scholarly journals Deep neural frameworks improve the accuracy of general practitioners in the classification of pigmented skin lesions

2020 ◽  
Author(s):  
Maximiliano Lucius ◽  
Jorge De All ◽  
José Antonio De All ◽  
Martín Belvisi ◽  
Luciana Radizza ◽  
...  
Keyword(s):  
High Resolution ◽  
General Practitioners ◽  
Clinical Data ◽  
Skin Lesions ◽  
Classification Performance ◽  
Image Resolution ◽  
Deep Convolutional Neural Networks ◽  
Random Dataset ◽  
Pigmented Skin Lesions

AbstractArtificial intelligence can be a key tool in the context of assisting in the diagnosis of dermatological conditions, particularly when performed by general practitioners with limited or no access to high resolution optical equipment. This study evaluates the performance of deep convolutional neural networks (DNNs) in the classification of seven pigmented skin lesions. Additionally, it assesses the improvement ratio in the classification performance when utilized by general practitioners. Open-source skin images were downloaded from the ISIC archive. Different DNNs (n=8) were trained based on a random dataset constituted by 8,015 images. A test set of 2,003 images has been used to assess the classifiers performance at low (300 × 224 RGB) and high (600 × 450 RGB) image resolution and aggregated clinical data (age, sex and lesion localization). We have also organized two different contests to compare the DNNs performance to that of general practitioners by means of unassisted image observation. Both at low and high image resolution, the DNNs framework being trained differentiated dermatological images with appreciable performance. In all cases, accuracy has been improved when adding clinical data to the framework. Finally, the lowest accurate DNN outperformed general practitioners. Physician’s accuracy was statistically improved when allowed to use the output of this algorithmic framework as guidance. DNNS are proven to be high performers as skin lesion classifiers. The aim is to include these AI tools in the context of general practitioners whilst improving their diagnosis accuracy in a routine clinical scenario when or where the use of high-resolution equipment is not accessible.

scholarly journals Deep Neural Frameworks Improve the Accuracy of General Practitioners in the Classification of Pigmented Skin Lesions

Diagnostics ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. 969
Author(s):  
Maximiliano Lucius ◽  
Jorge De All ◽  
José Antonio De All ◽  
Martín Belvisi ◽  
Luciana Radizza ◽  
...  
Keyword(s):  
General Practitioners ◽  
Skin Lesions ◽  
Image Resolution ◽  
Aggregated Data ◽  
Skin Imaging ◽  
High Image Resolution ◽  
Random Dataset ◽  
Algorithmic Framework ◽  
Diagnosis Accuracy ◽  
Pigmented Skin Lesions

This study evaluated whether deep learning frameworks trained in large datasets can help non-dermatologist physicians improve their accuracy in categorizing the seven most common pigmented skin lesions. Open-source skin images were downloaded from the International Skin Imaging Collaboration (ISIC) archive. Different deep neural networks (DNNs) (n = 8) were trained based on a random dataset constituted of 8015 images. A test set of 2003 images was used to assess the classifiers’ performance at low (300 × 224 RGB) and high (600 × 450 RGB) image resolution and aggregated data (age, sex and lesion localization). We also organized two different contests to compare the DNN performance to that of general practitioners by means of unassisted image observation. Both at low and high image resolution, the DNN framework differentiated dermatological images with appreciable performance. In all cases, the accuracy was improved when adding clinical data to the framework. Finally, the least accurate DNN outperformed general practitioners. The physician’s accuracy was statistically improved when allowed to use the output of this algorithmic framework as guidance. DNNs are proven to be high performers as skin lesion classifiers and can improve general practitioner diagnosis accuracy in a routine clinical scenario.

Skin Cancer Classification with Deep Convolutional Neural Networks

2020 ◽  
Vol 10 (7) ◽  
pp. 1707-1713 ◽  
Author(s):  
Mingang Chen ◽  
Wenjie Chen ◽  
Wei Chen ◽  
Lizhi Cai ◽  
Gang Chai
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Skin Diseases ◽  
Survival Rates ◽  
Skin Lesions ◽  
Classification Model ◽  
Deep Convolutional Neural Networks ◽  
Image Preprocessing ◽  
Skin Cancers

Skin cancers are one of the most common cancers in the world. Early detections and treatments of skin cancers can greatly improve the survival rates of patients. In this paper, a skin lesions classification system is developed with deep convolutional neural networks of ResNet50, which may help dermatologists to recognize skin cancers earlier. We utilize the ResNet50 as a pre-trained model. Then, by transfer learning, it is trained on our skin lesions dataset. Image preprocessing and dataset balancing methods are used to increase the accuracy of the classification model. In classification of skin diseases, our model achieves an overall accuracy of 83.74% on nine-class skin lesions. The experimental results show an impressive effect of the ResNet50 model in finegrained skin lesions classification and skin cancers recognition.

Detection and Classification of Skin Lesions using Probability Map-based Region Growing with BA-KNN Classifier (Preprint)

2021 ◽  
Author(s):  
Sivaraj S ◽  
Dr.R. Malmathanraj
Keyword(s):  
Skin Lesion ◽  
Region Growing ◽  
Skin Lesions ◽  
Classification Approach ◽  
Probability Map ◽  
Knn Classifier ◽  
Knn Classification ◽  
Pigmented Skin Lesions ◽  
Thresholding Algorithm

BACKGROUND Melanoma is one of the most hazardous existing diseases, and is a kind of threatening pigmented skin lesion. Appropriate automated diagnosis of skin lesions and the categorization of melanoma may be exceptionally enhancing premature identification of melanomas. OBJECTIVE However, Models of categorization based on deterministic skin lesion may influence multi-dimensional nonlinear problem provokes inaccurate and ineffective categorization. This research presents a novel hybrid BA-KNN classification approach for pigmented skin lesions in dermoscopy images. METHODS In the first step, the skin lesion is preprocessed via automatic preprocessing algorithm together with a fusion hair detection and removal strategy. Also, a new probability map based region growing and optimal thresholding algorithm is integrated in this system to enhance the rate of accuracy. RESULTS Moreover, to attain better efficacy, an estimate of ABCD as well as geometric features are considered during the feature extraction to describe the malignancy of the lesion. CONCLUSIONS The evaluation of the experiment reveals the efficiency of the proposed approach on dermoscopy images with better accuracy

scholarly journals Texture descriptors based on adaptive neighborhoods for classification of pigmented skin lesions

2015 ◽  
Vol 24 (6) ◽  
pp. 061104 ◽  
Author(s):  
Víctor González-Castro ◽  
Johan Debayle ◽  
Yanal Wazaefi ◽  
Mehdi Rahim ◽  
Caroline Gaudy-Marqueste ◽  
...  
Keyword(s):  
Skin Lesions ◽  
Pigmented Skin Lesions

scholarly journals Classification Of Skin Lesions By Topological Data Analysis Alongside With Neural Network

2020 ◽  
Author(s):  
Naiereh Elyasi ◽  
mehdi hosseini moghadam
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Data Analysis ◽  
Skin Diseases ◽  
Persistent Homology ◽  
Skin Lesions ◽  
Topological Data Analysis ◽  
Deep Convolutional Neural Networks ◽  
Classification Result

In this paper we use TDA mapper alongside with deep convolutional neural networks in the classification of 7 major skin diseases. First we apply kepler mapper with neural network as one of its filter steps to classify the dataset HAM10000. Mapper visualizes the classification result by a simplicial complex, where neural network can not do this alone, but as a filter step neural network helps to classify data better. Furthermore we apply TDA mapper and persistent homology to understand the weights of layers of mobilenet network in different training epochs of HAM10000. Also we use persistent diagrams to visualize the results of analysis of layers of mobilenet network.

Sign in / Sign up

Export Citation Format

Share Document