2020 International Conference on Computation, Automation and Knowledge Management (ICCAKM) · 2020 · 13 citations · 9 references
ComputingComputer ScienceDermatologyBiomedical ImagingComputer VisionMachine LearningCancer DetectionDeep LearningMedical Image AnalysisSkin TumorsTumor DetectionCross EntropyDeep Learning-based Lesion ClassificationDermoscopic Image AnalysisLesion Detection In ImagesMelanoma DiagnosisNeural Network ClassificationSkin Cancer DetectionSkin Lesion Detection
Melanoma is a type of skin cancer, which, if detected in its early stages, is highly curable. But its detection is hard, even under expert supervision. This paper is an attempt to make detection of Melanoma using deep learning techniques more efficient and reliable compared to existing techniques. The overall approach followed is to build a two-stage network. The first-stage network targets accurate segmentation of the skin lesion, from the actual dermoscopic images. The second-stage network is a classification network to predict the presence of Melanoma in the sample. For the segmentation stage network, both the U-NET and FCRN methods were implemented. For the classification network, the DRN architecture was implemented. In order to enhance the achieved results, the step-decay technique to modify learning rates was used. Using both binary cross-entropy and weighted binary cross-entropy improved the achieved results, driving towards better accuracy of detection.
9
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations
Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks
Lequan Yu, Hao Chen, Qi Dou et al. · IEEE Transactions on Medical Imaging · 2016 · 1.1K citations
Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network
Yuexiang Li, Linlin Shen · Sensors · 2018 · 631 citations · Full text
Melanoma detection by analysis of clinical images using convolutional neural network
Ebrahim Nasr-Esfahani, Shadrokh Samavi, Nader Karimi et al. · 2016 · 375 citations