Abstract
PurposeTo construct and verify a CT-based multidimensional nomogram for the evaluation of lymph node (LN) status in pancreatic ductal adenocarcinoma (PDAC).Materials and MethodsWe retrospectively assessed data from 172 patients with clinicopathologically confirmed PDAC surgically resected between February 2014 and November 2016. Patients were assigned to either a training cohort (n = 121) or a validation cohort (n = 51). We acquired radiomics features from the preoperative venous phase (VP) CT images. The maximum relevance–minimum redundancy (mRMR) algorithm and the least absolute shrinkage and selection operator (LASSO) methods were used to select the optimal features. We used multivariable logistic regression to construct a combined radiomics model for visualization in the form of a nomogram. Performance of the nomogram was evaluated by the receiver operating characteristic (ROC) curve approach, calibration testing, and analysis of clinical usefulness.ResultsA Rad score consisting of 10 LN status-related radiomics features was found to be significantly associated with the actual LN status (P < 0.01). A nomogram that consisted of Rad scores, CT-reported parenchymal atrophy, and CT-reported LN status performed well in terms of predictive power in the training cohort (area under the curve, 0.92), and this was confirmed in the validation cohort (area under the curve, 0.95). The nomogram also performed well in the calibration test and decision curve analysis, demonstrating its potential clinical value.ConclusionA multidimensional radiomics nomogram consisting of Rad scores, CT-reported parenchymal atrophy, and CT-reported LN status may contribute to the non-invasive evaluation of LN status in PDAC patients.
Highlights
Pancreatic ductal adenocarcinoma (PDAC) is notorious for its occult onset and early metastasis
For the purpose of determining the value of our nomogram for clinical applications, we adopted decision curve analysis (DCA) to further compare the net benefit obtained by the deployment of the nomogram and the clinical model
In the receiver operating characteristic (ROC) test, the nomogram displayed a superb ability for evaluating lymph node metastasis (LNM) in PDAC patients, with area under the curve (AUC) of 0.92 and 0.95 in the training and validation cohorts, respectively (Figures 4B,C and Table 3)
Summary
Pancreatic ductal adenocarcinoma (PDAC) is notorious for its occult onset and early metastasis. A Radiomics Nomogram for PDAC early PDAC patients, it is extremely difficult to make an early diagnosis of this disease. This results in limited and suboptimal treatment options for most patients [3]. Relatively poor accuracy can be achieved when evaluating the LN status solely from a morphological perspective (for example, by assessing changes in lymph node size, morphology, and intensity). These approaches are not able to provide effective guidance for clinical treatment and are far from satisfactory predictive factors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
