Pancreatic ductal adenocarcinoma: a radiomics nomogram outperforms clinical model and TNM staging for survival estimation after curative resection

Xie, Tianwen; Wang, Xuanyi; Li, Menglei; Tong, Tong; Yu, Xiaoli; Zhou, Zhengrong

doi:10.1007/s00330-019-06600-2

Cited by 66 publications

(59 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we know, radiomics has been widely applied in tumor research due to its merits of unwatched filter of comprehensive data obtained from an image. For example, radiomics could differentiate tumor heterogeneity and has often been performed to predict the prognosis of various cancers [ 18 , 19 ]. Hence, radiomics, a noninvasive, fast, reproducible, and low-cost technic, was utilized in COVID-19 for identifying the severity, so as to avoid unnecessary treatment and decrease patients’ anxiety, especially when human and material resources are extremely precious.…”

Section: Discussionmentioning

confidence: 99%

A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia

et al. 2021

View full text Add to dashboard Cite

Background Convenient and precise assessment of the severity in coronavirus disease 2019 (COVID-19) contributes to the timely patient treatment and prognosis improvement. We aimed to evaluate the ability of CT-based radiomics nomogram in discriminating the severity of patients with COVID-19 Pneumonia. Methods A total of 150 patients (training cohort n = 105; test cohort n = 45) with COVID-19 confirmed by reverse transcription polymerase chain reaction (RT-PCR) test were enrolled. Two feature selection methods, Max-Relevance and Min-Redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO), were used to extract features from CT images and construct model. A total of 30 radiomic features were finally retained. Rad-score was calculated by summing the selected features weighted by their coefficients. The radiomics nomogram incorporating clinical-radiological features was eventually constructed by multivariate regression analysis. Nomogram, calibration, and decision-curve analysis were all assessed. Results In both cohorts, 40 patients with COVID-19 pneumonia were severe and 110 patients were non-severe. By combining the 30 radiomic features extracted from CT images, the radiomics signature showed high discrimination between severe and non-severe patients in the training set [Area Under the Curve (AUC), 0.857; 95% confidence interval (CI), 0.775–0.918] and the test set (AUC, 0.867; 95% CI, 0.732–949). The final combined model that integrated age, comorbidity, CT scores, number of lesions, ground glass opacity (GGO) with consolidation, and radiomics signature, improved the AUC to 0.952 in the training cohort and 0.98 in the test cohort. The nomogram based on the combined model similarly exhibited excellent discrimination performance in both training and test cohorts. Conclusions The developed model based on a radiomics signature derived from CT images can be a reliable marker for discriminating the severity of COVID-19 pneumonia.

show abstract

Section: Discussionmentioning

confidence: 99%

A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Therefore, they are more effective in prognosis prediction than traditional TNM staging system (45). Although nomograms have been widely used to predict the prognosis of pancreatic cancer patients (46)(47)(48)(49), several factors limit their efficiency. Currently, no nomogram has been constructed for PDAC patients based on immune cell parameters and clinicopathological parameters in LSH.…”

Section: Discussionmentioning

confidence: 99%

Large-Section Histopathology Can Better Indicate the Immune Microenvironment and Predict the Prognosis of Pancreatic Ductal Adenocarcinoma Than Small-Section Histopathology

et al. 2021

View full text Add to dashboard Cite

Pancreatic ductal adenocarcinoma (PDAC) is a highly malignant tumor and is insensitive to radiotherapy and chemotherapy, as it is highly correlated with its complex tumor microenvironment (TME). A comprehensive description of PDAC’s immune microenvironment at the pathological level has not been reported, thus limiting its treatment. Previous studies have shown that large-section histopathology (LSH) can reveal the complete structure and margin of the tumor on a single slice and effectively reflect intratumoral heterogeneity. LSH, as opposed to classic small-section histopathology (SSH), can also be used to explore the infiltration state of immune cells in different regions. In the current study, EnVision immunohistochemical staining was used to explore the panoramic distribution of CD4-, CD8-, CD15-, CD20-, and CD56 (surface markers of helper T cells, cytotoxic T cells, neutrophils, B cells, and NK cells, respectively)-positive cells in 102 pairs of paraffin wax-embedded PDAC samples (LSH vs SSH) for the first time. These indicators were then analyzed, and correlations of clinicopathological characteristics with clinical prognoses were analyzed. The findings of this study show that LSH can effectively indicate more immune cells than SSH. Upregulated CD4, CD8, CD20, and CD56 or downregulated CD15 was correlated with a good prognosis in PDAC patients. However, analysis of SSH showed that only upregulated CD4 and CD8 can be used as indicators of a good prognosis. Multivariate Cox regression analysis showed that 7 variables, namely, pTNM stage (P=0.002), PDL1 expression (P=0.001), CDX2 expression (P=0.008), DPC4 expression (P=0.004), CD4 expression in LSH (P<0.001), CD8 expression in LSH (P=0.010) and CD15 expression in LSH (P=0.031), were significantly correlated with the prognosis of PDAC patients. The findings of this study indicate that LSH is an effective tool for a panoramic assessment of the immune microenvironment in pancreatic cancer patients.

show abstract

“…The radiomics risk score for the i-th patient is the summation of radiomics features multiplied by the corresponding coefficients derived from Lasso-Cox regression analysis, where n is the number of features selected by LASSO, β j is the j -th weighted coefficient of the selected feature, and X ij is the j -th selected radiomic features for i -th patient. This method has been widely used in many radiomics studies encompassing various tumor types [ 19 , 20 , 21 , 22 ].…”

Section: Methodsmentioning

confidence: 99%

Multi-Habitat Radiomics Unravels Distinct Phenotypic Subtypes of Glioblastoma with Clinical and Genomic Significance

Choi

Cho

Koo

et al. 2020

Cancers

View full text Add to dashboard Cite

We aimed to evaluate the potential of radiomics as an imaging biomarker for glioblastoma (GBM) patients and explore the molecular rationale behind radiomics using a radio-genomics approach. A total of 144 primary GBM patients were included in this study (training cohort). Using multi-parametric MR images, radiomics features were extracted from multi-habitats of the tumor. We applied Cox-LASSO algorithm to build a survival prediction model, which we validated using an independent validation cohort. GBM patients were consensus clustered to reveal inherent phenotypic subtypes. GBM patients were successfully stratified by the radiomics risk score, a weighted sum of radiomics features, corroborating the potential of radiomics as a prognostic biomarker. Using consensus clustering, we identified three distinct subtypes which significantly differed in the prognosis (“heterogenous enhancing”, “rim-enhancing necrotic”, and “cystic” subtypes). Transcriptomic traits enriched in individual subtypes were in accordance with imaging phenotypes summarized by radiomics. For example, rim-enhancing necrotic subtype was well described by radiomics profiling (T2 autocorrelation and flat shape) and highlighted by the inflammatory genomic signatures, which well correlated to its phenotypic peculiarity (necrosis). This study showed that imaging subtypes derived from radiomics successfully recapitulated the genomic underpinnings of GBMs and thereby confirmed the feasibility of radiomics as an imaging biomarker for GBM patients with comprehensible biologic annotation.

show abstract

Pancreatic ductal adenocarcinoma: a radiomics nomogram outperforms clinical model and TNM staging for survival estimation after curative resection

Cited by 66 publications

References 30 publications

A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia

A novel CT-based radiomics in the distinction of severity of coronavirus disease 2019 (COVID-19) pneumonia

Large-Section Histopathology Can Better Indicate the Immune Microenvironment and Predict the Prognosis of Pancreatic Ductal Adenocarcinoma Than Small-Section Histopathology

Multi-Habitat Radiomics Unravels Distinct Phenotypic Subtypes of Glioblastoma with Clinical and Genomic Significance

Contact Info

Product

Resources

About