OCE-NGC: A neutrosophic graph cut algorithm using optimized clustering estimation algorithm for dermoscopic skin lesion segmentation

Hawas, Ahmed Refaat; Guo, Yanhui; Du, Chunlai; Polat, Kemal; Ashour, Amira S.

doi:10.1016/j.asoc.2019.105931

Cited by 26 publications

(17 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Al-Masni et al [2] proposed a Full Resolution Convolutional Network (FrCN) for the skin lesion segmentation, which learns full resolution features from each pixel of an input image. A segmentation method is realized by Hawas et al [36] for the neutrosophic graph coping with the constraints that included small data set, removal of artifacts, excessive data increase, and contrast stretching. They also confirmed that the CNN model's performance with a domain transfer feature is better than the CNNs with a deep layer network.…”

Section: Methods For Lesion Segmentationmentioning

confidence: 99%

Dermo-DOCTOR: A framework for concurrent skin lesion detection and recognition using a deep convolutional neural network with end-to-end dual encoders

Hasan¹,

Roy²,

Mondal³

et al. 2021

Preprint

View full text Add to dashboard Cite

Background and ObjectiveAutomated skin lesion analysis for simultaneous detection and recognition is still challenging for inter-class homogeneity and intra-class heterogeneity, leading to low generic capability of a Single Convolutional Neural Network (CNN) with limited datasets. MethodsThis article proposes an end-to-end deep CNN-based framework for simultaneous detection and recognition of the skin lesions, named Dermo-DOCTOR, consisting of two encoders. The feature maps from two encoders are fused channel-wise, called Fused Feature Map (FFM). The FFM is utilized for decoding in the detection sub-network, concatenating each stage of two encoders' outputs with corresponding decoder layers to retrieve the lost spatial information due to pooling in the encoders. For the recognition sub-network, the outputs of three fully connected layers, utilizing feature maps of two encoders and FFM, are aggregated to obtain a final lesion class. We train and evaluate the proposed Dermo-Doctor utilizing two publicly available benchmark datasets, such as ISIC-2016 and ISIC-2017.

show abstract

Section: Methods For Lesion Segmentationmentioning

confidence: 99%

Dermo-DOCTOR: A framework for concurrent skin lesion detection and recognition using a deep convolutional neural network with end-to-end dual encoders

Hasan¹,

Roy²,

Mondal³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Although this technique offers advantages in terms of noise sensitivity and cluster initialization, it has drawbacks in terms of segmentation, which is caused by inappropriate data grouping. KMC and FCM were used in conjunction with bio-optimization techniques in [23][24][25], with the kernel function of the combined model being altered. FCM with Harmony Search Algorithm (FCM-HSA), FCM with Artificial Bee Colony (FCM-ABC), FCM with ant colony optimization (FCM-ACO), and FCM with genetic algorithm (FCM-GA) are just a few of the hybrid methodologies available.…”

Section: Literature Surveymentioning

confidence: 99%

SCDC-Net: Skin Cancer Detection and Classification using Deep Q Neural Network with Hybrid Features

Nyemeesha

2022

IJRITCC

View full text Add to dashboard Cite

Skin cancer is one of the most severe malignancies that may affect individuals of all ages. It can affect people of all races and ethnicities. Thus, early detection and treatment of skin cancer have the potential to save millions of lives. Because of the high degree of similarity between skin lesions, conventional machine learning approaches failed to provide the highest possible detection and classification accuracy in the skin cancer detection and classification (SCDC) system. To achieve the robust performance, this work is presented a SCDC-Net by employing deep learning, transfer learning models with hybrid features. Initially, UG-Net based transfer learning model is developed by combining generative adversarial networks (GAN) and U-Net. Here, UG-Net is used to remove hair from skin lesions and also preprocess enhances lesion. In addition, Hybrid U-Net (HU-Net) is used to localize the disease effected area of skin cancer. Further, various hybrid features are extracted from the segmented output by employing the gray-level cooccurrence matrix (GLCM) based texture characteristics, the discrete wavelet transform (DWT)-based low-level features, and the computation of image statistics for the texture, low-level, and colour features, respectively. In order to ensure the highest possible performance of the system, a deep q neural network (DQNN) was constructed for the classification of skin cancer using GLCM, DWT, and statistical colour features. The simulation results shows that the proposed method resulted in superior subjective and objective performance as compared to state of art approaches on ISIC-2019 public challenge dataset.

show abstract

“…Cụ thể, nhiều thuật toán mới ra đời đã chứng minh rằng phương pháp này là một hướng nghiên cứu đầy hứa hẹn trong cộng đồng nghiên cứu phân đoạn ảnh. Các phương pháp dựa trên lí thuyết đồ thị đã có nhiều ứng dụng quan trọng trong lĩnh vực thị giác máy tính, đặc biệt là các ứng dụng trong phân đoạn ảnh (Zhu, Zhang, Xu, & Deng, 2021;Hawas, Guo, Du, Polat, & Ashour, 2020;Bejar, Guimaraes, & Miranda, 2020;Wang, Oda, Hayashi, Yoshino, Yamamoto, Frangi, & Mori, 2020). Dựa trên các nguyên lí cấu trúc hình thức về mức độ tương đồng hoặc lân cận trong việc gom nhóm thị giác, đồ thị được chia thành các vùng tương ứng với một vùng hay đối tượng nào đó trong ảnh.…”

Section: E Hướng Tiếp Cận Phân Hoạch đồ Thịunclassified

Phân Đoạn Ảnh Và Ncuts

Ý¹,

Hùng²,

Huy³

et al. 2021

Tạp chí Khoa học

View full text Add to dashboard Cite

Trong nhiều thập kỉ qua, nhiều công trình nghiên cứu khoa học đóng góp không ngừng trong lĩnh vực thị giác máy tính nói chung cũng như nghiên cứu phân đoạn ảnh nói riêng. Trong đó, phân đoạn ảnh là quá trình tiền xử lí quan trọng trong hầu hết các ứng dụng xử lí ảnh. Chúng tôi tóm tắt và đánh giá các kĩ thuật phân đoạn ảnh và phân chia các kĩ thuật này thành các nhóm gồm: kĩ thuật dựa trên phát hiện cạnh/biên, kĩ thuật phân ngưỡng, phương trình vi phân, phương pháp gom nhóm, kĩ thuật dựa trên phân hoạch đồ thị. Tiếp theo, chúng tôi trình bày ưu điểm và khuyết điểm của thuật toán Ncuts, là thuật toán kinh điển khá phổ biến trong phân đoạn ảnh dựa trên đồ thị. Thuật toán Ncuts (Shi, & Malik, 2000) được đưa ra năm 2000 nhưng đã được áp dụng thành công và cho kết quả tối ưu cho nhiều ứng dụng xử lí ảnh cũng như các ứng dụng khoa học kĩ thuật.

show abstract

OCE-NGC: A neutrosophic graph cut algorithm using optimized clustering estimation algorithm for dermoscopic skin lesion segmentation

Cited by 26 publications

References 33 publications

Dermo-DOCTOR: A framework for concurrent skin lesion detection and recognition using a deep convolutional neural network with end-to-end dual encoders

Dermo-DOCTOR: A framework for concurrent skin lesion detection and recognition using a deep convolutional neural network with end-to-end dual encoders

SCDC-Net: Skin Cancer Detection and Classification using Deep Q Neural Network with Hybrid Features

Phân Đoạn Ảnh Và Ncuts

Contact Info

Product

Resources

About