What is it about?
Breastfeeding complications affect women worldwide, where 20% of mothers being expected to suffer with mastitis spectrum conditions and 80% expected to suffer with nipple pain and lesions. This work uses convolutional neural networks to automatically classify breast images among seven conditions: abscess, engorgement, dermatoses, mastitis, nipple blebs, nipple lesions, and healthy. The paper shows algorithm implementation, validation and metrics.
Featured Image
Photo by Ayla Meinberg on Unsplash
Why is it important?
This vision-based automated detection technique offers an opportunity to enhance postpartum care for mothers. It can help alleviate the workload of LCs by expediting decision-making processes through AI-based triage using images.
Perspectives
This work uniquely shows how AI can be used to address critical inequities in lactation care access and outcomes by helping providers identify and triage lesions using deep-learning.
Jessica de Souza
University of California San Diego
Read the Original
This page is a summary of: Augmenting Telepostpartum Care With Vision-Based Detection of Breastfeeding-Related Conditions: Algorithm Development and Validation, JMIR AI, June 2024, JMIR Publications Inc.,
DOI: 10.2196/54798.
You can read the full text:
Contributors
The following have contributed to this page
