Federated Learning for Masked Psoriasis Severity Classification

Moon, Cho-I; Lee, Jiwon; Kye, Seula; Baek, Yoo Sang; Lee, Onseok

doi:10.1109/sensors52175.2022.9967333

Cited by 2 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We aggregated the two evaluation scores into five groups to construct the dataset. The five groups consisted of healthy (0 points), mild (1–2 points), moderate (3–4 points), severe (5–6 points), and very severe (7–8 points) cases 29 . The dataset obtained from clinical sources encompasses a total of 829 images, with 656 allocated for training and 173 reserved for testing.…”

Section: Methodsmentioning

confidence: 99%

“…The five groups consisted of healthy (0 points), mild (1–2 points), moderate (3–4 points), severe (5–6 points), and very severe (7–8 points) cases. 29 The dataset obtained from clinical sources encompasses a total of 829 images, with 656 allocated for training and 173 reserved for testing. The augmented dataset consists of a total of 6632 images, with 5248 allocated for training and 1384 reserved for testing.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Parameter‐based transfer learning for severity classification of atopic dermatitis using hyperspectral imaging

Kim,

Baek,

Lee

2024

Skin Research and Technology

Self Cite

View full text Add to dashboard Cite

Background/purposeBecause atopic dermatitis (AD) is a chronic inflammatory skin condition that causes structural changes, there is a growing need for noninvasive research methods to evaluate this condition. Hyperspectral imaging (HSI) captures skin structure features by exploiting light wavelength variations in penetration depth. In this study, parameter‐based transfer learning was deployed to classify the severity of AD using HSI. Therefore, we aimed to obtain an optimal combination of classification results from the four models after constructing different source‐ and target‐domain datasets.MethodsWe designated psoriasis, skin cancer, eczema, and AD datasets as the source datasets, and the set of images acquired via hyperspectral camera as the target dataset for wavelength‐specific AD classification. We compared the severity classification performances of 96 combinations of sources, models, and targets.ResultsThe highest classification performance of 83% was achieved when ResNet50 was trained on the augmented psoriasis dataset as the source, with the resulting parameters used to train the model on the target Near‐infrared radiation (NIR) dataset. The second highest classification accuracy of 81% was achieved when ResNet50 was trained on the unaugmented psoriasis dataset as the source, with the resulting parameters used to train the model on the target R dataset. ResNet50 demonstrated potential as a generalized model for both the source and target data, also confirming that the psoriasis dataset is an effective training resource.ConclusionThe present study not only demonstrates the feasibility of the severity classification of AD based on hyperspectral images, but also showcases combinations and research scalability for domain exploration.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%