Prediction of synchronous distant metastasis of primary pancreatic ductal adenocarcinoma using the radiomics features derived from 18F-FDG PET/MR imaging DOI Creative Commons
Jing Gao,

Yaya Bai,

Fei Miao

et al.

Research Square (Research Square), Journal Year: 2022, Volume and Issue: unknown

Published: Sept. 20, 2022

Abstract Objective Despite the improved lesion detectability as outcome of 18 F-FDG PET/MR, small distant metastasis pancreatic ductal adenocarcinoma (PDAC) often remains invisible. Our goal is to explore potential joint radiomics analysis PET and MRI imaging (PET-MRI) primary tumors for predicting risk in patients with PDAC. Methods Nighty one PDAC before confirmation or exclusion SDM were retrospectively investigated. Among them, 66 who received PET/CT multi-sequence separately included development model (development cohort), 25 scanned hybrid PET/MR incorporated independent verification (external test cohort). A signature was constructed using selected PET-MRI features tumors. Furthermore, a nomogram developed by combining clinical indicators assisting this way assessment patients’ risk. Results In cohort, had better performance [area under curve (AUC): 0.93, sensitivity:87.0%, specificity:85.0%] than (AUC: 0.70, P < 0.001; sensitivity: 70%, specificity: 65%), well 0.89, > 0.05; 65%, 100%). For external test, yielded an AUC 0.85, sensitivity 78.6%, specificity 90.9%, which comparable (P = 0.34). Conclusions The preliminary results confirmed MRI-based robust effective prediction preoperative patients. in-depth tumor may offer complementary information provide hints cancer staging.

Language: Английский

Multiparametric MRI for Assessment of the Biological Invasiveness and Prognosis of Pancreatic Ductal Adenocarcinoma in the Era of Artificial Intelligence DOI Creative Commons
Ben Y. Zhao,

Buyue Cao,

Tianyi Xia

et al.

Journal of Magnetic Resonance Imaging, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 9, 2025

Pancreatic ductal adenocarcinoma (PDAC) is the deadliest malignant tumor, with a grim 5‐year overall survival rate of about 12%. As its incidence and mortality rates rise, it likely to become second‐leading cause cancer‐related death. The radiological assessment determined stage management PDAC. However, highly heterogeneous disease complexity tumor microenvironment, challenging adequately reflect biological aggressiveness prognosis accurately through morphological evaluation alone. With dramatic development artificial intelligence (AI), multiparametric magnetic resonance imaging (mpMRI) using specific contrast media special techniques can provide functional information high image quality powerful tool in quantifying intratumor characteristics. Besides, AI has been widespread field medical analysis. Radiomics high‐throughput mining quantitative features from that enables data be extracted applied for better decision support. Deep learning subset neural network algorithms automatically learn feature representations data. AI‐enabled biomarkers mpMRI have enormous promise bridge gap between personalized medicine demonstrate huge advantages predicting characteristics current AI‐based models PDAC operate mainly realm single modality relatively small sample size, technical reproducibility interpretation present barrage new potential challenges. In future, integration multi‐omics data, such as radiomics genomics, alongside establishment standardized analytical frameworks will opportunities increase robustness interpretability bring these closer clinical practice. Evidence Level 3 Technical Efficacy Stage 4

Language: Английский

Citations

1
Radiomics and deep learning models for CT pre-operative lymph node staging in pancreatic ductal adenocarcinoma: A systematic review and meta-analysis DOI
Roberto Castellana, Salvatore Claudio Fanni, Claudia Roncella

et al.

European Journal of Radiology, Journal Year: 2024, Volume and Issue: 176, P. 111510 - 111510

Published: May 18, 2024

Language: Английский

Citations

5
Preoperative Prediction of Lymph Node Metastasis of Pancreatic Ductal Adenocarcinoma Based on a Radiomics Nomogram of Dual-Parametric MRI Imaging DOI Creative Commons
Lin Shi, Ling Wang, Cuiyun Wu

et al.

Frontiers in Oncology, Journal Year: 2022, Volume and Issue: 12

Published: July 6, 2022

This study aims to uncover and validate an MRI-based radiomics nomogram for detecting lymph node metastasis (LNM) in pancreatic ductal adenocarcinoma (PDAC) patients prior surgery.We retrospectively collected 141 with pathologically confirmed PDAC who underwent preoperative T2-weighted imaging (T2WI) portal venous phase (PVP) contrast-enhanced T1-weighted (T1WI) scans between January 2017 December 2021. The were randomly divided into training (n = 98) validation 43) cohorts at a ratio of 7:3. For each sequence, 1037 features extracted analyzed. After applying the gradient-boosting decision tree (GBDT), key MRI selected. Three scores (rad-score 1 PVP, rad-score 2 T2WI, 3 T2WI combined PVP) calculated. Rad-score clinical independent risk factors construct prediction LNM by multivariable logistic regression analysis. predictive performances rad-scores assessed area under operating characteristic curve (AUC), utility was analysis (DCA).Six eight PVP ten found be associated LNM. Multivariate showed that MRI-reported LN status predictors. In cohorts, AUCs 1, 0.769 0.751, 0.807 0.784, 0.834 0.807, respectively. value similar both (P > 0.05). constructed encouraging benefit, AUC 0.845 cohort 0.816 cohort.The derived from based on outstanding performance PDAC.

Language: Английский

Citations

18
Clinical-Radiomics Nomogram Based on Contrast-Enhanced Ultrasound for Preoperative Prediction of Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma DOI Open Access
Liqing Jiang, Zijian Zhang,

Shiyan Guo

et al.

Cancers, Journal Year: 2023, Volume and Issue: 15(5), P. 1613 - 1613

Published: March 5, 2023

This study aimed to establish a new clinical-radiomics nomogram based on ultrasound (US) for cervical lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC). We collected 211 patients with PTC between June 2018 and April 2020, then we randomly divided these into the training set (n = 148) validation 63). 837 radiomics features were extracted from B-mode (BMUS) images contrast-enhanced (CEUS) images. The maximum relevance minimum redundancy (mRMR) algorithm, least absolute shrinkage selection operator (LASSO) backward stepwise logistic regression (LR) applied select key score (Radscore), including BMUS Radscore CEUS Radscore. clinical model established using univariate analysis multivariate LR. was finally presented as nomogram, performance of which evaluated by receiver operating characteristic curves, Hosmer-Lemeshow test, calibration decision curve (DCA). results show that constructed four predictors, gender, age, US-reported LNM, performed well both (AUC 0.820) 0.814). test curves demonstrated good calibration. DCA showed had satisfactory utility. can be used an effective tool individualized prediction LNM PTC.

Language: Английский

Citations

11
Contrast-enhanced MRI-based intratumoral heterogeneity assessment for predicting lymph node metastasis in resectable pancreatic ductal adenocarcinoma DOI Creative Commons

Junjian Shen,

Qin Li, Lei Li

et al.

Insights into Imaging, Journal Year: 2025, Volume and Issue: 16(1)

Published: March 30, 2025

Abstract Objectives To develop and validate a contrast-enhanced MRI-based intratumoral heterogeneity (ITH) model for predicting lymph node (LN) metastasis in resectable pancreatic ductal adenocarcinoma (PDAC). Methods Lesions were encoded into different habitats based on enhancement ratios at arterial, venous, delayed phases of MRI. Habitat models enhanced ratio mapping single sequences, radiomic models, clinical developed evaluating LN metastasis. The performance the was evaluated via metrics. Additionally, patients stratified high-risk low-risk groups an ensembled to assess prognosis after adjuvant therapy. Results We radiomics–habitat–clinical (RHC) that integrates radiomics, habitat, data precise prediction PDAC. RHC showed strong predictive performance, with area under curve (AUC) values 0.805, 0.779, 0.615 derivation, internal validation, external validation cohorts, respectively. Using optimal threshold 0.46, effectively patients, revealing significant differences recurrence-free survival overall (OS) ( p = 0.004 < 0.001). Adjuvant therapy improved OS group 0.004), but no benefit observed 0.069). Conclusion ITH provides reliable estimates PDAC may offer additional value guiding decision-making. Critical relevance statement This ensemble facilitates preoperative using offers foundation prognostic assessment supports management personalized treatment strategies. Key Points habitat can predict Both radiomics characteristics useful have potential enhance accuracy inform therapeutic decisions. Graphical

Language: Английский

Citations

0
Predictive role of radiomics features extracted from preoperative cross-sectional imaging of pancreatic ductal adenocarcinoma in detecting lymph node metastasis: a systemic review and meta-analysis DOI
Mohammad Mirza‐Aghazadeh‐Attari, Seyedeh Panid Madani,

Haneyeh Shahbazian

et al.

Abdominal Radiology, Journal Year: 2023, Volume and Issue: 48(8), P. 2570 - 2584

Published: May 18, 2023

Language: Английский

Citations

7
Setting the Research Agenda for Clinical Artificial Intelligence in Pancreatic Adenocarcinoma Imaging DOI Open Access
Megan Schuurmans, Natália Alves, Pierpaolo Vendittelli

et al.

Cancers, Journal Year: 2022, Volume and Issue: 14(14), P. 3498 - 3498

Published: July 19, 2022

Pancreatic ductal adenocarcinoma (PDAC), estimated to become the second leading cause of cancer deaths in western societies by 2030, was flagged as a neglected European Commission and United States Congress. Due lack investment research development, combined with complex aggressive tumour biology, PDAC overall survival has not significantly improved past decades. Cross-sectional imaging histopathology play crucial role throughout patient pathway. However, current clinical guidelines for diagnostic workup, stratification, treatment response assessment, follow-up are non-uniform evidence-based consensus. Artificial Intelligence (AI) can leverage multimodal data improve outcomes, but AI is too scattered lacking quality be incorporated into workflows. This review describes pathway derives touchpoints image-based collaboration multi-disciplinary, multi-institutional expert panel. The literature exploring address these thoroughly retrieved analysed identify existing trends knowledge gaps. results show absence multi-institutional, well-curated datasets, an essential building block robust applications. Furthermore, most unimodal, does use state-of-the-art techniques, lacks reliable ground truth. Based on this, future agenda clinically relevant, image-driven proposed.

Language: Английский

Citations

7
Prediction of synchronous distant metastasis of primary pancreatic ductal adenocarcinoma using the radiomics features derived from 18F-FDG PET and MRI DOI
Jing Gao, Yongrui Bai, Fei Miao

et al.

Clinical Radiology, Journal Year: 2023, Volume and Issue: 78(10), P. 746 - 754

Published: July 6, 2023

Language: Английский

Citations

3
Comparison of MRI and CT-based radiomics for preoperative prediction of lymph node metastasis in pancreatic ductal adenocarcinoma DOI

Piaoe Zeng,

Chao Qu, Jianfang Liu

et al.

Acta Radiologica, Journal Year: 2022, Volume and Issue: 64(7), P. 2221 - 2228

Published: Dec. 6, 2022

The preoperative prediction of lymph node metastasis (LNM) in pancreatic ductal adenocarcinoma (PDAC) is essential prognosis and treatment strategy formulation.To compare the performance computed tomography (CT) magnetic resonance imaging (MRI) radiomics models for LNM PDAC.In total, 160 consecutive patients with PDAC were retrospectively included, who divided into training validation sets (ratio 8:2). Two radiologists evaluated basing on morphological abnormalities. Radiomics features extracted from T2-weighted imaging, T1-weighted multiphase contrast enhanced MRI CT, respectively. Overall, 1184 each volume interest drawn. Only an intraclass correlation coefficient ≥0.75 included. Three sequential feature selection steps-variance threshold, variance thresholding least absolute shrinkage operator-were repeated 20 times fivefold cross-validation set. based CT multiparametric built five most frequent features. Model was using area under curve (AUC) values.Multiparametric model achieved improved AUCs (0.791 0.786 sets, respectively) than that (0.672 0.655 radiologists' assessment (0.600-0.613 0.560-0.587 respectively).Multiparametric may serve as a potential tool preoperatively evaluating had superior predictive to CT-based assessment.

Language: Английский

Citations

4
Editorial for “MRI Radiomics‐Based Nomogram From Primary Tumor for Pretreatment Prediction of Peripancreatic Lymph Node Metastasis in Pancreatic Ductal Adenocarcinoma: A Multicenter Study” DOI
Takeshi Yoshikawa, Daisuke Takenaka, Yoshiharu Ohno

et al.

Journal of Magnetic Resonance Imaging, Journal Year: 2022, Volume and Issue: 55(3), P. 840 - 841

Published: Feb. 1, 2022

Language: Английский

Citations

1