Identifying Pediatric Vascular Anomalies With Deep Learning

TL;DR

This study developed a CNN-based tool that classifies pediatric vascular anomalies from images, significantly improving diagnostic accuracy and operating in real-time on smartphones, aiding physicians especially in resource-limited settings.

Contribution

The paper presents a novel CNN model trained on a large dataset to accurately classify pediatric vascular anomalies and skin conditions, enhancing diagnostic support for clinicians.

Findings

CNN achieved an average AUC of 0.9731 across 12 classes.

Classifier increased pediatricians' diagnostic accuracy from 73.10% to 91.67%.

Runs in real-time on smartphones, aiding diagnosis in resource-limited areas.

Abstract

Vascular anomalies, more colloquially known as birthmarks, affect up to 1 in 10 infants. Though many of these lesions self-resolve, some types can result in medical complications or disfigurement without proper diagnosis or management. Accurately diagnosing vascular anomalies is challenging for pediatricians and primary care physicians due to subtle visual differences and similarity to other pediatric dermatologic conditions. This can result in delayed or incorrect referrals for treatment. To address this problem, we developed a convolutional neural network (CNN) to automatically classify images of vascular anomalies and other pediatric skin conditions to aid physicians with diagnosis. We constructed a dataset of 21,681 clinical images, including data collected between 2002-2018 at Seattle Children's hospital as well as five dermatologist-curated online repositories, and built a taxonomy over vascular anomalies and other common pediatric skin lesions. The CNN achieved an average AUC of 0.9731 when ten-fold cross-validation was performed across a taxonomy of 12 classes. The classifier's average AUC and weighted F1 score was 0.9889 and 0.9732 respectively when evaluated on a previously unseen test set of six of these classes. Further, when used as an aid by pediatricians (n = 7), the classifier increased their average visual diagnostic accuracy from 73.10% to 91.67%. The classifier runs in real-time on a smartphone and has the potential to improve diagnosis of these conditions, particularly in resource-limited areas.