Early stage diagnosis of laryngeal squamous cell carcinoma (SCC) is of primary importance for lowering patient mortality or after treatment morbidity. Despite the challenges in diagnosis reported in the clinical literature, few efforts have been invested in computer-assisted diagnosis. The objective of this paper is to investigate the use of texture-based machine-learning algorithms for early stage cancerous laryngeal tissue classification. To estimate the classification reliability, a measure of confidence is also exploited. From the endoscopic videos of 33 patients affected by SCC, a well-balanced dataset of 1320 patches, relative to four laryngeal tissue classes, was extracted. With the best performing feature, the achieved median classification recall was 93% [interquartile range [Formula: see text]]. When excluding low-confidence patches, the achieved median recall was increased to 98% ([Formula: see text]), proving the high reliability of the proposed approach. This research represents an important advancement in the state-of-the-art computer-assisted laryngeal diagnosis, and the results are a promising step toward a helpful endoscope-integrated processing system to support early stage diagnosis.

Background and Objective Early-stage diagnosis of laryngeal cancer is of primary importance to reduce patient morbidity. Narrow-band imaging (NBI) endoscopy is commonly used for screening purposes, reducing the risks linked to a biopsy but at the cost of some drawbacks, such as large amount of data to review to make the diagnosis. The purpose of this paper is to present a strategy to perform automatic selection of informative endoscopic video frames, which can reduce the amount of data to process and potentially increase diagnosis performance. Methods A new method to classify NBI endoscopic frames based on intensity, keypoint and image spatial content features is proposed. Support vector machines with the radial basis function and the one-versus-one scheme are used to classify frames as informative, blurred, with saliva or specular reflections, or underexposed. Results When Email address: sara.moccia@iit.it, sara.moccia@polimi.it (Sara Moccia) Preprint submitted to Computer Methods and Programs in Biomedicine February 9, 2018tested on a balanced set of 720 images from 18 different laryngoscopic videos, a classification recall of 91% was achieved for informative frames, significantly overcoming three state of the art methods (Wilcoxon rank-signed test, significance level = 0.05). Conclusions Due to the high performance in identifying informative frames, the approach is a valuable tool to perform informative frame selection, which can be potentially applied in different fields, such us computer-assisted diagnosis and endoscopic view expansion.

Objectives: Good laryngeal exposure (GLE) is typically regarded as an essential prerequisite for transoral laser microsurgery (TLM). The Laryngoscore is a preoperative scoring system aimed at predicting glottic visualization through the laryngoscope using easy patient-derived parameters. However, the presence of subjective variables may hamper its reliability and reproducibility. The aim of the present study was to provide a validation of the Laryngoscore and to develop a revised mini-version of the same, called mini-Laryngoscore (mLS), which could allow even quicker, yet sufficiently accurate, preoperative prediction of GLE.Study Design: Prospective cohort study. Methods: We prospectively evaluated 310 consecutive patients submitted to TLM between 2014 and 2017, grading each patient according to the variables considered in the Laryngoscore.Results: Among the 11 variables of the previous Laryngoscore, three were confirmed as statistically significant at validation: interincisors gap, thyromental distance, and upper jaw dental status. We chose these three variables as part of the revised mLS (ranging from 0 to 4). In our cohort, 30% of the patients obtained a score of 0, 57% a score of 1, 11% a score of 2, and 2% a score of ≥3. GLE was achieved in 97%, 85%, 65%, and 20% of cases, respectively.Conclusion: Our validation confirmed the predictive ability of the Laryngoscore. Furthermore, although composed of only three clinical parameters, the mLS was still able to convey useful information regarding the possibility of obtaining GLE.

COVID-19 infection can cause a wide spectrum of symptoms. The audio-vestibular system can also be involved, but there is still debate about this so findings need to be considered carefully. Furthermore, mother to fetus intrauterine transmission of COVID-19 infection in pregnant women is controversial. Few studies are available about the audio-vestibular symptomatology of newborns with intrauterine COVID19 exposure. Objectives This study investigates the possible correlation between the COVID19 gestational infection and hearing impairment onset in newborns. The involvement of hearing in COVID19 is verified so the timing and methodology of audiological evaluation of children can be planned. Methods Children were subject to newborn hearing screening and audiological evaluation. Newborn hearing screening is carried out prior to hospital discharge using the Automatic Transient Evoked Otoacoustic Emissions test. Audiological evaluation is performed within the child age of 4 months by using maternal, pregnancy, and perinatal case history, COVID19 case history, otoscopy, acoustic immittance test, Distortion Product Otoacoustic Emissions test, and the Auditory Brainstem Response test. Results 63 children were included in the study. 82.5% of these children were subjects of the newborn hearing screening program. The remaining 11 newborns were not subjected to hearing screening due to isolation measures and their audiological evaluation was carried out directly. Only one of 52 screened neonates showed a bilateral REFER test result but hearing threshold was normal at audiological evaluation. Audiological evaluation showed normal bilateral ABR thresholds in 59/63 children. Four children (6.3% of the total) had ABR threshold alterations but two showed normal threshold at ABR retest performed within 1 month of the first. The other two infants showed monolateral ABR alterations but one of these had a concomitant middle ear effusion. In conclusion, only one child (1.6% of the sample) had an altered ABR. This child had shown one positive SARS-CoV-2 swab in the absence of risk factors for hearing loss. Conclusion This study finds no evidence that maternal COVID19 infection is a risk factor in the development of congenital hearing loss in newborns.

(1) Background: Schwannomas of the vestibulocochlear nerve are benign, slow-growing tumors, arising from the Schwann cells. When they originate from neural elements within the vestibule or cochlea, they are defined as intralabyrinthine schwannomas (ILSs). Cochlear implant (CI) has been reported as a feasible solution for hearing restoration in these patients. (2) Methods: Two patients with single-sided deafness (SSD) due to sudden sensorineural hearing loss and ipsilateral tinnitus were the cases. MRI detected an ILS. CI was positioned using a standard round window approach without tumor removal. (3) Results: The hearing threshold was 35 dB in one case and 30 dB in the other 6 mo after activation. Speech audiometry with bisillables in quiet was 21% and 27% at 65 dB, and the tinnitus was completely resolved or reduced. In the localization test, a 25.9° error azimuth was obtained with CI on, compared to 43.2° without CI. The data log reported a daily use of 11 h and 14 h. In order to not decrease the CI’s performance, we decided not to perform tumor exeresis, but only CI surgery to restore functional binaural hearing. (4) Conclusions: These are the sixth and seventh cases in the literature of CI in patients with ILS without any tumor treatment and the first with SSD. Cochlear implant without tumor removal can be a feasible option for restoring binaural hearing without worsening the CI’s performance.