How advantageous is it to use computed tomography image-based artificial intelligence modelling in the differential diagnosis of chronic otitis media with and without cholesteatoma?

OBJECTIVE: Cholesteatoma (CHO) developing secondary to chronic otitis media (COM) can spread rapidly and cause important health problems such as hearing loss. Therefore, the presence of CHO should be diagnosed promptly with high accuracy and then treated surgically. The aim of this study was to investigate the effectiveness of artificial intelligence applications (AIA) in documenting the presence of CHO based on computed tomography (CT) images. PATIENTS AND METHODS: The study was performed on CT images of 100 CHO, 100 non-cholesteatoma (N-CHO) COM, and 100 control patients. Two AIA models including ResNet50 and MobileNetV2 were used for the classification of the images. RESULTS: Overall accuracy rate was 93.33% for the ResNet50 model and 86.67% for the MobilNetV2 model. Moreover, the diagnostic accuracy rates of these two models were 100% and 95% in the CHO group, 90% and 85% in the N-CHO group, and 90% and 80% in the control group, respectively. CONCLUSIONS: These results indicate that the use of AIA in the diagnosis of CHO will improve the diagnostic accuracy rates and will also help physicians in terms of reducing their workload and facilitating the selection of the correct treatment strategy.

A new and reliable landmark in parotid surgery: tragomastoid groove (Akil Groove).

OBJECTIVE: Parotid surgery is a frequently performed surgery in otorhinolaryngology practice with many possible complications. Due to the high ratio of facial paralysis during parotid surgery, we defined a new landmark for identifying and protecting the facial nerve as early as possible during surgery. MATERIALS AND METHODS: The study was designed as a prospective anatomical method. The important details and relationship of the tragomastoid groove to the facial nerve truncus were examined during surgery on 30 patients. In addition, the demographics of the patients, the type of surgery and the pathological results of surgeries were evaluated. RESULTS: The mean distance of the tragomastoid groove to the facial nerve truncus was 20.53±1.71 mm, the mean deepness of the tragomastoid groove was 1.91±0.26 mm, and the mean superficial part of the tragomastoid groove was 0.83±0.23 mm. The tragomastoid groove was situated either across from the facial nerve at the place where the facial nerve truncus exits the stylomastoid foramen or just inferior to the truncus in all patients. CONCLUSIONS: The tragomastoid groove was defined for the first time in the literature as a reliable landmark for identifying the facial nerve truncus easily during parotid surgery.

Laryngectomy: what is the impact of the type of surgery on life quality and sexual function?

The purpose of this study is to compare total and partial larygectomy on private life functions and sexuality in patients with laryngeal cancer. The study included 31 partial laryngectomy patients (Group 1) and 51 total laryngectomy patients (Group 2) who were operated for laryngeal cancer. European Organization for Research and Treatment of Cancer (EORTC) head and neck cancer module (QLQ-H&N35) and Arizona Sexual Experiences Scale (ASEX) forms were filled in by interviewing face to face with patients. HNSW (swallowing), HNSE (senses), HNSP (speech), HNSO (social eating), HNSX (sexuality), HNTE (problems with teeth), HNOM (problems with opening mouth) and HNCO (coughing) scores of EORTC QLQ-H&N35 were significantly higher in group 2 than in group 1. However, according to Arizona test results, there were no significant difference between the two groups.

Vestibular migraine screening in a migraine-diagnosed patient population, and assessment of vestibulocochlear function.

OBJECTIVE: The primary aim of this study is to do a vestibular migraine scan in a population of patients with migraine diagnosis using the most recent standardized diagnosis criterion which is International Classification of Headache Disorders (ICHD) 3 Beta and to identify the epidemiological data. The second part of the study involves performing several vestibulocochlear tests on patients who received vestibular migraine (VM) diagnosis to collect data that may be important for diagnostic purposes by comparing the patients with normal population when necessary. DESIGN: Blind, cross-sectional study. SETTING: Tertiary referral hospital. PARTICIPANTS: One hundred patients were scanned for VM using ICHD 3 Beta guideline. MAIN OUTCOME MEASURES: In order to evaluate the vestibulocochlear functions of the patients with VM diagnosis, audiometry, tympanometry, electrocochleography (EcochG), computerized dynamic posturography (CDP) and video head impulse test (vHIT) were performed; besides in order to evaluate the significance of the results of the tests, second group was formed with migraine patients without any vestibular complaints and control group was formed from healthy population when needed. RESULTS: VM prevalence was determined to be 21% in migraine patients which is much higher than stated in current literature. No significant difference was observed between migraine and VM patients with respect to audiometric and tympanometric measurements. According to the CDP results, balance defects were present in VM patients, even during attack-free periods. EcochG data suggests average SP/AP scores of VM patients are significantly higher than migraine patients. Furthermore, the number of patients who exceeded a limit value of 0.4 or 0.5 in SP/AP scores was significantly higher in VM patients than in migraine patients. Also vHIT results show that nearly half the VM patients, which is a significant ratio, have saccadic movements and this is thought to be compatible with peripheral vestibular involvement. CONCLUSION: Our results suggest VM disease is more common than previously thought. We believe that further EcochG-based studies would shed light on the controversial topic on the intersection and disjunction sets of MD and VM diseases. Although the results of the present study are compatible with peripheral vestibular effects, it is not possible to rule out another central mechanism at some other level.

Depression, self-esteem and sexual function in laryngeal cancer patients.

OBJECTIVE: The purpose of this study was to assess sexual function, affective disorders and self-esteem in patients who were surgically treated for laryngeal cancer. DESIGN: Retrospective, blind, cross-sectional study. SETTING: Single tertiary cancer centre. PARTICIPANTS: Seventy four patients who were operated on Istanbul University Cerrahpasa School of Medicine Otorhinolaryngology Department between 2008 and 2012 were classified according to the type of the operation as total laryngectomy (Group 1) and partial laryngectomy (Group 2). MAIN OUTCOME MEASURES: Sexual dysfunction, depression and self-esteem were evaluated with The Arizona Sexual Experiences Scale (ASEX), Beck's Depression Inventory (BDI) and Rosenberg Self-Esteem Scale (RSES), respectively. RESULTS: Average ASEX scores of the Group 1 were (13.98 ± 6.32) and Group 2 were (13.08 ± 4.96) without statistically significant difference (P = 0.537). Mean BDI score of Group 1 was (13.20 ± 10.41) higher than Group 2 (7.76 ± 8.14) and the difference was significant statistically (P = 0.026). Mean RSES scores of Group 1 and Group 2 were 20.68 ± 5.33 and 19.25 ± 4.70, respectively, again without significant difference (P = 0.262). However, when the average scores of each item of Rosenberg Scale were compared, significant difference was found in d4 (2.37 ± 0.78; 1.64 ± 0.99; P = 0.001), d6 (1.22 ± 1.05; 1.84 ± 1.14; P = 0.023), d10 (2.55 ± 2.39; 1.28 ± 1.49; P = 0.018) and d11 (1.35 ± 0.95; 2.00 ± 1.41; P = 0.021). BDI scores were correlated with RSES scores, and ASEX scores were correlated with age. CONCLUSION: The patients with total laryngectomy seem to have more psychological problems that must be addressed in the postoperative period.