Convolutional Neural Network Classifies Pathological Voice Change in Laryngeal Cancer with High Accuracy
Open Access
- 24 October 2020
- journal article
- research article
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 9 (11), 3415
- https://doi.org/10.3390/jcm9113415
Abstract
Voice changes may be the earliest signs in laryngeal cancer. We investigated whether automated voice signal analysis can be used to distinguish patients with laryngeal cancer from healthy subjects. We extracted features using the software package for speech analysis in phonetics (PRAAT) and calculated the Mel-frequency cepstral coefficients (MFCCs) from voice samples of a vowel sound of /a:/. The proposed method was tested with six algorithms: support vector machine (SVM), extreme gradient boosting (XGBoost), light gradient boosted machine (LGBM), artificial neural network (ANN), one-dimensional convolutional neural network (1D-CNN) and two-dimensional convolutional neural network (2D-CNN). Their performances were evaluated in terms of accuracy, sensitivity, and specificity. The result was compared with human performance. A total of four volunteers, two of whom were trained laryngologists, rated the same files. The 1D-CNN showed the highest accuracy of 85% and sensitivity and sensitivity and specificity levels of 78% and 93%. The two laryngologists achieved accuracy of 69.9% but sensitivity levels of 44%. Automated analysis of voice signals could differentiate subjects with laryngeal cancer from those of healthy subjects with higher diagnostic properties than those performed by the four volunteers.Keywords
This publication has 39 references indexed in Scilit:
- Laryngeal cancer mortality trends in European countriesInternational Journal of Cancer, 2015
- Trends in head and neck cancers in England from 1995 to 2011 and projections up to 2025Oral Oncology, 2015
- Influences of Fundamental Frequency, Formant Frequencies, Aperiodicity, and Spectrum Level on the Perception of Voice GenderJournal of Speech, Language, and Hearing Research, 2014
- Sex Disparities in Cancer Mortality and SurvivalCancer Epidemiology, Biomarkers & Prevention, 2011
- Artificial neural network analysis to assess hypernasality in patients treated for oral or oropharyngeal cancerLogopedics Phoniatrics Vocology, 2011
- Automatic Detection of Laryngeal Pathologies in Records of Sustained Vowels by Means of Mel-Frequency Cepstral Coefficient Parameters and Differentiation of Patients by SexFolia Phoniatrica et Logopaedica, 2009
- Automatic Detection of Voice Impairments by Means of Short-Term Cepstral Parameters and Neural Network Based DetectorsIEEE Transactions on Biomedical Engineering, 2004
- Glottic and Supraglottic Laryngeal Carcinoma: Differences in Epidemiology, Clinical Characteristics and PrognosisActa Oto-Laryngologica, 1999
- The Aging VoiceSeminars in Speech and Language, 1997
- Physiologic and acoustic differences between male and female voicesThe Journal of the Acoustical Society of America, 1989