Correlation between peri-operative complication in middle ear cholesteatoma surgery using STAMCO, ChOLE, and SAMEO-ATO classifications.

PURPOSE: To compare the relationship between the variable "complication" and the other variables of middle ear cholesteatoma classifications (STAMCO, ChOLE, and SAMEO-ATO). METHODS: Retrospective study of 110 patients that underwent 132 middle ear surgeries between the 1 January 2012 and the 31 December 2019 for chronic otitis with cholesteatoma classified according to STAMCO, ChOLE, and SAMEO-ATO classifications in a tertiary health care centre. RESULTS: Older age, male gender, STAMCO-T, and SAMEO-ATO [O1, T, O2, (s -)] and mastoid involvement (STAMCO-M and ChOLE-Ch) were associated with an increased risk of complication report. CONCLUSIONS: In our series, statistical analysis pointed out a relationship between surgical complications and age, gender, site, mastoidectomy type, and ossicular chain status at surgery. The choice of variables to be recorded for cholesteatoma staging should be carefully balanced, considering that "complication" variable could be a repetitive item.

Electric Bioimpedance Sensing for the Detection of Head and Neck Squamous Cell Carcinoma.

The early detection of head and neck squamous cell carcinoma (HNSCC) is essential to improve patient prognosis and enable organ and function preservation treatments. The objective of this study is to assess the feasibility of using electrical bioimpedance (EBI) sensing technology to detect HNSCC tissue. A prospective study was carried out analyzing tissue from 46 patients undergoing surgery for HNSCC. The goal was the correct identification of pathologic tissue using a novel needle-based EBI sensing device and AI-based classifiers. Considering the data from the overall patient cohort, the system achieved accuracies between 0.67 and 0.93 when tested on tissues from the mucosa, skin, muscle, lymph node, and cartilage. Furthermore, when considering a patient-specific setting, the accuracy range increased to values between 0.82 and 0.95. This indicates that more reliable results may be achieved when considering a tissue-specific and patient-specific tissue assessment approach. Overall, this study shows that EBI sensing may be a reliable technology to distinguish pathologic from healthy tissue in the head and neck region. This observation supports the continuation of this research on the clinical use of EBI-based devices for early detection and margin assessment of HNSCC.

Deep Learning Applied to White Light and Narrow Band Imaging Videolaryngoscopy: Toward Real-Time Laryngeal Cancer Detection.

OBJECTIVES: To assess a new application of artificial intelligence for real-time detection of laryngeal squamous cell carcinoma (LSCC) in both white light (WL) and narrow-band imaging (NBI) videolaryngoscopies based on the You-Only-Look-Once (YOLO) deep learning convolutional neural network (CNN). STUDY DESIGN: Experimental study with retrospective data. METHODS: Recorded videos of LSCC were retrospectively collected from in-office transnasal videoendoscopies and intraoperative rigid endoscopies. LSCC videoframes were extracted for training, validation, and testing of various YOLO models. Different techniques were used to enhance the image analysis: contrast limited adaptive histogram equalization, data augmentation techniques, and test time augmentation (TTA). The best-performing model was used to assess the automatic detection of LSCC in six videolaryngoscopies. RESULTS: Two hundred and nineteen patients were retrospectively enrolled. A total of 624 LSCC videoframes were extracted. The YOLO models were trained after random distribution of images into a training set (82.6%), validation set (8.2%), and testing set (9.2%). Among the various models, the ensemble algorithm (YOLOv5s with YOLOv5m-TTA) achieved the best LSCC detection results, with performance metrics in par with the results reported by other state-of-the-art detection models: 0.66 Precision (positive predicted value), 0.62 Recall (sensitivity), and 0.63 mean Average Precision at 0.5 intersection over union. Tests on the six videolaryngoscopies demonstrated an average computation time per videoframe of 0.026 seconds. Three demonstration videos are provided. CONCLUSION: This study identified a suitable CNN model for LSCC detection in WL and NBI videolaryngoscopies. Detection performances are highly promising. The limited complexity and quick computational times for LSCC detection make this model ideal for real-time processing. LEVEL OF EVIDENCE: 3 Laryngoscope, 132:1798-1806, 2022.

SmartProbe: a bioimpedance sensing system for head and neck cancer tissue detection.

OBJECTIVES: This study presents SmartProbe, an electrical bioimpedance (EBI) sensing system based on a concentric needle electrode (CNE). The system allows the use of commercial CNEs for accurate EBI measurement, and was specially developed for in-vivo real-time cancer detection. APPROACH: Considering the uncertainties in EBI measurements due to the CNE manufacturing tolerances, we propose a calibration method based on statistical learning. This is done by extracting the correlation between the measured impedance value |Z|, and the material conductivity σ, for a group of reference materials. By utilizing this correlation, the relationship of σ and |Z| can be described as a function and reconstructed using a single measurement on a reference material of known conductivity. MAIN RESULTS: This method simplifies the calibration process, and is verified experimentally. Its effectiveness is demonstrate by results that show less than 6% relative error. An additional experiment is conducted for evaluating the system's capability to detect cancerous tissue. Four types of ex-vivo human tissue from the head and neck region, including mucosa, muscle, cartilage and salivary gland, are characterized using SmartProbe. The measurements include both cancer and surrounding healthy tissue excised from 10 different patients operated on for head and neck cancer. The measured data is then processed using dimension reduction and analyzed for tissue classification. The final results show significant differences between pathologic and healthy tissues in muscle, mucosa and cartilage specimens. SIGNIFICANCE: These results are highly promising and indicate a great potential for SmartProbe to be used in various cancer detection tasks.