Filters








11 Hits in 6.6 sec

Deep Learning Based Skin Lesion Segmentation and Classification of Melanoma Using Support Vector Machine (SVM)

Seeja R D, Suresh A
2019 Asian Pacific Journal of Cancer Prevention  
It can be assist medical experts on early diagnosis of melanoma on dermoscopy images. Methods: First A Convolutional Neural Network (CNN) based U-net algorithm is used for segmentation process.  ...  Objective: The main objective of this study is to improve the classification performance of melanoma using deep learning based automatic skin lesion segmentation.  ...  Yu et al., (2017) present a hybrid classification framework for dermoscopy image assessment by combining deep convolutional neural network (CNN), Fisher vector (FV) and linear Support Vector Machine (  ... 
doi:10.31557/apjcp.2019.20.5.1555 pmid:31128062 pmcid:PMC6857898 fatcat:ax3ukxgldrefjla7lsoqn6ec3e

Automatic Skin Cancer Detection in Dermoscopy Images based on Ensemble Lightweight Deep Learning Network

Lisheng Wei, Kun Ding, Huosheng Hu
2020 IEEE Access  
INDEX TERMS Dermoscopy images, skin cancer detection, lightweight deep learning network, fine-grained feature.  ...  Then, two sets of feature vectors output from the feature extraction module are used to train the two classification networks and feature discrimination networks of the recognition model at the same time  ...  Deng et al. based on VGG-16 and hole convolution, design a fully convolutional neural network that can simultaneously extract global features and local features [41] . Li et al.  ... 
doi:10.1109/access.2020.2997710 fatcat:3xjmsc6eq5forbhler2q4jd4wy

Skin disease diagnosis with deep learning: a review [article]

Hongfeng Li, Yini Pan, Jie Zhao, Li Zhang
2020 arXiv   pre-print
Thereafter, popular deep learning frameworks facilitating the implementation of deep learning algorithms and performance evaluation metrics are presented.  ...  In this paper, we present a review on deep learning methods and their applications in skin disease diagnosis.  ...  Specifically, the authors first extracted representations of dermoscopy images via a pretrained deep residual network and obtained global image descriptors based on fisher vector encoding method.  ... 
arXiv:2011.05627v2 fatcat:dtdydy2orrd7tka4fpqml4znse

Multiclass Skin Lesion Classification Using Hybrid Deep Features Selection and Extreme Learning Machine

Farhat Afza, Muhammad Sharif, Muhammad Attique Khan, Usman Tariq, Hwan-Seung Yong, Jaehyuk Cha
2022 Sensors  
Manually detecting skin lesions from dermoscopy images is a difficult and time-consuming process.  ...  The proposed method includes five primary steps: image acquisition and contrast enhancement; deep learning feature extraction using transfer learning; best feature selection using hybrid whale optimization  ...  A deep residual network was used to extract deep feature and fisher vectors utilized for image encoding.  ... 
doi:10.3390/s22030799 pmid:35161553 pmcid:PMC8838278 fatcat:h7yoykfsvfgqtmb4jy4l4pp7zy

Dermatologist-Level Classification of Skin Cancer Using Cascaded Ensembling of Convolutional Neural Network and Handcrafted Features Based Deep Neural Network

Akhilesh Kumar Sharma, Shamik Tiwari, Gaurav Aggarwal, Nitika Goenka, Anil Kumar, Prasun Chakrabarti, Tulika Chakrabarti, Radomir Gono, Zbigniew Leonowicz, Michal Jasinski
2022 IEEE Access  
This offered model utilizes the convolutional neural network model to mine nonhandcrafted image features and colour moments and texture features as handcrafted features.  ...  The deep learning architectures such as recurrent networks and convolutional neural networks (ConvNets) are developed in the past, which are proven appropriate for non-handcrafted extraction of complex  ...  Yu et al. have offered a hybrid classification structure for dermoscopy images. This hybrid framework is designed by combining linear SVM, ConvNet and Fisher vector (FV) [21].  ... 
doi:10.1109/access.2022.3149824 fatcat:hqlfjusvavdpfcqkqai55nwe2u

Recent advancement in cancer detection using machine learning: Systematic survey of decades, comparisons and challenges

Tanzila Saba
2020 Journal of Infection and Public Health  
The study highlights how cancer diagnosis, cure process is assisted using machine learning with supervised, unsupervised and deep learning techniques.  ...  Several state of art techniques are categorized under the same cluster and results are compared on benchmark datasets from accuracy, sensitivity, specificity, false-positive metrics.  ...  Acknowledgements This work was supported by the research Project [Brain Tumor Detection and Classification using 3D CNN and Feature Selection Architecture]; Prince Sultan University; Saudi Arabia [SEED-CCIS  ... 
doi:10.1016/j.jiph.2020.06.033 pmid:32758393 fatcat:sglazth4znh5jjtozguaktruce

Machine Learning and Deep Learning Methods for Skin Lesion Classification and Diagnosis: A Systematic Review

Mohamed A. Kassem, Khalid M. Hosny, Robertas Damaševičius, Mohamed Meselhy Eltoukhy
2021 Diagnostics  
The studies are compared based on their contributions, the methods used and the achieved results.  ...  The work identified the main challenges of evaluating skin lesion segmentation and classification methods such as small datasets, ad hoc image selection and racial bias.  ...  There were several methods of learning with regard to deep learning based on transfer learning, while others were based on ensemble approaches, and some employed neural networks and hybrid techniques of  ... 
doi:10.3390/diagnostics11081390 fatcat:r4gyqfwberfofhcbx2xsn7vpf4

Techniques for Malignant Melanoma Diagnosis: A Systematic Literature Review

2020 International journal of recent technology and engineering  
The results propose the implementation of systems using Inception V3 and the classifier Support Vector Machine, which achieved high accuracies in malignant melanoma diagnosis based on images processing  ...  Although, many proposals have been made for automated detection and diagnosis of malignant melanoma based on images processing, there are still improvement opportunities for melanoma diagnosis.  ...  To perform the classification, they assembled Deep residual networks [47] , convolutional neural networks (CNN) [66] , fully convolutional U-Net architecture [67] and used an SVM classifier.  ... 
doi:10.35940/ijrte.c4282.099320 fatcat:ivhntb3ycbbinnidbc4bnf5i3e

A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification [article]

Yutong Xie, Jianpeng Zhang, Yong Xia, Chunhua Shen
2020 arXiv   pre-print
In this paper, we propose the mutual bootstrapping deep convolutional neural networks (MB-DCNN) model for simultaneous skin lesion segmentation and classification.  ...  This model consists of a coarse segmentation network (coarse-SN), a mask-guided classification network (mask-CN), and an enhanced segmentation network (enhanced-SN).  ...  [23] aggregated deep features produced by various layers of a residual network using Fisher vector (FV) encoding. Ge et al.  ... 
arXiv:1903.03313v4 fatcat:cv3ldlhts5gndpxb6ttmrlc3ya

2019 Index IEEE Transactions on Biomedical Engineering Vol. 66

2019 IEEE Transactions on Biomedical Engineering  
., +, TBME May 2019 1195-1206 Melanoma Recognition in Dermoscopy Images via Aggregated Deep Convolutional Features.  ...  ., +, TBME Sept. 2019 2423-2432 Image coding Melanoma Recognition in Dermoscopy Images via Aggregated Deep Convolutional Features.  ... 
doi:10.1109/tbme.2020.2964087 fatcat:mdfzsmdahnao5ccnuj232hycsm

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
2022
Data-driven algorithms are being studied and deployed in diverse domains to support critical decisions, directly impacting on people's well-being.  ...  As a result, a growing community of algorithmic fairness researchers has been investigating the equity of existing algorithms and proposing novel ones, advancing the understanding of the risks and opportunities  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc  ... 
doi:10.48550/arxiv.2202.01711 fatcat:mav36x3w5namjhurzpevtsmsju