Classification prediction of pancreatic cystic neoplasms based on radiomics deep learning models.

BACKGROUND: Preoperative prediction of pancreatic cystic neoplasm (PCN) differentiation has significant value for the implementation of personalized diagnosis and treatment plans. This study aimed to build radiomics deep learning (DL) models using computed tomography (CT) data for the preoperative differential diagnosis of common cystic tumors of the pancreas. METHODS: Clinical and CT data of 193 patients with PCN were collected for this study. Among these patients, 99 were pathologically diagnosed with pancreatic serous cystadenoma (SCA), 55 were diagnosed with mucinous cystadenoma (MCA) and 39 were diagnosed with intraductal papillary mucinous neoplasm (IPMN). The regions of interest (ROIs) were obtained based on manual image segmentation of CT slices. The radiomics and radiomics-DL models were constructed using support vector machines (SVMs). Moreover, based on the fusion of clinical and radiological features, the best combined feature set was obtained according to the Akaike information criterion (AIC) analysis. Then the fused model was constructed using logistic regression. RESULTS: For the SCA differential diagnosis, the fused model performed the best and obtained an average area under the curve (AUC) of 0.916. It had a best feature set including position, polycystic features (≥6), cystic wall calcification, pancreatic duct dilatation and radiomics-DL score. For the MCA and IPMN differential diagnosis, the fused model with AUC of 0.973 had a best feature set including age, communication with the pancreatic duct and radiomics score. CONCLUSIONS: The radiomics, radiomics-DL and fused models based on CT images have a favorable differential diagnostic performance for SCA, MCA and IPMN. These findings may be beneficial for the exploration of individualized management strategies.

Microvascular invasion risk scores affect the estimation of early recurrence after resection in patients with hepatocellular carcinoma: a retrospective study.

BACKGROUND: Microvascular invasion (MVI) is a histological factor that is closely related to the early recurrence of hepatocellular carcinoma (HCC) after resection. To investigate whether a noninvasive risk score system based on MVI status can be established to estimate early recurrence of HCC after resection. METHODS: Between January 2018 to March 2021, a total of 108 patients with surgically treated single HCC was retrospectively included in our study. Fifty-one patients were pathologically confirmed with MVI and 57 patients were absent of MVI. Univariate and multivariate logistic regression analysis of preoperative laboratory and magnetic resonance imaging (MRI) features were used to screen noninvasive risk factors in association with MVI in HCC. Risk scores based on the odds ratio (OR) values of MVI-related risk factors were calculated to estimate the early recurrence after resection of HCC. RESULTS: In multivariate logistic regression analysis, tumor size > 2 cm (P = 0.024, OR 3.05, 95% CI 1.19-11.13), Prothrombin induced by vitamin K absence-II > 32 mAU/ml (P = 0.001, OR 4.13, 95% CI 1.23-11.38), irregular tumor margin (P = 0.018, OR 3.10, 95% CI 1.16-8.31) and apparent diffusion coefficient value < 1007 × 10- 3mm2/s (P = 0.035, OR 2.27, 95% CI 1.14-7.71) were independent risk factors correlated to MVI in HCC. Risk scores of patients were calculated and were then categorized into high or low-risk levels. In multivariate cox survival analysis, only high-risk score of MVI was the independent risk factor of early recurrence (P = 0.009, OR 2.11, 95% CI 1.20-3.69), with a sensitivity and specificity of 0.52, 0.88, respectively. CONCLUSION: A risk score system based on MVI status can help stratify patients in high-risk of early recurrence after resection of HCC.

Deep Learning Algorithm­Based MRI Radiomics and Pathomics for Predicting Microsatellite Instability Status in Rectal Cancer: A Multicenter Study.

RATIONALE AND OBJECTIVES: To develop and validate multimodal deep-learning models based on clinical variables, multiparametric MRI (mp-MRI) and hematoxylin and eosin (HE) stained pathology slides for predicting microsatellite instability (MSI) status in rectal cancer patients. MATERIALS AND METHODS: A total of 467 surgically confirmed rectal cancer patients from three centers were included in this study. Patients from center 1 were randomly divided into a training set (242 patients) and an internal validation (invad) set (105 patients) in a 7:3 ratio. Patients from centers 2 and 3 (120 patients) were included in an external validation (exvad) set. HE and immunohistochemistry (IHC) staining were analyzed, and MSI status was confirmed by IHC staining. Independent predictive factors were identified through univariate and multivariate analyses based on clinical evaluations and were used to construct a clinical model. Deep learning with ResNet-101 was applied to preoperative MRI (T2WI, DWI, and contrast-enhanced T1WI sequences) and postoperative HE-stained images to calculate deep-learning radiomics score (DLRS) and deep-learning pathomics score (DLPS), respectively, and to DLRS and DLPS models. Receiver operating characteristic (ROC) curves were plotted, and the area under the curve (AUC) was used to evaluate and compare the predictive performance of each model. RESULTS: Among all rectal cancer patients, 82 (17.6%) had MSI. Long diameter (LD) and pathological T stage (pT) were identified as independent predictors and were used to construct the clinical model. After undergoing deep learning and feature selection, a final set of 30 radiomics features and 30 pathomics features were selected to construct the DLRS and DLPS models. A nomogram combining the clinical model, DLRS, and DLPS was created through weighted linear combination. The AUC values of the clinical model for predicting MSI were 0.714, 0.639, and 0.697 in the training, invad, and exvad sets, respectively. The AUCs of DLPS and DLRS ranged from 0.896 to 0.961 across the training, invad, and exvad sets. The nomogram achieved AUC values of 0.987, 0.987, and 0.974, with sensitivities of 1.0, 0.963, and 1.0 and specificities of 0.919, 0.949, and 0.867 in the training, invad, and exvad sets, respectively. The nomogram outperformed the other three models in all sets, with DeLong test results indicating superior predictive performance in the training set. CONCLUSION: The nomogram, incorporating clinical data, mp-MRI, and HE staining, effectively reflects tumor heterogeneity by integrating multimodal data. This model demonstrates high predictive accuracy and generalizability in predicting MSI status in rectal cancer patients.

Multiparametric MRI-based radiomics nomogram for the preoperative prediction of lymph node metastasis in rectal cancer: A two-center study.

PURPOSE: To develop a radiomic nomogram based on multiparametric magnetic resonance imaging for the preoperative prediction of lymph node metastasis (LNM) in rectal cancer. METHODS: This retrospective study included 318 patients with pathologically proven rectal adenocarcinoma from two hospitals. Radiomic features were extracted from T2-weighted imaging, diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging scans of the training cohort, and the radsore model was then constructed. The combined model was obtained by integrating the Radscore and clinical models. The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic effectiveness of each model, and the best-performing model was used to develop the nomogram. RESULTS: The Radscore and clinical models exhibited similar diagnostic efficacy (DeLong's test, P > 0.05). The AUC of the combined model was significantly higher than those of the clinical and Radscore models in the training cohort (AUC: 0.837 vs. 0.763 and 0.787, P: 0.02120 and 0.02309) and the external validation cohort (AUC: 0.880 vs. 0.797 and 0.779, P: 0.02310 and 0.02471). However, the diagnostic performance of the three models was comparable in the internal validation cohort (P > 0.05). Thus, among the three models, the combined model exhibited the highest diagnostic efficiency. The calibration curve exhibited satisfactory consistency between the nomogram predictions and the actual results. DCA confirmed the considerable clinical usefulness of the nomogram. CONCLUSION: The radiomics nomogram can accurately and noninvasively predict LNM in rectal cancer before surgery, serving as a convenient visualization tool for informing treatment decisions, including the choice of surgical approach and the need for neoadjuvant therapy.

Case report: Two rare uterine cesarean scar mass cases.

RATIONALE: Gestational trophoblastic neoplasia (GTN) located in the cesarean scar is a rare disease that has imaging appearances similar to those of an exogenous scar incision pregnancy and is often misdiagnosed due to insufficient clinical experience. PATIENT CONCERNS: We report 2 cases of uterine cesarean scar mass. Two patients with different diagnoses had similar clinical complaints as abnormal vaginal bleeding, enlargement of uterus isthmus by physical examination, and mixed echo mass in uterine low segment by ultrasound examination; however, their magnetic resonance imaging images showed very different features. DIAGNOSES: One patient was diagnosed with cesarean scar pregnancy (CSP) and one patient was diagnosed with cesarean scar GTN. INTERVENTIONS: The CSP patient underwent surgery by laparoscopy combined with hysteroscopy after uterine artery embolism and obtained pathological confirmation. The GTN patient received chemotherapy. OUTCOMES: For the CSP patient, her serum ß-human chorionic gonadotropin (hCG) concentration returned to normal 2 weeks later, and B-ultrasound showed that the niche was completely repaired 3 months after the operation. The intrauterine lesions of the GTN patient disappeared completely 3 months after serum ß-hCG normalization. And her ß-hCG was normal at all follow-up visits until now. LESSONS: Clinicians should consider GTN when identifying masses at scar incision sites. Magnetic resonance imaging images improve the understanding of the imaging features in patients suspected of having CSP/GTN.

Anti-PD-1 Therapy-A Potential Treatment for Myocardial Metastasis From Nasopharyngeal Carcinoma: A Case Report.

Myocardial metastasis of nasopharyngeal carcinoma (NPC) is rarely reported in the literature. Some autopsy studies found metastases in more than 10% of cases with malignant neoplasm. However, patients are often diagnosed during the postmortem because myocardial metastasis is often asymptomatic, and its Cardiac complications tend to be severe and fatal. Patients with Cardiac metastases are often treated with chemotherapy or surgical intervention, although the prognosis is poor. Immunotherapy with anti-programmed cell death receptor-1 or ligand-1 (PD-1 or PD-L1) inhibitors has recently been reported to be therapeutically significant in multiple cancers, including melanoma, nonsmall cell lung cancer, and NPC, but the treatment of myocardial metastasis of NPC has not been reported. This study described the case of a 50-year-old male patient who presented initially with NPC and received radiotherapy as first-line therapy. For 20 years, he had recurrent Cardiac metastasis of NPC. The pathological examination suggested tPD-L1 expression. Therefore, off-label sintilimab (200 mg every 21 days) was administered. After 10 cycles of treatment, myocardial metastasis shrank and the enlarged mediastinal lymph nodes disappeared. This case report demonstrated that Cardiac metastasis of NPC expressing PD-L1 might have a sustained response to PD-L1 inhibitor-directed therapy.