A Multiplanar Radiomics Model Based on Cranial Ultrasound to Predict the White Matter Injury in Premature Infants and an Analysis of its Correlation With Neurodevelopment.

OBJECTIVES: To develop and evaluate a multiplanar radiomics model based on cranial ultrasound (CUS) to predict white matter injury (WMI) in premature infants and explore its correlation with neurodevelopment. METHODS: We retrospectively reviewed 267 premature infants. The radiomics features were extracted from five standard sections of CUS. The Spearman's correlation coefficient combined with the least absolute shrinkage and selection operator (LASSO) was applied to select features and build radiomics signature, and a multiplanar radiomics model was constructed based on the radiomics signature of five planes. The performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC). Infants with WMI were re-examined by ultrasound at 2 and 4 weeks after birth, and the recovery degree of WMI was evaluated using multiplanar radiomics. The relationship between WMI and the recovery degree and neurodevelopment was analyzed. RESULTS: The AUC of the multiplanar radiomics in the training and validation sets were 0.94 and 0.91, respectively. The neurodevelopmental function scores in infants with WMI were significantly lower than those in healthy preterm infants and full-term newborns (P < .001). There were statistically significant differences in the neurodevelopmental function scores of infants between the 2- and 4-week lesion disappearance and 4-week lesion persistence (P < .001). CONCLUSIONS: The multiplanar radiomics model showed a good performance in predicting the WMI of premature infants. It can not only provide objective and accurate results but also dynamically monitor the degree of recovery of WMI to predict the prognosis of premature infants.

Identification of Cholangiocarcinoma Associated with Hepatolithiasis via the Combination of miRNA and Ultrasound.

BACKGROUND: Identification of cholangiocarcinoma (CCA) associated with hepatolithiasis (HL) is difficult. There is no effective method to discriminate CCA associated with HL (HL-CCA) from HL currently. OBJECTIVE: To explore the value of clinical data, ultrasonic characteristics and miRNA expression level in the identification of HL-CCA. METHODS: Thirty-one patients with HL-CCA in Huazhong University of Science and Technology Union Shenzhen Hospital were enrolled in the observation group, while 40 patients with HL alone were included in the control group. The clinical data, ultrasonic characteristics, and miRNA expression level of the two groups were recorded and analyzed to explore the potential indicators for the identification of HL-CCA. RESULTS: The accuracy of ultrasound in the diagnosis of HL-CCA was low (54.84%). Multivariate logistic regression analysis showed that liver abscess (P=0.021), indistinct border demarcation (P=0.015), non-homogenous echotexture (P=0.019), missed portal vein around lesion (P=0.032), miRNA-21 (P=0.018) and miRNA-221 (P=0.009) were the potential indicators for the identification of HL-CCA. The combined diagnosis based on logistic regression contained liver abscess, border demarcation, echotexture, portal vein around lesion, miRNA-21 and miRNA-221. The results showed that the accuracy of combined diagnosis identifying HL-CCA was the most accurate (AUC=0.911), which was significantly greater than the AUC of miRNA-21 or miRNA-221 individually (P<0.05), with a sensitivity and specificity of 77.42% and 97.50%, respectively. CONCLUSION: Patients with HL-CCA show high incidence of hepatic abscess and elevated miRNA-21 and miRNA-221 expression level. The ultrasonic features are more likely to show indistinct border demarcation, non-homogenous echotexture, and missed portal vein around lesion. The combined diagnosis is more accurate in the identification of HL-CCA.

Sonographic findings of nasopharyngeal carcinoma and its involvement in the parapharyngeal space.

OBJECTIVES: The purpose of this study was to determine the sonographic performance in pathologically proven cases of nasopharyngeal carcinoma and its involvement in the parapharyngeal space. METHODS: The study included 58 patients being treated for suspected nasopharyngeal carcinoma detected by routine nasopharyngoscopy who underwent pathologic biopsy. Sonography was performed immediately thereafter with a convex array transducer in both the B-mode and color mode. Forty-five of the 58 patients (90 parapharyngeal spaces) in whom nasopharyngeal carcinoma was proved by both sonography and pathologic biopsy underwent preradiotherapy magnetic resonance imaging (MRI). The sonographic findings were compared to the pathologic findings. The sonographic findings of parapharyngeal space involvement were correlated with the MRI findings. RESULTS: The normal anatomy of the nasopharynx and parapharyngeal space, nasopharyngeal carcinoma, and its relationship with the parapharyngeal space were well shown on sonography. The sensitivity of sonography for detection of nasopharyngeal carcinoma was 97.8%, and the specificity was 41.7%. The sonographic findings of parapharyngeal space involvement had a high degree of agreement with MRI (κ = 0.757; P < .001). CONCLUSIONS: These promising initial data indicate that sonography may be a useful tool for diagnosing nasopharyngeal carcinoma and defining the relationship between the tumor and the parapharyngeal space.