Deep learning-based computer aided diagnosis model for skin cancer detection and classification

e22018 Background: The prevalence of skin cancer is increasing worldwide. According to World Health Organization (WHO),there is one in every three cancers diagnosed in US is a skin cancer. Traditional ways for skin cancer diagnosis have shown many limitations: inadequate accuracy, consume much time, and effort. In order to assist dermatologists for earlier and accurate diagnosis, we propose to develop a computer aided diagnosis systems for automatic classification of skin lesions. Deep learning architectures are used in this area based on a new convolutional neural network that can classify skin lesions with improved accuracy. Methods: A public dataset of skin lesions HAM10000 ("Human Against Machine with 10000 training images") is used for training and testing. For the validation of our work, a private dataset is collected from a dermatology office in Besançon (France). This dataset contains 45 different dermatoscopic images of skin lesions (Basal cell carcinoma, squamous cell carcinoma and Actinic keratosis) with their histology results. In this research, a three-phase approach was proposed and implemented: Phase one is preprocessing the data; by amputate missing values using the mean filling method. The dermoscopy images in the dataset were downscaled to 224X224 pixels. Then, data augmentation was applied to solve the imbalanced data problem. Finally, the ten-fold cross-validation method was applied to compare the performance of three CNN architectures used in literature: DenseNet 201, ResNet 152, and VGGNet with our proposed architecture. Results: Results obtained with our model show the highest classification accuracy 0.95, a sensitivity of 0, 96, a specificity of 0.94, and outperforms other algorithms in classifying these skin lesions. Conclusions: Our research improves the performance of computer aided diagnosis systems for skin lesions by giving an accurate classification. The use of this system helps dermatologists to make accurate classification with lower time, cost, and effort. Our future work will focus on generalizing the domain by developing a model that can classify various lesions using various types of data (dermoscopic images, histological images, clinical data, sensors data...etc) using the advanced techniques in literature of transfer learning and adaptors models.

Download Full-text

Computer Aided Diagnosis Systems for Lung Cancer Detection

Immunology Endocrine & Metabolic Agents - Medicinal Chemistry ◽

10.2174/1871522216666161014160132 ◽

2016 ◽

Vol 16 (999) ◽

pp. 1-1

Author(s):

Javeria Amin ◽

Muhammad Sharif ◽

Mussarat Yasmin

Keyword(s):

Lung Cancer ◽

Cancer Detection ◽

Computer Aided Diagnosis ◽

Computer Aided ◽

Lung Cancer Detection ◽

Aided Diagnosis

Download Full-text

553 A computer-aided diagnosis system for bullous disease based on deep learning

Journal of Investigative Dermatology ◽

10.1016/j.jid.2019.03.629 ◽

2019 ◽

Vol 139 (5) ◽

pp. S95

Author(s):

Y. Wang ◽

X. He ◽

F. Li ◽

W. Zhu

Keyword(s):

Deep Learning ◽

Computer Aided Diagnosis ◽

Diagnosis System ◽

Bullous Disease ◽

Computer Aided ◽

Aided Diagnosis

Download Full-text

Quantifying the uncertainty of deep learning-based computer-aided diagnosis for patient safety

Current Directions in Biomedical Engineering ◽

10.1515/cdbme-2019-0057 ◽

2019 ◽

Vol 5 (1) ◽

pp. 223-226

Author(s):

Max-Heinrich Laves ◽

Sontje Ihler ◽

Tobias Ortmaier ◽

Lüder A. Kahrs

Keyword(s):

Monte Carlo ◽

Patient Safety ◽

Deep Learning ◽

Epistemic Uncertainty ◽

Computer Aided Diagnosis ◽

Uncertainty Estimation ◽

Test Time ◽

Prediction Uncertainty ◽

Computer Aided ◽

Aided Diagnosis

AbstractIn this work, we discuss epistemic uncertainty estimation obtained by Bayesian inference in diagnostic classifiers and show that the prediction uncertainty highly correlates with goodness of prediction. We train the ResNet-18 image classifier on a dataset of 84,484 optical coherence tomography scans showing four different retinal conditions. Dropout is added before every building block of ResNet, creating an approximation to a Bayesian classifier. Monte Carlo sampling is applied with dropout at test time for uncertainty estimation. In Monte Carlo experiments, multiple forward passes are performed to get a distribution of the class labels. The variance and the entropy of the distribution is used as metrics for uncertainty. Our results show strong correlation with ρ = 0.99 between prediction uncertainty and prediction error. Mean uncertainty of incorrectly diagnosed cases was significantly higher than mean uncertainty of correctly diagnosed cases. Modeling of the prediction uncertainty in computer-aided diagnosis with deep learning yields more reliable results and is therefore expected to increase patient safety. This will help to transfer such systems into clinical routine and to increase the acceptance of machine learning in diagnosis from the standpoint of physicians and patients.

Download Full-text

The Role and Impact of Deep Learning Methods in Computer-Aided Diagnosis Using Gastrointestinal Endoscopy

Diagnostics ◽

10.3390/diagnostics11040694 ◽

2021 ◽

Vol 11 (4) ◽

pp. 694

Author(s):

Xuejiao Pang ◽

Zijian Zhao ◽

Ying Weng

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Clinical Practice ◽

Gastrointestinal Endoscopy ◽

Computer Aided Diagnosis ◽

Learning Methods ◽

Learning Abilities ◽

Cad System ◽

Computer Aided ◽

Aided Diagnosis

At present, the application of artificial intelligence (AI) based on deep learning in the medical field has become more extensive and suitable for clinical practice compared with traditional machine learning. The application of traditional machine learning approaches to clinical practice is very challenging because medical data are usually uncharacteristic. However, deep learning methods with self-learning abilities can effectively make use of excellent computing abilities to learn intricate and abstract features. Thus, they are promising for the classification and detection of lesions through gastrointestinal endoscopy using a computer-aided diagnosis (CAD) system based on deep learning. This study aimed to address the research development of a CAD system based on deep learning in order to assist doctors in classifying and detecting lesions in the stomach, intestines, and esophagus. It also summarized the limitations of the current methods and finally presented a prospect for future research.

Download Full-text