Iterated graph cut method for automatic and accurate segmentation of finger-vein images

Lei, Lei; Xi, Feng; Chen, Shengyao; Liu, Zhong

doi:10.1007/s10489-020-01828-8

Cited by 9 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The other radiologist reviewed the segmentation result independently to sure the accuracy of the segmentation. In addition, for the purpose of quantitative comparisons the segmentation agreements, three assessment metrics including dice coefficient (DC) ( 36 ), global consistency error (GCE) ( 37 ) and probabilistic rand index (PRI) ( 38 , 39 ), are introduced to evaluate the segmentation results. The values of DC, GCE and PRI are 0.873, 0.052 and 0.792, respectively.…”

Section: Materials and Workflow For Hcc Gradingmentioning

confidence: 99%

Dictionary learning LASSO for feature selection with application to hepatocellular carcinoma grading using contrast enhanced magnetic resonance imaging

Lei

et al. 2023

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

IntroductionThe successful use of machine learning (ML) for medical diagnostic purposes has prompted myriad applications in cancer image analysis. Particularly for hepatocellular carcinoma (HCC) grading, there has been a surge of interest in ML-based selection of the discriminative features from high-dimensional magnetic resonance imaging (MRI) radiomics data. As one of the most commonly used ML-based selection methods, the least absolute shrinkage and selection operator (LASSO) has high discriminative power of the essential feature based on linear representation between input features and output labels. However, most LASSO methods directly explore the original training data rather than effectively exploiting the most informative features of radiomics data for HCC grading. To overcome this limitation, this study marks the first attempt to propose a feature selection method based on LASSO with dictionary learning, where a dictionary is learned from the training features, using the Fisher ratio to maximize the discriminative information in the feature.MethodsThis study proposes a LASSO method with dictionary learning to ensure the accuracy and discrimination of feature selection. Specifically, based on the Fisher ratio score, each radiomic feature is classified into two groups: the high-information and the low-information group. Then, a dictionary is learned through an optimal mapping matrix to enhance the high-information part and suppress the low discriminative information for the task of HCC grading. Finally, we select the most discrimination features according to the LASSO coefficients based on the learned dictionary.Results and discussionThe experimental results based on two classifiers (KNN and SVM) showed that the proposed method yielded accuracy gains, compared favorably with another 5 state-of-the-practice feature selection methods.

show abstract

Section: Materials and Workflow For Hcc Gradingmentioning

confidence: 99%

Dictionary learning LASSO for feature selection with application to hepatocellular carcinoma grading using contrast enhanced magnetic resonance imaging

Lei

et al. 2023

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, all these methods suffer from low accuracy and poor robustness of segmentation results [16]. To overcome these problems, more and more modern mathematical knowledge and tools, such as statistical theory, graph theory, partial differential equations, and variational methods, have been used in the field of image segmentation, resulting in many excellent methods such as Markov random field models [17,18], graph-based segmentation methods [19][20][21][22], and variational model-based methods [23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38].…”

Section: Introductionmentioning

confidence: 99%

Multi-Phase Image Segmentation Based on Low-Rank Prior Decomposition

Guo

Huo

2022

IEEE Access

View full text Add to dashboard Cite

Natural images usually contain structure component and texture component. The existing image segmentation models based on piecewise smooth cannot handle such natural images containing texture well. For this reason, in this paper, a multi-region image segmentation model based on low-rank prior decomposition is proposed. We use the low-rank prior to characterize the texture component, and the total variational norm to characterize the piecewise smooth structure component so that the proposed method can perform image decomposition and image segmentation tasks simultaneously. Then, the decomposed structure image can be used for image segmentation, and thus we can improve the accuracy of segmentation. To solve the new model, the alternating direction multiplier method is designed. The experimental results show that compared with the related classical models, the new model can significantly improve the subjective visual effect of image segmentation and the mean values of the precision rate, F1measure, and Jaccard similarity coefficient for the new model on the test images are at least 3.29%, 1.74%, and 3.13% higher, respectively..

show abstract