Segmentation of skin lesion images using discrete wavelet transform

Ramya, J.; VijayLakshmi, H. C.; Saifuddin, Huda

doi:10.1016/j.bspc.2021.102839

Cited by 22 publications

(6 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chagas et al [29] extracted the features of the skin lesion area using a sliding window. Ramya et al [30] addressed the complexities inherent in dermoscopy images by utilizing wavelet transforms. Garg and Jindal [31] introduced a segmentation technique for skin lesion using dermoscopic images.…”

Section: Traditional Skin Lesion Segmentation Methodsmentioning

confidence: 99%

Weakly supervised skin lesion segmentation based on spot‐seeds guided optimal regions

Al‐Huda

Yuan

Yao

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Automatic skin lesion segmentation is the most critical and relevant task in computeraided skin cancer diagnosis. Methods based on convolutional neural networks (CNNs) are mainly used in current skin lesion segmentation. The requirement of huge pixellevel labels is a significant obstacle to achieve semantic segmentation of skin lesion by CNNs. In this paper, a novel weakly supervised framework for skin lesion segmentation is presented, which generates high-quality pixel-level annotations and optimizes the segmentation network. A hierarchical image segmentation algorithm can predict a boundary map for training images. Then, the optimal regions of candidate hierarchical levels are selected. Afterward, Superpixels-CRF built on the optimal regions is guided by spot seeds to propagate information from spot seeds to unlabeled regions, resulting in high-quality pixel-level annotations. Using these high-quality pixel-level annotations, a segmentation network can be trained and segmentation masks can be predicted. To iteratively optimize the segmentation network, the predicted segmentation masks are refined and the segmentation network are retrained. Comparative experiments demonstrate that the proposed segmentation framework reduces the gap between weakly and fully supervised skin lesion segmentation methods, and achieves state-of-the-art performance while reducing human labeling efforts.

show abstract

Section: Traditional Skin Lesion Segmentation Methodsmentioning

confidence: 99%

Weakly supervised skin lesion segmentation based on spot‐seeds guided optimal regions

Al‐Huda

Yuan

Yao

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Researchers have introduced a hybrid k-means segmentation [4], in which images are segmented using kmeans clustering to locate the precise lesion region, and then the firefly technique is implemented to improve segmentation accuracy [5]. In histogram segmentation with the Genetic algorithm, initially computation of a set of image pixels using c-means clustering is employed, then graph cut methodology is employed to attain the segmentation of skin lesions [6,7].…”

Section: Skin Lesion Segmentation Using Deep Learningmentioning

confidence: 99%

Enhancing skin lesion segmentation with U-Net++: Design, analysis, and performance evaluation

Patil,

Patil

2024

View full text Add to dashboard Cite

The present research examines the enhancement of skin lesion segmentation with U-Net++. Achieving accurate classification of dermoscopy images is heavily contingent on the precise segmentation of skin lesions or nodules. However, this task is considerably challenging due to the elusive edges, irregular perimeters, and variations both within and across lesion classes. Despite numerous existing algorithms for segmenting skin lesions from dermoscopic images, they often fall short of industry benchmarks in terms of precision. To address this, our research introduces a novel U-Net++ architecture, implementing tailored adjustments to feature map dimensions. The aim is to significantly enhance automated segmentation precision for dermoscopic images. Our evaluation involved a comprehensive assessment of the model's performance, encompassing an exploration of various parameters such as epochs, batch size, and optimizer selections. Additionally, we conducted extensive testing using augmentation techniques to bolster the image volume within the HAM10000 dataset. A key innovation in our research is the integration of a hair removal process into the U-Net++ algorithm, significantly enhancing image quality and subsequently leading to improved segmentation accuracy. The results of our proposed method demonstrate substantial advancements, showcasing an impressive Mean Intersection over Union (IoU) of 84.1%, a Mean Dice Coefficient of 91.02%, and a Segmentation Test Accuracy of 95.10%. Our suggested U-Net++ algorithm does a better job of segmenting than U-Net, Modified U-Net, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). This shows that it could be used to improve dermoscopy image analysis. Our proposed algorithm shows remarkable improvement in both observational outcomes and classifier performance.

show abstract

“…This method gathered the Jaccard coefficient with 0.989 in ISIC 2018 and 0.96 in ISIC 2016.The disadvantages of this method includes the sensitivity and the specificity rate were less. Ramya et al [18] offered that detection of malignant melanoma skin cancer by segmentation via automated (CAD). The main attribute of this technique was handling the complexities which include hair follicles, moles, swellings, sweat glands, recognizing the distinct layers by using a discrete wavelet transform.…”

Section: Related Workmentioning

confidence: 99%

An Effective Skin Lesion Segmentation in Dermoscopic Images using Optimized Deep Learning Framework

Kaur¹,

Kaur²

2023

INDJCSE

View full text Add to dashboard Cite

Melanoma is the most threatening type of skin cancer caused by the uncontrolled growth of melanocytes. Analysis of melanoma skin cancer in advance is significant for the better treatment to avoid transferring into other parts of the body. Manual inspections are done by the specialists tends to inaccurate outcomes. The effective role to identify the disease is processed through medical image processing. Segmentation of an image is indulged for extracting precise information of each image pixel with certain characteristics. Computer Aided Diagnosis (CAD) based deep learning technique is applied effectively for the evaluation of different skin conditions using dermoscopic images. Several computational methods are utilised for the exact and rapid identification of the lesion. The proposed method of Deep CNN-OAD (Convolutional neural network-Optimized Adam) comprises the following steps as Pre-processing, Colour enhancement and image segmentation. The input images are pre-processed by Adaptive bilateral filtering and Min-Max normalisation methods in order to remove noises. Afterwards, colour enhancement is done through equalisation of adaptive histogram for upgrading the quality of an image. Finally, Deep CNN-OAD is used for accurately segmenting the lesions. MATLAB is the simulation tool used for predicting the performance of output. The proposed method is examined with the ISIC 2019 dataset. The mean value of various performance metrics are evaluated on the basis of sample comparison. The accuracy rate achieved through segmentation performance is 94.06% in the proposed work.

show abstract

Segmentation of skin lesion images using discrete wavelet transform

Cited by 22 publications

References 46 publications

Weakly supervised skin lesion segmentation based on spot‐seeds guided optimal regions

Weakly supervised skin lesion segmentation based on spot‐seeds guided optimal regions

Enhancing skin lesion segmentation with U-Net++: Design, analysis, and performance evaluation

An Effective Skin Lesion Segmentation in Dermoscopic Images using Optimized Deep Learning Framework

Contact Info

Product

Resources

About