Deep learning for diagnosis of head and neck cancers through radiographic data: a systematic review and meta-analysis.

PURPOSE: This study aims to review deep learning applications for detecting head and neck cancer (HNC) using magnetic resonance imaging (MRI) and radiographic data. METHODS: Through January 2023, a PubMed, Scopus, Embase, Google Scholar, IEEE, and arXiv search were carried out. The inclusion criteria were implementing head and neck medical images (computed tomography (CT), positron emission tomography (PET), MRI, Planar scans, and panoramic X-ray) of human subjects with segmentation, object detection, and classification deep learning models for head and neck cancers. The risk of bias was rated with the quality assessment of diagnostic accuracy studies (QUADAS-2) tool. For the meta-analysis diagnostic odds ratio (DOR) was calculated. Deeks' funnel plot was used to assess publication bias. MIDAS and Metandi packages were used to analyze diagnostic test accuracy in STATA. RESULTS: From 1967 studies, 32 were found eligible after the search and screening procedures. According to the QUADAS-2 tool, 7 included studies had a low risk of bias for all domains. According to the results of all included studies, the accuracy varied from 82.6 to 100%. Additionally, specificity ranged from 66.6 to 90.1%, sensitivity from 74 to 99.68%. Fourteen studies that provided sufficient data were included for meta-analysis. The pooled sensitivity was 90% (95% CI 0.820.94), and the pooled specificity was 92% (CI 95% 0.87-0.96). The DORs were 103 (27-251). Publication bias was not detected based on the p-value of 0.75 in the meta-analysis. CONCLUSION: With a head and neck screening deep learning model, detectable screening processes can be enhanced with high specificity and sensitivity.

Evaluation and relation of oral health-related quality of life and oral health status in Thalassemia Major patients, a cross-sectional study.

BACKGROUND: Beta-Thalassemia is the most common human inherited disease, directly impacting patients' physical and psychosocial aspects. The present study evaluated oral health status, oral health-related quality of life (OHRQoL), and their correlation in Thalassemia Major patients. METHODS: Two hundred Thalassemia Major patients aged 12-49 participated in this cross-sectional study. Subjects were selected among the patients referred to the Faculty of Dentistry of Isfahan University of Medical Sciences using simple sampling. Oral Health Impact Profile 14 (OHIP 14) was used to assess OHRQoL. The decayed, Missing, and Filled Teeth (DMFT) index was used as an oral health index. SPSS 22 was used for analysis, using T and Pearson Correlation tests. RESULTS: 53% of participants were female, and 47% were male. The mean OHIP-14 score (± SD) was 13.20 (± 7.01). The mean DMFT score was 9.54 (± 5.72). DMFT and total OHIP 14 scores correlated significantly (p < 0.001, r = 0.78). All domains of the OHIP-14 score were also significantly correlated with DMFT (p < 0.05). CONCLUSIONS: Poor oral health conditions might adversely affect OHRQoL in TM patients. It seems necessary to provide oral treatment needs in order to improve OHRQoL in patients suffering from this particular disease.

The effect of sage (Salvizan gel) compared to triamcinolone acetonide on the treatment of recurrent aphthous stomatitis: a double-blinded randomized clinical trial.

BACKGROUND: Recurrent Aphthous Stomatitis (RAS) is one of the most common lesions of the oral mucosa. Herbal medicine can be used for the treatment of this disease. The present study aimed to compare the effects of topical application of Sage (Salvizan) and triamcinolone acetonide gels on RAS. METHODS: This double-blind clinical study recruited sixty patients with minor aphthous ulcers. Half of the patients were treated with Salvizan gel, and the other half were treated with oral triamcinolone acetonide gel. The effect of Salvizan topical gel was evaluated and compared with that of oral triamcinolone acetonide gel. Factors such as Pain recovery time, wound healing time, and pain level was evaluated. Data were analyzed by SPSS version 22 using independent t-test, paired t-test, repeated measures ANOVA, and survival analysis, including Kaplan-Meier and Cox regression. RESULTS: The mean duration of pain recovery was 1.5 days for Salvizan and 2.5 days for triamcinolone acetonide (p < 0.001). Moreover, the duration of wound healing was 3.3 days for Salvizan and 6 days for triamcinolone acetonide (p < 0.001). Patients' satisfaction from factors such as taste and smell had no significant difference between the two groups. CONCLUSION: The results of this study showed that Salvizan gel is very effective in the treatment of RAS. It was significantly better than triamcinolone acetonide in the pain recovery and wound healing. These promising results favor herbal treatments and show that they can be used more commonly for treating diseases such as RAS. TRIAL REGISTRATION: This study was approved by the ethics committee of Isfahan University of Medical Sciences (IR.MUI. RESEARCH: REC.1399.834) on 17/03/2021. It was also registered in the Iranian Registry of Clinical Trials (IRCT20100202003251N7).