others showed a preference for 15 iterations. We shall thus proceed to optimize the reconstruction parameters for even higher sensitivity collimators using this CMO, and then do the final comparison between collimators using their individually optimized parameters with human observers and three times the test images to reduce the statistical variation seen in our present results.

Proceedings Article | 3 March 2011 Paper

Incorporating holistic visual search concepts into a SPECT myocardial perfusion imaging numerical observer

J. Michael O'Connor, Howard Gifford, Jovan Brankov, P. Pretorius

Proceedings Volume 7966, 79660D (2011) https://doi.org/10.1117/12.877010

KEYWORDS: Single photon emission computed tomography, Visualization, Visual process modeling, Heart, Image processing, Image segmentation, Signal attenuation, Statistical analysis, Computer simulations, Computer aided diagnosis and therapy

Read Abstract +

Proceedings Article | 14 March 2009 Paper

Dose reduction in digital breast tomosynthesis using a penalized maximum likelihood reconstruction

Mini Das, Howard Gifford, Michael O'Connor, Stephen Glick

Proceedings Volume 7258, 725855 (2009) https://doi.org/10.1117/12.813952

KEYWORDS: Signal to noise ratio, Breast, Reconstruction algorithms, Digital breast tomosynthesis, Signal attenuation, Tumor growth modeling, Optical spheres, Visibility, Visualization, Image filtering

Read Abstract +

Proceedings Article | 11 March 2009 Paper

Enhanced computer simulation of CT mammography using a flat-panel imager

Clay Didier, J. Michael O'Connor, Yu Chen, Stephen Glick

Proceedings Volume 7258, 72580J (2009) https://doi.org/10.1117/12.813963

KEYWORDS: Sensors, Modulation transfer functions, Monte Carlo methods, Scintillators, Photons, Computer simulations, Breast, Imaging systems, X-rays, Tissues

Read Abstract +

Proceedings Article | 3 April 2008 Paper

Evaluation of a variable dose acquisition methodology for breast tomosynthesis

Mini Das, Howard Gifford, Michael O'Connor, Stephen Glick

Proceedings Volume 6913, 691319 (2008) https://doi.org/10.1117/12.773106

KEYWORDS: Breast, Mammography, 3D modeling, Sensors, Image compression, Mathematical modeling, X-rays, X-ray computed tomography, 3D acquisition, Systems modeling

Read Abstract +

Proceedings Article | 19 March 2008 Paper

Temporal change analysis for improved tumor detection in dedicated CT breast imaging using affine and free-form deformation

Joyoni Dey, J. Michael O'Connor, Yu Chen, Stephen Glick

Proceedings Volume 6913, 69131D (2008) https://doi.org/10.1117/12.769551

KEYWORDS: Breast, Computed tomography, Tumors, Image registration, X-ray computed tomography, Mammography, Breast cancer, 3D image processing, Visualization, Tissues

Read Abstract +

Proceedings Article | 18 March 2008 Paper

Using mastectomy specimens to develop breast models for breast tomosynthesis and CT breast imaging

J. Michael O'Connor, Mini Das, Clay Didier, Mufeed Mah'D, Stephen Glick

Proceedings Volume 6913, 691315 (2008) https://doi.org/10.1117/12.772666

KEYWORDS: Breast, 3D modeling, Systems modeling, X-ray computed tomography, Sensors, Tumor growth modeling, Tissues, Breast imaging, Data modeling, X-rays

Read Abstract +

Proceedings Article | 18 March 2008 Paper

Quantitative comparison of weighted Feldkamp FBP full-scan and half-scan algorithms for contrast-enhanced CT breast imaging

Clay Didier, Yu Chen, J. Michael O'Connor, Mufeed Mah'D, Stephen Glick

Proceedings Volume 6913, 69133B (2008) https://doi.org/10.1117/12.773395

KEYWORDS: Computed tomography, Sensors, Breast imaging, Tumors, Reconstruction algorithms, Breast cancer, X-ray computed tomography, Monte Carlo methods, Diagnostics, X-rays

Read Abstract +

Proceedings Article | 21 March 2007 Paper

Characterization of a prototype tabletop x-ray CT breast imaging system

J. Michael O'Connor, Stephen Glick, Xing Gong, Clay Didier, Mufeed Mah'd

Proceedings Volume 6510, 65102T (2007) https://doi.org/10.1117/12.713751

KEYWORDS: Modulation transfer functions, X-rays, X-ray computed tomography, Sensors, X-ray imaging, Optical spheres, Breast, Prototyping, Imaging systems, Breast imaging

Read Abstract +

Showing 5 of 17 publications

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

Keywords/Phrases

Search In:

Publication Years