Aileen O'Shea

Dr. Aileen O'Shea


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2020 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
MLMatthew D. Li
Matthew D. Li
NANishaeminth Thumbavanam Arun
Nishaeminth Thumbavanam Arun
MGMishka Gidwani
Mishka Gidwani
KCKen Chang
Ken Chang
FDFrancis Deng
Francis Deng
JKJayashree Kalpathy-Cramer
Jayashree Kalpathy-Cramer
Purpose To develop an automated measure of COVID-19 pulmonary disease severity on chest radiographs (CXRs), for longitudinal disease tracking and outcome prediction. Materials and Methods A convolu...

21 May 2022 in Magnetic Resonance Materials in Physics, Biology and Medicine
Verified
Journal Article
Closed access
PDF file
AOAileen O'Shea
Aileen O'Shea
MHMukesh Harisinghani
Mukesh Harisinghani

1 January 2022 in RadioGraphics
Verified
Journal Article
Closed access
GFGabrielle Figueiredo
Gabrielle Figueiredo
AOAileen O'Shea
Aileen O'Shea
GNGrace Mary Neville
Grace Mary Neville
SLSusanna I Lee
Susanna I Lee
Key imaging and clinical features of pelvic mesenchymal tumors enable the radiologist to diagnose a tumor as originating from the mesenchymal tissues of the pelvis and narrow the differential diagn... Most pelvic tumors originate from the organs. Less commonly, tumors can arise from the various anatomic pelvic compartments and are comprised of mesenchymal tissue: muscles, connective tissue, vess... Created with BioRender.com

1 May 2020 in Seminars in Reproductive Medicine
Verified
Journal Article
Closed access
PDF file
AOAileen O'Shea
Aileen O'Shea
GFGabrielle Figueiredo
Gabrielle Figueiredo
SLSusanna I. Lee
Susanna I. Lee
Uterine adenomyosis can be diagnosed on ultrasonography (US) and magnetic resonance imaging (MRI) with a high degree of accuracy. Adenomyosis is a myometrial process that can appear as diffuse or focal on imaging. Diffuse adenomyosis typically causes uterine enlargement, while focal adenomyosis can mimic other myometrial lesions, such as leiomyomas. Imaging features frequently seen on US include a heterogenous thickened myometrium and myometrial cysts. On MRI, widening of the junctional zone, whether focal or diffuse, and the presence of myometrial cysts, either simple or hemorrhagic, support the diagnosis of adenomyosis. Despite these characteristic imaging appearances, there are several gynecologic pathologies which can mimic adenomyosis and it is important to be vigilant of these when interpreting cross-sectional imaging exams. The decision to evaluate patients with US or MRI is contingent on multiple factors, including availability of the necessary technology and expertise for the latter. However, MRI appears to offer greater specificity and positive predictive value for the diagnosis of adenomyosis.

31 October 2019 in Abdominal Radiology
Verified
Journal Article
Closed access
PDF file
AOAileen O'Shea
Aileen O'Shea
AKAoife Kilcoyne
Aoife Kilcoyne
SHSandeep S. Hedgire
Sandeep S. Hedgire
MHMukesh G. Harisinghani
Mukesh G. Harisinghani

26 May 2020 in medRxiv
Verified
Preprint
Open access
PDF file
MLMatthew D. Li
Matthew D. Li
NANishanth Thumbavanam Arun
Nishanth Thumbavanam Arun
MGMishka Gidwani
Mishka Gidwani
KCKen Chang
Ken Chang
FDFrancis Deng
Francis Deng
JKJayashree Kalpathy-Cramer
Jayashree Kalpathy-Cramer
Purpose: To develop an automated measure of COVID-19 pulmonary disease severity on chest radiographs (CXRs), for longitudinal disease evaluation and clinical risk stratification. Materials and Methods: A convolutional Siamese neural network-based algorithm was trained to output a measure of pulmonary disease severity on anterior-posterior CXRs (pulmonary x-ray severity (PXS) score), using weakly-supervised pretraining on ~160,000 images from CheXpert and transfer learning on 314 CXRs from patients with COVID-19. The algorithm was evaluated on internal and external test sets from different hospitals, containing 154 and 113 CXRs respectively. The PXS score was correlated with a radiographic severity score independently assigned by two thoracic radiologists and one in-training radiologist. For 92 internal test set patients with follow-up CXRs, the change in PXS score was compared to radiologist assessments of change. The association between PXS score and subsequent intubation or death was assessed. Results: The PXS score correlated with the radiographic pulmonary disease severity score assigned to CXRs in the COVID-19 internal and external test sets (ρ=0.84 and ρ=0.78 respectively). The direction of change in PXS score in follow-up CXRs agreed with radiologist assessment (ρ=0.74). In patients not intubated on the admission CXR, the PXS score predicted subsequent intubation or death within three days of hospital admission (area under the receiver operator characteristic curve=0.80 (95%CI 0.75-0.85)). Conclusion: A Siamese neural network-based severity score automatically measures COVID-19 pulmonary disease severity in chest radiographs, which can be scaled and rapidly deployed for clinical triage and workflow optimization. SUMMARY: A convolutional Siamese neural network-based algorithm can calculate a continuous radiographic pulmonary disease severity score in COVID-19 patients, which can be used for longitudinal disease evaluation and clinical risk stratification. KEY RESULTS: A Siamese neural network-based severity score correlates with radiologist-annotated pulmonary disease severity on chest radiographs from patients with COVID-19 (ρ=0.84 and ρ=0.78 in internal and external test sets respectively). The direction of change in the severity score in follow-up radiographs is concordant with radiologist assessment (ρ=0.74). The admission chest radiograph severity score can help predict subsequent intubation or death within three days of admission (receiver operator characteristic area under the curve=0.80).