Objective erythema assessment of Psoriasis lesions for Psoriasis Area and Severity Index (PASI) evaluation

Banu, Simona Maria; Toacse, Gheorghe; Danciu, Gabriel

doi:10.1109/icepe.2014.6969867

Cited by 9 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 8 , 9 In addition, for automatic segmentation and severity scoring of a single psoriasis lesion, several attempts have been made to leverage traditional machine learning algorithms, both supervised and unsupervised. 10 , 11 , 12 , 13 , 14 , 15 , 16 More recently, deep learning‐based Convolutional Neural Networks (CNNs) have obtained state‐of‐the‐art results in computer vision problems including image classification and image segmentation. 17 Given the superior performance of these CNNs, some attempts for deep learning‐based automated severity scoring in psoriasis have been reported, 18 , 19 but these studies were based on the analysis of a single psoriasis plaque and only focused on one or a subset of severity scores (i.e.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image‐based automated Psoriasis Area Severity Index scoring by Convolutional Neural Networks

Schaap

Cardozo

Patel

et al. 2021

Acad Dermatol Venereol

View full text Add to dashboard Cite

Background The Psoriasis Area and Severity Index (PASI) score is commonly used in clinical practice and research to monitor disease severity and determine treatment efficacy. Automating the PASI score with deep learning algorithms, like Convolutional Neural Networks (CNNs), could enable objective and efficient PASI scoring. Objectives To assess the performance of image-based automated PASI scoring in anatomical regions by CNNs and compare the performance of CNNs to image-based scoring by physicians.Methods Imaging series were matched to PASI subscores determined in real life by the treating physician. CNNs were trained using standardized imaging series of 576 trunk, 614 arm and 541 leg regions. CNNs were separately trained for each PASI subscore (erythema, desquamation, induration and area) in each anatomical region (trunk, arms and legs). The head region was excluded for anonymity. Additionally, PASI-trained physicians retrospectively determined imagebased subscores on the test set images of the trunk. Agreement with the real-life scores was determined with the intraclass correlation coefficient (ICC) and compared between the CNNs and physicians.Results Intraclass correlation coefficients between the CNN and real-life scores of the trunk region were 0.616, 0.580, 0.580 and 0.793 for erythema, desquamation, induration and area, respectively, with similar results for the arms and legs region. PASI-trained physicians (N = 5) were in moderate-good agreement (ICCs 0.706-0.793) with each other for image-based PASI scoring of the trunk region. ICCs between the CNN and real-life scores were slightly higher for erythema (0.616 vs. 0.558), induration (0.580 vs. 0.573) and area scoring (0.793 vs. 0.694) than image-based scoring by physicians. Physicians slightly outperformed the CNN on desquamation scoring (0.580 vs. 0.589).Conclusions Convolutional Neural Networks have the potential to automatically and objectively perform image-based PASI scoring at an anatomical region level. For erythema, desquamation and induration scoring, CNNs performed similar to physicians, while for area scoring CNNs outperformed physicians on image-based PASI scoring.

show abstract

Section: Introductionmentioning

confidence: 99%

“…erythema, induration, desquamation or area). 11 , 12 , 13 , 15 , 16 , 18 , 19 Since the PASI score is decomposed into four subscores at an anatomical region level, lesion level analysis is inadequate for PASI scoring.…”

Section: Introductionmentioning

confidence: 99%