Automated laryngeal mass detection algorithm for home-based self-screening test based on convolutional neural network

Abstract

Background Early detection of laryngeal masses without periodic visits to hospitals is essential for improving the possibility of full recovery and the long-term survival ratio after prompt treatment, as well as reducing the risk of clinical infection. Results We first propose a convolutional neural network model for automated laryngeal mass detection based on diagnostic images captured at hospitals. Thereafter, we propose a pilot system, composed of an embedded controller, a camera module, and an LCD display, that can be utilized for a home-based self-screening test. In terms of evaluating the model’s performance, the experimental results indicated a final validation loss of 0.9152 and a F1-score of 0.8371 before post-processing. Additionally, the F1-score of the original computer algorithm with respect to 100 randomly selected color-printed test images was 0.8534 after post-processing while that of the embedded pilot system was 0.7672. Conclusions The proposed technique is expected to increase the ratio of early detection of laryngeal masses without the risk of clinical infection spread, which could help improve convenience and ensure safety of individuals, patients, and medical staff.

Advances in Image‐Based Artificial Intelligence in Otorhinolaryngology–Head and Neck Surgery: A Systematic Review

“…Some studies have applied AI to the automatic recognition of vocal mass 29,94 and the classification of pharynx 58 . Most of these studies combined AI predictions with laryngoscopic images 29,54,55,64‐67,77,94 . The remaining studies combined AI with CT, 27,28,49,61 PET‐CT, 86,87 and MRI 58,72 …”

“…Most applications of AI in pharyngology involve the detection of laryngeal squamous cell carcinoma (LSCC) 27,28,49,65,86,87 and laryngeal cancer 54,61,66,67,72,77 (Supplemental File 3, available online). Some studies have applied AI to the automatic recognition of vocal mass 29,94 and the classification of pharynx.…”

“…58 Most of these studies combined AI predictions with laryngoscopic images. 29,54,55,[64][65][66][67]77,94 The remaining studies combined AI with CT, 27,28,49,61 PET-CT, 86,87 and MRI. 58,72 All the studies used single-center data to train the AI model, except for 1 using public data.…”

Artificial Intelligence for Upper Aerodigestive Tract Endoscopy and Laryngoscopy: A Guide for Physicians and State‐of‐the‐Art Review

“…However, the model did not achieve real-time performances (5-40 seconds per frame). 29 Segmentation AI-based models can also be used for automatically delineating the boundaries of structures and lesions of the UADT. This task could have interesting clinical implications, especially when applied to cancer lesions.…”

Acoustic event characterization for service robot using convolutional networks

“…Each of these systems, including the sound event identification event, must be capable of running on the robot hardware, considering the possibility of restricted communication in cases of emergency [26]. CNNs can create models that can be deployed on small embedded systems without excessive resource consumption [27], [28]. The current frameworks have compatibility for their implementation on different systems, which also facilitates their continuous updating.…”