Multi-instance learning based artificial intelligence model to assist vocal fold leukoplakia diagnosis: A multicentre diagnostic study.

OBJECTIVE: To develop a multi-instance learning (MIL) based artificial intelligence (AI)-assisted diagnosis models by using laryngoscopic images to differentiate benign and malignant vocal fold leukoplakia (VFL). METHODS: The AI system was developed, trained and validated on 5362 images of 551 patients from three hospitals. Automated regions of interest (ROI) segmentation algorithm was utilized to construct image-level features. MIL was used to fusion image level results to patient level features, then the extracted features were modeled by seven machine learning algorithms. Finally, we evaluated the image level and patient level results. Additionally, 50 videos of VFL were prospectively gathered to assess the system's real-time diagnostic capabilities. A human-machine comparison database was also constructed to compare the diagnostic performance of otolaryngologists with and without AI assistance. RESULTS: In internal and external validation sets, the maximum area under the curve (AUC) for image level segmentation models was 0.775 (95 % CI 0.740-0.811) and 0.720 (95 % CI 0.684-0.756), respectively. Utilizing a MIL-based fusion strategy, the AUC at the patient level increased to 0.869 (95 % CI 0.798-0.940) and 0.851 (95 % CI 0.756-0.945). For real-time video diagnosis, the maximum AUC at the patient level reached 0.850 (95 % CI, 0.743-0.957). With AI assistance, the AUC improved from 0.720 (95 % CI 0.682-0.755) to 0.808 (95 % CI 0.775-0.839) for senior otolaryngologists and from 0.647 (95 % CI 0.608-0.686) to 0.807 (95 % CI 0.773-0.837) for junior otolaryngologists. CONCLUSIONS: The MIL based AI-assisted diagnosis system can significantly improve the diagnostic performance of otolaryngologists for VFL and help to make proper clinical decisions.

Evaluation of P53 gene expression by immunohistochemistry to diagnosis oral precancerous lesions.

Oral Precancerous lesions include leukoplakia, erythroplakia, and mucosa palate changes due to reverse smoking. Assessing the prevalence of these lesions in a cross-sectional study can be effective in the timely prevention and treatment of lesions, in any community. Hence, in the present study, evaluation of P53 gene expression was done by immunohistochemistry method to diagnosis oral precancerous lesions. For this purpose, 111 Chinese patients (54 women and 57 men) were selected for examination. The age range of these patients was 22 to 69 years, and their average age was 32.6 years. All patients were examined by one physician. Oral mucosa was used for immunohistochemical evaluations. All samples taken from patients' mucosa were evaluated by one pathologist under a light microscope. 80 cases of the 111 patients were smokers and 27 were non-smokers. Among the 80 smokers, 56.25% had leukoplakia, 3.75% had erythroplakia, and 40% had mucosa palate changes. Regarding non-smokers, 74.07% had leukoplakia and 25.93% had erythroplakia. None of the non-smokers had mucosa palate changes. In terms of the lesion location, in patients with leukoplakia 89.23%, and patients with erythroplakia 90% of the lesion was located in the cheek mucosa and buccal vestibule. Also, in patients with leukoplakia 9.23%, and patients with erythroplakia 10% of the lesion was located in the lips vestibular mucosa. Only 1.54% of leukoplakia had a lesion in the vermilion border, and none of the erythroplakia patients had a lesion on the vermilion border. 76 patients (68.46%) showed positive expression of the P53 gene. The expression level of the P53 gene did not show a significant relationship with age, and the genders did not have a statistically significant difference in terms of gene expression. The expression level of the P53 gene was 59.8% in leukoplakia, 70% in erythroplakia, and 40% in Mucosa palate changes. The present study showed that the evaluation of P53 gene expression was well able to detect oral precancerous lesions and their severity by increasing their expression rate.

Significance of Cytokeratin-1 Single-Nucleotide Polymorphism and Protein Level in Susceptibility to Vocal Leukoplakia and Laryngeal Squamous Cell Carcinoma.

OBJECTIVE: To investigate the association between the cytokeratin (CK)-1 single-nucleotide polymorphism (SNP), the protein level of CK-1 and the risk of vocal leukoplakia and laryngeal squamous cell carcinoma (LSCC). METHODS: In this case-control study, 155 patients with vocal leukoplakia, 323 patients with LSCC, and 266 healthy controls were genotyped for the CK-1 (SNP RS14024) gene using pyrosequencing. The protein expression level of CK-1 was analyzed in vocal leukoplakia, LSCC, and vocal polyp patients by immunohistochemistry (IHC). RESULTS: Of the CK-1 RS14024 polymorphism, the heterozygote AG and homozygote GG genotype exhibited a significantly increased risk of LSCC (AG: OR = 2.16, p = 0.014; GG: OR = 2.15, p = 0.018) compared to normal controls. A higher protein expression level of CK-1 was detected in patients with LSCC compared to vocal leukoplakia and polyps (both p < 0.001), and a significant increasing trend of CK-1 protein expression level from mild-moderate dysplasia to moderate-severe dysplasia in vocal leukoplakia patients was also observed (p = 0.006). CONCLUSIONS: This study demonstrates that the CK-1 SNP and high protein expression levels are associated with vocal leukoplakia and LSCC and promote the transformation from vocal leukoplakia to LSCC in a Chinese Han population.

Clinical utility and effectiveness of a training programme in the application of a new classification of narrow-band imaging for vocal cord leukoplakia: A multicentre study.

OBJECTIVE: To analyse the application of a new narrow-band imaging (NBI) classification in the diagnosis of vocal cord leukoplakia by laryngologists with different levels of laryngoscopic experience and to explore the impact of NBI training programmes on laryngologists' identification of benign and malignant leukoplakia. DESIGN: Prospective multicentre study. SETTING: Tertiary hospitals. PARTICIPANTS: Sixteen laryngologists were divided into less-experienced and experienced groups and received NBI training course. Thirty cases of vocal cord leukoplakia were investigated. MAIN OUTCOME MEASURES: Diagnostic accuracy and interobserver agreement under white light imaging (WLI), before and after NBI training, were analysed among doctors with varying levels of experience. RESULTS: The accuracy in the less-experienced group was significantly lower than that of experience group (0.59 vs 0.69) under WLI. There was no significant difference in the diagnostic accuracy between the less-experienced group and the experienced group before NBI training (0.75 vs 0.74) and after NBI training (0.79 vs 0.83). NBI training could improve the interobserver agreement from fair or moderate to good agreement. CONCLUSION: The new NBI diagnostic classification is helpful for identifying benign and malignant vocal cord leukoplakia. In addition, the NBI training programme can improve the diagnostic accuracy and interobserver agreement of less-experienced doctors to the level of experienced laryngologists.

Recurrence of vocal fold leukoplakia after carbon dioxide laser therapy.

This work aims to analyze the recurrence of vocal fold leukoplakia after carbon dioxide (CO2) laser resection. In this retrospective study, all patients undergoing CO2 laser resection of vocal fold leukoplakia were followed up for at least 2 years. Recurrence was diagnosed as any presence of leukoplakia in the vocal cord subsequent to previous successful complete resection. A total of 326 patients with complete resection of vocal fold leukoplakia and follow-up subsequent surveillance laryngoscopy were studied. The recurrence rate, the recurrence time, and risk factors were evaluated. Of these, 52 (16.0%) patients experienced recurrence with a mean follow-up time of 50.5 ± 15.4 months. The mean time to recurrence was 16.2 ± 14.1 months. Univariate analysis showed that the size of lesion (P < 0.001, Pearson χ 2 test; P < 0.001, log-rank test) and the pathological grade (P = 0.025, Pearson χ 2 test; P = 0.028, log-rank test) were significantly related to recurrence. The size of lesion was an independent prognostic factor for recurrence using multivariate analysis (P = 0.001, logistic regression; P = 0.001, Cox proportional hazards model). Considering the possible recurrence of vocal fold leukoplakia, long-term follow-up is required after CO2 laser resection. In conclusion, the size of lesion combined with the pathological grade are important risk factors that predict vocal fold leukoplakia recurrence.

Sensitivity and specificity of stroboscopy in preoperative differentiation of dysplasia from early invasive glottic carcinoma.

Leukoplakia is a descriptive clinical term designating a white patch or plaque of the mucosa and must be complemented by histology, which can range from simple totally benign keratosis with or without atypia up to invasive carcinoma. The aim of this study is to evaluate the accuracy of videostroboscopy in preoperative differentiation of early invasive glottic carcinoma from intraepithelial atypia and dysplasia. 46 patients with a total of 60 leukoplakia lesions on the vocal folds were included in the study. Videostroboscopy was used to divide them into two groups based on preservation of the mucosal wave and this was correlated with the final pathology after treatment. The sensitivity and specificity of videostroboscopy in predicting invasive nature of the lesions based on absence or reduction of the mucosal wave were 96.8 and 92.8 %, respectively, with an overall accuracy of 95 %. We suggest that routine application of videostroboscopy can be an important, simple, non-invasive tool, to achieve, in a single procedure, proper and accurate evaluation of glottic leukoplakia.

Positive therapy of andrographolide in vocal fold leukoplakia.

PURPOSE: Vocal fold leukoplakia is a premalignant precursor of squamous cell carcinoma. Although many efforts have been contributed to therapy of this disease, none exhibits a satisfactory result. The aims of this study were to investigate the effectiveness and feasibility of andrographolide therapy in vocal fold leukoplakia and to explore the preliminary mechanism underlying. MATERIALS AND METHODS: Forty-one eligible patients were enrolled in the study. The patients were treated for 10-minute exposures of 5 ml (25mg/ml) andrographolide injection aerosols twice a day, and 2 weeks was considered as one treatment course. Electronic laryngoscope was used to observe the condition of vocal fold leukoplakia during the treatment. Every patient received one or two treatment courses, and the follow-up was carried out for 12 months. Toxic reactions of treatments were evaluated on the basis of the standards of the United States MD Anderson Cancer Center. Moreover, laryngeal carcinoma cell line Hep2 was applied to explore the mechanism of effect of andrographolide. Anti-proliferative effect on Hep2, cell nuclear morphology, express of mitogen-activated protein kinases (MAPK) and pro-apoptotic protein were detected after andrographolide treatment. RESULTS: We found that andrographolide exhibited significant curative effects on treatments, which were accompanied by thinning of the lesion of leukoplakia, reduction in the whitish surface area, and return of pink or red epithelium. A complete response up to 85% was observed, and no toxic side effect events occurred during the study. No patient with a complete response had a recurrence in the follow-up. Moreover, cellular experiments in Hep2 indicated that andrographolide activated MAPK pathway and caspase cascade, and finally induced apoptosis in laryngeal carcinoma cell. CONCLUSIONS: The advantages of andrographolide are connected with minimally invasive and localized character of the treatment and no damage of collagenous tissue structures, which are more convenient and less painful for patients. These results suggest that andrographolide treatment is a viable strategy for curing vocal fold leukoplakia.

Laryngoscopy-based scoring system for the diagnosis of vocal fold leukoplakia.

OBJECTIVE: To propose a scoring system based on laryngoscopic characteristics for the differential diagnosis of benign and malignant vocal fold leukoplakia. METHODS: Laryngoscopic images from 200 vocal fold leukoplakia cases were retrospectively analysed. The laryngoscopic signs of benign and malignant vocal fold leukoplakia were compared, and statistically significant features were assigned and accumulated to establish the leukoplakia finding score. RESULTS: A total of five indicators associated with malignant vocal fold leukoplakia were included to construct the leukoplakia finding score, with a possible range of 0-10 points. A score of 6 points or more was indicative of a diagnosis of malignant vocal fold leukoplakia. The sensitivity, specificity and accuracy values of the leukoplakia finding score were 93.8 per cent, 83.6 per cent and 86.0 per cent, respectively. The consistency in the leukoplakia finding score obtained by different laryngologists was strong (kappa = 0.809). CONCLUSION: This scoring system based on laryngoscopic characteristics has high diagnostic value for distinguishing benign and malignant vocal fold leukoplakia.

Association and prognostic value of serum inflammation markers in patients with leukoplakia and oral cavity cancer.

BACKGROUND: Oral cavity cancer ranks as the fourth leading cancer in men in Taiwan. The development of a serum biomarker panel for early detection and disease monitoring is, therefore, warranted. METHODS: Nine inflammation-associated markers were investigated in 46 patients with leukoplakia, 151 patients with untreated oral cavity squamous cell carcinoma (OSCC), and 111 age- and gender-matched healthy controls using enzyme-linked immunosorbent assay. During a subsequent 28-month surveillance of OSCC patients, serum samples were prospectively collected at predetermined intervals following the completion of therapy. RESULTS: Logistic regression analysis showed matrix metalloproteases (MMP)-2, MMP-9, C-reactive protein (CRP), transforming growth factor-ß1 (TGF-ß1), and E-selectin having the best discrimination power between groups and significant elevation trends of those five markers were noted from control to OSCC. By combining those five markers, a 0.888 and 0.938 area under curve by ROC curve analysis with 67.4% and 80% overall sensitivity and fixed 90% specificity for leukoplakia and OSCC groups were demonstrated. In the follow-up period, 25 OSCC patients developed recurring or secondary tumors. All examined markers had decreased in relapse-free patients following treatment. However, in patients with relapse, interleukin-6, CRP, and serum amyloid A remained at elevated levels. Statistical analysis showed that patients with CRP ≧2 mg/L and E-selectin ≧85 ng/mL at baseline had highest probability of relapse (odds ratio=3.029, p<0.05). CONCLUSIONS: The results indicate that inflammation plays a crucial role in the pathogenesis process of OSCC. By examining the inflammation markers, physicians could potentially identify patients at risk of cancer transformation or relapse.

Exfoliative cytology and cytocentrifuge preparation of oral premalignant and malignant lesions.

OBJECTIVE: Oral exfoliative cytology is a sensitive and reliable diagnostic tool for the early diagnosis of oral cancer. Traditional exfoliative cytology, though popular, has limitations which could be overcome using cytocentrifuge preparations. The purpose of this study was to compare the efficacy of cytocentrifuged specimens with that of conventionally prepared smears in the diagnosis of oral premalignancy and malignancy. STUDY DESIGN: Exfoliative cytology was performed on 30 patients with oral premalignant and malignant lesions. The yield was smeared immediately onto a slide for conventional exfoliative cytology (group A). The lesion was then scraped again and the yield was suspended in a bottle containing a fixative solution for cytocentrifuge apparatus-assisted smearing (group B). Both smears were stained with rapid Papanicolaou stain and assessed for cellularity, cellular and nuclear morphology, evaluation of mitosis and background. RESULT: All the criteria assessed were statistically significant (p value of <0.001) in group B except for mitosis, which was significant in group A. CONCLUSION: Cytocentrifuge preparations can preserve the cellular details and reduce the overlapping of cells, enabling precise interpretation and thus aiding in the diagnosis of premalignant and malignant lesions of the oral cavity.

[Improving diagnostics of leukoplakia].

The study included 32 patients (among them 20 patients with simple and 12 with verrucous leukoplakia) and presents both classic and advanced diagnostic methods for this disease: clinical examination, histological and immunohistochemical studies. The latter allows revealing neoplastic transformation of the oral mucosa.

[The value of high-definition intelligent endoscopy combined with stroboscopy in the diagnosis and treatment of vocal cord leukoplakia].

Objective: To evaluate the clinical value of high-definition intelligent endoscopy (iSCAN) combined with stroboscopy in identifying vocal cord leukoplakia. Methods: Seventy-nine patients with vocal cord leukoplakia who underwent CO2 laser laryngeal microsurgery and diagnosed by histopathology were recruited between October 2020 to August 2021. The morphological features, microvascular morphology and mucosal waves were observed by stroboscope; SPSS 20.0 software was used for statistical analysis. Results: There were 79 patients with a total of 119 lesions (56 on left and 63 on right).Pathological examination showed that 51 sides of the vocal cords were malignant lesions (severe dysplasia, carcinoma in situ and invasive carcinoma), and 68 sides were benign lesions.Under stroboscopy, 69 sides of mucosal wave were normal or slightly decreased, and 50 sides were severely decreased or disappeared.The decrease degree of mucosal wave was positively correlated with malignant lesions (ρ=0.687, P<0.001).Under iSCAN endoscopy, there was a positive correlation between the morphological changes of microvessels at the lesion site (vertical) and the malignant lesion (ρ=0.687, P<0.001).Univariate analysis showed that lesion size, thickness, uneven color, granular elevation, peripheral erythema and asymmetry were positively correlated with malignant lesions (ρ=0.530, 0.401, 0.538, 0.315, 0.497, 0.281, P<0.05).Logistic regression analysis showed that the risk of pathological malignancy with large lesions was 5.437 times higher than those of small lesions, the vertical vascular changes under iSCAN were 8.711 times higher than that of normal vascular morphology, and the severe reduction or disappearance of mucosal waves was 9.12 times higher than that of normal or mild reduction of mucosal waves. Conclusion: ISCAN can be combined with staphyloscopy to comprehensively observe and evaluate the changes of vocal cord morphology, submucosal microvessels and mucosal wave of vocal cord in patients with vocal cord leukoplosis, thus improving the ability to distinguish benign and malignant lesions.

Glycogenic Acanthosis: An Unusual Cause of Vocal Fold Leukoplakia.

Glycogenic acanthosis is a common benign lesion of the esophagus; however, reports of extra-esophageal manifestations are exceedingly rare. This case represents the first report of laryngeal glycogenic acanthosis found in a living patient, presenting as vocal fold leukoplakia. Glycogenic acanthosis may be considered among the differential diagnoses of conditions presenting as vocal fold leukoplakia. Laryngoscope, 132:1641-1643, 2022.

Non-invasive diagnosis and monitoring of actinic cheilitis with reflectance confocal microscopy.

BACKGROUND: Actinic cheilitis (AC) represents the equivalent of actinic keratosis on the lip. Various treatment modalities are available and the efficacy of diclofenac in hyaluronic acid has recently been described. Reflectance confocal microscopy (RCM) is a non-invasive imaging technique which has recently been applied for the diagnosis of actinic keratoses. Herein, we describe the applicability of RCM for the diagnosis of AC and for monitoring of treatment response of AC to diclofenac in hyaluronic acid. METHODS: Ten Caucasian patients with clinical suspicion for AC were included in this study. To obtain a non-invasive diagnosis, RCM was performed at baseline, followed by biopsy and respective confocal-histopathological correlation. Six patients with a histological diagnosis of AC were treated with diclofenac in hyaluronic acid, whereby monitoring was performed by RCM. RESULTS: Reflectance confocal microscopy was able to correctly identify 6/7 cases of AC and 3/3 cases of benign lesions. The most important RCM criteria for diagnosis of AC were cellular atypia at the stratum spinosum and granulosum with atypical honeycomb pattern. One patient with AC was misclassified as inflammatory cheilitis by RCM as it showed marked inflammatory response and lacked clear signs of cellular atypia on RCM imaging. Following topical treatment with diclofenac gel, 5/6 patients (83%) showed a good treatment response with regression of dysplasia on consecutive RCM examination. CONCLUSIONS: Reflectance confocal microscopy is a promising tool for the non-invasive diagnosis and monitoring of actinic cheilitis. However, marked inflammation represents a potential diagnostic pitfall. In this regard, biopsy should be performed in doubtful cases.

Laryngeal Leukoplakia: State of the Art Review.

OBJECTIVE: This state-of-the-art article reviews the epidemiology, diagnosis, and management of vocal fold leukoplakia, with focus on recent advances. It focuses on the clinical challenges that otolaryngologists face balancing both oncological efficacy and functional outcomes in leukoplakia and presents the current philosophies and techniques to consider when managing such patients. DATA SOURCES: PubMed/MEDLINE. REVIEW METHODS: We conducted a detailed review of publications related to vocal cord and laryngeal leukoplakia, dysplasia, hyperkeratosis, leukoplakia endoscopy, and leukoplakia management focusing specifically on oncologic outcomes, voice preservation, current and emerging diagnosis, and management techniques. CONCLUSIONS: There has been a paradigm shift away from performing "vocal cord stripping" procedures that can cause irreversible hoarseness toward voice preservation surgery while achieving comparable oncologic control. Surgical technical and instrumental developments have been designed to maximally treat superficial disease while preserving underling vibratory mucosa. Recent improvements in histopathological grading systems and advances in biomarker classification may allow for improved oncologic risk stratification. Furthermore, improvements in endoscopic imaging capabilities and contact endoscopy are currently being studied for their potential diagnostic significance. IMPLICATIONS FOR PRACTICE: To optimally manage vocal fold leukoplakia, the otolaryngologist should become familiar with the oncologic implications of the disease and the importance of obtaining pathologic diagnosis to rule out malignancy. In addition, the surgeon should maintain surgical techniques and knowledge of available instruments and lasers that can assist in surgical management while prioritizing the preservation of vibratory tissue and voice quality. Finally, the surgeon and the patient should understand the clinical importance of routine endoscopic surveillance.

Laryngoscopic characteristics related to the risk of cancerization of vocal cord leukoplakia.

BACKGROUND: The diagnosis of vocal cord leukoplakia mainly relies on laryngoscopy. The morphology of vocal cord leukoplakia under laryngoscope is closely related to the pathological nature of leukoplakia. The specific manifestations associated with high-risk vocal cord leukoplakia remain to be explored. OBJECTIVE: To investigate the characteristics of low-risk and high-risk vocal cord leukoplakia under conventional white light imaging (WLI) laryngoscopy and its correlations with narrow band imaging (NBI) laryngoscopy. METHODS: One hundred and seventy-five cases of vocal cord leukoplakia were divided into low-risk and high-risk groups. The characteristics of low-risk and high-risk vocal cord leukoplakia under WLI laryngoscopy and its correlations with NBI laryngoscopy were analyzed. RESULTS: Logistic regression analysis showed that thickness and hyperemia were independent factors (p < .05). Hyperemia had a strong consistency with the visualization of spots under NBI laryngoscopy (kappa = 0.758). The sign of hyperemia and the NBI classification had equivalent diagnostic efficacy for predicting the risk of cancerization of vocal cord leukoplakia. CONCLUSION: The sign of hyperemia under WLI laryngoscopy is significantly correlated with the visualized spots under NBI laryngoscopy. Hyperemia is an important feature for predicting malignant potential of vocal cord leukoplakia.

Clinicopathologic Aspects of Vocal Fold Leukoplakia in Smokers and Nonsmokers.

BACKGROUND: We aimed to investigate possible causes of leukoplakia and squamous cell carcinoma. We particularly sought to characterize the effect of smoking history because leukoplakia has been observed in nonsmokers. METHODS: We retrospectively identified patients with a diagnosis of leukoplakia who were treated at Mayo Clinic (Jacksonville, Florida), in the Department of Otorhinolaryngology, from 1/1/2006 through 8/31/2019. Each patient was age- and sex-matched (1:2 ratio) to control patients without leukoplakia. Information about possible risk factors, chief symptoms, and social history with smoking and alcohol use was obtained from health records. Nine risk factors were analyzed independently with multivariate analysis. Continuous risk factors were compared between cases and controls with the Wilcoxon rank sum test; categorical variables were compared with the χ2 test. RESULTS: The final cohort consisted of 72 patients with leukoplakia (mean [SD] age, 66 [11] years; 61 men [85%]) and 144 age- and sex-matched controls. Compared with the control group, significantly more cases were current smokers (26% vs. 5%) and fewer were never-smokers. (17% vs. 51%) (P < 0.001). Cases also had a significantly longer duration of smoking history compared with controls (median, 30 vs. 0 years; P < 0.001). Alcohol consumption was not significantly different between cases and controls (53% vs. 54%; P > 0.99). When assessing never-smokers and those who had not smoked for more than 25 years, a history of smoking (P = 0.002) and the number of years smoked (P = 0.002) were significantly different for cases and controls. CONCLUSION: Most vocal fold leukoplakia lesions have a low risk of malignancy. It is important to evaluate the characteristics of the lesion and assess the patient's risk factors. Follow-up is a key factor in patient management, but for patients with recurrent leukoplakia, the duration and frequency of surveillance is still controversial and varies among medical centers. Future prospective studies with advanced analyses are warranted because they may strengthen the ability to identify clinical factors that influence the development of squamous cell carcinoma.

Comparison Between Early Glottic Carcinoma and Epithelial Dysplastic Lesions of the Vocal Fold Via Voice Analysis.

OBJECTIVE: Vocal fold leukoplakia is clinically defined by the presence of white mucosal lesions. Benign and malignant lesions of vocal fold leukoplakia can be distinguished clinically based on pathological biopsy. This study compared the acoustic and aerodynamic parameters of vocal cord carcinoma and dysplasia (mild to severe). MATERIALS AND METHODS: From February 2014 to December 2018, 1,925 voice evaluation assessments were collected before laryngeal microsurgery (LMS). Of 147 patients clinically diagnosed with vocal cord leukoplakia before LMS, 112 male patients were selected for examination. The pathologic findings after LMS were divided into the carcinoma group (56 patients) and dysplasia group (56 patients). Only patients with carcinoma in situ and early glottis cancer were included in the carcinoma group. Analysis of covariance was used to calibrate the age between the two groups. RESULTS: There was no difference in smoking duration between the two groups. F0 (P < 0.00), jitter (P < 0.00), and mean pitch (P = 0.010) were significantly higher, while the mean sound pressure level parameter (P = 0.024) was significantly lower, in the carcinoma group than in the noncarcinoma group. CONCLUSIONS: In patients with early glottis cancer, differences in voice analysis parameters may be used to differentiate between early glottic carcinoma and noncarcinoma.