Improving Acne Image Grading with Label Distribution Smoothing
This work addresses the need for more reliable automated acne grading tools to assist dermatologists, though it appears incremental as it builds directly on existing label distribution learning approaches.
The paper tackled the problem of automated acne severity grading from images by addressing limitations in label distribution learning caused by varying lesion counts across severity grades. The result was improved performance on the ACNE04 benchmark dataset through a method combining label distribution learning with a novel label smoothing scheme.
Acne, a prevalent skin condition, necessitates precise severity assessment for effective treatment. Acne severity grading typically involves lesion counting and global assessment. However, manual grading suffers from variability and inefficiency, highlighting the need for automated tools. Recently, label distribution learning (LDL) was proposed as an effective framework for acne image grading, but its effectiveness is hindered by severity scales that assign varying numbers of lesions to different severity grades. Addressing these limitations, we proposed to incorporate severity scale information into lesion counting by combining LDL with label smoothing, and to decouple if from global assessment. A novel weighting scheme in our approach adjusts the degree of label smoothing based on the severity grading scale. This method helped to effectively manage label uncertainty without compromising class distinctiveness. Applied to the benchmark ACNE04 dataset, our model demonstrated improved performance in automated acne grading, showcasing its potential in enhancing acne diagnostics. The source code is publicly available at http://github.com/openface-io/acne-lds.