FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897734487> ?p ?o ?g. }

• W2897734487 endingPage "100" @default.
• W2897734487 startingPage "99" @default.
• W2897734487 abstract "HomeRadiologyVol. 290, No. 1 PreviousNext Reviews and CommentaryFree AccessEditorialCT-based Radiomics for Biliary Tract Cancer: A Possible Solution for Predicting Lymph Node MetastasesAndrea Laghi , Cecilia VoenaAndrea Laghi , Cecilia VoenaAuthor AffiliationsFrom the Department of Surgical and Medical Sciences and Translational Medicine, Sapienza–University of Rome. Sant’Andrea University Hospital, Via di Grottarossa 1035, 00189 Rome, Italy (A.L.); and Istituto Nazionale di Fisica Nucleare, Sezione di Roma, Rome, Italy (C.V.).Address correspondence to A.L. (e-mail: [email protected]).Andrea Laghi Cecilia VoenaPublished Online:Oct 16 2018https://doi.org/10.1148/radiol.2018182158MoreSectionsPDF ToolsImage ViewerAdd to favoritesCiteTrack CitationsPermissionsReprints ShareShare onFacebookTwitterLinked In See also the article by Ji et al in this issue.IntroductionBiliary tract cancers, composed of cholangiocarcinoma (intrahepatic, proximal, and distal) and gallbladder cancer, are uncommon tumors that account for 3% of all gastrointestinal malignancies. Current treatments include surgical resection and, for early stage hilar cholangiocarcinoma, liver transplant. Unfortunately, despite radical surgery, prognosis is still poor with high rate of local recurrence and low rate of overall 5-year survival (1).Although preoperative lymph node (LN) status is not included in some of the available staging systems, the detection of LN metastases is a strong predictor of worse long-term outcome after surgery (2). With the possible advent of more efficient neoadjuvant therapeutic strategies, including immunotherapy, LN assessment might become even more valuable for stratifying patients who may benefit from preoperative oncologic treatment (1).Characterization of LN status is a well-known challenge in the field of oncologic imaging, not only in biliary tract cancers. Accuracy is disappointing, particularly with CT, which relies only on size measurements for diagnosis (3). Better but still not optimal results have been obtained at functional MRI with diffusion-weighted sequences and calculation of apparent diffusion coefficient value (4), and with metabolic imaging, by using fluorine 18 fluorodeoxyglucose PET/CT (5).The urgent need for noninvasive, individualized prediction of LN metastases has led researchers to investigate the role radiomics could play in this field of research. Radiomics refers to the extraction of quantitative features by using dedicated algorithms obtained from imaging data that are undetectable at visual morphologic analysis. Those data are subsequently mined to create a radiomic signature, a series of radiomics features ideally associated unequivocally with a specific pathologic change, in this case a tumor. The further goal of radiomics analytics is to develop decision support tools, such as predictive models, by incorporating radiomics signature and other morphologic features (6). Radiomics models providing individualized risk estimation of LN metastasis have been developed and validated in studies focused on esophageal (7), colorectal (8), and bladder cancers (9) with good results.The study by Ji et al in this issue of Radiology (10) follows the same direction as previous studies (7–9) by investigating the potential role of a CT-based radiomics model, which combines data derived from the radiomics signature of the primary tumor with CT-reported LN status to predict LN metastasis in biliary tract cancers. LN status at conventional CT is the combination of three CT parameters related to metastatic LNs: size larger than 10 mm in short-axis diameter, central necrosis, and LN hyperattenuation compared with liver parenchyma in the venous phase of contrast agent–enhanced CT. The further advance of this study is the evaluation of the radiomics model as an independent preoperative predictor of disease-specific survival and recurrence-free survival.This radiomics approach explored different radiomics features including shape, first order, and statistics-based textural features to highlight various properties of the images. One study strength is that a large number of radiomics features (n = 93) were extracted by using an open-source software. Only those features that showed good intra- and interobserver reproducibility were considered for subsequent analysis (57 of 93). A logistic regression algorithm approach, which allows also for feature redundancy elimination, was chosen to select the relevant LN status–related features and to build a radiomics signature.The aim of the study by Ji et al (10) was to extract a radiomics signature of the primary cancer associated with either normal or metastatic LNs. Among the many radiomics features investigated in the primary cohort (177 patients), three features were most important: one shape-based feature (the so-called minor axis, ie, the smallest diameter of the primary tumor), one first-order feature (the skewness of the intensity histogram, ie, the asymmetry in the statistical distribution about its mean), and one textural feature (the zone entropy, ie, a measurement of the spatial randomness of the intensities). The radiomics signature alone positively correlated with LN status in the patient primary cohort and also showed favorable predictive efficacy (area under the curve, 0.77; 95% confidence interval: 0.66, 0.88) in the patient validation cohort.The next step was the creation of a radiomics model by using a multivariable logistic regression analysis that combined the radiomics signature and the LN status at conventional CT. To facilitate the clinical usage, the radiomics model was presented as a nomogram.Another study strength is the comparison of the radiomics model (ie, radiomics signature and CT-reported LN status) with a clinical model (built by using two independent predictors: CT-reported tumor size and LN status) and with CT-reported LN status alone. In the patient validation cohort of 70 consecutive patients, the area under the curve of the radiomics model was 0.80 (95% confidence interval: 0.70, 0.90), which was higher than the clinical model (area under the curve, 0.73; 95% confidence interval: 0.61, 0.84; P = .06) and CT-reported LN status alone (area under the curve, 0.63; 95% confidence interval: 0.52, 0.74; P = .003). Moreover, the nomogram calibration curve showed good agreement between the predicted and observed LN metastasis status after histologic verification.The radiomics nomogram allowed for patients to be assigned to a high- or low-risk group. This risk classifier for LN metastasis status achieved a sensitivity of 72.0% (90 of 125); a specificity of 76.2% (93 of 122); a positive and negative predictive value of 75.6% (90 of 119) and 72.6% (93 of 128), respectively; and an overall accuracy of 74.0% (128 of 173) for the entire patient cohort. To further evaluate the incremental benefit of the use of a radiomics model, a decision curve analysis was performed. The decision curve measures the net benefit of each model, calculated by summing the benefits (true-positive findings) and subtracting the harms (false-positive findings), weighted by a factor related to the relative harm of undetected metastasis compared with the harm of unnecessary treatment. The decision curve showed that if the threshold probability was over 10%, the application of radiomics model to predict LN metastasis added more benefit than treating all or no patients; the radiomics model was also more beneficial than the clinical prediction model and the CT-reported LN status. Moreover, radiomics-predicted lymph node metastasis emerged as a preoperative predictor of both disease-specific survival and recurrence-free survival after curative intent resection of biliary tract cancers (hazard ratios, 3.37 and 1.98, respectively). Overall, there was important personalized information for medical decision support.There are limitations. Although the model was built with rigorous methodologic structure, a multicentric study collecting a larger number of patients would be necessary to check for the generalizability of the radiomics signature. The influence of different CT parameters (eg, kilovolt, milliampere-seconds, and reconstruction filters) on extraction of radiomics features was not among the objectives of this study, although this is a relevant variable that might affect data consistency and limit the extensive use of the model. A correlation with genomic profile of biliary tract cancers may have been desirable, especially in the era of target therapy where specific genomic profiles are associated with either response or resistance to a specific drug. Nevertheless, radiomics approaches seem to have a bright future, especially if collaborative multidisciplinary teams are involved. Ultimately, to achieve personalized medicine, personalized imaging must be involved.Disclosures of Conflicts of Interest: A.L. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: disclosed money paid to author for lectures from Bayer Healthcare, Bracco, and GE Healthcare. Other relationships: disclosed no relevant relationships. C.V. disclosed no relevant relationships.References1. Rizvi S, Khan SA, Hallemeier CL, Kelley RK, Gores GJ. Cholangiocarcinoma - evolving concepts and therapeutic strategies. Nat Rev Clin Oncol 2018;15(2):95–111. Crossref, Medline, Google Scholar2. Kambakamba P, Linecker M, Slankamenac K, DeOliveira ML. Lymph node dissection in resectable perihilar cholangiocarcinoma: a systematic review. Am J Surg 2015;210(4):694–701. Crossref, Medline, Google Scholar3. Lee HY, Kim SH, Lee JM, et al. Preoperative assessment of resectability of hepatic hilar cholangiocarcinoma: combined CT and cholangiography with revised criteria. Radiology 2006;239(1):113–121. Link, Google Scholar4. Holzapfel K, Gaa J, Schubert EC, et al. Value of diffusion-weighted MR imaging in the diagnosis of lymph node metastases in patients with cholangiocarcinoma. Abdom Radiol (NY) 2016;41(10):1937–1941. Crossref, Medline, Google Scholar5. Hu JH, Tang JH, Lin CH, Chu YY, Liu NJ. Preoperative staging of cholangiocarcinoma and biliary carcinoma using 18F-fluorodeoxyglucose positron emission tomography: a meta-analysis. J Investig Med 2018;66(1):52–61. Crossref, Medline, Google Scholar6. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology 2016;278(2):563–577. Link, Google Scholar7. Tan X, Ma Z, Yan L, Ye W, Liu Z, Liang C. Radiomics nomogram outperforms size criteria in discriminating lymph node metastasis in resectable esophageal squamous cell carcinoma. Eur Radiol 2018 Jun 19 [Epub ahead of print]. Google Scholar8. Huang YQ, Liang CH, He L, et al. Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 2016;34(18):2157–2164. Crossref, Medline, Google Scholar9. Wu S, Zheng J, Li Y, et al. A radiomics nomogram for the preoperative prediction of lymph node metastasis in bladder cancer. Clin Cancer Res 2017;23(22):6904–6911. Crossref, Medline, Google Scholar10. Ji G, Zhang Y, Zhang H, et al. Biliary tract cancer at CT: a radiomics-based model to predict lymph node metastasis and survival outcomes. Radiology 2019;290:90–98. Link, Google ScholarArticle HistoryReceived: Sept 17 2018Revision requested: Sept 18 2018Revision received: Sept 21 2018Accepted: Sept 26 2018Published online: Oct 16 2018Published in print: Jan 2019 FiguresReferencesRelatedDetailsCited ByThe diagnostic value of a non-contrast computed tomography scan-based radiomics model for acute aortic dissectionZewangZhou, JinquanYang, ShuntaoWang, WeihaoLi, LeiXie, YifanLi, ChangzhengZhang2021 | Medicine, Vol. 100, No. 22Radiographic imaging assessment of prognosis of intrahepatic cholangiocarcinomaXiaoqingLin, JinyuanLiao2020 | Chinese Journal of Academic Radiology, Vol. 3, No. 2Applying a radiomics-based strategy to preoperatively predict lymph node metastasis in the resectable pancreatic ductal adenocarcinomaPengLiu, QianbiaoGu, XiaoliHu, XianzhengTan, JianbinLiu, AnXie, FengHuang2020 | Journal of X-Ray Science and Technology, Vol. 28, No. 6The Roles of Ultrasound-Based Radiomics In Precision Diagnosis and Treatment of Different Cancers: A Literature ReviewMao, MDBing, Duan, MDShaobo, Liu, MDRuiqing, Li, PhDNa, Li, PhDYaqiong, Zhang, MDLianzhong2020 | ADVANCED ULTRASOUND IN DIAGNOSIS AND THERAPY, Vol. 4, No. 4Accompanying This ArticleBiliary Tract Cancer at CT: A Radiomics-based Model to Predict Lymph Node Metastasis and Survival OutcomesOct 16 2018RadiologyRecommended Articles Mass-forming Intrahepatic Cholangiocarcinoma: Diffusion-weighted Imaging as a Preoperative Prognostic MarkerRadiology2016Volume: 281Issue: 1pp. 119-128Intrahepatic Mass-forming Cholangiocarcinoma: Arterial Enhancement Patterns at MRI and PrognosisRadiology2019Volume: 290Issue: 3pp. 691-699Biliary Tract Cancer at CT: A Radiomics-based Model to Predict Lymph Node Metastasis and Survival OutcomesRadiology2018Volume: 290Issue: 1pp. 90-98Baseline Volumetric Multiparametric MRI: Can It Be Used to Predict Survival in Patients with Unresectable Intrahepatic Cholangiocarcinoma Undergoing Transcatheter Arterial Chemoembolization?Radiology2018Volume: 289Issue: 3pp. 843-853Small Intrahepatic Cholangiocarcinoma and Hepatocellular Carcinoma in Cirrhotic Livers May Share Similar Enhancement Patterns at Multiphase Dynamic MR ImagingRadiology2016Volume: 281Issue: 1pp. 150-157See More RSNA Education Exhibits Radiogenomics In Hepatobiliary CancersDigital Posters2021Diagnosis and Management of Cholangiocarcinoma: Pearls and PitfallsDigital Posters2022A Tour of Biliary Disorders, Anomalies, and Malignancies in ChildrenDigital Posters2022 RSNA Case Collection Intrahepatic Cholangiocarcinoma RSNA Case Collection2020Metastatic cholangiocarcinomaRSNA Case Collection2021Gallbladder CarcinomaRSNA Case Collection2021 Vol. 290, No. 1 Metrics Altmetric Score PDF download" @default.
• W2897734487 created "2018-10-26" @default.
• W2897734487 creator A5025318079 @default.
• W2897734487 creator A5076361485 @default.
• W2897734487 date "2019-01-01" @default.
• W2897734487 modified "2023-09-23" @default.
• W2897734487 title "CT-based Radiomics for Biliary Tract Cancer: A Possible Solution for Predicting Lymph Node Metastases" @default.
• W2897734487 cites W2150907283 @default.
• W2897734487 cites W2153296763 @default.
• W2897734487 cites W2174661749 @default.
• W2897734487 cites W2346343836 @default.
• W2897734487 cites W2409286244 @default.
• W2897734487 cites W2753148287 @default.
• W2897734487 cites W2754843044 @default.
• W2897734487 cites W2763492611 @default.
• W2897734487 cites W2896617188 @default.
• W2897734487 doi "https://doi.org/10.1148/radiol.2018182158" @default.
• W2897734487 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30325279" @default.
• W2897734487 hasPublicationYear "2019" @default.
• W2897734487 type Work @default.
• W2897734487 sameAs 2897734487 @default.
• W2897734487 citedByCount "7" @default.
• W2897734487 countsByYear W28977344872020 @default.
• W2897734487 countsByYear W28977344872021 @default.
• W2897734487 countsByYear W28977344872022 @default.
• W2897734487 crossrefType "journal-article" @default.
• W2897734487 hasAuthorship W2897734487A5025318079 @default.
• W2897734487 hasAuthorship W2897734487A5076361485 @default.
• W2897734487 hasBestOaLocation W28977344871 @default.
• W2897734487 hasConcept C121608353 @default.
• W2897734487 hasConcept C126322002 @default.
• W2897734487 hasConcept C126838900 @default.
• W2897734487 hasConcept C142724271 @default.
• W2897734487 hasConcept C2775982439 @default.
• W2897734487 hasConcept C2778559731 @default.
• W2897734487 hasConcept C2780258809 @default.
• W2897734487 hasConcept C2780849966 @default.
• W2897734487 hasConcept C3017919176 @default.
• W2897734487 hasConcept C71924100 @default.
• W2897734487 hasConceptScore W2897734487C121608353 @default.
• W2897734487 hasConceptScore W2897734487C126322002 @default.
• W2897734487 hasConceptScore W2897734487C126838900 @default.
• W2897734487 hasConceptScore W2897734487C142724271 @default.
• W2897734487 hasConceptScore W2897734487C2775982439 @default.
• W2897734487 hasConceptScore W2897734487C2778559731 @default.
• W2897734487 hasConceptScore W2897734487C2780258809 @default.
• W2897734487 hasConceptScore W2897734487C2780849966 @default.
• W2897734487 hasConceptScore W2897734487C3017919176 @default.
• W2897734487 hasConceptScore W2897734487C71924100 @default.
• W2897734487 hasIssue "1" @default.
• W2897734487 hasLocation W28977344871 @default.
• W2897734487 hasLocation W28977344872 @default.
• W2897734487 hasOpenAccess W2897734487 @default.
• W2897734487 hasPrimaryLocation W28977344871 @default.
• W2897734487 hasRelatedWork W1974125869 @default.
• W2897734487 hasRelatedWork W2012872319 @default.
• W2897734487 hasRelatedWork W2049214470 @default.
• W2897734487 hasRelatedWork W2053411225 @default.
• W2897734487 hasRelatedWork W2897734487 @default.
• W2897734487 hasRelatedWork W2902148150 @default.
• W2897734487 hasRelatedWork W2983202017 @default.
• W2897734487 hasRelatedWork W3145321080 @default.
• W2897734487 hasRelatedWork W393292547 @default.
• W2897734487 hasRelatedWork W4237682097 @default.
• W2897734487 hasVolume "290" @default.
• W2897734487 isParatext "false" @default.
• W2897734487 isRetracted "false" @default.
• W2897734487 magId "2897734487" @default.
• W2897734487 workType "article" @default.