scholarly journals Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Cheng-Hong Yang ◽  
Jai-Hong Ren ◽  
Hsiu-Chen Huang ◽  
Li-Yeh Chuang ◽  
Po-Yin Chang
Keyword(s):  
Image Segmentation ◽  
Skin Cancer ◽  
Skin Lesion ◽  
Survival Rates ◽  
Skin Lesions ◽  
Manual Segmentation ◽  
Cure Rate ◽  
Dice Coefficient ◽  
Skin Imaging ◽  
Low Efficiency

Melanoma is a type of skin cancer that often leads to poor prognostic responses and survival rates. Melanoma usually develops in the limbs, including in fingers, palms, and the margins of the nails. When melanoma is detected early, surgical treatment may achieve a higher cure rate. The early diagnosis of melanoma depends on the manual segmentation of suspected lesions. However, manual segmentation can lead to problems, including misclassification and low efficiency. Therefore, it is essential to devise a method for automatic image segmentation that overcomes the aforementioned issues. In this study, an improved algorithm is proposed, termed EfficientUNet++, which is developed from the U-Net model. In EfficientUNet++, the pretrained EfficientNet model is added to the UNet++ model to accelerate segmentation process, leading to more reliable and precise results in skin cancer image segmentation. Two skin lesion datasets were used to compare the performance of the proposed EfficientUNet++ algorithm with other common models. In the PH2 dataset, EfficientUNet++ achieved a better Dice coefficient (93% vs. 76%–91%), Intersection over Union (IoU, 96% vs. 74%–95%), and loss value (30% vs. 44%–32%) compared with other models. In the International Skin Imaging Collaboration dataset, EfficientUNet++ obtained a similar Dice coefficient (96% vs. 94%–96%) but a better IoU (94% vs. 89%–93%) and loss value (11% vs. 13%–11%) than other models. In conclusion, the EfficientUNet++ model efficiently detects skin lesions by improving composite coefficients and structurally expanding the size of the convolution network. Moreover, the use of residual units deepens the network to further improve performance.

scholarly journals Teaching Skin Cancer Detection to Medical Students Using a Dermoscopic Algorithm

PRiMER ◽  
2021 ◽  
Vol 5 ◽  
Author(s):  
Peggy R. Cyr ◽  
Wendy Craig ◽  
Hadjh Ahrns ◽  
Kathryn Stevens ◽  
Caroline Wight ◽  
...  
Keyword(s):  
Primary Care ◽  
Medical Students ◽  
Skin Cancer ◽  
Primary Care Physicians ◽  
Survival Rates ◽  
Family Physicians ◽  
Skin Lesions ◽  
Posttest Score ◽  
Malignant Skin ◽  
Attending Physicians

Introduction: Early detection of melanoma skin cancer improves survival rates. Training family physicians in dermoscopy with the triage amalgamated dermoscopic algorithm (TADA) has high sensitivity and specificity for identifying malignant skin neoplasms. In this study we evaluated the effectiveness of TADA training among medical students, compared with practicing clinicians. Methods: We incorporated the TADA framework into 90-minute workshops that taught dermoscopy to family physicians, primary care residents, and first- and second-year medical students. The workshop reviewed the clinical and dermoscopic features of benign and malignant skin lesions and included a hands-on interactive session using a dermatoscope. All participants took a 30-image pretest and a different 30-image posttest. Results: Forty-six attending physicians, 25 residents, and 48 medical students participated in the workshop. Mean pretest scores were 20.1, 20.3, and 15.8 for attending physicians, resident physicians and students, respectively (P<.001); mean posttest scores were 24.5, 25.9, and 24.1, respectively (P=.11). Pre/posttest score differences were significant (P<.001) for all groups. The medical students showed the most gain in their pretest and posttest scores. Conclusion: After short dermoscopy workshop, medical students perform as well as trained physicians in identifying images of malignant skin lesions. Dermoscopy training may be a valuable addition to the medical school curriculum as this skill can be used by primary care physicians as well as multiple specialists including dermatologists, gynecologists, otolaryngologists, plastic surgeons, and ophthalmologists, who often encounter patients with concerning skin lesions.

scholarly journals Intelligent Dermatologist Tool for Classifying Multiple Skin Cancer Subtypes by Incorporating Manifold Radiomics Features Categories

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Omneya Attallah ◽  
Maha Sharkas
Keyword(s):  
Skin Cancer ◽  
Binary Classification ◽  
Survival Rates ◽  
Skin Lesions ◽  
Accurate Diagnosis ◽  
Computer Assisted ◽  
Discrete Wavelet ◽  
Cancer Subtypes ◽  
Low Level ◽  
High Level

The rates of skin cancer (SC) are rising every year and becoming a critical health issue worldwide. SC’s early and accurate diagnosis is the key procedure to reduce these rates and improve survivability. However, the manual diagnosis is exhausting, complicated, expensive, prone to diagnostic error, and highly dependent on the dermatologist’s experience and abilities. Thus, there is a vital need to create automated dermatologist tools that are capable of accurately classifying SC subclasses. Recently, artificial intelligence (AI) techniques including machine learning (ML) and deep learning (DL) have verified the success of computer-assisted dermatologist tools in the automatic diagnosis and detection of SC diseases. Previous AI-based dermatologist tools are based on features which are either high-level features based on DL methods or low-level features based on handcrafted operations. Most of them were constructed for binary classification of SC. This study proposes an intelligent dermatologist tool to accurately diagnose multiple skin lesions automatically. This tool incorporates manifold radiomics features categories involving high-level features such as ResNet-50, DenseNet-201, and DarkNet-53 and low-level features including discrete wavelet transform (DWT) and local binary pattern (LBP). The results of the proposed intelligent tool prove that merging manifold features of different categories has a high influence on the classification accuracy. Moreover, these results are superior to those obtained by other related AI-based dermatologist tools. Therefore, the proposed intelligent tool can be used by dermatologists to help them in the accurate diagnosis of the SC subcategory. It can also overcome manual diagnosis limitations, reduce the rates of infection, and enhance survival rates.

Proposed Threshold Algorithm for Accurate Segmentation for Skin Lesion

2015 ◽  
Vol 4 (2) ◽  
pp. 40-47
Author(s):  
T. Y. Satheesha ◽  
D. Sathyanarayana ◽  
M. N. Giri Prasad
Keyword(s):  
Skin Cancer ◽  
Skin Lesion ◽  
Skin Lesions ◽  
Large Set ◽  
Threshold Values ◽  
Diagnostic Systems ◽  
Automated Diagnosis ◽  
Algorithm Efficiency ◽  
Threshold Algorithms ◽  
Threshold Technique

Automated diagnosis of skin cancer can be easily achieved only by effective segmentation of skin lesion. But this is a highly challenging task due to the presence of intensity variations in the images of skin lesions. The authors here, have presented a histogram analysis based fuzzy C mean threshold technique to overcome the drawbacks. This not only reduces the computational complexity but also unifies advantages of soft and hard threshold algorithms. Calculation of threshold values even the presence of abrupt intensity variations is simplified. Segmentation of skin lesions is easily achieved, in a more efficient way in the following algorithm. The experimental verification here is done on a large set of skin lesion images containing every possible artifacts which highly contributes to reversed segmentation outputs. This algorithm efficiency was measured based on a comparison with other prominent threshold methods. This approach has performed reasonably well and can be implemented in the expert skin cancer diagnostic systems

A Study on Automatic Segmentation and Classification of Skin Lesions in Dermoscopic Images

2015 ◽  
Vol 6 (4) ◽  
pp. 51-61
Author(s):  
Ebtihal Abdullah Al-Mansour ◽  
Arfan Jaffar
Keyword(s):  
Skin Cancer ◽  
Imaging Techniques ◽  
Automatic Segmentation ◽  
Survival Rates ◽  
Skin Lesions ◽  
Incidence Rates ◽  
Automated System ◽  
Final State ◽  
Survey Paper ◽  
Real Scenario

Malignant Melanoma is one of the rare and the deadliest form of skin cancer if left untreated. Death rate due to this cancer is three times more than all other skin-related malignancies combined. Incidence rates of melanoma have been increasing, especially among young adults, but survival rates are high if detected early. There is a need for an automated system to assess a patient's risk of melanoma using digital dermoscopy, that is, a skin imaging technique widely used for pigmented skin lesion inspection. Although many automated and semi-automated methods are available to diagnose skin cancer but each has its own limitations and there is no final, state-of-the art technique to date which is able to be implemented in real scenario. This survey paper is based on techniques used to segment the skin cancer, analysis of their merits and demerits and their applications on advanced imaging techniques.

scholarly journals Skin Cancer Image Segmentation Based on Symmetrical Threshold Contour Algorithm

2020 ◽  
Vol 9 (1) ◽  
pp. 2390-2398
Keyword(s):  
Image Segmentation ◽  
Skin Cancer ◽  
Skin Lesion ◽  
Contour Detection ◽  
Cancerous Lesion ◽  
Image Contour ◽  
Thresholding Algorithm ◽  
Cancer Lesion ◽  
Lesion Skin

Image segmentation is a process of identifying sub patterns in a given image. The purpose of skin cancer image segmentation is to represent it ina meaningful way for effectiveanalysis. Segmentation of skin cancer image is mostly used to detect the boundaries and objects present in a skin lesion. This approach describes the skin cancer image segmentation based on symmetrical threshold contour algorithm with similar thresholding values for segmentation of the accurate cancerous lesion. Skin cancer lesion shape and structure is the most important parameter in this method. In this paper, skin cancer image contour detection isbased on symmetrical thresholding algorithm using MATLAB soft ware.

Proposed Threshold Algorithm for Accurate Segmentation for Skin Lesion

Oncology ◽  
2017 ◽  
pp. 302-309
Author(s):  
T. Y. Satheesha ◽  
D. Sathyanarayana ◽  
M. N. Giri Prasad
Keyword(s):  
Computational Complexity ◽  
Skin Cancer ◽  
Skin Lesion ◽  
Skin Lesions ◽  
Large Set ◽  
Diagnostic Systems ◽  
Automated Diagnosis ◽  
Algorithm Efficiency ◽  
Threshold Algorithms ◽  
Threshold Technique

Automated diagnosis of skin cancer can be easily achieved only by effective segmentation of skin lesion. But this is a highly challenging task due to the presence of intensity variations in the images of skin lesions. The authors here, have presented a histogram analysis based fuzzy C mean threshold technique to overcome the drawbacks. This not only reduces the computational complexity but also unifies advantages of soft and hard threshold algorithms. Calculation of threshold values even the presence of abrupt intensity variations is simplified. Segmentation of skin lesions is easily achieved, in a more efficient way in the following algorithm. The experimental verification here is done on a large set of skin lesion images containing every possible artifacts which highly contributes to reversed segmentation outputs. This algorithm efficiency was measured based on a comparison with other prominent threshold methods. This approach has performed reasonably well and can be implemented in the expert skin cancer diagnostic systems.

scholarly journals Detection of Melanoma Skin Cancer using Convolutional Neural Network algorithm

2020 ◽  
Vol 9 (7) ◽  
pp. 115-118
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Skin Cancer ◽  
Skin Lesion ◽  
Convolutional Neural Network ◽  
Data Augmentation ◽  
Health Sector ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Melanoma Skin

Skin Cancer, a health issue which might cause severe consequences if not detected and controlled properly. Since there is a huge evolution in the health sector because of development in computer technologies, it is possible to analyze images efficiently and make correct decisions. Deep learning algorithms can be used for analyzing dermoscopic images by learning features of images in an incremental manner. Aim of our proposed method is to categorize skin lesion image as Benign or Melanoma and also to study the performance of Convolutional Neural Network algorithm using data augmentation technique and without data augmentation technique. The proposed method uses dataset from ISIC archive 2019. Steps involved in the proposed method are Image Pre-Processing, Image Segmentation and Image Classification. Initially, Image Pre-Processing algorithm is performed on skin lesion image. Image Segmentation algorithm is used to obtain Region of Interest (ROI) from pre-processed image. Then, Convolutional Neural Network algorithm classifies image as melanoma or benign. The Proposed method can rapidly detect melanoma skin cancer which aids in starting the treatment process without delay.

scholarly journals Skin Lesion Segmentation in Dermoscopy Imagery

2022 ◽  
Author(s):  
Shelly Garg ◽  
Balkrishan Jindal
Keyword(s):  
Skin Lesion ◽  
Error Rate ◽  
Morphological Operations ◽  
Dice Coefficient ◽  
Skin Imaging ◽  
Average Accuracy ◽  
Proposed Model ◽  
Input Sample ◽  
Time Accuracy ◽  
Sensitivity Specificity

The main purpose of this study is to find an optimum method for segmentation of skin lesion images. In the present world, Skin cancer has proved to be the most deadly disease. The present research paper has developed a model which encompasses two gradations, the first being pre-processing for the reduction of unwanted artefacts like hair, illumination or many other by enhanced technique using threshold and morphological operations to attain higher accuracy and the second being segmentation by using k-mean with optimized Firefly Algorithm (FFA) technique. The online image database from the International Skin Imaging Collaboration (ISIC) archive dataset and dermatology service of Hospital Pedro Hispano (PH2) dataset has been used for input sample images. The parameters on which the proposed method is measured are sensitivity, specificity, dice coefficient, jacquard index, execution time, accuracy, error rate. From the results, authors have observed proposed model gives the average accuracy value of huge number of cancer images using ISIC dataset is 98.9% and using PH2 dataset is 99.1% with minimize average less error rate. It also estimates the dice coefficient value 0.993 using ISIC and 0.998 using PH2 datasets. However, the results for the rest of the parameters remain quite the same. Therefore the outcome of this model is highly reassuring.

scholarly journals Real-Time Mobile-Phone-Aided Melanoma Skin Lesion Detection Using Triangulation Technique

2020 ◽  
Vol 11 (3) ◽  
pp. 9-31
Author(s):  
Kumud Tiwari ◽  
Sachin Kumar ◽  
R. K. Tiwari
Keyword(s):  
Skin Cancer ◽  
Skin Lesion ◽  
Cancer Detection ◽  
Mobile Application ◽  
Laboratory Testing ◽  
Skin Lesions ◽  
Lesion Detection ◽  
Detection Accuracy ◽  
Skin Cancer Detection ◽  
Melanoma Skin

Melanoma is a harmful disease among all types of skin cancer. Genetic factors and the exposure of UV rays causes melanoma skin lesions. Early diagnosis is important to identify malignant melanomas to improve the patient prognosis. A biopsy is a traditional method which is painful and invasive when used for skin cancer detection. This method requires laboratory testing which is not very efficient and time-consuming to detect skin lesions. To solve the above issue, a computer aided diagnosis (CAD) for skin lesion detection is needed. In this article, we have developed a mobile application with the capabilities to segment skin lesions in dermoscopy images using a triangulation method and categorize them into malignant or bengin lesions through a supervised method which is convolution neural network (CNN). This mobile application will make the skin cancer detection non-invasive which does not require any laboratory testing, making the detection less time consuming and inexpensive with a detection accuracy of 81%.

Sign in / Sign up

Export Citation Format

Share Document