SESarah Eskreis-Winkler

Sarah Eskreis-Winkler

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Sarah Eskreis-Winkler has a total of 123 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Accuracy of Retrieval-Augmented Large Language Model–Generated Preconsult Summaries in Breast Surgical Oncology

    by Tracy-Ann Moo, Robert James, Solange Bayard, Andreas Giannakou, Lisa R. Allen, Giacomo Montagna, Ivan Pan, Varadan Sevilimedu, Sarah Eskreis-Winkler, Monica Morrow

    PURPOSE: Radiology and pathology reports are important in breast surgical oncology planning, but are often unstructured and variable, requiring time-intensive previsit review and preparation. Here we evaluate the accuracy, completeness, and safety of retrieval-augmented large language model (LLM)–generated structured preconsult summaries compared with clinical staff–authored summaries. METHODS: In this single-institution retrospective validation study, 200 randomly sampled new breast surgical oncology consultations were included. LLM summaries were generated and compared with human summaries documented in consultation notes. Field-level accuracy, omission rate, and fabrication rate among extracted radiology and pathology variables were measured. Error analysis included patient level and clinically significant fabrication rates. RESULTS: Artificial intelligence (AI)–generated summaries demonstrated high field-level accuracy, with fabrication rates ≤2%. Accuracy rates were significantly higher than those observed in staff-authored notes across multiple domains, including nodal status (95% v 72%, P < .001) and documentation of invasive tumor component on biopsy (94% v 30%, P < .001). In contrast, staff-authored summaries were more accurate for receptor status (96% v 86%, P = .002). At the patient level, fabrication occurred in 16 AI-generated summaries (8%), including six clinically significant cases (3%). Staff-authored summaries demonstrated fabrication in six cases (3.0%), with one clinically significant instance (0.5%). CONCLUSION: In this retrospective validation study, structured retrieval-augmented LLM-generated preconsult summaries demonstrated field-level accuracy comparable with or exceeding staff-authored documentation across most radiologic and pathologic variables, with low per-field fabrication rates. Clinically significant errors occurred in a small proportion of summaries and were largely confined to identifiable high-risk variables that are amenable to targeted verification. With appropriate human oversight and safeguards, LLM-based structured information extraction may support documentation standardization and improved workflow efficiency in breast surgical oncology.


  • Contrast-enhanced Mammography for Breast Cancer Screening in Women at Increased Risk: Comparison of Prevalence and Incidence Screens

    by Carol H. Lee, Tali Amir, Varadan Sevilimedu, Sarah Eskreis-Winkler, Delia Keating, Donna D’ALessio, Maxine S. Jochelson, Gordon P. Watt, Kimberly N. Feigin, Noam Nissan, et al.

    The ability of contrast-enhanced mammography to help detect cancer during prevalence screening in women at increased risk for breast cancer is maintained in subsequent incidence screens, with better specificity and accuracy.

  • Interval Cancers after Negative Screening Contrast-enhanced Mammography

    by Tali Amir, Carol H. Lee, Sarah Eskreis-Winkler, Molly P. Hogan, Noam Nissan, Varadan Sevilimedu, Victoria L. Mango, Kimberly N. Feigin, Maxine S. Jochelson, Christopher E. Comstock, et al.

    In patients undergoing screening contrast-enhanced mammography, the interval cancer rate was 2.29 cancers per 1000 examinations, and invasive interval cancers were associated with moderate or marked background parenchymal enhancement.


  • Is Neoadjuvant Chemotherapy Justified When Triple-Negative Breast Cancer or HER2-Positive Breast Cancer Presents as ≥1 cm of Only Calcifications or as a Subcentimeter Mass with Surrounding Calcifications?

    by Max O. Meneveau, Varadan Sevilimedu, Tiana Le, Sarah Eskreis-Winkler, Monica Morrow

    Neoadjuvant chemotherapy (NAC) is considered for patients with cN0 triple-negative (TN) or HER2-positive breast cancer ≥1 cm. If the mammogram shows

  • Adaptive Breast MRI Scanning Using AI

    by Sarah Eskreis-Winkler, Arka Bhowmik, Lori H. Kelly, Roberto Lo Gullo, Donna D’aLessio, Kristin Belen, Molly P. Hogan, Nicole B. Saphier, Varadan Sevilimedu, Janice S. Sung, et al.

    Image-based artificial intelligence triage could be used to make modifications to breast MRI scanning protocols in real time, ensuring that sufficient diagnostic information is obtained for each patient as quickly as possible.


  • Racial Disparities in Preoperative Breast MRI Use and Surgical Margin Outcomes among Patients with Recently Diagnosed Breast Cancer

    by Amber Simmons, Lynn K. Han, Jeffrey S. Reiner, Victoria L. Mango, Varadan Sevilimedu, Katja Pinker, Hong Zhang, Tracy-Ann Moo, Sarah Eskreis-Winkler

    Black patients with recently diagnosed breast cancer were less likely to undergo preoperative breast MRI and more likely to have positive surgical margins when preoperative MRI was not performed, in comparison with White patients.


  • Open Access

    Development of an MRI Radiomic Machine-Learning Model to Predict Triple-Negative Breast Cancer Based on Fibroglandular Tissue of the Contralateral Unaffected Breast in Breast Cancer Patients

    by Roberto Lo Gullo, Rosa Elena Ochoa-Albiztegui, Jayasree Chakraborty, Sunitha B. Thakur, Mark Robson, Maxine S. Jochelson, Keitha Varela, Daphne Resch, Sarah Eskreis-Winkler, Katja Pinker

    Aim: The purpose of this study was to develop a radiomic-based machine-learning model to predict triple-negative breast cancer (TNBC) based on the contralateral unaffected breast’s fibroglandular tissue (FGT) in breast cancer patients. Materials and methods: This study retrospectively included 541 patients (mean age, 51 years; range, 26–82) who underwent a screening breast MRI between November 2016 and September 2018 and who were subsequently diagnosed with biopsy-confirmed, treatment-naïve breast cancer. Patients were divided into training (n = 250) and validation (n = 291) sets. In the training set, 132 radiomic features were extracted using the open-source CERR platform. Following feature selection, the final prediction model was created, based on a support vector machine with a polynomial kernel of order 2. Results: In the validation set, the final prediction model, which included four radiomic features, achieved an F1 score of 0.66, an area under the curve of 0.71, a sensitivity of 54% [47–60%], a specificity of 74% [65–84%], a positive predictive value of 84% [78–90%], and a negative predictive value of 39% [31–47%]. Conclusions: TNBC can be predicted based on radiomic features extracted from the FGT of the contralateral unaffected breast of patients, suggesting the potential for risk prediction specific to TNBC.


  • AI Applications to Breast MRI: Today and Tomorrow

    by Roberto Lo Gullo, Joren Brunekreef, Eric Marcus, Lynn K. Han, Sarah Eskreis‐Winkler, Sunitha B. Thakur, Ritse Mann, Kevin Groot Lipman, Jonas Teuwen, Katja Pinker

    In breast imaging, there is an unrelenting increase in the demand for breast imaging services, partly explained by continuous expanding imaging indications in breast diagnosis and treatment. As the human workforce providing these services is not growing at the same rate, the implementation of artificial intelligence (AI) in breast imaging has gained significant momentum to maximize workflow efficiency and increase productivity while concurrently improving diagnostic accuracy and patient outcomes. Thus far, the implementation of AI in breast imaging is at the most advanced stage with mammography and digital breast tomosynthesis techniques, followed by ultrasound, whereas the implementation of AI in breast magnetic resonance imaging (MRI) is not moving along as rapidly due to the complexity of MRI examinations and fewer available dataset. Nevertheless, there is persisting interest in AI‐enhanced breast MRI applications, even as the use of and indications of breast MRI continue to expand. This review presents an overview of the basic concepts of AI imaging analysis and subsequently reviews the use cases for AI‐enhanced MRI interpretation, that is, breast MRI triaging and lesion detection, lesion classification, prediction of treatment response, risk assessment, and image quality. Finally, it provides an outlook on the barriers and facilitators for the adoption of AI in breast MRI.Level of Evidence: 5Technical Efficacy: Stage 6


  • Caution on the CONTRRAST Trial

    by Sarah Eskreis-Winkler, Maxine S. Jochelson, Katja Pinker, Janice S. Sung, Christopher Comstock

  • Open Access

    Artificial Intelligence-Enhanced Breast MRI

    by Roberto Lo Gullo, Eric Marcus, Jorge Huayanay, Sarah Eskreis-Winkler, Sunitha Thakur, Jonas Teuwen, Katja Pinker

    Primary systemic therapy (PST) is the treatment of choice in patients with locally advanced breast cancer and is nowadays also often used in patients with early-stage breast cancer. Although imaging remains pivotal to assess response to PST accurately, the use of imaging to predict response to PST has the potential to not only better prognostication but also allow the de-escalation or omission of potentially toxic treatment with undesirable adverse effects, the accelerated implementation of new targeted therapies, and the mitigation of surgical delays in selected patients. In response to the limited ability of radiologists to predict response to PST via qualitative, subjective assessments of tumors on magnetic resonance imaging (MRI), artificial intelligence–enhanced MRI with classical machine learning, and in more recent times, deep learning, have been used with promising results to predict response, both before the start of PST and in the early stages of treatment. This review provides an overview of the current applications of artificial intelligence to MRI in assessing and predicting response to PST, and discusses the challenges and limitations of their clinical implementation.