Advancement and independent validation of a deep learning-based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity index
ObjectiveTo improve and validate a convolutional neural network (CNN)-based model for the automated scoring of nail psoriasis severity using the modified Nail Psoriasis Severity Index (mNAPSI) with adequate accuracy across all severity classes and without dependency on standardized conditions.Method...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-04-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2025.1574413/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849471403428937728 |
|---|---|
| author | Stephan Kemenes Stephan Kemenes Liu Chang Maja Schlereth Rita Noversa de Sousa Rita Noversa de Sousa Ioanna Minopoulou Pauline Fenzl Pauline Fenzl Giulia Corte Giulia Corte Melek Yalcin Mutlu Melek Yalcin Mutlu Michael Wolfgang Höner Michael Wolfgang Höner Ioannis Sagonas Ioannis Sagonas Birte Coppers Birte Coppers Anna-Maria Liphardt Anna-Maria Liphardt David Simon Arnd Kleyer Lukas Folle Michael Sticherling Michael Sticherling Georg Schett Georg Schett Andreas Maier Filippo Fagni Filippo Fagni |
| author_facet | Stephan Kemenes Stephan Kemenes Liu Chang Maja Schlereth Rita Noversa de Sousa Rita Noversa de Sousa Ioanna Minopoulou Pauline Fenzl Pauline Fenzl Giulia Corte Giulia Corte Melek Yalcin Mutlu Melek Yalcin Mutlu Michael Wolfgang Höner Michael Wolfgang Höner Ioannis Sagonas Ioannis Sagonas Birte Coppers Birte Coppers Anna-Maria Liphardt Anna-Maria Liphardt David Simon Arnd Kleyer Lukas Folle Michael Sticherling Michael Sticherling Georg Schett Georg Schett Andreas Maier Filippo Fagni Filippo Fagni |
| author_sort | Stephan Kemenes |
| collection | DOAJ |
| description | ObjectiveTo improve and validate a convolutional neural network (CNN)-based model for the automated scoring of nail psoriasis severity using the modified Nail Psoriasis Severity Index (mNAPSI) with adequate accuracy across all severity classes and without dependency on standardized conditions.MethodsPatients with psoriasis (PsO), psoriatic arthritis (PsA), and non-psoriatic controls including healthy individuals and patients with rheumatoid arthritis were included for training, while validation utilized an independent cohort of psoriatic patients. Nail photographs were pre-processed and segmented and mNAPSI scores were annotated by five expert readers. A CNN based on Bidirectional Encoder representation from Image Transformers (BEiT) architecture and pre-trained on ImageNet-22k was fine-tuned for mNAPSI classification. Model performance was compared with human annotations by using area under the receiver operating characteristic curve (AUROC) and other metrics. A reader study was performed to assess inter-rater variability.ResultsIn total, 460 patients providing 4,400 nail photographs were included in the training dataset. The independent validation dataset included 118 further patients who provided 929 nail photographs. The CNN demonstrated high classification performance on the training dataset, achieving mean (SD) AUROC of 86% ± 7% across mNAPSI classes. Performance remained robust on the independent validation dataset, with a mean AUROC of 80% ± 9%, despite variability in imaging conditions. Compared with human annotation, the CNN achieved a Pearson correlation of 0.94 on a patient-level, which remained consistent in the validation dataset.ConclusionWe developed and validated a CNN that enables the automated, objective scoring of nail psoriasis severity based on mNAPSI with high reliability and without need of image standardization. This approach has potential clinical utility for enabling a standardized time-efficient assessment of nail involvement in the psoriatic disease and possibly as a self-reporting tool. |
| format | Article |
| id | doaj-art-04e1f1502c9f447dabc7bd08e95e2b53 |
| institution | Kabale University |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-04e1f1502c9f447dabc7bd08e95e2b532025-08-20T03:24:51ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-04-011210.3389/fmed.2025.15744131574413Advancement and independent validation of a deep learning-based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity indexStephan Kemenes0Stephan Kemenes1Liu Chang2Maja Schlereth3Rita Noversa de Sousa4Rita Noversa de Sousa5Ioanna Minopoulou6Pauline Fenzl7Pauline Fenzl8Giulia Corte9Giulia Corte10Melek Yalcin Mutlu11Melek Yalcin Mutlu12Michael Wolfgang Höner13Michael Wolfgang Höner14Ioannis Sagonas15Ioannis Sagonas16Birte Coppers17Birte Coppers18Anna-Maria Liphardt19Anna-Maria Liphardt20David Simon21Arnd Kleyer22Lukas Folle23Michael Sticherling24Michael Sticherling25Georg Schett26Georg Schett27Andreas Maier28Filippo Fagni29Filippo Fagni30Department of Dermatology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyPattern Recognition Lab, Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, GermanyDepartment Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Internal Medicine 3 – Rheumatology and Immunology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Rheumatology and Clinical Immunology, Charité – Universitätsmedizin Berlin, Berlin, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Internal Medicine 3 – Rheumatology and Immunology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Internal Medicine 3 – Rheumatology and Immunology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Internal Medicine 3 – Rheumatology and Immunology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Dermatology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Dermatology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Internal Medicine 3 – Rheumatology and Immunology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Internal Medicine 3 – Rheumatology and Immunology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Rheumatology and Clinical Immunology, Charité – Universitätsmedizin Berlin, Berlin, GermanyDepartment of Rheumatology and Clinical Immunology, Charité – Universitätsmedizin Berlin, Berlin, GermanyPattern Recognition Lab, Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, GermanyDepartment of Dermatology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Internal Medicine 3 – Rheumatology and Immunology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyPattern Recognition Lab, Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, GermanyDeutsches Zentrum Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyDepartment of Internal Medicine 3 – Rheumatology and Immunology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, GermanyObjectiveTo improve and validate a convolutional neural network (CNN)-based model for the automated scoring of nail psoriasis severity using the modified Nail Psoriasis Severity Index (mNAPSI) with adequate accuracy across all severity classes and without dependency on standardized conditions.MethodsPatients with psoriasis (PsO), psoriatic arthritis (PsA), and non-psoriatic controls including healthy individuals and patients with rheumatoid arthritis were included for training, while validation utilized an independent cohort of psoriatic patients. Nail photographs were pre-processed and segmented and mNAPSI scores were annotated by five expert readers. A CNN based on Bidirectional Encoder representation from Image Transformers (BEiT) architecture and pre-trained on ImageNet-22k was fine-tuned for mNAPSI classification. Model performance was compared with human annotations by using area under the receiver operating characteristic curve (AUROC) and other metrics. A reader study was performed to assess inter-rater variability.ResultsIn total, 460 patients providing 4,400 nail photographs were included in the training dataset. The independent validation dataset included 118 further patients who provided 929 nail photographs. The CNN demonstrated high classification performance on the training dataset, achieving mean (SD) AUROC of 86% ± 7% across mNAPSI classes. Performance remained robust on the independent validation dataset, with a mean AUROC of 80% ± 9%, despite variability in imaging conditions. Compared with human annotation, the CNN achieved a Pearson correlation of 0.94 on a patient-level, which remained consistent in the validation dataset.ConclusionWe developed and validated a CNN that enables the automated, objective scoring of nail psoriasis severity based on mNAPSI with high reliability and without need of image standardization. This approach has potential clinical utility for enabling a standardized time-efficient assessment of nail involvement in the psoriatic disease and possibly as a self-reporting tool.https://www.frontiersin.org/articles/10.3389/fmed.2025.1574413/fullpsoriasispsoriatic arthritisnail diseaseNAPSIMNAPSIartificial intelligence |
| spellingShingle | Stephan Kemenes Stephan Kemenes Liu Chang Maja Schlereth Rita Noversa de Sousa Rita Noversa de Sousa Ioanna Minopoulou Pauline Fenzl Pauline Fenzl Giulia Corte Giulia Corte Melek Yalcin Mutlu Melek Yalcin Mutlu Michael Wolfgang Höner Michael Wolfgang Höner Ioannis Sagonas Ioannis Sagonas Birte Coppers Birte Coppers Anna-Maria Liphardt Anna-Maria Liphardt David Simon Arnd Kleyer Lukas Folle Michael Sticherling Michael Sticherling Georg Schett Georg Schett Andreas Maier Filippo Fagni Filippo Fagni Advancement and independent validation of a deep learning-based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity index Frontiers in Medicine psoriasis psoriatic arthritis nail disease NAPSI MNAPSI artificial intelligence |
| title | Advancement and independent validation of a deep learning-based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity index |
| title_full | Advancement and independent validation of a deep learning-based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity index |
| title_fullStr | Advancement and independent validation of a deep learning-based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity index |
| title_full_unstemmed | Advancement and independent validation of a deep learning-based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity index |
| title_short | Advancement and independent validation of a deep learning-based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity index |
| title_sort | advancement and independent validation of a deep learning based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity index |
| topic | psoriasis psoriatic arthritis nail disease NAPSI MNAPSI artificial intelligence |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2025.1574413/full |
| work_keys_str_mv | AT stephankemenes advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT stephankemenes advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT liuchang advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT majaschlereth advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT ritanoversadesousa advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT ritanoversadesousa advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT ioannaminopoulou advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT paulinefenzl advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT paulinefenzl advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT giuliacorte advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT giuliacorte advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT melekyalcinmutlu advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT melekyalcinmutlu advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT michaelwolfganghoner advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT michaelwolfganghoner advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT ioannissagonas advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT ioannissagonas advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT birtecoppers advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT birtecoppers advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT annamarialiphardt advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT annamarialiphardt advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT davidsimon advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT arndkleyer advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT lukasfolle advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT michaelsticherling advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT michaelsticherling advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT georgschett advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT georgschett advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT andreasmaier advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT filippofagni advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex AT filippofagni advancementandindependentvalidationofadeeplearningbasedtoolforautomatedscoringofnailpsoriasisseverityusingthemodifiednailpsoriasisseverityindex |