Cancer larynx detection using glottal flow parameters and statistical tools

Aicha, Anis Ben; Ezzine, Kadria

doi:10.1109/isivc.2016.7893963

Cited by 12 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several ML methods using vocal recordings perform binary classification to distinguish voices from patients with laryngeal cancer from those with healthy voices or benign voice disorders with accuracy ranging from 85.2% to 98% [81][82][83][84][85][86][87][88]89 ], which is derived from a transformation of the audio signal and provides a compact representation of the spectral properties of a sound. Others algorithms rely on acoustic features (jitter, shimmer, and harmonic features) [81,88] and glottal air-flow parameters [84,86]. Studies in this category use various preprocessing, feature extraction, and classifications methods, including different neural network methods [81-84,86,87,89 & ], support vector machine [81,85], hidden Markov models [88], and Gaussian mixture models [85].…”

Section: Machine Learning Models Utilizing Voice and Speech To Screen...mentioning

confidence: 99%

Machine learning in the evaluation of voice and swallowing in the head and neck cancer patient

Srinivasan,

Liu,

Rameau

2023

Current Opinion in Otolaryngology &Amp; Head &Amp; Neck Surgery

View full text Add to dashboard Cite

Purpose of review The purpose of this review is to present recent advances and limitations in machine learning applied to the evaluation of speech, voice, and swallowing in head and neck cancer. Recent findings Novel machine learning models incorporating diverse data modalities with improved discriminatory capabilities have been developed for predicting toxicities following head and neck cancer therapy, including dysphagia, dysphonia, xerostomia, and weight loss as well as guiding treatment planning. Machine learning has been applied to the care of posttreatment voice and swallowing dysfunction by offering objective and standardized assessments and aiding innovative technologies for functional restoration. Voice and speech are also being utilized in machine learning algorithms to screen laryngeal cancer. Summary Machine learning has the potential to help optimize, assess, predict, and rehabilitate voice and swallowing function in head and neck cancer patients as well as aid in cancer screening. However, existing studies are limited by the lack of sufficient external validation and generalizability, insufficient transparency and reproducibility, and no clear superior predictive modeling strategies. Algorithms and applications will need to be trained on large multiinstitutional data sets, incorporate sociodemographic data to reduce bias, and achieve validation through clinical trials for optimal performance and utility.

show abstract

Section: Machine Learning Models Utilizing Voice and Speech To Screen...mentioning

confidence: 99%

Machine learning in the evaluation of voice and swallowing in the head and neck cancer patient

Srinivasan,

Liu,

Rameau

2023

Current Opinion in Otolaryngology &Amp; Head &Amp; Neck Surgery

View full text Add to dashboard Cite

show abstract

“…The use of such a tool may also be able to screen patients with concerns regarding their voice quality, prioritise those at highest risk of a cancer diagnosis, expediting their specific care pathway, and increase the accessibility of diagnosis by reducing the need for expensive medical equipment. Indeed several papers have presented ML and AI methods for detecting laryngeal cancer from speech [4,5,6,7,8]. All of these papers use data from a single dataset where the speech has been recorded in controlled environments.…”

Section: Introductionmentioning

confidence: 99%

A Pipeline to Evaluate the Effects of Noise on Machine Learning Detection of Laryngeal Cancer

Paterson¹,

Moor²,

Cutillo³

2023

Interspeech 2023

View full text Add to dashboard Cite

Cases of laryngeal cancer are rising, with diagnosis often involving invasive biopsy procedures. An alternate approach is to identify high-risk patients by analysis of voice recordings which can alert clinical teams to those patients that need prioritisation. We propose a pipeline for evaluating speech classifier performance in the presence of noise. We perform experiments using the pipeline with several classifiers and denoising techniques. Random forest classifier performed best with an accuracy of 81.2% on clean data dropping to 63.8% when noise was added to recordings. The accuracy of all classifiers was reduced by added noise, signal denoising improved classifier accuracy but could not fully reverse the effects of noise. The effects of noise on classification is a complex issue which must be resolved for these detection systems to be implemented in clinical practice. We show that the proposed pipeline allows for the evaluation of classifier performance in the presence of noise.

show abstract

“…Most of these studies analyze sound in the audible bandwidth, which gives incomplete information on the vibratory state of the vocal cords, while some others worked on the improvement of existing techniques such as local imaging or scanning. [7][8][9][10][11] In this context, this work aims to evaluate some larynx physical property variations through a non-intrusive passive smart listening collar. The latter can provide systematic and in vivo screening for some laryngeal diseases, including laryngeal cancer, by spectrotemporal analysis of the voice signal resonance.…”

Section: Introductionmentioning

confidence: 99%

Passive wideband concentric rings resonator for vocal cords abnormalities detection: Application on larynx cancer pathologies

Matta

Diab

Saad

et al. 2020

Review of Scientific Instruments

View full text Add to dashboard Cite

This work addresses the study and design of a diagnostic device consisting of a thin-film sensor array based on 8-mm concentered rings, acting as an autonomous acoustic sensor covering a wide range of resonance frequencies (0.1 KHz-2 MHz). In addition to its advantageous shape, this device integrates both the active vibratory element and the embedded electronics dedicated to coding, control, and analysis. The results show that the experimental device could be the basis of a telemedical platform for the objective assessment and monitoring of chronic laryngeal dysphonia through the spectro-temporal analysis of the vibration of the vocal cords. Furthermore, this non-invasive, non-intrusive protocol does not require the physical cooperation of the patient.

show abstract

Cancer larynx detection using glottal flow parameters and statistical tools

Cited by 12 publications

References 13 publications

Machine learning in the evaluation of voice and swallowing in the head and neck cancer patient

Machine learning in the evaluation of voice and swallowing in the head and neck cancer patient

A Pipeline to Evaluate the Effects of Noise on Machine Learning Detection of Laryngeal Cancer

Passive wideband concentric rings resonator for vocal cords abnormalities detection: Application on larynx cancer pathologies

Contact Info

Product

Resources

About