BACKGROUND
Breastfeeding benefits both mother and infant and is a topic of attention in public health. After childbirth, untreated medical conditions or lack of support lead many mothers to discontinue breastfeeding. For instance, nipple damage and mastitis affect 80% and 20% of US mothers, respectively. Lactation Consultants (LCs) help mothers with breastfeeding, providing in-person, remote, and hybrid lactation support. LCs guide, encourage and find ways for mothers to have a better experience breastfeeding. Current telehealth services help mothers seek LCs for breastfeeding support, where images help them identify and address many issues. Due to the disproportional ratio of LCs and mothers in need, these professionals are often overloaded and burned out.
OBJECTIVE
We investigate the effectiveness of a convolution neural network (CNN) in detecting healthy lactating breasts and six breastfeeding-related issues by only using red, green, and blue (RGB) images. Our goal is to assess the applicability of this algorithm as an auxiliary resource for LCs to manage their time more effectively, respond promptly to patient needs, and enhance the overall experience and care for breastfeeding mothers.
METHODS
We evaluate the potential for a classification model to detect breastfeeding-related conditions using 1,000 breast and nipple images gathered from online and physical educational resources. We used the CNN VGG-16 to classify the images across seven classes: healthy, abscess, mastitis, nipple blebs, dermatosis, engorgement, and nipple damage by improper feeding or misuse of breast pumps. We also present an analysis of the classification challenges, identifying image traits that may confound the detection model.
RESULTS
The model achieves an area under the ROC curve (AUC) above 0.93 and 90% accuracy in the multi-class classification of specific breastfeeding-related conditions. Several factors contributed to the misclassification of images, including (1) similar visual features in the conditions that precede other conditions (such as the mastitis spectrum disorder), (2) partially covered breasts and/or nipples, and (3) images depicting multiple conditions in the same breast.
CONCLUSIONS
This vision-based automated detection technique offers an opportunity to enhance postpartum care for mothers and can potentially help alleviate the workload of LCs by expediting decision-making processes.