SISTER: Spectral-Image Similarity-Based Tensor With Enhanced-Sparsity Reconstruction for Sparse-View Multi-Energy CT

Hu, Dianlin; Wu, Weiwen; Xu, Moran; Zhang, Yanbo; Liu, Jin; Ge, Rongjun; Chen, Yang; Luo, Limin; Coatrieux, Gouenou

doi:10.1109/tci.2019.2956886

Cited by 43 publications

(24 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When using multi-center datasets, the imaging quality is another issue that needs to pay attention. Some notable works have discussed imaging quality issues ( 28 – 30 ), which inspire us to carry out future work.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study

et al. 2021

View full text Add to dashboard Cite

BackgroundHistologic phenotype identification of Non-Small Cell Lung Cancer (NSCLC) is essential for treatment planning and prognostic prediction. The prediction model based on radiomics analysis has the potential to quantify tumor phenotypic characteristics non-invasively. However, most existing studies focus on relatively small datasets, which limits the performance and potential clinical applicability of their constructed models.MethodsTo fully explore the impact of different datasets on radiomics studies related to the classification of histological subtypes of NSCLC, we retrospectively collected three datasets from multi-centers and then performed extensive analysis. Each of the three datasets was used as the training dataset separately to build a model and was validated on the remaining two datasets. A model was then developed by merging all the datasets into a large dataset, which was randomly split into a training dataset and a testing dataset. For each model, a total of 788 radiomic features were extracted from the segmented tumor volumes. Then three widely used features selection methods, including minimum Redundancy Maximum Relevance Feature Selection (mRMR), Sequential Forward Selection (SFS), and Least Absolute Shrinkage and Selection Operator (LASSO) were used to select the most important features. Finally, three classification methods, including Logistics Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) were independently evaluated on the selected features to investigate the prediction ability of the radiomics models.ResultsWhen using a single dataset for modeling, the results on the testing set were poor, with AUC values ranging from 0.54 to 0.64. When the merged dataset was used for modeling, the average AUC value in the testing set was 0.78, showing relatively good predictive performance.ConclusionsModels based on radiomics analysis have the potential to classify NSCLC subtypes, but their generalization capabilities should be carefully considered.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This dictionary can form a database and learn the mapping from low-resolution images to high-resolution images from the database. However, such methods are computationally complex and require many computing resources [2] [3]. Based on CNN (Convolutional Neural Network) model, SRCNN [4] first introduced CNN into SISR.…”

Section: Image Super Resolutionmentioning

confidence: 99%

Deep Iteration Assisted by Multi-level Obey-pixel Network Discriminator (DIAMOND) for Medical Image Recovery

Xu,

Hu,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Image restoration is a typical ill-posed problem, and it contains various tasks. In the medical imaging field, an ill-posed image interrupts diagnosis and even following image processing. Both traditional iterative and up-to-date deep networks have attracted much attention and obtained a significant improvement in reconstructing satisfying images. This study combines their advantages into one unified mathematical model and proposes a general image restoration strategy to deal with such problems. This strategy consists of two modules. First, a novel generative adversarial net(GAN) with WGAN-GP training is built to recover image structures and subtle details. Then, a deep iteration module promotes image quality with a combination of pre-trained deep networks and compressed sensing algorithms by ADMM optimization. (D)eep (I)teration module suppresses image artifacts and further recovers subtle image details, (A)ssisted by (M)ulti-level (O)bey-pixel feature extraction networks (D)iscriminator to recover general structures. Therefore, the proposed strategy is named DIAMOND.

show abstract

“…The image-domain based methods [19,20] firstly reconstruct images from the spectral CT dataset and then decompose the materials from the reconstructed results. There are many iterative reconstruction methods developed for the first step, but less work concerned about the second step, such as TDL [21], L0TDL [22], SSCMF [23], NLCTF [24], ASSIST [25], L0-PICCS [26], SISTER [27]. In this work, we focus on the second step of the image-domain based methods.…”

Section: Introductionmentioning

confidence: 99%

Image-Domain Based Material Decomposition by Multi-Constraint Optimization for Spectral CT

Feng

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

As a new generation computed tomography (CT) technology, spectral CT has great potential in many aspects, especially in the identification and decomposition of materials. To achieve higher accuracy of materials decomposition, we propose a multi-constraint based nonlocal total variation (NLTV) method, named as MCNLTV. Because image-domain based material decomposition belongs to the twostep material decomposition method, the Filter Back-Projection (FBP) algorithm or SART algorithm is used to reconstruct spectral CT images in the first step. Then the material attenuation coefficient matrix is obtained from the reconstruction results. In the second step, MCNLTV regularization is utilized to obtain the material decomposition image. Both simulation experiments and real data experiments are carried out. Experiment results show that the proposed method can obtain higher accuracy of material decomposition than traditional total variation based material decomposition (TVMD), ROF-LLT regularization and direct inverse transformation (DI) for spectral CT. INDEX TERMS Spectral CT; image-domain; multi-constraint optimization; material decomposition.

show abstract

SISTER: Spectral-Image Similarity-Based Tensor With Enhanced-Sparsity Reconstruction for Sparse-View Multi-Energy CT

Cited by 43 publications

References 49 publications

Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study

Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study

Deep Iteration Assisted by Multi-level Obey-pixel Network Discriminator (DIAMOND) for Medical Image Recovery

Image-Domain Based Material Decomposition by Multi-Constraint Optimization for Spectral CT

Contact Info

Product

Resources

About