Dataset Information

Development of a radiomics model to diagnose pheochromocytoma preoperatively: a multicenter study with prospective validation.

ABSTRACT:

Background

Preoperative diagnosis of pheochromocytoma (PHEO) accurately impacts preoperative preparation and surgical outcome in PHEO patients. Highly reliable model to diagnose PHEO is lacking. We aimed to develop a magnetic resonance imaging (MRI)-based radiomic-clinical model to distinguish PHEO from adrenal lesions.

Methods

In total, 305 patients with 309 adrenal lesions were included and divided into different sets. The least absolute shrinkage and selection operator (LASSO) regression model was used for data dimension reduction, feature selection, and radiomics signature building. In addition, a nomogram incorporating the obtained radiomics signature and selected clinical predictors was developed by using multivariable logistic regression analysis. The performance of the radiomic-clinical model was assessed with respect to its discrimination, calibration, and clinical usefulness.

Results

Seven radiomics features were selected among the 1301 features obtained as they could differentiate PHEOs from other adrenal lesions in the training (area under the curve [AUC], 0.887), internal validation (AUC, 0.880), and external validation cohorts (AUC, 0.807). Predictors contained in the individualized prediction nomogram included the radiomics signature and symptom number (symptoms include headache, palpitation, and diaphoresis). The training set yielded an AUC of 0.893 for the nomogram, which was confirmed in the internal and external validation sets with AUCs of 0.906 and 0.844, respectively. Decision curve analyses indicated the nomogram was clinically useful. In addition, 25 patients with 25 lesions were recruited for prospective validation, which yielded an AUC of 0.917 for the nomogram.

Conclusion

We propose a radiomic-based nomogram incorporating clinically useful signatures as an easy-to-use, predictive and individualized tool for PHEO diagnosis.

SUBMITTER: Kong J

PROVIDER: S-EPMC8760711 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundThere is an unmet need for non-invasive biomarkers for the diagnosis of nonalcoholic steatohepatitis (NASH) in non-specialized settings. We aimed to develop and validate a non-invasive test for diagnosing NASH in individuals with biopsy-proven nonalcoholic fatty liver disease (NAFLD).MethodsWe developed a non-invasive test named the acNASH index that combines serum creatinine and aspartate aminotransferase levels in a derivation cohort of 390 Chinese NAFLD patients admitted to the hepatology center of the First Affiliated Hospital of Wenzhou Medical University (China) between December 2016 and September 2019 and subsequently validated in five external cohorts of different ethnicities of patients with biopsy-confirmed NAFLD (pooled n=1,089).FindingsThe performance of the acNASH index for identifying NASH (defined as NAFLD activity score ≥5 with score of ≥1 for each steatosis, lobular inflammation and ballooning) was good in the derivation cohort with an area under receiver operating characteristics (AUROC) of 0·818 (95%CI 0·777-0·860). A cutoff of acNASH index <4·15 gave a sensitivity (Se) of 91%, a specificity (Sp) of 48% and a negative predictive value (NPV) of 83% for ruling-out NASH, conversely, a cutoff of acNASH >7·73 gave a Sp of 91%, Se of 53% and a positive predictive value (PPV) of 85% for ruling-in NASH. In the pooled validation cohort (n=1,089), the diagnostic performance of the index was also good with AUROC=0·805 (95%CI 0·780-0·830), NPV of 93% for ruling-out NASH and PPV of 73% for ruling-in NASH. Subgroup analyses showed similar performance in patients with diabetes or subjects with normal serum transaminase levels.InterpretationThe acNASH index shows promising utility as a simple non-invasive biomarker for diagnosing NASH among adults with biopsy-proven NAFLD of different ethnicities from different countries.FundingThe National Natural Science Foundation of China (82070588), High Level Creative Talents from Department of Public Health in Zhejiang Province (S2032102600032) and Project of New Century 551 Talent Nurturing in Wenzhou.

Project description:To validate recent guidance changes by establishing the performance of cut-off values for embryo crown-rump length and mean gestational sac diameter to diagnose miscarriage with high levels of certainty. Secondary aims were to examine the influence of gestational age on interpretation of mean gestational sac diameter and crown-rump length values, determine the optimal intervals between scans and findings on repeat scans that definitively diagnose pregnancy failure.)Prospective multicentre observational trial.Seven hospital based early pregnancy assessment units in the United Kingdom.2845 women with intrauterine pregnancies of unknown viability included if transvaginal ultrasonography showed an intrauterine pregnancy of uncertain viability. In three hospitals this was initially defined as an empty gestational sac <20 mm mean diameter with or without a visible yolk sac but no embryo, or an embryo with crown-rump length <6 mm with no heartbeat. Following amended guidance in December 2011 this definition changed to a gestational sac size <25 mm or embryo crown-rump length <7 mm. At one unit the definition was extended throughout to include a mean gestational sac diameter <30 mm or embryo crown-rump length <8 mm.Mean gestational sac diameter, crown-rump length, and presence or absence of embryo heart activity at initial and repeat transvaginal ultrasonography around 7-14 days later. The final outcome was pregnancy viability at 11-14 weeks' gestation.The following indicated a miscarriage at initial scan: mean gestational sac diameter ? 25 mm with an empty sac (364/364 specificity: 100%, 95% confidence interval 99.0% to 100%), embryo with crown-rump length ? 7 mm without visible embryo heart activity (110/110 specificity: 100%, 96.7% to 100%), mean gestational sac diameter ? 18 mm for gestational sacs without an embryo presenting after 70 days' gestation (907/907 specificity: 100%, 99.6% to 100%), embryo with crown-rump length ? 3 mm without visible heart activity presenting after 70 days' gestation (87/87 specificity: 100%, 95.8% to 100%). The following were indicative of miscarriage at a repeat scan: initial scan and repeat scan after seven days or more showing an embryo without visible heart activity (103/103 specificity: 100%, 96.5% to 100%), pregnancies without an embryo and mean gestational sac diameter <12 mm where the mean diameter has not doubled after 14 days or more (478/478 specificity: 100%, 99.2% to 100%), pregnancies without an embryo and mean gestational sac diameter ? 12 mm showing no embryo heartbeat after seven days or more (150/150 specificity: 100%, 97.6% to 100%).Recently changed cut-off values of gestational sac and embryo size defining miscarriage are appropriate and not too conservative but do not take into account gestational age. Guidance on timing between scans and expected findings on repeat scans are still too liberal. Protocols for miscarriage diagnosis should be reviewed to account for this evidence to avoid misdiagnosis and the risk of terminating viable pregnancies.

Project description:Background: Lymph node (LN) metastasis is the most important prognostic factor in esophageal squamous cell carcinoma (ESCC). Traditional clinical factor and existing methods based on CT images are insufficiently effective in diagnosing LN metastasis. A more efficient method to predict LN status based on CT image is needed. Methods: In this multicenter retrospective study, 411 patients with pathologically confirmed ESCC were registered from two hospitals. Quantitative image features including handcrafted-, computer vision-(CV-), and deep-features were extracted from preoperative arterial phase CT images for each patient. A handcrafted-, CV-, and deep-radiomics signature were built, respectively. Then, multiple radiomics models were constructed by merging independent clinical risk factor into radiomics signatures. The performance of models were evaluated with respect to the discrimination, calibration, and clinical usefulness. Finally, an independent external validation cohort was used to validate the model's predictive performance. Results: Five, seven, and nine features were selected for building handcrafted-, CV-, and deep-radiomics signatures from extracted features, respectively. Those signatures were statistically significant different between LN-positive and LN-negative patients in all cohorts (p < 0.001). The developed multiple level CT radiomics model that integrates multiple radiomics signatures with clinical risk factor, was superior to traditional clinical factors and the results reported by existing methods, and achieved satisfactory discrimination performance with C-statistic of 0.875 in development cohort, 0.874 in internal validation cohort and 0.840 in independent external validation cohort. Nomogram and decision curve analysis (DCA) further confirmed our method may serve as an effective tool for clinicians to evaluate the risk of LN metastasis in patients with ESCC and further choose treatment strategy. Conclusions: The proposed multiple level CT radiomics model which integrate multiple level radiomics features into clinical risk factor can be used for preoperative predicting LN metastasis of patients with ESCC.