Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learning

Abstract Nailfold Capillaroscopy (NFC) is a simple, non-invasive diagnostic tool used to detect microvascular changes in nailfold. Chronic pathological changes associated with a wide range of systemic diseases, such as diabetes, cardiovascular disorders, and rheumatological conditions like systemic...

Full description

Saved in:
Bibliographic Details
Main Authors: Mona Ebadi Jalal, Omar S. Emam, Cristián Castillo-Olea, Begoña García-Zapirain, Adel Elmaghraby
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-85277-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832594793161555968
author Mona Ebadi Jalal
Omar S. Emam
Cristián Castillo-Olea
Begoña García-Zapirain
Adel Elmaghraby
author_facet Mona Ebadi Jalal
Omar S. Emam
Cristián Castillo-Olea
Begoña García-Zapirain
Adel Elmaghraby
author_sort Mona Ebadi Jalal
collection DOAJ
description Abstract Nailfold Capillaroscopy (NFC) is a simple, non-invasive diagnostic tool used to detect microvascular changes in nailfold. Chronic pathological changes associated with a wide range of systemic diseases, such as diabetes, cardiovascular disorders, and rheumatological conditions like systemic sclerosis, can manifest as observable microvascular changes in the terminal capillaries of nailfolds. The current gold standard relies on experts performing manual evaluations, which is an exhaustive time-intensive, and subjective process. In this study, we demonstrate the viability of a deep learning approach as an automated clinical screening tool. Our dataset consists of NFC images from a total of 225 participants, with normal images accounting for 6% of the dataset. This study introduces a robust framework utilizing cascade transfer learning based on EfficientNet-B0 to differentiate between normal and abnormal cases within NFC images. The results demonstrate that pre-trained EfficientNet-B0 on the ImageNet dataset, followed by transfer learning from domain-specific classes, significantly enhances the classifier’s performance in distinguishing between Normal and Abnormal classes. Our proposed model achieved superior performance, with accuracy, precision, recall, F1 score, and ROC_AUC of 1.00, significantly outperforming both models of single transfer learning on the pre-trained EfficientNet-B0 and cascade transfer learning on a convolutional neural network, which each attained an accuracy, precision, recall, and F1 score of 0.67 and a ROC_AUC of 0.83. The framework demonstrates the potential to facilitate early preventive measures and timely interventions that aim to improve healthcare delivery and patients’ quality of life.
format Article
id doaj-art-ca5465d4f08c451ab995e649200723d7
institution Kabale University
issn 2045-2322
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ca5465d4f08c451ab995e649200723d72025-01-19T12:20:18ZengNature PortfolioScientific Reports2045-23222025-01-0115111210.1038/s41598-025-85277-8Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learningMona Ebadi Jalal0Omar S. Emam1Cristián Castillo-Olea2Begoña García-Zapirain3Adel Elmaghraby4Hive AI Innovation Studio, Department of Computer Science and Engineering, University of LouisvilleHive AI Innovation Studio, Department of Computer Science and Engineering, University of LouisvilleLa Salle UniversityeVIDA Lab, University of DeustoHive AI Innovation Studio, Department of Computer Science and Engineering, University of LouisvilleAbstract Nailfold Capillaroscopy (NFC) is a simple, non-invasive diagnostic tool used to detect microvascular changes in nailfold. Chronic pathological changes associated with a wide range of systemic diseases, such as diabetes, cardiovascular disorders, and rheumatological conditions like systemic sclerosis, can manifest as observable microvascular changes in the terminal capillaries of nailfolds. The current gold standard relies on experts performing manual evaluations, which is an exhaustive time-intensive, and subjective process. In this study, we demonstrate the viability of a deep learning approach as an automated clinical screening tool. Our dataset consists of NFC images from a total of 225 participants, with normal images accounting for 6% of the dataset. This study introduces a robust framework utilizing cascade transfer learning based on EfficientNet-B0 to differentiate between normal and abnormal cases within NFC images. The results demonstrate that pre-trained EfficientNet-B0 on the ImageNet dataset, followed by transfer learning from domain-specific classes, significantly enhances the classifier’s performance in distinguishing between Normal and Abnormal classes. Our proposed model achieved superior performance, with accuracy, precision, recall, F1 score, and ROC_AUC of 1.00, significantly outperforming both models of single transfer learning on the pre-trained EfficientNet-B0 and cascade transfer learning on a convolutional neural network, which each attained an accuracy, precision, recall, and F1 score of 0.67 and a ROC_AUC of 0.83. The framework demonstrates the potential to facilitate early preventive measures and timely interventions that aim to improve healthcare delivery and patients’ quality of life.https://doi.org/10.1038/s41598-025-85277-8Nailfold capillaroscopyAbnormality detectionClassificationTransfer learningDeep learning
spellingShingle Mona Ebadi Jalal
Omar S. Emam
Cristián Castillo-Olea
Begoña García-Zapirain
Adel Elmaghraby
Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learning
Scientific Reports
Nailfold capillaroscopy
Abnormality detection
Classification
Transfer learning
Deep learning
title Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learning
title_full Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learning
title_fullStr Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learning
title_full_unstemmed Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learning
title_short Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learning
title_sort abnormality detection in nailfold capillary images using deep learning with efficientnet and cascade transfer learning
topic Nailfold capillaroscopy
Abnormality detection
Classification
Transfer learning
Deep learning
url https://doi.org/10.1038/s41598-025-85277-8
work_keys_str_mv AT monaebadijalal abnormalitydetectioninnailfoldcapillaryimagesusingdeeplearningwithefficientnetandcascadetransferlearning
AT omarsemam abnormalitydetectioninnailfoldcapillaryimagesusingdeeplearningwithefficientnetandcascadetransferlearning
AT cristiancastilloolea abnormalitydetectioninnailfoldcapillaryimagesusingdeeplearningwithefficientnetandcascadetransferlearning
AT begonagarciazapirain abnormalitydetectioninnailfoldcapillaryimagesusingdeeplearningwithefficientnetandcascadetransferlearning
AT adelelmaghraby abnormalitydetectioninnailfoldcapillaryimagesusingdeeplearningwithefficientnetandcascadetransferlearning