Benign and Malignant Skin Lesion Classification Comparison for Three Deep-Learning Architectures

Yılmaz, Ercüment; Trocan, Maria

doi:10.1007/978-3-030-41964-6_44

Cited by 16 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Evaluation of the final performances on the test set images to understand the model’s ability to classify new images, not used during training. In our study, transfer learning was applied using three different CNN architectures: AlexNet , GoogleNet, and ResNet [ 14 ]. The AlexNet [ 15 ] employed a series of convolutional layers to extract a higher-level representation of the image content.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

The Role in Teledermoscopy of an Inexpensive and Easy-to-Use Smartphone Device for the Classification of Three Types of Skin Lesions Using Convolutional Neural Networks

et al. 2021

View full text Add to dashboard Cite

Background. The use of teledermatology has spread over the last years, especially during the recent SARS-Cov-2 pandemic. Teledermoscopy, an extension of teledermatology, consists of consulting dermoscopic images, also transmitted through smartphones, to remotely diagnose skin tumors or other dermatological diseases. The purpose of this work was to verify the diagnostic validity of images acquired with an inexpensive smartphone microscope (NurugoTM), employing convolutional neural networks (CNN) to classify malignant melanoma (MM), melanocytic nevus (MN), and seborrheic keratosis (SK). Methods. The CNN, trained with 600 dermatoscopic images from the ISIC (International Skin Imaging Collaboration) archive, was tested on three test sets: ISIC images, images acquired with the NurugoTM, and images acquired with a conventional dermatoscope. Results. The results obtained, although with some limitations due to the smartphone device and small data set, were encouraging, showing comparable results to the clinical dermatoscope and up to 80% accuracy (out of 10 images, two were misclassified) using the NurugoTM demonstrating how an amateur device can be used with reasonable levels of diagnostic accuracy. Conclusion. Considering the low cost and the ease of use, the NurugoTM device could be a useful tool for general practitioners (GPs) to perform the first triage of skin lesions, aiding the selection of lesions that require a face-to-face consultation with dermatologists.

show abstract

Section: Methodsmentioning

confidence: 99%

“…In our study, transfer learning was applied using three different CNN architectures: AlexNet , GoogleNet, and ResNet [ 14 ]. The AlexNet [ 15 ] employed a series of convolutional layers to extract a higher-level representation of the image content.…”

Section: Methodsmentioning

confidence: 99%

The Role in Teledermoscopy of an Inexpensive and Easy-to-Use Smartphone Device for the Classification of Three Types of Skin Lesions Using Convolutional Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In our case the models were train on 10 000 steps. Contrary to the approach in [7], and above mentioned, we consider only the saliency generated region of interest for training our data. The value global step present on the x axis of the Figure 5 and 6 is the actualization of the weights of the model after computed the batch size (of 32 images in our case).…”

Section: Classification Performance Evaluationmentioning

confidence: 99%

“…With the recent advances in medical image processing field, it is possible to improve the dermatological diagnostic performance by using computer-assisted diagnostic systems. For this purpose, various machine learning algorithms are designed and tested to be used in the diagnosis of melanoma [7]. Deep learning models, which have gained popularity in recent years, have been effective in solving image recognition and classification problems.…”

Section: Introductionmentioning

confidence: 99%

Melanoma Detection Using Deep Learning

Favole

Trocan

Yılmaz

2020

Computational Collective Intelligence

Self Cite

View full text Add to dashboard Cite

In this paper, we describe a region of interest-based approach for the classification of dermoscopic images of skin lesions, which nowadays contributes to early identification of skin melanoma. Once the region of interest detected, it will be further processed in order to be used for training and hence classification using deep learning methods. The main goal is to compare three different convolutional neural networks (CNNs) models and determine the one which provides the best accuracy, knowing that only salient parts of the skin lesions images have been used for training.

show abstract

“…Finally, different color-based features were extracted, which were then classified using multilayer perceptron and different machine learning algorithms. Yilmaz and Trocan [76] compared the performance of deep CNN, such as AlexNet, GoogLeNet, and ResNet-50 for the SLC. The authors experimentally demonstrated that ResNet-50 was the best performing classifier, whereas AlexNet was better for time complexity.…”

Section: Introductionmentioning

confidence: 99%

DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation

Mte

2021

Preprint

View full text Add to dashboard Cite

Although automated Skin Lesion Classification (SLC) is a crucial integral step in computer-aided diagnosis, it remains a challenging task due to inconsistency in texture, color, indistinguishable boundaries, and shapes. In this article, we propose an automatic and robust framework for the dermoscopic SLC named Dermoscopic Expert (DermoExpert). The DermoExpert consists of a preprocessing, a hybrid Convolutional Neural Network (hybrid-CNN), and transfer learning. The proposed hybrid-CNN classifier consists of three distinct feature extractors, with the same input images, which are fused to achieve better-depth feature maps of the corresponding lesion. Those distinct and fused feature maps are classified using the different fully connected layers, which are then ensembled to get a final prediction probability. In the preprocessing, we use lesion segmentation, augmentation, and class rebalancing. For boosting the lesion recognition, we have also employed geometric and intensity-based augmentation as well as the class rebalancing by penalizing the loss of the majority class and adding extra images to the minority classes. Additionally, we leverage the knowledge from a pre-trained model, also known as transfer learning, to build a generic classifier, although small datasets are being used. In the end, we design and implement a web application by deploying the weights of our DermoExpert for automatic lesion recognition. We evaluate our DermoExpert on the ISIC-2016, ISIC-2017, and ISIC-2018 datasets, where our DermoExpert has achieved the area under the receiver operating characteristic curve (AUC) of 0.96, 0.95, and 0.97, respectively. The experimental results outperform the recent state-of-the-art by a margin of 10.0 % and 2.0 % respectively for ISIC-2016 and ISIC-2017 datasets in terms of AUC. The DermoExpert also outperforms, in concerning a balanced accuracy, by a margin of 3.0 % for ISIC-2018 dataset. Since our framework can provide better-classification on three different test datasets, even with limited training data, it can lead to better-recognition of melanoma to aid dermatologists. Our source code, and segmented masks, for ISIC-2018 dataset, will be made publicly available for the research community for further improvements.

show abstract

Benign and Malignant Skin Lesion Classification Comparison for Three Deep-Learning Architectures

Cited by 16 publications

References 21 publications

The Role in Teledermoscopy of an Inexpensive and Easy-to-Use Smartphone Device for the Classification of Three Types of Skin Lesions Using Convolutional Neural Networks

The Role in Teledermoscopy of an Inexpensive and Easy-to-Use Smartphone Device for the Classification of Three Types of Skin Lesions Using Convolutional Neural Networks

Melanoma Detection Using Deep Learning

DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation

Contact Info

Product

Resources

About