1
|
Horton G, Philteos J, Lin RJ. Malignant Transformation of Dysplastic Vocal Fold Lesions: A Systematic Review and Meta-Analysis. JAMA Otolaryngol Head Neck Surg 2024; 150:556-563. [PMID: 38753339 PMCID: PMC11099843 DOI: 10.1001/jamaoto.2024.1008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2023] [Accepted: 03/25/2024] [Indexed: 05/19/2024]
Abstract
Importance The reported rates of malignant transformation of dysplastic laryngeal lesions are highly variable, as is time to malignant degeneration. Objective To evaluate the rate of and time to malignant transformation of dysplastic laryngeal lesions based on the World Health Organization (WHO) dysplasia classification system. Data Sources PubMed, MEDLINE, Embase, CINAHL, CENTRAL, and Cochrane Reviews were searched from the date of database inception to June 8, 2023. Study Selection English-language articles assessing the rate of malignant transformation using the 2005 WHO dysplasia classification system were included in this systematic review and meta-analysis. Data Extraction and Synthesis The study was reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guideline. Data extraction was performed by 2 independent investigators. Study quality was assessed using a validated quality tool. When possible, data were pooled using random-effects meta-analysis. Main Outcome Measures The primary outcome measure was the malignant transformation rate in each laryngeal dysplasia category. Secondary outcome measure was the time interval over which malignant transformation had occurred. Results A total of 5585 records were screened, 61 full texts were assessed, and 18 retrospective cohort studies with 3243 participants were included in the final review. The weighted pooled mean malignant transformation rates of mildly, moderately, and severely dysplastic lesions were 10.9%, 23.3%, and 30.5%, respectively. Malignant transformation rate of nondysplastic laryngeal lesions was 4.5%. Moderately and severely dysplastic lesions had significantly higher odds of malignant transformation compared with mildly dysplastic lesions (moderate: odds ratio [OR], 2.90 [95% CI, 2.06-4.09]; I2 = 0%; severe: OR, 3.42 [95% CI, 2.11-5.52]; I2 = 40%). Lesions without dysplasia had a significantly lower odds of malignant transformation compared with lesions with mild dysplasia (OR, 0.48; 95% CI, 0.28-0.81; I2 = 0%). The overall mean time to malignant transformation was 28.8 months (range, 22.0-35.6 months) for all dysplasia grades. Conclusion and Relevance This systematic review and meta-analysis found that the rate of malignant transformation increased with the grade of laryngeal dysplasia. Moderately dysplastic lesions were more likely to undergo malignant degeneration compared with mildly dysplastic lesions.
Collapse
Affiliation(s)
- Garret Horton
- Department of Otolaryngology–Head & Neck Surgery, University of Toronto, Toronto, Ontario, Canada
| | - Justine Philteos
- Department of Otolaryngology–Head & Neck Surgery, University of Toronto, Toronto, Ontario, Canada
| | - R. Jun Lin
- Department of Otolaryngology–Head & Neck Surgery, Temerty Faculty of Medicine, University of Toronto, Unity Health Toronto–St Michael’s Hospital, Toronto, Ontario, Canada
| |
Collapse
|
2
|
Tie CW, Li DY, Zhu JQ, Wang ML, Wang JH, Chen BH, Li Y, Zhang S, Liu L, Guo L, Yang L, Yang LQ, Wei J, Jiang F, Zhao ZQ, Wang GQ, Zhang W, Zhang QM, Ni XG. Multi-Instance Learning for Vocal Fold Leukoplakia Diagnosis Using White Light and Narrow-Band Imaging: A Multicenter Study. Laryngoscope 2024. [PMID: 38801129 DOI: 10.1002/lary.31537] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/29/2024] [Revised: 05/01/2024] [Accepted: 05/09/2024] [Indexed: 05/29/2024]
Abstract
OBJECTIVES Vocal fold leukoplakia (VFL) is a precancerous lesion of laryngeal cancer, and its endoscopic diagnosis poses challenges. We aim to develop an artificial intelligence (AI) model using white light imaging (WLI) and narrow-band imaging (NBI) to distinguish benign from malignant VFL. METHODS A total of 7057 images from 426 patients were used for model development and internal validation. Additionally, 1617 images from two other hospitals were used for model external validation. Modeling learning based on WLI and NBI modalities was conducted using deep learning combined with a multi-instance learning approach (MIL). Furthermore, 50 prospectively collected videos were used to evaluate real-time model performance. A human-machine comparison involving 100 patients and 12 laryngologists assessed the real-world effectiveness of the model. RESULTS The model achieved the highest area under the receiver operating characteristic curve (AUC) values of 0.868 and 0.884 in the internal and external validation sets, respectively. AUC in the video validation set was 0.825 (95% CI: 0.704-0.946). In the human-machine comparison, AI significantly improved AUC and accuracy for all laryngologists (p < 0.05). With the assistance of AI, the diagnostic abilities and consistency of all laryngologists improved. CONCLUSIONS Our multicenter study developed an effective AI model using MIL and fusion of WLI and NBI images for VFL diagnosis, particularly aiding junior laryngologists. However, further optimization and validation are necessary to fully assess its potential impact in clinical settings. LEVEL OF EVIDENCE 3 Laryngoscope, 2024.
Collapse
Affiliation(s)
- Cheng-Wei Tie
- Department of Endoscopy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - De-Yang Li
- The First Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Ji-Qing Zhu
- Department of Endoscopy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Mei-Ling Wang
- Department of Endoscopy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China
| | - Jian-Hui Wang
- Department of Endoscopy, Shanxi Province Cancer Hospital/Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences/Cancer Hospital Affiliated to Shanxi Medical University, Taiyuan, China
| | - Bing-Hong Chen
- Department of Endoscopy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China
| | - Ying Li
- Department of Endoscopy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China
| | - Sen Zhang
- Department of Otolaryngology Head and Neck Surgery, The First Hospital, Shanxi Medical University, Taiyuan, China
| | - Lin Liu
- Department of Otolaryngology Head and Neck Surgery, Dalian Friendship Hospital, Dalian, China
| | - Li Guo
- Department of Otolaryngology Head and Neck Surgery, The First Affiliated Hospital, College of Clinical Medicine of Henan University of Science and Technology, Luoyang, China
| | - Long Yang
- Department of Otolaryngology, The Second People's Hospital of Baoshan City, Baoshan, China
| | - Li-Qun Yang
- Department of Otolaryngology, The Second People's Hospital of Baoshan City, Baoshan, China
| | - Jiao Wei
- Department of Otolaryngology, Qujing Second People's Hospital of Yunnan Province, Qujing, China
| | - Feng Jiang
- Department of Otolaryngology, Kunming First People's Hospital, Kunming, China
| | - Zhi-Qiang Zhao
- Department of Otolaryngology, Baoshan People's Hospital, Baoshan, China
| | - Gui-Qi Wang
- Department of Endoscopy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Wei Zhang
- Department of Endoscopy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China
| | - Quan-Mao Zhang
- Department of Endoscopy, Shanxi Province Cancer Hospital/Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences/Cancer Hospital Affiliated to Shanxi Medical University, Taiyuan, China
| | - Xiao-Guang Ni
- Department of Endoscopy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| |
Collapse
|
3
|
Katalinic M, Schenk M, Franke S, Katalinic A, Neumuth T, Dietz A, Stoehr M, Gaebel J. Generation of a Realistic Synthetic Laryngeal Cancer Cohort for AI Applications. Cancers (Basel) 2024; 16:639. [PMID: 38339389 PMCID: PMC10854797 DOI: 10.3390/cancers16030639] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2023] [Revised: 01/27/2024] [Accepted: 01/29/2024] [Indexed: 02/12/2024] Open
Abstract
BACKGROUND Obtaining large amounts of real patient data involves great efforts and expenses, and processing this data is fraught with data protection concerns. Consequently, data sharing might not always be possible, particularly when large, open science datasets are needed, as for AI development. For such purposes, the generation of realistic synthetic data may be the solution. Our project aimed to generate realistic cancer data with the use case of laryngeal cancer. METHODS We used the open-source software Synthea and programmed an additional module for development, treatment and follow-up for laryngeal cancer by using external, real-world (RW) evidence from guidelines and cancer registries from Germany. To generate an incidence-based cohort view, we randomly drew laryngeal cancer cases from the simulated population and deceased persons, stratified by the real-world age and sex distributions at diagnosis. RESULTS A module with age- and stage-specific treatment and prognosis for laryngeal cancer was successfully implemented. The synthesized population reflects RW prevalence well, extracting a cohort of 50,000 laryngeal cancer patients. Descriptive data on stage-specific and 5-year overall survival were in accordance with published data. CONCLUSIONS We developed a large cohort of realistic synthetic laryngeal cancer cases with Synthea. Such data can be shared and published open source without data protection issues.
Collapse
Affiliation(s)
- Mika Katalinic
- Innovation Center Computer Assisted Surgery, Faculty of Medicine, University Leipzig, 04109 Leipzig, Germany; (M.K.)
| | - Martin Schenk
- Innovation Center Computer Assisted Surgery, Faculty of Medicine, University Leipzig, 04109 Leipzig, Germany; (M.K.)
| | - Stefan Franke
- Innovation Center Computer Assisted Surgery, Faculty of Medicine, University Leipzig, 04109 Leipzig, Germany; (M.K.)
| | - Alexander Katalinic
- Institute of Social Medicine and Epidemiology, University of Luebeck, 23562 Luebeck, Germany;
| | - Thomas Neumuth
- Innovation Center Computer Assisted Surgery, Faculty of Medicine, University Leipzig, 04109 Leipzig, Germany; (M.K.)
| | - Andreas Dietz
- Department of Otolaryngology, Head and Neck Surgery, University Hospital Leipzig, 04103 Leipzig, Germany
| | - Matthaeus Stoehr
- Department of Otolaryngology, Head and Neck Surgery, University Hospital Leipzig, 04103 Leipzig, Germany
| | - Jan Gaebel
- Innovation Center Computer Assisted Surgery, Faculty of Medicine, University Leipzig, 04109 Leipzig, Germany; (M.K.)
| |
Collapse
|
4
|
Viana Pinto J, Ruas JJ, Rodrigues JA, Pinto I, Leal M, Vales F, Moura CP. Prognostic Role of the Initial Grade of Dysplasia on Premalignant Vocal Fold Lesions. J Voice 2022:S0892-1997(22)00217-X. [PMID: 36075803 DOI: 10.1016/j.jvoice.2022.07.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2022] [Revised: 07/13/2022] [Accepted: 07/14/2022] [Indexed: 11/19/2022]
Abstract
PURPOSE The main objective of this study was to analyze the prognostic role of the initial grade of dysplasia on the progression to SCC. STUDY DESIGN Retrospective cohort. METHODS This study was performed in the Otorhinolaryngology Department of a tertiary hospital center from January 2010 to December 2020. Every patient submitted to a microlaryngoscopy during this period with a histology of dysplasia on the first biopsy was included. RESULTS A total of 112 patients were included and median follow-up was 24 months (range 1-120 months). Mean age at diagnosis was 59.71 (+/- 12.03) and 88 patients were male (78.6%). Initial grade of dysplasia was mild on 60 patients (53.6%), moderate on 24 (21.4%), severe on 18 (16.1%), and carcinoma in situ in 10 (8.9%). Overall, 25 patients (21.4%) developed invasive squamous cell carcinoma (SCC) and 15 (13.4%) died during follow-up. On an adjusted 5 year's progression free survival analysis, considering gender, age, dysplasia grade, tobacco and alcohol consumption, the initial grade of dysplasia was the only factor significantly associated with progression to carcinoma (P = .047). When compared to mild dysplasia, moderate dysplasia had a Hazard Ratio (HR) of 0.81 (95%CI 0.21-3.22); severe dysplasia had a HR of 1.76 (95%CI 0.59-5.30) and carcinoma in situ had a HR of 4.25 (95%CI 1.44-12.59). CONCLUSION The initial dysplasia grade seems to be the most important prognostic factor regarding progression to SCC in patients with premalignant vocal fold disease.
Collapse
Affiliation(s)
- João Viana Pinto
- Serviço de Otorrinolaringologia, Centro Hospitalar Universitário de São João, EPE, Porto, Portugal; Unidade de Otorrinolaringologia, Departamento de Cirurgia e Fisiologia, Faculdade de Medicina da Universidade do Porto, Porto, Portugal; Centro de Investigação em Tecnologias e Serviços de Saúde (CINTESIS), Porto, Portugal.
| | - José João Ruas
- Serviço de Otorrinolaringologia, Centro Hospitalar Universitário de São João, EPE, Porto, Portugal; Unidade de Otorrinolaringologia, Departamento de Cirurgia e Fisiologia, Faculdade de Medicina da Universidade do Porto, Porto, Portugal
| | - João Aragão Rodrigues
- Serviço de Anatomia Patológica, Centro Hospitalar Universitário de São João, EPE, Porto, Portugal
| | - Isabel Pinto
- Serviço de Otorrinolaringologia, Centro Hospitalar Universitário de São João, EPE, Porto, Portugal; Unidade de Otorrinolaringologia, Departamento de Cirurgia e Fisiologia, Faculdade de Medicina da Universidade do Porto, Porto, Portugal
| | - Manuel Leal
- Serviço de Otorrinolaringologia, Centro Hospitalar Universitário de São João, EPE, Porto, Portugal; Unidade de Otorrinolaringologia, Departamento de Cirurgia e Fisiologia, Faculdade de Medicina da Universidade do Porto, Porto, Portugal
| | - Fernando Vales
- Serviço de Otorrinolaringologia, Centro Hospitalar Universitário de São João, EPE, Porto, Portugal; Unidade de Otorrinolaringologia, Departamento de Cirurgia e Fisiologia, Faculdade de Medicina da Universidade do Porto, Porto, Portugal
| | - Carla Pinto Moura
- Serviço de Otorrinolaringologia, Centro Hospitalar Universitário de São João, EPE, Porto, Portugal; Serviço de Genética Médica, Centro Hospitalar Universitário S. João/Faculdade Medicina da Universidade do Porto, Porto, Portugal; I3S, Instituto de Investigação e Inovação em Saúde, Universidade do Porto, Porto, Portugal
| |
Collapse
|
5
|
Laryngeal dysplasia: a 10-year review of rates of progression to invasive carcinoma and treatment-specific outcomes in a regional ENT department in Northern Ireland. The Journal of Laryngology & Otology 2022; 136:547-553. [DOI: 10.1017/s0022215122000366] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
AbstractBackgroundLaryngeal dysplasia represents a complex pre-malignant condition characterised by a spectrum of mucosal changes, with a reported malignant transformation rate from dysplasia to invasive carcinoma of 14.0 per cent.ObjectiveTo identify whether increasing glottic dysplasia severity is associated with higher local malignant transformation rates or adverse clinical outcomes.MethodsThis retrospective cohort study identified 125 patients with any histopathological grade of glottic dysplasia over a 10-year period who were followed up for a standardised 10-year period.ResultsThe malignant transformation rate was 21.8 per cent over 10 years, demonstrating a statistically significant greater risk with increasing dysplasia severity. The mean time to transformation was 52 months, with time to transformation statistically associated with increasing dysplasia severity. Rapid progression to carcinoma within 12 months occurred in 40 per cent of cases, and 58 per cent of subsequently diagnosed laryngeal squamous cell carcinomas were tumour stage T1.ConclusionLaryngeal dysplasia carries a significant malignant potential, appearing greatest within 12 months of diagnosis and with increasing severity of dysplasia.
Collapse
|