Machine learning classification of placental villous infarction, perivillous fibrin deposition, and intervillous thrombus
Placenta · 2023
DOI: 10.1016/j.placenta.2023.03.003 ↗Kurz gefasst
Fachartikel in der Zeitschrift Placenta, 2023. Verfasst von Jeffery A Goldstein und 3 weiteren Autor:innen. Beteiligte Einrichtung: Northwestern University, Department of Pathology, Chicago, IL, USA. Electronic address: ja.goldstein@northwestern.edu. Hauptthemen laut MEDLINE: Placenta Diseases, Thrombosis. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIBIB NIH HHS, NLM NIH HHS, NCI NIH HHS.
Abstract (Originalsprache)
INTRODUCTION: Placental parenchymal lesions are commonly encountered and carry significant clinical associations. However, they are frequently missed or misclassified by general practice pathologists. Interpretation of pathology slides has emerged as one of the most successful applications of machine learning (ML) in medicine with applications ranging from cancer detection and prognostication to transplant medicine. The goal of this study was to use a whole-slide learning model to identify and classify placental parenchymal lesions including villous infarctions, intervillous thrombi (IVT), and perivillous fibrin deposition (PVFD). METHODS: We generated whole slide images from placental discs examined at our institution with infarct, IVT, PVFD, or no macroscopic lesion. Slides were analyzed as a set of overlapping patches. We extracted feature vectors from each patch using a pretrained convolutional neural network (EfficientNetV2L). We trained a model to assign attention to each vector and used the attentions as weights to produce a pooled feature vector. The pooled vector was classified as normal or 1 of 3 lesions using a fully connected network. Patch attention was plotted to highlight informative areas of the slide. RESULTS: Overall balanced accuracy in a test set of held-out slides was 0.86 with receiver-operator characteristic areas under the curve of 0.917-0.993. Cases of PVFD were frequently miscalled as normal or infarcts, the latter possibly due to the perivillous fibrin found at the periphery of infarctions. We used attention maps to further understand some errors, including one most likely due to poor tissue fixation and processing. DISCUSSION: We used a whole-slide learning paradigm to train models to recognize three of the most common placental parenchymal lesions. We used attention maps to gain insight into model function, which differed from intuitive explanations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Northwestern University, Department of Pathology, Chicago, IL, USA. Electronic address: ja.goldstein@northwestern.edu.
- Northwestern University, Department of Pathology, Chicago, IL, USA.
- Northwestern University, Department of Pathology, Chicago, IL, USA; Northwestern University, McCormick School of Engineering, Evanston, IL, USA.
Förderung
- NIBIB NIH HHS
- NLM NIH HHS
- NCI NIH HHS
- NCATS NIH HHS
- National Institutes of Health
Zitieren
APA
Goldstein, J. A., Nateghi, R., Irmakci, I., & Cooper, L. A. D. (2023). Machine learning classification of placental villous infarction, perivillous fibrin deposition, and intervillous thrombus. Placenta. https://doi.org/10.1016/j.placenta.2023.03.003
Vancouver
Goldstein JA, Nateghi R, Irmakci I, Cooper LAD. Machine learning classification of placental villous infarction, perivillous fibrin deposition, and intervillous thrombus. Placenta. 2023. doi:10.1016/j.placenta.2023.03.003
BibTeX
@article{Goldstein2023,
author = {Goldstein, Jeffery A and Nateghi, Ramin and Irmakci, Ismail and Cooper, Lee A D},
title = {Machine learning classification of placental villous infarction, perivillous fibrin deposition, and intervillous thrombus},
journal = {Placenta},
year = {2023},
doi = {10.1016/j.placenta.2023.03.003}
}
EUVIMED