Automatic segmentation of dermoscopy images using saliency combined with adaptive thresholding based on wavelet transform

Hu, Kai; Liu, Si; Zhang, Yuan; Cao, Chunhong; Xiao, Fen; Gao, Xieping

doi:10.1007/s11042-019-7160-0

Cited by 21 publications

(25 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhou et al designed a new nectar source selection method and crossover operation to guide the evolution of the population and introduced a backward learning variation strategy to improve the convergence speed of the algorithm [11]. Hu et al proposed an improved search equation that better balances the exploration and exploitation capabilities of the algorithm [12].…”

Section: Related Workmentioning

confidence: 99%

Otsu’s Image Segmentation Algorithm with Memory‐Based Fruit Fly Optimization Algorithm

Chai

2021

Complexity

View full text Add to dashboard Cite

In this paper, the most common pepper noise in grayscale image noise is investigated in depth in the median filtering algorithm, and the improved median filtering algorithm, adaptive switching median filtering algorithm, and adaptive polar median filtering algorithm are applied to the OTSU algorithm. Two improved OTSU algorithms such as the adaptive switched median filter-based OTSU algorithm and the polar adaptive median filter-based OTSU algorithm are obtained. The experimental results show that the algorithm can better cope with grayscale images contaminated by pretzel noise, and the segmented grayscale images are not only clear but also can better retain the detailed features of grayscale images. A genetic algorithm is a kind of search algorithm with high adaptive, fast operation speed, and good global space finding ability, and it will have a good effect when applied to the threshold finding of the OTSU algorithm. However, the traditional genetic algorithm will fall into the local optimal solution in different degrees when finding the optimal threshold. The advantages of the two interpolation methods proposed in this paper are that one is the edge grayscale image interpolation algorithm using OTSU threshold adaptive segmentation and the other is the edge grayscale image interpolation algorithm using local adaptive threshold segmentation, which can accurately divide the grayscale image region according to the characteristics of different grayscale images and effectively improve the loss of grayscale image edge detail information and jagged blur caused by the classical interpolation algorithm. The visual effect of grayscale images is enhanced by selecting grayscale images from the standard grayscale image test set and interpolating them with bilinear interpolation, bucolic interpolation, NEDI interpolation, and FEOI interpolation for interpolation simulation validation. The subjective evaluation and objective evaluation, as well as the running time, are compared, respectively, showing that the method of this paper can effectively improve the quality of grayscale image interpolation.

show abstract

Section: Related Workmentioning

confidence: 99%

Otsu’s Image Segmentation Algorithm with Memory‐Based Fruit Fly Optimization Algorithm

Chai

2021

Complexity

View full text Add to dashboard Cite

show abstract

“…However, for biomedical images, finding contours is a difficult task due to great variance in image quality. The authors in [20] used domain adaptation to minimize the inter-domain and intra-domain gap in three steps, which was also naturally an unsupervised and pre-trained approach to produce segmentation labels, but also requires high quality images, and resemblance in the two domains [21] proposes an unsupervised skin lesion segmentation method to combine color and brightness saliency maps into enhanced fusion saliency. Although it shows good results on dermoscopy images, it relies too much on coloring and contrast information and cannot effectively perform salient segmentation on grey-scale images (such as CECT).…”

Section: Unsupervised Biomedical Image Segmentationmentioning

confidence: 99%

PUB-SalNet: A Pre-Trained Unsupervised Self-Aware Backpropagation Network for Biomedical Salient Segmentation

et al. 2020

View full text Add to dashboard Cite

Salient segmentation is a critical step in biomedical image analysis, aiming to cut out regions that are most interesting to humans. Recently, supervised methods have achieved promising results in biomedical areas, but they depend on annotated training data sets, which requires labor and proficiency in related background knowledge. In contrast, unsupervised learning makes data-driven decisions by obtaining insights directly from the data themselves. In this paper, we propose a completely unsupervised self-aware network based on pre-training and attentional backpropagation for biomedical salient segmentation, named as PUB-SalNet. Firstly, we aggregate a new biomedical data set from several simulated Cellular Electron Cryo-Tomography (CECT) data sets featuring rich salient objects, different SNR settings, and various resolutions, which is called SalSeg-CECT. Based on the SalSeg-CECT data set, we then pre-train a model specially designed for biomedical tasks as a backbone module to initialize network parameters. Next, we present a U-SalNet network to learn to selectively attend to salient objects. It includes two types of attention modules to facilitate learning saliency through global contrast and local similarity. Lastly, we jointly refine the salient regions together with feature representations from U-SalNet, with the parameters updated by self-aware attentional backpropagation. We apply PUB-SalNet for analysis of 2D simulated and real images and achieve state-of-the-art performance on simulated biomedical data sets. Furthermore, our proposed PUB-SalNet can be easily extended to 3D images. The experimental results on the 2d and 3d data sets also demonstrate the generalization ability and robustness of our method.

show abstract

“…Currently, the detection of the object from the images by selecting the salient features has been getting great attention from researchers [5], [18], [19]. Saliencybased object identification has split into two categories: the unsupervised model has generated the map directly by getting the details and characteristics of an image.…”

Section: Figure 1: Benign and Malignant Melanomamentioning

confidence: 99%

An Improved Framework by Mapping Salient Features for Skin Lesion Detection and Classification using the Optimized Hybrid Features

Javed¹

2019

IJATCSE

View full text Add to dashboard Cite

Skin cancer extensively influences the quality of life and it can be dangerous or even lead patients towards death. For the skin lesion analysis, computer-aided systems are very helpful for a dermatologist. To segment, the lesion area is becoming a challenging task even for computer-aided systems due to the various difficulties such as similarities between the lesion and healthy skin area due to the poor contrast, uneven lesion edges, and other artifacts (bubbles, hairs, and ruler marker, etc.). This paper presents an improved saliency-based segmentation method to overcome challenges the current methods. The deep color and PHOG optimized features are passed into the support vector machine (SVM) to classify the images into two categories as benign or melanoma. The classification experiments are accomplished on three datasets termed as ISBI 2016, ISBI 2017, and PH2. The improved accuracies of 90.1%, 99.8 %, and 98.8 % are attained respectively for each dataset.

show abstract

Automatic segmentation of dermoscopy images using saliency combined with adaptive thresholding based on wavelet transform

Cited by 21 publications

References 42 publications

Otsu’s Image Segmentation Algorithm with Memory‐Based Fruit Fly Optimization Algorithm

Otsu’s Image Segmentation Algorithm with Memory‐Based Fruit Fly Optimization Algorithm

PUB-SalNet: A Pre-Trained Unsupervised Self-Aware Backpropagation Network for Biomedical Salient Segmentation

An Improved Framework by Mapping Salient Features for Skin Lesion Detection and Classification using the Optimized Hybrid Features

Contact Info

Product

Resources

About