Diffusion weighted magnetic resonance imaging of liver: Principles, clinical applications and recent updates

Shenoy-Bhangle, Anuradha S.; Baliyan, Vinit; Kordbacheh, Hamed; Guimarães, Alexander R.; Kambadakone, Avinash

doi:10.4254/wjh.v9.i26.1081

Cited by 48 publications

(45 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the viewpoint of feature analysis in image processing, ADC is a voxel‐based feature that uses voxel intensities of the ADC map as features in classification. Although it is very simple to use and is intuitive to interpret clinical results, previous studies have reported conflicting results using the ADC value to estimate the pathological grade of HCC . This conflict of reported results may be due to the overlap in the ADC values of different malignant HCCs, while another possible reason is that ADC measurements may result from calculation errors as they are very sensitive to motion and artifacts in DWI, which remarkably decreases the performance of ADC measurement for lesion characterization .…”

Section: Introductionmentioning

confidence: 99%

Grading of hepatocellular carcinoma based on diffusion weighted images with multiple b‐values using convolutional neural networks

et al. 2019

View full text Add to dashboard Cite

Purpose To effectively grade hepatocellular carcinoma (HCC) based on deep features derived from diffusion weighted images (DWI) with multiple b‐values using convolutional neural networks (CNN). Materials and Methods Ninety‐eight subjects with 100 pathologically confirmed HCC lesions from July 2012 to October 2018 were included in this retrospective study, including 47 low‐grade and 53 high‐grade HCCs. DWI was performed for each subject with a 3.0T MR scanner in a breath‐hold routine with three b‐values (0,100, and 600 s/mm2). First, logarithmic transformation was performed on original DWI images to generate log maps (logb0, logb100, and logb600). Then, a resampling method was performed to extract multiple 2D axial planes of HCCs from the log map to increase the dataset for training. Subsequently, 2D CNN was used to extract deep features of the log map for HCCs. Finally, fusion of deep features derived from three b‐value log maps was conducted for HCC malignancy classification. Specifically, a deeply supervised loss function was devised to further improve the performance of lesion characterization. The data set was split into two parts: the training and validation set (60 HCCs) and the fixed test set (40 HCCs). Four‐fold cross validation with 10 repetitions was performed to assess the performance of deep features extracted from single b‐value images for HCC grading using the training and validation set. Receiver operating characteristic curve (ROC) and area under the curve (AUC) values were used to assess the characterization performance of the proposed deep feature fusion method to differentiate low‐grade and high‐grade in the fixed test set. Results The proposed fusion of deep features derived from logb0, logb100, and logb600 with deeply supervised loss function generated the highest accuracy for HCC grading (80%), thus outperforming the method of deep feature derived from the ADC map directly (72.5%), the original b0 (65%), b100 (68%), and b600 (70%) images. Furthermore, AUC values of the deep features of the ADC map, the deep feature fusion with concatenation, and the proposed deep feature fusion with deeply supervised loss function were 0.73, 0.78, and 0.83, respectively. Conclusion The proposed fusion of deep features derived from the logarithm of the three b‐value images yields high performance for HCC grading, thus providing a promising approach for the assessment of DWI in lesion characterization.

show abstract

Section: Introductionmentioning

confidence: 99%

Grading of hepatocellular carcinoma based on diffusion weighted images with multiple b‐values using convolutional neural networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Furthermore, DWI imaging is susceptible to artifacts (e.g., blurring, ghosting, and distortions) and offers a limited image quality; therefore, DWI is currently used as complementary and not as a replacement to conventional sequences in the evaluation of NAFLD [47].…”

Section: Diffusion-weighted Mr Imagingmentioning

confidence: 99%

“…DWI does not require administration of intravenous contrast; consequently the technique might represent a reasonable option for patients with kidney failure, where gadolinium-based contrast substances represent a contraindication due to the increased risk of developing nephrogenic systemic fibrosis, while iodinated CT contrast might lead to an even greater impairment of renal function, being also contraindicated [47].…”

Section: Diffusion-weighted Mr Imagingmentioning

confidence: 99%

Current Noninvasive MR-Based Imaging Methods in Assessing NAFLD Patients

Feier¹,

Muntean²,

Bastati³

et al. 2019

Nonalcoholic Fatty Liver Disease - An Update

View full text Add to dashboard Cite

The chapter will focus on the different aspects of nonalcoholic fatty liver disease (NAFLD). An update in noninvasive MR-based imaging will be offered in detail, pointing mainly to fat, iron, and fibrosis deposition and the accuracy of quantitative methods in disease grading and severity assessment. NAFLD is the most common cause of chronic liver disease (CLD) in Western countries. MRI is used to evaluate the disease, to assess the severity, and to quantify the amount of fat deposition, being also the method of choice to evaluate and quantify iron overload. Diagnosis and staging of liver fibrosis is one of the most challenging aspects of noninvasive imaging. "Virtual biopsy" refers to the possibility of imaging techniques to depict, map, and measure fibrosis minimizing the need for invasive liver biopsies in CLD. MRI allows an accurate determination of steatosis, iron overload, and fibrosis, even if they coexist.

show abstract

“…Данная методика практически не приводит к удлинению времени выполнения МРТ и легка в применении [42]. Из недостатков ДВИ отмечают низкую воспроизводимость значений ИКД из-за отсутствия стандартизации методики, а также высокую чувствительность к артефактам [29,34]. МР-перфузия является новейшей методикой, позволяющей по аналогии с КТ-перфузией не только диагностировать морфологические изменения, но и определять функциональные параметры органов и тканей.…”

Section: компьютерная томографияunclassified

Radiological Methods in Diagnostics of Focal Liver Lesions

Schekoturov¹,

Bakhtiozin²,

Серова³

et al. 2018

Rejr

View full text Add to dashboard Cite

ель исследования. Особое место среди заболеваний печени занимают различные опухоли и опухолеподобные поражения. За последние годы, благодаря внедрению в клиническую практику более совершенной диагностической аппаратуры и достаточно широкому применению различных контрастных препаратов при исследованиях брюшной полости с помощью ультразвукового метода (УЗИ), мультиспиральной компьютерной томографии (МСКТ) и магнитно-резонансной томографии (МРТ) значительно повысились возможности диагностики различных очаговых поражений печени. Кроме того, упростилась дифференциальная диагностика доброкачественных и злокачественных новообразований, в том числе, при размерах очагов менее 1 см. В данном научном обзоре описаны возможности как «рутинного» метода исследования печени-УЗИ, так и новейших методик, которые внедряются в современную практику, таких как УЗИ с внутривенным контрастированием, УЗИ эластография и перфузионная КТ и МРТ. Представлены преимущества каждого из методов, а также ограничения их применения в клинической практике.

show abstract

Diffusion weighted magnetic resonance imaging of liver: Principles, clinical applications and recent updates

Cited by 48 publications

References 101 publications

Grading of hepatocellular carcinoma based on diffusion weighted images with multiple b‐values using convolutional neural networks

Grading of hepatocellular carcinoma based on diffusion weighted images with multiple b‐values using convolutional neural networks

Current Noninvasive MR-Based Imaging Methods in Assessing NAFLD Patients

Radiological Methods in Diagnostics of Focal Liver Lesions

Contact Info

Product

Resources

About