Discrimination between non-functioning pituitary adenomas and hypophysitis using machine learning methods based on magnetic resonance imaging‑derived texture features

Purpose

Hypophysitis is a heterogeneous condition that includes inflammation of the pituitary gland and infundibulum, and it can cause symptoms related to mass effects and hormonal deficiencies. We aimed to evaluate the potential role of machine learning methods in differentiating hypophysitis from non-functioning pituitary adenomas.

Methods

The radiomic parameters obtained from T1A-C images were used. Among the radiomic parameters, parameters capable of distinguishing between hypophysitis and non-functioning pituitary adenomas were selected. In order to avoid the effects of confounding factors and to improve the performance of the classifiers, parameters with high correlation with each other were eliminated. Machine learning algorithms were performed with the combination of gray-level run-length matrix-low gray level run emphasis, gray-level co-occurrence matrix-correlation, and gray-level co-occurrence entropy.

Results

A total of 34 patients were included, 17 of whom had hypophysitis and 17 had non-functioning pituitary adenomas. Among the 38 radiomics parameters obtained from post-contrast T1-weighted images, 10 tissue features that could differentiate the lesions were selected. Machine learning algorithms were performed using three selected parameters; gray level run length matrix-low gray level run emphasis, gray-level co-occurrence matrix-correlation, and gray level co-occurrence entropy. Error matrices were calculated by using the machine learning algorithm and it was seen that support vector machines showed the best performance in distinguishing the two lesion types.

Conclusions

Our analysis reported that support vector machines showed the best performance in distinguishing hypophysitis from non-functioning pituitary adenomas, emphasizing the importance of machine learning in differentiating the two lesions.

     

Efficacy of hepatitis B vaccination and interferon-alpha-2b combination therapy versus interferon-alpha-2b monotherapy in children with chronic hepatitis B

BACKGROUND: Although interferon (IFN) has been approved in the treatment of chronic hepatitis B in children, it is effective only in 30-40% of patients. In some studies it has been suggested that therapeutic use of anti-hepatitis B virus (HBV) vaccine may be beneficial in patients with chronic hepatitis B. The aim of the present study was to compare the efficacy of hepatitis B vaccination and IFN-alpha-2b in combination and IFN-alpha-2b monotherapy in children with chronic hepatitis B. METHODS: Fifty treatment-naive children with chronic hepatitis B infection were randomly assigned to receive either 5 million units/m(2) recombinant IFN-alpha-2b subcutaneously three times per week for 9 months, and pre-S2/S vaccine at the beginning and 4 and 24 weeks after initiation of IFN therapy (n = 25) or recombinant IFN-alpha-2b (5 million units/m(2) subcutaneously thrice weekly) alone for 9 months (n = 25). Children were followed for at least 6 months after the end of therapy. RESULTS: There was no statistically significant difference in the mean alanine aminotransferase levels, histologic activity index and fibrosis scores between combination and IFN monotherapy groups at the end of the therapy and end of the follow-up period. When combination and monotherapy groups were compared, the mean HBV-DNA values were significantly reduced in combination group at the end of the therapy (P = 0.004), but no statistically significant difference was found at the end of the follow up. Sustained HBeAg seroconversion with clearance of HBV-DNA was obtained in 13 of 25 children (52%) treated with combination therapy, and in eight of 25 patients (32%) treated with IFN monotherapy (P = 0.251). CONCLUSION: Although the difference was statistically insignificant, the sustained response rates were better in the combination therapy group than in the monotherapy group. The potential benefit of combining IFN and hepatitis B vaccine should be investigated in further studies with different regimens of combination therapy.     

Analysis of insulin like growth factor 1 and insulin like growth factor binding protein 3 levels in bronchoalveolar lavage fluid and serum of patients with lung cancer

OBJECTIVE: Insulin like growth factor 1 (IGF-1) is recognized as a potent mitogen for many cancer cell lines and there is good evidence that lung cancer cells produce both IGF-1 and insulin like growth factor binding protein 3 (IGFBP-3). The aim of this study was to investigate the clinical significance of IGF-1 and IGFBP-3 levels in serum and in bronchoalveolar lavage (BAL) fluid by comparing lung cancer patients with healthy controls. METHODS: BAL fluid and serum samples were obtained from 24 lung cancer patients and 12 healthy controls, and were analyzed for IGF-1 and IGFBP-3 levels by a two site immunoradiometric assay. The recovered BAL fluid was standardized by albumin to remove the variable of dilution and the data was expressed in epithelial lining fluid (ELF). RESULTS: Serum IGF-1 and IGFBP-3 levels were lower in lung cancer patients, but the difference between the groups did not reach a statistical significance. IGF-1/IGFBP-3 ratio in ELF was significantly lower in lung cancer patients (P=0.035). Mean IGF-1 level in ELF was determined to be significantly lower in patients with distant metastasis (P=0.04). Serum IGF-1/IGFBP-3 ratio was found to be significantly lower in patients with distant (P=0.04) and nodal metastasis (P=0.03). Tumor stage was negatively correlated with IGF-1 level in ELF (P=0.05, r=-0.4) and serum IGF-1/IGFBP-3 ratio (P=0.04, r=-0.4). CONCLUSION: IGF-1 and IGFBP-3 levels both in serum and ELF might serve a clinical significance in patients with lung cancer. However, further studies comprising more cases are needed to investigate the clinical significance of IGF-1 and IGFBP-3 in lung cancer.     

Contribution of DOG1 expression to the diagnosis of gastrointestinal stromal tumors

Gastrointestinal stromal tumors (GIST) are the most common mesenchymal tumors of the gastrointestinal tract, and the majority contain KIT or PDGFRA-activating mutations. However, up to 10% of GISTs are c-kit-negative. Antibodies with increased sensitivity and specificity for the detection of c-kit-negative GIST cases may be of value, especially because some of these cases may also benefit from tyrosine kinase inhibitor therapy.     

A novel PSEN2 p.Ser175Phe variant in a family with Alzheimer’s disease

Neurological Sciences - Alzheimer’s disease (AD) can be either sporadic or familial, and familial forms of AD accounts for only 5% of the cases. So far, autosomal dominantly inherited...