Corpus ID: 201307251

A CNN toolbox for skin cancer classification

  title={A CNN toolbox for skin cancer classification},
  author={Fabrizio Nunnari and Daniel Sonntag},
We describe a software toolbox for the configuration of deep neural networks in the domain of skin cancer classification. The implemented software architecture allows developers to quickly set up new convolutional neural network (CNN) architectures and hyper-parameter configurations. At the same time, the user interface, manageable as a simple spreadsheet, allows non-technical users to explore different configuration settings that need to be explored when switching to different data sets. In… Expand
A Study on the Fusion of Pixels and Patient Metadata in CNN-Based Classification of Skin Lesion Images
A study on the fusion of pixel data and patient metadata for improving the classification of skin lesion images shows that age is the most useful metadatum as a decision criterion, followed by body location and gender. Expand
Deep Melanoma classification with K-Fold Cross-Validation for Process optimization
Results reveal that the model built by the approach proposed in this paper can effectively achieve a better prediction and enhance the accuracy of the model, which proves that K-Fold can achieve better performance on a small skin cancer dataset. Expand
The Skincare project, an interactive deep learning system for differential diagnosis of malignant skin lesions. Technical Report
The overall description of the outcome of the Skincare project is given, and the steps to support communication and coordination between humans and machine in IML are focused on, which are an integral part of the development of future cognitive assistants in the medical domain. Expand
On the Overlap Between Grad-CAM Saliency Maps and Explainable Visual Features in Skin Cancer Images
It is found that the best threshold value, i.e., the threshold at which one can measure the highest Jaccard index, varies significantly among features; ranging from 0.3 to 0.7, shows that higher resolution saliency maps could help doctors in spotting wrong classifications. Expand
Achievements and Challenges in Explaining Deep Learning based Computer-Aided Diagnosis Systems
Current state-of-the-art in explaining and interpreting Deep Learning based algorithms in applications of medical research and diagnosis of diseases is provided and some of the remaining challenges that stand in the way of practical applications of AI as a clinical decision support tool are highlighted. Expand
A Competitive Deep Neural Network Approach for the ImageCLEFmed Caption 2020 Task
The aim of ImageCLEFmed Caption task is to develop a system that automatically labels radiology images with relevant medical concepts. We describe our Deep Neural Network (DNN) based approach forExpand


Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review
This study presents the first systematic review of the state-of-the-art research on classifying skin lesions with CNNs, and discusses why the comparability of the presented procedures is very difficult and which challenges must be addressed in the future. Expand
Dermatologist-level classification of skin cancer with deep neural networks
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. Expand
Rethinking Skin Lesion Segmentation in a Convolutional Classifier
The results indicate that segmentation border enlargement produces, to a certain degree, better results across all metrics of interest when using a convolutional based classifier built using the transfer learning paradigm. Expand
Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task.
A CNN trained by open-source images exclusively outperformed 136 of the 157 dermatologists and all the different levels of experience (from junior to chief physicians) in terms of average specificity and sensitivity. Expand
Fine-tuning deep CNN models on specific MS COCO categories
An overview of the publicly available py-faster-rcnn-ft software library that can be used to fine-tune the VGG_CNN_M_1024 model on custom subsets of the Microsoft Common Objects in Context dataset is provided. Expand
Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC)
  • D. Gutman, N. Codella, +4 authors A. Halpern
  • Computer Science, Medicine
  • 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
  • 2018
The design, implementation, and results of the latest installment of the dermoscopic image analysis benchmark challenge are described, to support research and development of algorithms for automated diagnosis of melanoma, the most lethal skin cancer. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists
For the first time, a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts, was compared and most dermatologists were outperformed by the CNN. Expand
Dermoscopy Image Analysis: Overview and Future Directions
A brief overview of this exciting subfield of medical image analysis, primarily focusing on three aspects of it, namely, segmentation, feature extraction, and classification is presented. Expand
The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions
The HAM10000 (“Human Against Machine with 10000 training images”) dataset is released, which 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. Expand