Dr. Aimilia Gastounioti Profile

Dr. Aimilia Gastounioti

Assistant Professor at Washington Univ School of Medicine

SPIE Involvement:

Conference Program Committee | Author

Area of Expertise:

breast cancer , computational imaging analytics , machine learning , precision medicine , big data , breast cancer risk

Websites:

Personal Website | Company Website

Profile Summary

Dr. Aimilia Gastounioti grew up in Athens, Greece. She received her Ph.D. in Engineering from the National Technical University of Athens in 2014, performed partly in collaboration with the Center for Visual Computing/INRIA GALEN Research Group at the Ecole Centrale de Paris. Subsequently, she worked as Postdoctoral Researcher and then as Research Associate in the Department of Radiology at the University of Pennsylvania. In 2021, she was appointed as Assistant Professor at Washington University School of Medicine, where she is developing a research program on translational biomedical imaging research, computational image analytics and artificial intelligence for breast cancer screening. She has co-authored more than 100 peer-reviewed journal articles and papers in premier scientific meetings. Among others, Aimilia has received research funding from the Susan G. Komen foundation for breast cancer and the Penn Institute for Translational Medicine and Therapeutics. Aimilia is also an Associate member of the American Association for Cancer Research (AACR).

Publications (15)

Proceedings Article | 29 May 2024 Paper

Paper

Advancing volumetric breast density segmentation: a deep learning approach with digital breast tomosynthesis

Nehal Doiphode, Vinayak Ahluwalia, Walter Mankowski, Eric Cohen, Sarthak Pati, Lauren Pantalone, Spyridon Bakas, Ari Brooks, Celine Vachon, Emily Conant, Aimilia Gastounioti, Despina Kontos

Proceedings Volume 13174, 131740O (2024) https://doi.org/10.1117/12.3027010

KEYWORDS: Image segmentation, Breast, Digital breast tomosynthesis, Breast cancer, 3D modeling, Breast density, 3D image processing

Read Abstract +

Recognizing breast density as a critical risk factor for breast cancer, traditionally assessed through subjective radiological evaluation within the BI-RADS framework, this research seeks to mitigate inter-observer variability through automated, quantitative analysis. The transition to DBT offers a quasi-3D perspective potentially enhancing the accuracy of BD assessments yet faces limitations with current FDA-cleared methods for volumetric breast density (VBD) estimation. Addressing these challenges, our work introduces a fully automated computational tool leveraging deep learning to accurately assess VBD from 3D DBT images without reliance on raw 2D data. Employing retrospective data compliant with privacy regulations, this study utilized DBT screening examinations from the Hospital of the University of Pennsylvania. The development of a three-class segmentation model, based on the U-Net architecture, was undertaken to differentiate between non-breast/background, fatty breast tissue, and dense breast tissue in DBT images. A novel two-stage training method was devised to enhance model performance, particularly in avoiding mis-segmentation issues common in high-resolution medio-lateral oblique images. This approach first utilized resized images for global shape information recognition, followed by refined segmentation using a 3D U-Net on filtered input, emphasizing accurate dense tissue identification. Our model demonstrated exemplary performance, with the Dice score—a critical metric for evaluating segmentation accuracy—revealing substantial agreement between the model's predictions and actual data. Validation of the model's effectiveness in breast cancer risk estimation was conducted through a case-control study, demonstrating a statistically significant association between DL-estimated VBD and cancer diagnosis. Additional factors, including BMI and age at screening, were also found to be significantly associated with cancer status, underscoring the multifactorial nature of breast cancer risk. The model's predictive capability was further evidenced by an AUC of 0.63, indicating good performance. The study's implications are profound, offering a clinically significant tool for personalized breast cancer risk prediction and potentially enhancing screening strategies across diverse populations.

Proceedings Article | 3 April 2024 Presentation + Paper

Presentation + Paper

Breast density assessment via deep learning: head-to-head model comparisons in full-field digital mammograms and synthetic mammograms

Krisha Anant, Juanita Hernandez Lopez, Sneha Das Gupta, Debbie Bennett, Aimilia Gastounioti

Proceedings Volume 12927, 129270C (2024) https://doi.org/10.1117/12.3008648

KEYWORDS: Breast density, Mammography, Deep learning, Digital breast tomosynthesis, Education and training, Digital mammography, Image classification, Breast, Molybdenum, Medicine

Read Abstract +

To enhance reproducibility and robustness in mammographic density assessment, various deep learning models have been proposed to automatically classify mammographic images into BI-RADS density categories. Our study aims to compare the performances of different deep learning models in making breast density classifications from full-field digital mammography (FFDM) versus synthetic mammography (SM), the newer 2D mammographic image format acquired with digital breast tomosynthesis (DBT). We retrospectively analyzed negative (BI-RADS 1 or 2) routine mammographic screening exams (Selenia or Selenia Dimensions; Hologic) acquired at sites within the Barnes-Jewish/Christian (BJC) Healthcare network in St. Louis, MO from 2015 to 2018. BI-RADS breast density assessments of radiologists were obtained from BJC’s mammography reporting software (Magview 7.1). For each mammographic imaging modality, a balanced dataset of 4,000 women was selected so there were equal numbers of women in each of the four BI-RADS density categories, and each woman had at least one mediolateral oblique (MLO) and one craniocaudal (CC) view per breast in that mammographic imaging modality. Previously validated pre-processing steps were applied to all FFDM and SM images to standardize image orientation and intensity. Images were then split into training, validation, and test sets at ratios of 80%, 10%, and 10%, respectively, while maintaining the distribution of breast density categories and ensuring that all images of the same woman appear only in one set. ResNet-50 and EfficientNet-B0 architectures were optimized, trained, and evaluated separately for different imaging modalities. Overall, the models had comparable performance, though ResNet-50 performed slightly better in most cases. Furthermore, FFDM images had better classification accuracies than SM images. Our preliminary findings suggest that further deep learning developments and optimizations may be needed as we develop breast density deep learning models for the newer mammographic imaging modality, DBT.

Proceedings Article | 3 April 2024 Poster + Paper

Poster + Paper

Beyond mammographic density: a computational imaging approach to identify effects of early adulthood adiposity on breast parenchymal tissue patterns in premenopausal women

Sneha Das Gupta, Kayla Getz, Juanita Hernandez Lopez, Debbie Bennett, Adetunji Toriola, Aimilia Gastounioti

Proceedings Volume 12927, 1292722 (2024) https://doi.org/10.1117/12.3008639

KEYWORDS: Breast, Mammography, Breast density, Adipose tissue, Breast cancer, Radiomics, Computational imaging, Principal component analysis

Read Abstract +

Early-adulthood adiposity measures, such as weight and body-mass index, are associated with breast cancer risk. Moreover, studies have shown that breast parenchymal tissue patterns as reflected in digital mammograms (DMs) are also associated with breast cancer risk. We retrospectively analyzed DMs and early-adulthood adiposity data of 326 premenopausal women with the aim to assess the relationship of early-adulthood adiposity and breast parenchymal tissue patterns later in life. Radiomic features were extracted from DMs using a well-validated computational imaging pipeline and fused into woman-specific radiomic feature vectors via principal component analysis. Unsupervised hierarchical clustering was then applied to radiomic feature vectors to identify distinct phenotypes (clusters) of breast parenchymal complexity. For each early-adulthood adiposity measure, its associations with the identified breast parenchymal complexity clusters were assessed via logistic regression, adjusted for age at screening, race, family history of breast cancer, and parity. Two statistically significant clusters of breast parenchymal complexity (p-value < 0.001), “cluster 0” and “cluster 1”, were identified on the basis of principal components. Compared to women of high breast parenchymal complexity (“cluster 0”), women assigned to the cluster of lower breast parenchymal complexity (“cluster 1”) were associated with higher early-adulthood adiposity and larger adiposity changes over time. Among all early-adulthood adiposity measures, strongest associations with breast parenchymal complexity clusters were found for annual weight change from age 18 to age at DM screening (odds ratio [OR] = 2.46, 95% CI: [1.52, 3.99]) and annual weight change from age 30 to age at DM screening (OR = 1.73, 95% CI: [1.25, 2.39]). Our preliminary data suggest that adiposity in early adulthood, as well as weight gain from early adulthood to attained age are inversely associated with breast parenchymal complexity among premenopausal women and may have a lifelong impact on breast parenchymal tissue patterns.

Proceedings Article | 13 July 2022 Paper

Paper

External validation of an AI-driven breast cancer risk prediction model in a racially diverse cohort of women undergoing mammographic screening

Aimilia Gastounioti, Mikael Eriksson, Eric Cohen, Walter Mankowski, Lauren Pantalone, Anne Marie McCarthy, Despina Kontos, Per Hall, Emily Conant

Proceedings Volume 12286, 1228617 (2022) https://doi.org/10.1117/12.2627140

KEYWORDS: Breast cancer, Artificial intelligence, Breast, Digital mammography, Machine learning

Read Abstract +

Proceedings Article | 22 May 2020 Paper

Paper

Automatic breast segmentation in digital mammography using a convolutional neural network

Omid Haji Maghsoudi, Aimilia Gastounioti, Lauren Pantalone, Emily Conant, Despina Kontos

Proceedings Volume 11513, 1151322 (2020) https://doi.org/10.1117/12.2564235

KEYWORDS: Image segmentation, Breast, Digital mammography, Breast cancer, Tissues, Convolutional neural networks, Radiology, Data modeling, Cancer, Algorithm development

Read Abstract +

Proceedings Article | 22 May 2020 Paper

Paper

Calculation of radiomic features to validate the textural realism of physical anthropomorphic phantoms for digital mammography

Raymond Acciavatti, Eric Cohen, Omid Haji Maghsoudi, Aimilia Gastounioti, Lauren Pantalone, Meng-Kang Hsieh, Bruno Barufaldi, Predrag Bakic, Jinbo Chen, Emily Conant, Despina Kontos, Andrew D. Maidment

Proceedings Volume 11513, 1151309 (2020) https://doi.org/10.1117/12.2564363

KEYWORDS: Breast, Digital mammography, Mammography, Imaging systems, Wavelets, X-ray imaging, Feature extraction, Breast cancer

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Paper

Robust radiomic feature selection in digital mammography: understanding the effect of imaging acquisition physics using phantom and clinical data analysis

Raymond Acciavatti, Eric Cohen, Omid Haji Maghsoudi, Aimilia Gastounioti, Lauren Pantalone, Meng-Kang Hsieh, Emily Conant, Christopher Scott, Stacey Winham, Karla Kerlikowske, Celine Vachon, Andrew D. Maidment, Despina Kontos

Proceedings Volume 11314, 113140W (2020) https://doi.org/10.1117/12.2549163

KEYWORDS: Digital mammography, Breast, Feature selection, Breast cancer, Feature extraction, Data analysis

Read Abstract +

Proceedings Article | 13 March 2019 Paper

Paper

Associations between mammographic phenotypes and histopathologic features in ductal carcinoma in situ

Ruvini Navaratna, Aimilia Gastounioti, Meng-Kang Hsieh, Lauren Pantalone, Marie Shelanski, Emily Conant, Despina Kontos

Proceedings Volume 10950, 109502K (2019) https://doi.org/10.1117/12.2512464

KEYWORDS: Breast, Breast cancer, Receptors, Mammography, Statistical analysis, Principal component analysis, Biopsy, Feature extraction

Read Abstract +

Proceedings Article | 6 July 2018 Paper

Paper

Validation of the textural realism of a 3D anthropomorphic phantom for digital breast tomosynthesis

Raymond Acciavatti, Meng-Kang Hsieh, Aimilia Gastounioti, Yifan Hu, Jinbo Chen, Andrew D. Maidment, Despina Kontos

Proceedings Volume 10718, 107180R (2018) https://doi.org/10.1117/12.2318029

KEYWORDS: Digital breast tomosynthesis, Mammography, Breast, Image analysis, Cancer, Image acquisition, 3D acquisition, 3D image reconstruction

Read Abstract +

Proceedings Article | 2 March 2018 Paper

Paper

Volumetric versus area-based density assessment: comparisons using automated quantitative measurements from a large screening cohort

Aimilia Gastounioti, Meng-Kang Hsieh, Lauren Pantalone, Emily Conant, Despina Kontos

Proceedings Volume 10574, 105742H (2018) https://doi.org/10.1117/12.2293051

KEYWORDS: Breast, Digital breast tomosynthesis, Breast cancer, Digital mammography, Image segmentation

Read Abstract +

SPIE Journal Paper | 11 January 2018 Open Access

Open Access

Cancer imaging phenomics toolkit: quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome

Christos Davatzikos, Saima Rathore, Spyridon Bakas, Sarthak Pati, Mark Bergman, Ratheesh Kalarot, Patmaa Sridharan, Aimilia Gastounioti, Nariman Jahani, Eric Cohen, Hamed Akbari, Birkan Tunc, Jimit Doshi, Drew Parker, Michael Hsieh, Aristeidis Sotiras, Hongming Li, Yangming Ou, Robert K. Doot, Michel Bilello, Yong Fan, Russell T. Shinohara, Paul Yushkevich, Ragini Verma, Despina Kontos

JMI, Vol. 5, Issue 01, 011018, (January 2018) https://doi.org/10.1117/12.10.1117/1.JMI.5.1.011018

KEYWORDS: Tumors, Magnetic resonance imaging, Cancer, Breast, Analytics, Diagnostics, Image segmentation, Brain, Tissues, Feature extraction

Read Abstract +

Proceedings Article | 3 March 2017 Presentation + Paper

Presentation + Paper

Mammographic phenotypes of breast cancer risk driven by breast anatomy

Aimilia Gastounioti, Andrew Oustimov, Meng-Kang Hsieh, Lauren Pantalone, Emily Conant, Despina Kontos

Proceedings Volume 10134, 1013417 (2017) https://doi.org/10.1117/12.2254630

KEYWORDS: Nipple, Volume rendering, Image segmentation, Data modeling, Breast cancer, Digital mammography

Read Abstract +

Proceedings Article | 3 March 2017 Presentation + Paper

Presentation + Paper

Convolutional neural network approach for enhanced capture of breast parenchymal complexity patterns associated with breast cancer risk

Andrew Oustimov, Aimilia Gastounioti, Meng-Kang Hsieh, Lauren Pantalone, Emily Conant, Despina Kontos

Proceedings Volume 10134, 101340S (2017) https://doi.org/10.1117/12.2254506

KEYWORDS: Convolutional neural networks, Computer architecture, Receivers, Breast cancer, Neural networks, Digital mammography, Image fusion

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Paper

Parenchymal texture measures weighted by breast anatomy: preliminary optimization in a case-control study

Aimilia Gastounioti, Brad Keller, Meng-Kang Hsieh, Emily Conant, Despina Kontos

Proceedings Volume 9785, 97850M (2016) https://doi.org/10.1117/12.2217697

KEYWORDS: Breast, Breast cancer, Digital mammography, Mammography, Feature extraction, Volume rendering, Image segmentation, Nipple

Read Abstract +

Proceedings Article | 23 March 2016 Paper

Paper

Preliminary evaluation of a fully automated quantitative framework for characterizing general breast tissue histology via color histogram and color texture analysis

Brad Keller, Aimilia Gastounioti, Rebecca Batiste, Despina Kontos, Michael Feldman

Proceedings Volume 9791, 97910A (2016) https://doi.org/10.1117/12.2217094

KEYWORDS: Tissues, Feature extraction, Breast, Visualization, Collagen, Image segmentation, Tissue optics, Image analysis, Breast cancer, Pathology, Cancer

Read Abstract +

Showing 5 of 15 publications

Conference Committee Involvement (3)

Computer-Aided Diagnosis

17 February 2025 | San Diego, California, United States

Computer-Aided Diagnosis

19 February 2024 | San Diego, California, United States

Computer-Aided Diagnosis

20 February 2023 | San Diego, California, United States

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