Pre-trained CNN Based Deep Features with Hand-Crafted Features and Patient Data for Skin Lesion Classification

Yayilgan, Sule Yildirim; Arifaj, Blend; Rahimpour, Masoomeh; Hardeberg, Jon Yngve; Ahmedi, Lule

doi:10.1007/978-3-030-71711-7_13

Cited by 5 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have indicated that embeddings extracted from deep convolutional neural networks (CNNs) are powerful for various visual recognition tasks [ 35 , 36 , 37 ]. Their outstanding performance as image representation learners grew the trend of utilizing them as optimized feature generators for skin lesion classification [ 38 , 39 , 40 , 41 , 42 , 43 ]. Our work, aligned with previous research evidence, explores the efficiency of the pretrained CNN, namely the VGG16 [ 44 ] as the starting point, for the generation of image embeddings in order to discriminate between cases of atypical MM and atypical SK.…”

Section: Methodsmentioning

confidence: 99%

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer

Spyridonos

Gaitanis

Likas

et al. 2021

Cancers

View full text Add to dashboard Cite

Malignant melanomas resembling seborrheic keratosis (SK-like MMs) are atypical, challenging to diagnose melanoma cases that carry the risk of delayed diagnosis and inadequate treatment. On the other hand, SK may mimic melanoma, producing a ‘false positive’ with unnecessary lesion excisions. The present study proposes a computer-based approach using dermoscopy images for the characterization of SΚ-like MMs. Dermoscopic images were retrieved from the International Skin Imaging Collaboration archive. Exploiting image embeddings from pretrained convolutional network VGG16, we trained a support vector machine (SVM) classification model on a data set of 667 images. SVM optimal hyperparameter selection was carried out using the Bayesian optimization method. The classifier was tested on an independent data set of 311 images with atypical appearance: MMs had an absence of pigmented network and had an existence of milia-like cysts. SK lacked milia-like cysts and had a pigmented network. Atypical MMs were characterized with a sensitivity and specificity of 78.6% and 84.5%, respectively. The advent of deep learning in image recognition has attracted the interest of computer science towards improved skin lesion diagnosis. Open-source, public access archives of skin images empower further the implementation and validation of computer-based systems that might contribute significantly to complex clinical diagnostic problems such as the characterization of SK-like MMs.

show abstract

Section: Methodsmentioning

confidence: 99%

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer

Spyridonos

Gaitanis

Likas

et al. 2021

Cancers

View full text Add to dashboard Cite

show abstract

“…The effectiveness of automated techniques for skin lesion detection depends on the selection of relevant descriptive characteristics extracted from dermoscopy images [34].…”

Section: Image Feature Extractionmentioning

confidence: 99%

A multimodal and interpretable-based approach for improving melanoma detection using dermoscopy images

Gómez-Martínez,

Chushig-Muzo,

Veierød

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: The global incidence of skin cancers, particularly melanoma, the deadliest among them, has risen in recent decades. Artificial Intelligence (AI) has yielded remarkable results across diverse domains including healthcare. However, most AI models for skin cancer prediction primarily focus on a single data type or modality, such as images. Emerging research highlights the potential of multimodal approaches to enhance predictive performance and interpretability in clinical tasks. Methods: In this work, the effectiveness of multimodal fusion methods —including early and late fusion— for the detection of melanoma is assessed. Three public skin image datasets (ISIC, PH2, and Derm7pt) were considered, and two types of modalities were used, including dermoscopy images and tabular data comprising metadata, image features, and image embeddings. This study employed AI-based image classification and extended feature extraction to capture the color and texture characteristics of skin lesions, aiming to discover factors related to melanoma. Results: Experimental findings reveal that the proposed multimodal fusion methods outperform single-modality models. Early fusion methods achieve the highest classification results, with an overall AUCROC of 0.873, 0.963, and 0.857 for ISIC, PH2, and Derm7pt, respectively. Compared with models trained with single-modality data, fusion approaches exhibited notable improvements of 6.67% (ISIC), 8.27% (Derm7pt), and 7% (PH2) in AUCROC. Two post-hoc techniques were used for detecting salient regions in dermoscopy images and identifying the most relevant image features for melanoma diagnosis. Conclusions: These results hold promise for early skin lesion detection, contributing valuable support to dermatologists in their daily practice.

show abstract

“…Deep learning methods instead forego hand-crafted features in favor of a deep hierarchy of data-driven features. In the domain of skin lesions, a common approach rests on CNN models with softmax output layers to detect disease [31]. Recent studies have proposed numerous advances to improve the classification accuracy of skin lesions.…”

Section: Related Workmentioning

confidence: 99%

Deep Clustering via Center-Oriented Margin Free-Triplet Loss for Skin Lesion Detection in Highly Imbalanced Datasets

Öztürk

Çukur

2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Melanoma is a fatal skin cancer that is curable and has dramatically increasing survival rate when diagnosed at early stages. Learning-based methods hold significant promise for the detection of melanoma from dermoscopic images. However, since melanoma is a rare disease, existing databases of skin lesions predominantly contain highly imbalanced numbers of benign versus malignant samples. In turn, this imbalance introduces substantial bias in classification models due to the statistical dominance of the majority class. To address this issue, we introduce a deep clustering approach based on the latentspace embedding of dermoscopic images. Clustering is achieved using a novel center-oriented margin-free triplet loss (COM-Triplet) enforced on image embeddings from a convolutional neural network backbone. The proposed method aims to form maximally-separated cluster centers as opposed to minimizing classification error, so it is less sensitive to class imbalance. To avoid the need for labeled data, we further propose to implement COM-Triplet based on pseudo-labels generated by a Gaussian mixture model (GMM). Comprehensive experiments show that deep clustering with COM-Triplet loss outperforms clustering with triplet loss, and competing classifiers in both supervised and unsupervised settings.

show abstract

Pre-trained CNN Based Deep Features with Hand-Crafted Features and Patient Data for Skin Lesion Classification

Cited by 5 publications

References 40 publications

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer

A multimodal and interpretable-based approach for improving melanoma detection using dermoscopy images

Deep Clustering via Center-Oriented Margin Free-Triplet Loss for Skin Lesion Detection in Highly Imbalanced Datasets

Contact Info

Product

Resources

About