Value of CT-Based Deep Learning Model in Differentiating Benign and Malignant Solid Pulmonary Nodules ≤ 8 mm.

RATIONALE AND OBJECTIVES: We examined the effectiveness of computed tomography (CT)-based deep learning (DL) models in differentiating benign and malignant solid pulmonary nodules (SPNs) ≤ 8 mm. MATERIALS AND METHODS: The study patients (n = 719) were divided into internal training, internal validation, and external validation cohorts; all had small SPNs and had undergone preoperative chest CTs and surgical resection. We developed five DL models incorporating features of the nodule and five different peri-nodular regions with the Multiscale Dual Attention Network (MDANet) to differentiate benign and malignant SPNs. We selected the best-performing model, which was then compared to four conventional algorithms (VGG19, ResNet50, ResNeXt50, and DenseNet121). Furthermore, another five DL models were constructed using MDANet to distinguish benign tumors from inflammatory nodules and the one performed best was selected out. RESULTS: Model 4, which incorporated the nodule and 15 mm peri-nodular region, best differentiated benign and malignant SPNs. The model had an area under the curve (AUC), accuracy, recall, precision, and F1-score of 0.730, 0.724, 0.711, 0.705, and 0.707 in the external validation cohort. Model 4 also performed better than the other four conventional algorithms. Model 8, which incorporated the nodule and 10 mm peri-nodular region, was the best model for distinguishing benign tumors from inflammatory nodules. The model had an AUC, accuracy, recall, precision, and F1-score of 0.871, 0.938, 0.863, 0.904, and 0.882 in the external validation cohort. CONCLUSION: The study concludes that CT-based DL models built with MDANet can accurately discriminate among small benign and malignant SPNs, benign tumors and inflammatory nodules.

Association of the NOTCH4 Gene Polymorphism rs204993 with Schizophrenia in the Chinese Han Population.

NOTCH4 regulates signaling pathways associated with neuronal maturation, a process involved in the development and patterning of the central nervous system. The NOTCH4 gene has also been identified as a possible susceptibility gene for schizophrenia (SCZ). The objective of this study was to examine the relationship between NOTCH4 polymorphisms and SCZ in the Chinese Han population. The rs2071287 and rs204993 polymorphisms of the NOTCH4 gene were analyzed in 443 patients with SCZ and 628 controls of Han Chinese descent. Single SNP allele-, genotype-, and gender-specific associations were analyzed using different models (i.e., additive, dominant, and recessive models). This association study revealed that the rs204993 polymorphism is significantly associated with susceptibility for SCZ and that the AA genotype of rs204993 is associated with a higher risk for SCZ (P = 0.027; OR = 1.460; 95% CI, 1.043-2.054). Our data are consistent with those obtained in previous studies that suggested that rs204993 is associated with SCZ and that the AA genotype of rs204993 demonstrates a higher risk. Further large-scale association analyses in Han Chinese populations are warranted.

Lack of Association between the TSPAN18 Gene and Schizophrenia Based on New Data from Han Chinese and a Meta-Analysis.

Tetraspanin-18 (TSPAN18) potentially plays a role in the calcium signaling that is associated with dopamine-induced cortical neuron apoptosis and is considered to be an important mechanism in the pathogenesis of schizophrenia (SCZ). Furthermore, a genome-wide association study (GWAS) identified TSPAN18 as a possible susceptibility gene for SCZ. To validate these findings and reveal the effects of different inheritance models, seven single nucleotide polymorphisms (SNPs) of the TSPAN18 gene were analyzed in 443 patients with SCZ and 628 controls of Han Chinese descent via the SNPscan method. Single SNP, genotype, and association analyses with different models (i.e., additive, dominant, and recessive models) were performed, and the published datasets (2062 cases and 2053 controls) were combined with our results to determine the inheritance effects of the SNPs on SCZ. We observed genotypes and allele distributions of TSPAN18 gene did not show any significant associations in the Han Chinese population based on our experimental and meta-analytical results. Our findings indicate that the TSPAN18 gene is unlikely to be a major susceptibility gene for schizophrenia in Han Chinese.