Automated Measurement of Pancreatic Fat Deposition on Dixon <scp>MRI</scp> Using <scp>nnU‐Net</scp>

Lin, Dingyi; Wang, Ziyan; Li, Hong; Zhang, Hongxi; Deng, Liping; Hong, Richang; Sun, Shuiya; Zheng, Fenping; Zhou, Jiaqiang; Wang, Min

doi:10.1002/jmri.28275

Cited by 12 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the deep-learningbased identification of CT biomarkers facilitates the diag-nosis of T2D, such as measurements of pancreatic CT attenuation and visceral fat (Tallam et al, 2022). A 3D dualcontrast nnU-Net aided segmentation of pancreas on Dixon MRI images automates the assessment of pancreatic fat distribution with high reliability (Lin et al, 2023). In terms of pancreatic aging, a recent study by Le Goallec et al (2022) built an abdominal age predictor by training convolutional neural networks to predict abdominal age from liver MRIs and pancreas MRIs, which is driven by both liver and pancreas anatomical features, as well as surrounding organs and tissues.…”

Section: Imaging Traitsmentioning

confidence: 99%

Biomarkers of aging

Bao

Cao

Chen

et al. 2023

Sci. China Life Sci.

153

View full text Add to dashboard Cite

Aging biomarkers are a combination of biological parameters to (i) assess age-related changes, (ii) track the physiological aging process, and (iii) predict the transition into a pathological status. Although a broad spectrum of aging biomarkers has been developed, their potential uses and limitations remain poorly characterized. An immediate goal of biomarkers is to help us answer the following three fundamental questions in aging research: How old are we? Why do we get old? And how can we age slower? This review aims to address this need. Here, we summarize our current knowledge of biomarkers developed for cellular, organ, and organismal levels of aging, comprising six pillars: physiological characteristics, medical imaging, histological features, cellular alterations, molecular changes, and secretory factors. To fulfill all these requisites, we propose that aging biomarkers should qualify for being specific, systemic, and clinically relevant. Supporting Information The supporting information is available online at 10.1007/s11427-023-2305-0. The supporting materials are published as submitted, without typesetting or editing. The responsibility for scientific accuracy and content remains entirely with the authors.

show abstract

Section: Imaging Traitsmentioning

confidence: 99%

Biomarkers of aging

Bao

Cao

Chen

et al. 2023

Sci. China Life Sci.

153

View full text Add to dashboard Cite

show abstract

“…The entire network merely needs to study the difference between the input and output, reducing the learning targets and difficulties. In addition, this 3D volumetric network architecture, which could obtain context from adjacent slices for grasping richer boundary information about the pancreas (40). As expected, the performance of 3D CNN network is better than 2D network.…”

Section: Discussionmentioning

confidence: 60%

One 3D VOI-based deep learning radiomics strategy, clinical model and radiologists for predicting lymph node metastases in pancreatic ductal adenocarcinoma based on multiphasic contrast-enhanced computer tomography

Liao

Yang

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

PurposeWe designed to construct one 3D VOI-based deep learning radiomics strategy for identifying lymph node metastases (LNM) in pancreatic ductal adenocarcinoma on the basis of multiphasic contrast-enhanced computer tomography and to assist clinical decision-making.MethodsThis retrospective research enrolled 139 PDAC patients undergoing pre-operative arterial phase and venous phase scanning examination between 2015 and 2021. A primary group (training group and validation group) and an independent test group were divided. The DLR strategy included three sections. (1) Residual network three dimensional-18 (Resnet 3D-18) architecture was constructed for deep learning feature extraction. (2) Least absolute shrinkage and selection operator model was used for feature selection. (3) Fully connected network served as the classifier. The DLR strategy was applied for constructing different 3D CNN models using 5-fold cross-validation. Radiomics scores (Rad score) were calculated for distinguishing the statistical difference between negative and positive lymph nodes. A clinical model was constructed by combining significantly different clinical variables using univariate and multivariable logistic regression. The manifestation of two radiologists was detected for comparing with computer-developed models. Receiver operating characteristic curves, the area under the curve, accuracy, precision, recall, and F1 score were used for evaluating model performance.ResultsA total of 45, 49, and 59 deep learning features were selected via LASSO model. No matter in which 3D CNN model, Rad score demonstrated the deep learning features were significantly different between non-LNM and LNM groups. The AP+VP DLR model yielded the best performance in predicting status of lymph node in PDAC with an AUC of 0.995 (95% CI:0.989-1.000) in training group; an AUC of 0.940 (95% CI:0.910-0.971) in validation group; and an AUC of 0.949 (95% CI:0.914-0.984) in test group. The clinical model enrolled the histological grade, CA19-9 level and CT-reported tumor size. The AP+VP DLR model outperformed AP DLR model, VP DLR model, clinical model, and two radiologists.ConclusionsThe AP+VP DLR model based on Resnet 3D-18 demonstrated excellent ability for identifying LNM in PDAC, which could act as a non-invasive and accurate guide for clinical therapeutic strategies. This 3D CNN model combined with 3D tumor segmentation technology is labor-saving, promising, and effective.

show abstract

“…Despite various MRI-based methods assessing fat tissue, proton density fat fraction (PDFF) obtained using multiecho Dixon technology is considered the most practical and objective as it provides quantitative measurement of fat fraction through water and fat separation 33,34 . Moreover, it has excellent agreement with MR spectroscopy, which is generally the clinical criterion standard noninvasive technique for in vivo fat quantification, and has a wider spatial coverage of the pancreas 35 .…”

Section: Relaxation Timesmentioning

confidence: 99%

Quantitative Magnetic Resonance Imaging for the Pancreas

Fukukura

Kanki

2023

Invest Radiol

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is important for evaluating pancreatic disorders, and anatomical landmarks play a major role in the interpretation of results. Quantitative MRI is an effective diagnostic modality for various pathologic conditions, as it allows the investigation of various physical parameters. Recent advancements in quantitative MRI techniques have significantly improved the accuracy of pancreatic MRI. Consequently, this method has become an essential tool for the diagnosis, treatment, and monitoring of pancreatic diseases. This comprehensive review article presents the currently available evidence on the clinical utility of quantitative MRI of the pancreas.

show abstract

Automated Measurement of Pancreatic Fat Deposition on Dixon MRI Using nnU‐Net

Cited by 12 publications

References 37 publications

Biomarkers of aging

Biomarkers of aging

One 3D VOI-based deep learning radiomics strategy, clinical model and radiologists for predicting lymph node metastases in pancreatic ductal adenocarcinoma based on multiphasic contrast-enhanced computer tomography

Quantitative Magnetic Resonance Imaging for the Pancreas

Contact Info

Product

Resources

About