Skip to main content

Michael Robert Harowicz

Assistant Professor of Radiology
Radiology, Cardiothoracic Imaging

Selected Publications


Massive Mysteries.

Journal Article Am J Cardiol · October 1, 2023 Papillary fibroelastomas are benign masses often originating from the endocardium of the aortic and mitral valves. Rarely, these neoplasms are found in areas of the heart embryonically distinct from the aortic and mitral valves. Diagnosis of a papillary fi ... Full text Link to item Cite

Preoperative Planning for Structural Heart Disease.

Journal Article Radiol Clin North Am · July 2020 Preoperative assessment with computed tomography (CT) is critical before transcatheter interventions for structural heart disease. CT provides information for device selection, device sizing, and vascular access approach. The interpreting radiologist must ... Full text Link to item Cite

Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ.

Journal Article Comput Biol Med · December 2019 PURPOSE: To determine whether deep learning-based algorithms applied to breast MR images can aid in the prediction of occult invasive disease following the diagnosis of ductal carcinoma in situ (DCIS) by core needle biopsy. MATERIALS AND METHODS: Our study ... Full text Link to item Cite

Deep learning for identifying radiogenomic associations in breast cancer.

Journal Article Comput Biol Med · June 2019 RATIONALE AND OBJECTIVES: To determine whether deep learning models can distinguish between breast cancer molecular subtypes based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS: In this institutional review board- ... Full text Link to item Cite

Association of distant recurrence-free survival with algorithmically extracted MRI characteristics in breast cancer.

Journal Article J Magn Reson Imaging · June 2019 BACKGROUND: While important in diagnosis of breast cancer, the scientific assessment of the role of imaging in prognosis of outcomes and treatment planning is limited. PURPOSE: To evaluate the potential of using quantitative imaging variables for stratifyi ... Full text Link to item Cite

Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set.

Journal Article Breast Cancer Res Treat · January 2019 PURPOSE: To determine whether a multivariate machine learning-based model using computer-extracted features of pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict pathologic complete response (pCR) to neoadjuvant therap ... Full text Link to item Cite

Intra-tumor molecular heterogeneity in breast cancer: definitions of measures and association with distant recurrence-free survival.

Journal Article Breast Cancer Res Treat · November 2018 PURPOSE: The purpose of the study was to define quantitative measures of intra-tumor heterogeneity in breast cancer based on histopathology data gathered from multiple samples on individual patients and determine their association with distant recurrence-f ... Full text Link to item Cite

A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features.

Journal Article Br J Cancer · August 2018 BACKGROUND: Recent studies showed preliminary data on associations of MRI-based imaging phenotypes of breast tumours with breast cancer molecular, genomic, and related characteristics. In this study, we present a comprehensive analysis of this relationship ... Full text Link to item Cite

Breast cancer MRI radiomics: An overview of algorithmic features and impact of inter-reader variability in annotating tumors.

Journal Article Med Phys · July 2018 PURPOSE: To review features used in MRI radiomics of breast cancer and study the inter-reader stability of the features. METHODS: We implemented 529 algorithmic features that can be extracted from tumor and fibroglandular tissue (FGT) in breast MRIs. The f ... Full text Link to item Cite

A study of association of Oncotype DX recurrence score with DCE-MRI characteristics using multivariate machine learning models.

Journal Article J Cancer Res Clin Oncol · May 2018 PURPOSE: To determine whether multivariate machine learning models of algorithmically assessed magnetic resonance imaging (MRI) features from breast cancer patients are associated with Oncotype DX (ODX) test recurrence scores. METHODS: A set of 261 female ... Full text Link to item Cite

Association of high proliferation marker Ki-67 expression with DCEMR imaging features of breast: A large scale evaluation

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2018 One of the methods widely used to measure the proliferative activity of cells in breast cancer patients is the immunohistochemical (IHC) measurement of the percentage of cells stained for nuclear antigen Ki-67. Use of Ki-67 expression as a prognostic marke ... Full text Cite

Deep learning-based features of breast MRI for prediction of occult invasive disease following a diagnosis of ductal carcinoma in situ: Preliminary data

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2018 Approximately 25% of patients with ductal carcinoma in situ (DCIS) diagnosed from core needle biopsy are subsequently upstaged to invasive cancer at surgical excision. Identifying patients with occult invasive disease is important as it changes treatment a ... Full text Cite

Breast cancer molecular subtype classification using deep features: Preliminary results

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2018 Radiogenomics is a field of investigation that attempts to examine the relationship between imaging characteris-tics of cancerous lesions and their genomic composition. This could offer a noninvasive alternative to establishing genomic characteristics of t ... Full text Cite

Can algorithmically assessed MRI features predict which patients with a preoperative diagnosis of ductal carcinoma in situ are upstaged to invasive breast cancer?

Journal Article J Magn Reson Imaging · November 2017 PURPOSE: To assess the ability of algorithmically assessed magnetic resonance imaging (MRI) features to predict the likelihood of upstaging to invasive cancer in newly diagnosed ductal carcinoma in situ (DCIS). MATERIALS AND METHODS: We identified 131 pati ... Full text Link to item Cite

Can BI-RADS features on mammography be used as a surrogate for expensive genomic testing in breast cancer patients?

Conference Proceedings of SPIE - The International Society for Optical Engineering · February 3, 2017 Cite

Algorithms for prediction of the Oncotype DX recurrence score using clinicopathologic data: a review and comparison using an independent dataset.

Journal Article Breast Cancer Res Treat · February 2017 PURPOSE: Given the potential savings in cost and resource utilization, several algorithms have been proposed to predict Oncotype DX recurrence score (ODX RS) using commonly acquired histopathologic variables. Although it is promising, additional independen ... Full text Link to item Cite

Can BI-RADS features on mammography be used as a surrogate for expensive genomic testing in breast cancer patients?

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2017 Medical oncologists increasingly rely on expensive genomic analysis to stratify patients for different treatment. The genomic markers are able to divide patients into groups that behave differently in terms of tumor presentation, likelihood of metastatic s ... Full text Cite

Interobserver variability in identification of breast tumors in MRI and its implications for prognostic biomarkers and radiogenomics.

Journal Article Med Phys · August 2016 PURPOSE: To assess the interobserver variability of readers when outlining breast tumors in MRI, study the reasons behind the variability, and quantify the effect of the variability on algorithmic imaging features extracted from breast MRI. METHODS: Four r ... Full text Link to item Cite

Massive Mysteries.

Journal Article Am J Cardiol · October 1, 2023 Papillary fibroelastomas are benign masses often originating from the endocardium of the aortic and mitral valves. Rarely, these neoplasms are found in areas of the heart embryonically distinct from the aortic and mitral valves. Diagnosis of a papillary fi ... Full text Link to item Cite

Preoperative Planning for Structural Heart Disease.

Journal Article Radiol Clin North Am · July 2020 Preoperative assessment with computed tomography (CT) is critical before transcatheter interventions for structural heart disease. CT provides information for device selection, device sizing, and vascular access approach. The interpreting radiologist must ... Full text Link to item Cite

Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ.

Journal Article Comput Biol Med · December 2019 PURPOSE: To determine whether deep learning-based algorithms applied to breast MR images can aid in the prediction of occult invasive disease following the diagnosis of ductal carcinoma in situ (DCIS) by core needle biopsy. MATERIALS AND METHODS: Our study ... Full text Link to item Cite

Deep learning for identifying radiogenomic associations in breast cancer.

Journal Article Comput Biol Med · June 2019 RATIONALE AND OBJECTIVES: To determine whether deep learning models can distinguish between breast cancer molecular subtypes based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS: In this institutional review board- ... Full text Link to item Cite

Association of distant recurrence-free survival with algorithmically extracted MRI characteristics in breast cancer.

Journal Article J Magn Reson Imaging · June 2019 BACKGROUND: While important in diagnosis of breast cancer, the scientific assessment of the role of imaging in prognosis of outcomes and treatment planning is limited. PURPOSE: To evaluate the potential of using quantitative imaging variables for stratifyi ... Full text Link to item Cite

Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set.

Journal Article Breast Cancer Res Treat · January 2019 PURPOSE: To determine whether a multivariate machine learning-based model using computer-extracted features of pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict pathologic complete response (pCR) to neoadjuvant therap ... Full text Link to item Cite

Intra-tumor molecular heterogeneity in breast cancer: definitions of measures and association with distant recurrence-free survival.

Journal Article Breast Cancer Res Treat · November 2018 PURPOSE: The purpose of the study was to define quantitative measures of intra-tumor heterogeneity in breast cancer based on histopathology data gathered from multiple samples on individual patients and determine their association with distant recurrence-f ... Full text Link to item Cite

A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features.

Journal Article Br J Cancer · August 2018 BACKGROUND: Recent studies showed preliminary data on associations of MRI-based imaging phenotypes of breast tumours with breast cancer molecular, genomic, and related characteristics. In this study, we present a comprehensive analysis of this relationship ... Full text Link to item Cite

Breast cancer MRI radiomics: An overview of algorithmic features and impact of inter-reader variability in annotating tumors.

Journal Article Med Phys · July 2018 PURPOSE: To review features used in MRI radiomics of breast cancer and study the inter-reader stability of the features. METHODS: We implemented 529 algorithmic features that can be extracted from tumor and fibroglandular tissue (FGT) in breast MRIs. The f ... Full text Link to item Cite

A study of association of Oncotype DX recurrence score with DCE-MRI characteristics using multivariate machine learning models.

Journal Article J Cancer Res Clin Oncol · May 2018 PURPOSE: To determine whether multivariate machine learning models of algorithmically assessed magnetic resonance imaging (MRI) features from breast cancer patients are associated with Oncotype DX (ODX) test recurrence scores. METHODS: A set of 261 female ... Full text Link to item Cite

Association of high proliferation marker Ki-67 expression with DCEMR imaging features of breast: A large scale evaluation

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2018 One of the methods widely used to measure the proliferative activity of cells in breast cancer patients is the immunohistochemical (IHC) measurement of the percentage of cells stained for nuclear antigen Ki-67. Use of Ki-67 expression as a prognostic marke ... Full text Cite

Deep learning-based features of breast MRI for prediction of occult invasive disease following a diagnosis of ductal carcinoma in situ: Preliminary data

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2018 Approximately 25% of patients with ductal carcinoma in situ (DCIS) diagnosed from core needle biopsy are subsequently upstaged to invasive cancer at surgical excision. Identifying patients with occult invasive disease is important as it changes treatment a ... Full text Cite

Breast cancer molecular subtype classification using deep features: Preliminary results

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2018 Radiogenomics is a field of investigation that attempts to examine the relationship between imaging characteris-tics of cancerous lesions and their genomic composition. This could offer a noninvasive alternative to establishing genomic characteristics of t ... Full text Cite

Can algorithmically assessed MRI features predict which patients with a preoperative diagnosis of ductal carcinoma in situ are upstaged to invasive breast cancer?

Journal Article J Magn Reson Imaging · November 2017 PURPOSE: To assess the ability of algorithmically assessed magnetic resonance imaging (MRI) features to predict the likelihood of upstaging to invasive cancer in newly diagnosed ductal carcinoma in situ (DCIS). MATERIALS AND METHODS: We identified 131 pati ... Full text Link to item Cite

Can BI-RADS features on mammography be used as a surrogate for expensive genomic testing in breast cancer patients?

Conference Proceedings of SPIE - The International Society for Optical Engineering · February 3, 2017 Cite

Algorithms for prediction of the Oncotype DX recurrence score using clinicopathologic data: a review and comparison using an independent dataset.

Journal Article Breast Cancer Res Treat · February 2017 PURPOSE: Given the potential savings in cost and resource utilization, several algorithms have been proposed to predict Oncotype DX recurrence score (ODX RS) using commonly acquired histopathologic variables. Although it is promising, additional independen ... Full text Link to item Cite

Can BI-RADS features on mammography be used as a surrogate for expensive genomic testing in breast cancer patients?

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2017 Medical oncologists increasingly rely on expensive genomic analysis to stratify patients for different treatment. The genomic markers are able to divide patients into groups that behave differently in terms of tumor presentation, likelihood of metastatic s ... Full text Cite

Interobserver variability in identification of breast tumors in MRI and its implications for prognostic biomarkers and radiogenomics.

Journal Article Med Phys · August 2016 PURPOSE: To assess the interobserver variability of readers when outlining breast tumors in MRI, study the reasons behind the variability, and quantify the effect of the variability on algorithmic imaging features extracted from breast MRI. METHODS: Four r ... Full text Link to item Cite

Predictive parameters for the antecedent development of hip pathology associated with long segment fusions to the pelvis for the treatment of adult spinal deformity.

Journal Article Surg Neurol Int · 2016 BACKGROUND: The surgical treatment of adult scoliosis frequently involves long segment fusions across the lumbosacral joints that redistribute tremendous amounts of force to the remaining mobile spinal segments as well as to the pelvis and hip joints. Whet ... Full text Link to item Cite