An EfficientNet-based modified sigmoid transform for enhancing dermatological macro-images of melanoma and nevi skin lesions.

Humans Image Processing, Computer-Assisted / methods Melanoma / diagnostic imaging Neural Networks, Computer Nevus Skin Diseases Skin Neoplasms / diagnostic imaging
Convolutional neural network Deep learning Image enhancement Macro-images Sigmoid transform Skin lesions

Journal

Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513

Informations de publication

Date de publication:
Jul 2022
Historique:
received: 15 02 2022
revised: 28 04 2022
accepted: 03 06 2022
pubmed: 21 6 2022
medline: 7 7 2022
entrez: 20 6 2022
Statut: ppublish

Résumé

During the initial stages, skin lesions may not have sufficient intensity difference or contrast from the background region on dermatological macro-images. The lack of proper light exposure at the time of capturing the image also reduces the contrast. Low contrast between lesion and background regions adversely impacts segmentation. Enhancement techniques for improving the contrast between lesion and background skin on dermatological macro-images are limited in the literature. An EfficientNet-based modified sigmoid transform for enhancing the contrast on dermatological macro-images is proposed to address this issue. A modified sigmoid transform is applied in the HSV color space. The crossover point in the modified sigmoid transform that divides the macro-image into lesion and background is predicted using a modified EfficientNet regressor to exclude manual intervention and subjectivity. The Modified EfficientNet regressor is constructed by replacing the classifier layer in the conventional EfficientNet with a regression layer. Transfer learning is employed to reduce the training time and size of the dataset required to train the modified EfficientNet regressor. For training the modified EfficientNet regressor, a set of value components extracted from the HSV color space representation of the macro-images in the training dataset is fed as input. The corresponding set of ideal crossover points at which the values of Dice similarity coefficient (DSC) between the ground-truth images and the segmented output images obtained from Otsu's thresholding are maximum, is defined as the target. On images enhanced with the proposed framework, the DSC of segmented results obtained by Otsu's thresholding increased from 0.68 ± 0.34 to 0.81 ± 0.17. The proposed algorithm could consistently improve the contrast between lesion and background on a comprehensive set of test images, justifying its applications in automated analysis of dermatological macro-images.

Sections du résumé

BACKGROUND AND OBJECTIVE OBJECTIVE
During the initial stages, skin lesions may not have sufficient intensity difference or contrast from the background region on dermatological macro-images. The lack of proper light exposure at the time of capturing the image also reduces the contrast. Low contrast between lesion and background regions adversely impacts segmentation. Enhancement techniques for improving the contrast between lesion and background skin on dermatological macro-images are limited in the literature. An EfficientNet-based modified sigmoid transform for enhancing the contrast on dermatological macro-images is proposed to address this issue.
METHODS METHODS
A modified sigmoid transform is applied in the HSV color space. The crossover point in the modified sigmoid transform that divides the macro-image into lesion and background is predicted using a modified EfficientNet regressor to exclude manual intervention and subjectivity. The Modified EfficientNet regressor is constructed by replacing the classifier layer in the conventional EfficientNet with a regression layer. Transfer learning is employed to reduce the training time and size of the dataset required to train the modified EfficientNet regressor. For training the modified EfficientNet regressor, a set of value components extracted from the HSV color space representation of the macro-images in the training dataset is fed as input. The corresponding set of ideal crossover points at which the values of Dice similarity coefficient (DSC) between the ground-truth images and the segmented output images obtained from Otsu's thresholding are maximum, is defined as the target.
RESULTS RESULTS
On images enhanced with the proposed framework, the DSC of segmented results obtained by Otsu's thresholding increased from 0.68 ± 0.34 to 0.81 ± 0.17.
CONCLUSIONS CONCLUSIONS
The proposed algorithm could consistently improve the contrast between lesion and background on a comprehensive set of test images, justifying its applications in automated analysis of dermatological macro-images.

Identifiants

DOI: 10.1016/j.cmpb.2022.106935 PMID: 35724474
pubmed: 35724474
pii: S0169-2607(22)00317-0
doi: 10.1016/j.cmpb.2022.106935
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

106935

Informations de copyright

Copyright © 2022. Published by Elsevier B.V.

Déclaration de conflit d'intérêts

Declaration of Competing Interest Authors declare that they have no conflict of interest.

Auteurs

Vipin Venugopal (V)

Department of Electronics and Communication Engineering, National Institute of Technology Puducherry, Karaikal, Puducherry 609609, India. Electronic address: vipinscms@gmail.com.

Justin Joseph (J)

School of Bioengineering, VIT Bhopal University, Sehore, Madhya Pradesh 466114, India. Electronic address: josephjusti@gmail.com.

M Vipin Das (M)

Department of Dermatology, Kerala Health Services, Trivandrum, Kerala 695035, India. Electronic address: vipindasm144@gmail.com.

Malaya Kumar Nath (M)

Department of Electronics and Communication Engineering, National Institute of Technology Puducherry, Karaikal, Puducherry 609609, India. Electronic address: malaya.nath@nitpy.ac.in.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female

Evaluation of Low-Value Services Across Major Medicare Advantage Insurers and Traditional Medicare.

Ciara Duggan, Adam L Beckman, Ishani Ganguli et al.
1.00
Humans United States Aged Cross-Sectional Studies Medicare Part C

Effectiveness of Virtual Yoga for Chronic Low Back Pain: A Randomized Clinical Trial.

Hallie Tankha, Devyn Gaskins, Amanda Shallcross et al.
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH

questionsmedicales.fr › Eucaryotes › Animaux › Chordés › Vertébrés › Mammifères › Eutheria › Primates › Haplorhini › Catarrhini › Hominidae › Humains › An EfficientNet-based modified sigmoid...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Traitement d'image par ordinateur › An EfficientNet-based modified sigmoid...
questionsmedicales.fr › Tumeurs › Tumeurs par type histologique › Naevus et mélanomes › Mélanome › An EfficientNet-based modified sigmoid...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Réseaux neuronaux (ordinateur) › An EfficientNet-based modified sigmoid...
questionsmedicales.fr › Tumeurs › Tumeurs par type histologique › Naevus et mélanomes › Naevus › An EfficientNet-based modified sigmoid...
questionsmedicales.fr › Maladies de la peau et du tissu conjonctif › Maladies de la peau › An EfficientNet-based modified sigmoid...
questionsmedicales.fr › Maladies de la peau et du tissu conjonctif › Maladies de la peau › Tumeurs cutanées › An EfficientNet-based modified sigmoid...