scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Skin Lesion Classification using Deep Learning and Image Processing

TL;DR: In this paper, a Convolutional Neural Network was fabricated (using TensorFlow) obtaining an accuracy of 81.24%. Further Transfer Learning Approach was implemented in PyTorch, which yielded accuracies of 96.40%, 98.20%, 98,70% and 99.04% respectively for Wide Resnet101, Resnet50, Densenet121 and VGG19 with batch normalization, which are all trained end-to-end from images directly, to proliferate the scalability of these models and curtail initial diagnostic costs.
Abstract: Skin Cancer is the most common (accounting for 40% of cancer cases globally) and potentially life-threatening type of cancers. It was diagnosed in about 5.6 million individuals last year. Automated classification of skin lesions through images has been a challenge throughout the years because of fine variability in their appearance. Deep Learning techniques exhibit potential in tackling fine-margined image-based analysis and manage to provide accurate results. The three modelling stages include data collection and augmentation, model architecture and finally prediction into 7 different types of skin cancer namely actinic keratoses, basal cell carcinoma, benign keratosis-like lesions, dermatofibroma, melanoma, melanocytic nevi and vascular lesions. A Convolutional Neural Network was fabricated (using TensorFlow) obtaining an accuracy of 81.24%. Further Transfer learning Approach was implemented in PyTorch, which yielded accuracies of 96.40%, 98.20%, 98.70% and 99.04% respectively for Wide Resnet101, Resnet50, Densenet121 and VGG19 with batch normalization, which are all trained end-to-end from images directly, to proliferate the scalability of these models and curtail initial diagnostic costs. The aim of this research paper is to render non-invasive skin cancer screening a common norm, making it simpler.
Citations
More filters
Journal ArticleDOI
TL;DR: A comprehensive literature survey and review of a total of 594 publications (356 for skin lesion segmentation and 238 for skin lesions classification) published between 2011 and 2022 is provided in this article .

7 citations

Journal ArticleDOI
TL;DR: This study presents the design and implementation of a transfer learning model using Convolutional Neural Networks with variable training epoch numbers to classify skin lesion images obtained by smartphones and shows the efficacy of transfer learning in skin lesions diagnosis.
Abstract: The computer-aided diagnosis (CAD) and the analysis of skin lesions using deep learning models have become common in the last decade. The proposed CAD systems have considered various datasets and deep learning models. The transfer of knowledge from particular pre-trained models to others has also gained importance due to the efficient convergence and superior results. This study presents the design and implementation of a transfer learning model using Convolutional Neural Networks (CNN) with variable training epoch numbers to classify skin lesion images obtained by smartphones. The model is divided into the inner and external CNN models to train and transfer the knowledge, and the preprocessing and data augmentation are not applied. Several experiments are performed to classify cancerous and non-cancerous skin lesions and all skin lesion types provided in the dataset separately. The designed model increased the classification rates by 20% compared to the conventional CNN. The transfer learning model achieved 0.81, 0.88, and 0.86 mean recall, mean specificity, and mean accuracy in detecting cancerous lesions, and 0.83, 0.90, and 0.86 macro recall, macro precision, and macro F1 score in classifying six skin lesions. The obtained results show the efficacy of transfer learning in skin lesion diagnosis.

1 citations

Journal ArticleDOI
TL;DR: A comprehensive literature review of cutting-edge CAD techniques published between 2011 and 2020 is provided, anticipated that it will guide researchers of all levels in the process of developing an automated and robust CAD system for skin lesion analysis.
Abstract: The Computer-aided Diagnosis or Detection (CAD) approach for skin lesion analysis is an emerging field of research that has the potential to alleviate the burden and cost of skin cancer screening. Researchers have recently indicated increasing interest in developing such CAD systems, with the intention of providing a user-friendly tool to dermatologists in order to reduce the challenges that are raised by manual inspection. The purpose of this article is to provide a comprehensive literature review of cutting-edge CAD techniques published between 2011 and 2020. The Preferred Reporting Items for Systematic Reviews and MetaAnalyses (PRISMA) method was used to identify a total of 365 publications, 221 for skin lesion segmentation and 144 for skin lesion classification. These articles are analyzed and summarized in a number of different ways so that we can contribute vital information regarding the methods for the development of CAD systems. These ways include: relevant and essential definitions and theories, input data (datasets utilization, preprocessing, augmentations, and fixing imbalance problems), method configuration (techniques, architectures, module frameworks, and losses), training tactics (hyperparameter settings), and evaluation criteria (metrics). We also intend to investigate a variety of performance-enhancing approaches, including ensemble and post-processing. In addition, in this survey, we highlight the primary difficulties associated with evaluating skin lesion segmentation and classification systems using minimal datasets, as well as the potential solutions to these difficulties. In conclusion, enlightening findings, recommendations, and trends are discussed for the pur1 ar X iv :2 20 8. 12 23 2v 1 [ ee ss .I V ] 2 5 A ug 2 02 2 pose of future research surveillance in related fields of interest. It is anticipated that it will guide researchers of all levels, from beginners to experts, in the process of developing an automated and robust CAD system for skin lesion analysis.

1 citations

Journal ArticleDOI
TL;DR: In this article , a machine learning methodology for assessing the quality of green space at a human-perception level using transfer learning on pre-trained models was proposed, which achieved high scores across six performance metrics: accuracy, precision, recall, F1-score, Cohen's Kappa, and average ROC-AUC.
Abstract: Green space is any green infrastructure consisting of vegetation. Green space is linked with improving mental and physical health, providing opportunities for social interactions and physical activities, and aiding the environment. The quality of green space refers to the condition of the green space. Past machine learning-based studies have emphasized that littering, lack of maintenance, and dirtiness negatively impact the perceived quality of green space. These methods assess green spaces and their qualities without considering the human perception of green spaces. Domain-based methods, on the other hand, are labour-intensive, time-consuming, and challenging to apply to large-scale areas. This research proposes to build, evaluate, and deploy a machine learning methodology for assessing the quality of green space at a human-perception level using transfer learning on pre-trained models. The results indicated that the developed models achieved high scores across six performance metrics: accuracy, precision, recall, F1-score, Cohen’s Kappa, and Average ROC-AUC. Moreover, the models were evaluated for their file size and inference time to ensure practical implementation and usage. The research also implemented Grad-CAM as means of evaluating the learning performance of the models using heat maps. The best-performing model, ResNet50, achieved 98.98% accuracy, 98.98% precision, 98.98% recall, 99.00% F1-score, a Cohen’s Kappa score of 0.98, and an Average ROC-AUC of 1.00. The ResNet50 model has a relatively moderate file size and was the second quickest to predict. Grad-CAM visualizations show that ResNet50 can precisely identify areas most important for its learning. Finally, the ResNet50 model was deployed on the Streamlit cloud-based platform as an interactive web application.
References
More filters
Proceedings Article
21 Jun 2010
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
Abstract: Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all have the same weights but have progressively more negative biases. The learning and inference rules for these "Stepped Sigmoid Units" are unchanged. They can be approximated efficiently by noisy, rectified linear units. Compared with binary units, these units learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset. Unlike binary units, rectified linear units preserve information about relative intensities as information travels through multiple layers of feature detectors.

14,799 citations

Journal ArticleDOI
02 Feb 2017-Nature
TL;DR: This work demonstrates an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists, trained end-to-end from images directly, using only pixels and disease labels as inputs.
Abstract: Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. We train a CNN using a dataset of 129,450 clinical images-two orders of magnitude larger than previous datasets-consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi. The first case represents the identification of the most common cancers, the second represents the identification of the deadliest skin cancer. The CNN achieves performance on par with all tested experts across both tasks, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists. Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 (ref. 13) and can therefore potentially provide low-cost universal access to vital diagnostic care.

8,424 citations

Book ChapterDOI
Chuanqi Tan1, Fuchun Sun1, Tao Kong1, Wenchang Zhang1, Chao Yang1, Chunfang Liu1 
04 Oct 2018
TL;DR: Deep transfer learning relaxes the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the test data, which motivates researchers to use transfer learning to solve the problem of insufficient training data as mentioned in this paper.
Abstract: As a new classification platform, deep learning has recently received increasing attention from researchers and has been successfully applied to many domains. In some domains, like bioinformatics and robotics, it is very difficult to construct a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation, which limits its development. Transfer learning relaxes the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the test data, which motivates us to use transfer learning to solve the problem of insufficient training data. This survey focuses on reviewing the current researches of transfer learning by using deep neural network and its applications. We defined deep transfer learning, category and review the recent research works based on the techniques used in deep transfer learning.

1,543 citations

Journal ArticleDOI
TL;DR: The HAM10000 dataset as mentioned in this paper contains 10015 dermatoscopic images from different populations acquired and stored by different modalities and applied different acquisition and cleaning methods and developed semi-automatic workflows utilizing specifically trained neural networks.
Abstract: Training of neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available datasets of dermatoscopic images. We tackle this problem by releasing the HAM10000 ("Human Against Machine with 10000 training images") dataset. We collected dermatoscopic images from different populations acquired and stored by different modalities. Given this diversity we had to apply different acquisition and cleaning methods and developed semi-automatic workflows utilizing specifically trained neural networks. The final dataset consists of 10015 dermatoscopic images which are released as a training set for academic machine learning purposes and are publicly available through the ISIC archive. This benchmark dataset can be used for machine learning and for comparisons with human experts. Cases include a representative collection of all important diagnostic categories in the realm of pigmented lesions. More than 50% of lesions have been confirmed by pathology, while the ground truth for the rest of the cases was either follow-up, expert consensus, or confirmation by in-vivo confocal microscopy.

1,528 citations

Book ChapterDOI
01 Jan 1999
TL;DR: This paper attempts to show that for recognizing simple objects with high shape variability such as handwritten characters, it is possible, and even advantageous, to feed the system directly with minimally processed images and to rely on learning to extract the right set of features.
Abstract: Finding an appropriate set of features is an essential problem in the design of shape recognition systems. This paper attempts to show that for recognizing simple objects with high shape variability such as handwritten characters, it is possible, and even advantageous, to feed the system directly with minimally processed images and to rely on learning to extract the right set of features. Convolutional Neural Networks are shown to be particularly well suited to this task. We also show that these networks can be used to recognize multiple objects without requiring explicit segmentation of the objects from their surrounding. The second part of the paper presents the Graph Transformer Network model which extends the applicability of gradient-based learning to systems that use graphs to represents features, objects, and their combinations.

863 citations