Diagnosis of Early Glottic Cancer Using Laryngeal Image and Voice Based on Ensemble Learning of Convolutional Neural Network Classifiers

Kwon, Ickhwan; Wang, Soo-Geun; Shin, Sung‐Chan; Cheon, Yong-Il; Lee, Byung‐Joo; Lee, Jin‐Choon; Lim, Dong-Won; Jo, Cheolwoo; Cho, Youngseuk; Shin, Bhum Jae

doi:10.1016/j.jvoice.2022.07.007

Cited by 21 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The features of the MFCCs of healthy and laryngeal cancer speech are quite distinct in table 2, so there is no performance improvement in applying the CNN after image conversion. These results demonstrate a significant improvement in accuracy by more than 0.25 compared to prior studies 12,13 . This improvement is attributed to the effect of segmenting the audio signals into fine-grained MFCC data, which enhances data augmentation while preserving key features.…”

Section: Healthy Vs Laryngeal Cancermentioning

confidence: 45%

“…Kim et al 12 distinguished laryngeal cancer and healthy controls with 0.85 accuracy in one-dimensional convolutional neural network (1D-CNN) using voice data. Kwon et al 13 acquired 0.95 of accuracy in the fusion of the laryngeal image and voice data by ensemble learning of two CNN models for the same task, but the accuracy was limited to 0.71, when classifying with only voice data. These voice-based AI laryngeal cancer diagnosis models have the limitation of simply classifying laryngeal cancer and healthy condition.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of laryngeal diseases including laryngeal cancer, benign mucosal disease, and vocal cord paralysis by artificial intelligence using voice analysis

Kim,

Song,

Park

et al. 2023

Preprint

View full text Add to dashboard Cite

Voice change is often the first sign of laryngeal cancer, leading to diagnosis through hospital laryngoscopy. Screening for laryngeal cancer solely based on voice could enhance early detection. However, identifying voice indicators specific to laryngeal cancer is challenging, especially when differentiating it from other laryngeal ailments. This study presents an artificial intelligence model designed to distinguish between healthy voices, laryngeal cancer voices, and those of the other laryngeal conditions. We gathered voice samples of individuals with laryngeal cancer, vocal cord paralysis, benign mucosal diseases, and healthy participants. Comprehensive testing was conducted to determine the best mel-frequency cepstral coefficient conversion and machine learning techniques, with results analyzed in-depth. In our tests, laryngeal diseases distinguishing from healthy voices achieved an accuracy of 0.85 to 0.97. However, when multiclass classification, accuracy ranged from 0.74 to 0.83. These findings highlight the challenges of artificial intelligence-driven voice-based diagnosis due to overlaps with benign conditions but also underscore its potential.

show abstract

Section: Healthy Vs Laryngeal Cancermentioning

confidence: 45%

Section: Introductionmentioning

confidence: 99%

Classification of laryngeal diseases including laryngeal cancer, benign mucosal disease, and vocal cord paralysis by artificial intelligence using voice analysis

Kim,

Song,

Park

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…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].…”

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

confidence: 99%

“…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% [81–88,89 ▪ ]. The most common feature extracted is the Mel-frequency cepstral coefficient (MFCC) [81–83,85,89 ▪ ], which is derived from a transformation of the audio signal and provides a compact representation of the spectral properties of a sound.…”

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

confidence: 99%

“…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]. The studies show no clear advantage to using neural networks compared to other ML methods and no clear difference based on features extracted.…”

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

confidence: 99%

See 1 more Smart Citation

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

The Use of Deep Learning Software in the Detection of Voice Disorders: A Systematic Review

Barlow,

Sragi,

Rivera‐Rivera

et al. 2024

Otolaryngol.--head neck surg.

View full text Add to dashboard Cite

ObjectiveTo summarize the use of deep learning in the detection of voice disorders using acoustic and laryngoscopic input, compare specific neural networks in terms of accuracy, and assess their effectiveness compared to expert clinical visual examination.Data SourcesEmbase, MEDLINE, and Cochrane Central.Review MethodsDatabases were screened through November 11, 2023 for relevant studies. The inclusion criteria required studies to utilize a specified deep learning method, use laryngoscopy or acoustic input, and measure accuracy of binary classification between healthy patients and those with voice disorders.ResultsThirty‐four studies met the inclusion criteria, with 18 focusing on voice analysis, 15 on imaging analysis, and 1 both. Across the 18 acoustic studies, 21 programs were used for identification of organic and functional voice disorders. These technologies included 10 convolutional neural networks (CNNs), 6 multilayer perceptrons (MLPs), and 5 other neural networks. The binary classification systems yielded a mean accuracy of 89.0% overall, including 93.7% for MLP programs and 84.5% for CNNs. Among the 15 imaging analysis studies, a total of 23 programs were utilized, resulting in a mean accuracy of 91.3%. Specifically, the twenty CNNs achieved a mean accuracy of 92.6% compared to 83.0% for the 3 MLPs.ConclusionDeep learning models were shown to be highly accurate in the detection of voice pathology, with CNNs most effective for assessing laryngoscopy images and MLPs most effective for assessing acoustic input. While deep learning methods outperformed expert clinical exam in limited comparisons, further studies integrating external validation are necessary.

show abstract

Diagnosis of Early Glottic Cancer Using Laryngeal Image and Voice Based on Ensemble Learning of Convolutional Neural Network Classifiers

Cited by 21 publications

References 21 publications

Classification of laryngeal diseases including laryngeal cancer, benign mucosal disease, and vocal cord paralysis by artificial intelligence using voice analysis

Classification of laryngeal diseases including laryngeal cancer, benign mucosal disease, and vocal cord paralysis by artificial intelligence using voice analysis

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

The Use of Deep Learning Software in the Detection of Voice Disorders: A Systematic Review

Contact Info

Product

Resources

About