Scholars@Duke
Yekaterina Shpanskaya

Yekaterina Shpanskaya

Assistant Professor of Radiology
Radiology, Neuroradiology

Scholarly Works

Follow-up Recommendations for Young, Average Risk Women With BI-RADS 3 Masses.

Journal article J Breast Imaging · March 3, 2026 OBJECTIVE: To determine the outcome and malignancy rate of BI-RADS 3 masses during follow-up at 6, 12, and 24 months. METHODS: This retrospective cohort study identified female patients <35 years of age with an oval, parallel, circumscribed mass assigned a ... Full text Link to item Cite

Echogenic Rind Associated With Suspicious Masses on Ultrasound: Performance for Breast Cancer Diagnosis and Associations With Pathologic Tumor Characteristics.

Journal article AJR Am J Roentgenol · December 2025 BACKGROUND. The 6th edition of the BI-RADS ultrasound lexicon is anticipated to include echogenic rind as a renamed associated feature, defined as a thick hyperechoic band partially or completely surrounding a mass and disrupting surrounding tissue texture ... Full text Link to item Cite

Intramedullary Spinal Cord Tumors and Tumor-Like Lesions.

Journal article Magn Reson Imaging Clin N Am · May 2025 Intramedullary spinal cord tumors are rare neoplasms that can result in significant patient morbidity and mortality. Symptom onset is often insidious and not specific; thus, imaging is imperative for accurate diagnosis and localization of these tumors. Rad ... Full text Link to item Cite

Shoulder Effusion as Ultrasound Mimic of Axillary Lymphadenopathy

Journal article Applied Radiology · December 1, 2023 Full text Cite

MRI Radiogenomics of Pediatric Medulloblastoma: A Multicenter Study.

Journal article Radiology · August 2022 Background Radiogenomics of pediatric medulloblastoma (MB) offers an opportunity for MB risk stratification, which may aid therapeutic decision making, family counseling, and selection of patient groups suitable for targeted genetic analysis. Purpose To de ... Full text Link to item Cite

Attention-guided deep learning for gestational age prediction using fetal brain MRI.

Journal article Sci Rep · January 26, 2022 Magnetic resonance imaging offers unrivaled visualization of the fetal brain, forming the basis for establishing age-specific morphologic milestones. However, gauging age-appropriate neural development remains a difficult task due to the constantly changin ... Full text Link to item Cite

MRI Correlates of Ototoxicity in the Auditory Pathway in Children Treated for Medulloblastoma.

Journal article Otol Neurotol · January 1, 2022 OBJECTIVE: To assess diffusion and perfusion changes of the auditory pathway in pediatric medulloblastoma patients exposed to ototoxic therapies. STUDY DESIGN: Retrospective cohort study. SETTING: A single academic tertiary children's hospital. PATIENTS: T ... Full text Link to item Cite

Author Correction: PENet—a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging (npj Digital Medicine, (2020), 3, 1, (61), 10.1038/s41746-020-0266-y)

Journal article Npj Digital Medicine · December 1, 2020 The original version of the published Article did not acknowledge the passing of the sixth Author, Norah Borus. To improve clarity, the Author contributions have been updated to include the following: Norah Borus was not able to review the manuscript prior ... Full text Cite

PENet—a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging

Journal article Npj Digital Medicine · December 1, 2020 Pulmonary embolism (PE) is a life-threatening clinical problem and computed tomography pulmonary angiography (CTPA) is the gold standard for diagnosis. Prompt diagnosis and immediate treatment are critical to avoid high morbidity and mortality rates, yet P ... Full text Cite

Deep Learning for Pediatric Posterior Fossa Tumor Detection and Classification: A Multi-Institutional Study.

Journal article AJNR Am J Neuroradiol · September 2020 BACKGROUND AND PURPOSE: Posterior fossa tumors are the most common pediatric brain tumors. MR imaging is key to tumor detection, diagnosis, and therapy guidance. We sought to develop an MR imaging-based deep learning model for posterior fossa tumor detecti ... Full text Link to item Cite

Altered cerebral perfusion in children with Langerhans cell histiocytosis after chemotherapy.

Journal article Pediatr Blood Cancer · March 2020 BACKGROUND AND PURPOSE: Children with Langerhans cell histiocytosis (LCH) may develop a wide array of neurological symptoms, but associated cerebral physiologic changes are poorly understood. We examined cerebral hemodynamic properties of pediatric LCH usi ... Full text Link to item Cite

Deep Learning for Automated Classification of Inferior Vena Cava Filter Types on Radiographs.

Journal article J Vasc Interv Radiol · January 2020 PURPOSE: To demonstrate the feasibility and evaluate the performance of a deep-learning convolutional neural network (CNN) classification model for automated identification of different types of inferior vena cava (IVC) filters on radiographs. MATERIALS AN ... Full text Link to item Cite

Diffusion tensor magnetic resonance imaging of the optic nerves in pediatric hydrocephalus.

Journal article Neurosurg Focus · December 1, 2019 OBJECTIVE: While conventional imaging can readily identify ventricular enlargement in hydrocephalus, structural changes that underlie microscopic tissue injury might be more difficult to capture. MRI-based diffusion tensor imaging (DTI) uses properties of ... Full text Link to item Cite

Arterial spin labeling perfusion changes of the frontal lobes in children with posterior fossa syndrome.

Journal article J Neurosurg Pediatr · October 1, 2019 OBJECTIVE: Posterior fossa syndrome (PFS) is a common complication following the resection of posterior fossa tumors in children. The pathophysiology of PFS remains incompletely elucidated; however, the wide-ranging symptoms of PFS suggest the possibility ... Full text Link to item Cite

Posterior fossa syndrome and increased mean diffusivity in the olivary bodies.

Journal article J Neurosurg Pediatr · October 1, 2019 OBJECTIVE: Posterior fossa syndrome (PFS) is a common postoperative complication following resection of posterior fossa tumors in children. It typically presents 1 to 2 days after surgery with mutism, ataxia, emotional lability, and other behavioral sympto ... Full text Link to item Cite

Deep Learning-Assisted Diagnosis of Cerebral Aneurysms Using the HeadXNet Model.

Journal article JAMA Netw Open · June 5, 2019 IMPORTANCE: Deep learning has the potential to augment clinician performance in medical imaging interpretation and reduce time to diagnosis through automated segmentation. Few studies to date have explored this topic. OBJECTIVE: To develop and apply a neur ... Full text Link to item Cite

Age-Dependent White Matter Characteristics of the Cerebellar Peduncles from Infancy Through Adolescence.

Journal article Cerebellum · June 2019 Cerebellum-cerebrum connections are essential for many motor and cognitive functions and cerebellar disorders are prevalent in childhood. The middle (MCP), inferior (ICP), and superior cerebellar peduncles (SCP) are the major white matter pathways that per ... Full text Link to item Cite

MR Imaging-Based Radiomic Signatures of Distinct Molecular Subgroups of Medulloblastoma.

Journal article AJNR Am J Neuroradiol · January 2019 BACKGROUND AND PURPOSE: Distinct molecular subgroups of pediatric medulloblastoma confer important differences in prognosis and therapy. Currently, tissue sampling is the only method to obtain information for classification. Our goal was to develop and val ... Full text Link to item Cite

CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison

Conference 33rd Aaai Conference on Artificial Intelligence Aaai 2019 31st Innovative Applications of Artificial Intelligence Conference Iaai 2019 and the 9th Aaai Symposium on Educational Advances in Artificial Intelligence Eaai 2019 · January 1, 2019 Large, labeled datasets have driven deep learning methods to achieve expert-level performance on a variety of medical imaging tasks. We present CheXpert, a large dataset that contains 224,316 chest radiographs of 65,240 patients. We design a labeler to aut ... Full text Cite

Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists.

Journal article PLoS Med · November 2018 BACKGROUND: Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to ... Full text Link to item Cite

Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet.

Journal article PLoS Med · November 2018 BACKGROUND: Magnetic resonance imaging (MRI) of the knee is the preferred method for diagnosing knee injuries. However, interpretation of knee MRI is time-intensive and subject to diagnostic error and variability. An automated system for interpreting knee ... Full text Link to item Cite

Sex Differences in Cognitive Decline in Subjects with High Likelihood of Mild Cognitive Impairment due to Alzheimer's disease.

Journal article Sci Rep · May 10, 2018 Sex differences in Alzheimer's disease (AD) biology and progression are not yet fully characterized. The goal of this study is to examine the effect of sex on cognitive progression in subjects with high likelihood of mild cognitive impairment (MCI) due to ... Full text Link to item Cite

Intracranial pressure management

Book section · December 15, 2017 Full text Cite

Does Preoperative BMI Level Affect Outcomes of Bariatric Surgery?

Journal article Surgery for Obesity and Related Diseases · October 2017 Full text Cite

Does Preoperative Insulin Resistance Affect the Outcomes of Bariatric Surgery?

Journal article Surgery for Obesity and Related Diseases · October 2017 Full text Cite

Comorbidity Remission Following Intragastric Dual Balloon Placement

Journal article Surgery for Obesity and Related Diseases · October 2017 Full text Cite

Characterizing gene and protein crosstalks in subjects at risk of developing Alzheimer's disease: A new computational approach

Journal article Processes · September 1, 2017 Alzheimer's disease (AD) is a major public health threat; however, despite decades of research, the disease mechanisms are not completely understood, and there is a significant dearth of predictive biomarkers. The availability of systems biology approaches ... Full text Cite

Prevalence of Abnormal Laboratory Values Before and After Bariatric Surgery

Journal article Surgery for Obesity and Related Diseases · August 2016 Full text Cite

Educational attainment and hippocampal atrophy in the Alzheimer's disease neuroimaging initiative cohort.

Journal article J Neuroradiol · December 2014 INTRODUCTION: Subjects with higher cognitive reserve (CR) may be at a lower risk for Alzheimer's disease (AD), but the neural mechanisms underlying this are not known. Hippocampal volume loss is an early event in AD that triggers cognitive decline. MATERIA ... Full text Link to item Cite

Impact of ¹⁸F-florbetapir PET imaging of β-amyloid neuritic plaque density on clinical decision-making.

Journal article Neurocase · August 2014 ¹⁸F-florbetapir positron emission tomography (PET) imaging of the brain is now approved by the Food and Drug Administration (FDA) approved for estimation of β -amyloid neuritic plaque density when evaluating patients with cognitive impairment. However, its ... Full text Link to item Cite

Mapping the effects of ApoE4, age and cognitive status on 18F-florbetapir PET measured regional cortical patterns of beta-amyloid density and growth.

Journal article Neuroimage · September 2013 BACKGROUND: Although it is well known that many clinical and genetic factors have been associated with beta-amyloid deposition, few studies have examined the interactions of such factors across different stages of Alzheimer's pathogenesis. METHODS: We used ... Full text Link to item Cite

SPICE: discovery of phenotype-determining component interplays.

Journal article BMC Syst Biol · May 14, 2012 BACKGROUND: A latent behavior of a biological cell is complex. Deriving the underlying simplicity, or the fundamental rules governing this behavior has been the Holy Grail of systems biology. Data-driven prediction of the system components and their compon ... Full text Link to item Cite

NIBBS-search for fast and accurate prediction of phenotype-biased metabolic systems.

Journal article PLoS Comput Biol · 2012 Understanding of genotype-phenotype associations is important not only for furthering our knowledge on internal cellular processes, but also essential for providing the foundation necessary for genetic engineering of microorganisms for industrial use (e.g. ... Full text Link to item Cite