Laryngeal Dysplasia: Persisting Dilemmas, Disagreements and Unsolved Problems—A Short Review

Gale, Nina; Cardesa, Antonio; Hernández-Prera, Juan C.; Slootweg, Pieter J.; Wenig, Bruce M.; Zidar, Nina

doi:10.1007/s12105-020-01149-9

Cited by 14 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As dysplasia grading is difficult and reproducibility between pathologists is low to moderate, a blind reviewed test set was generated in order to properly assess the AI model performance. We observed that the agreement between the two reviewers on this test set was in line with previous reports (6,8–11), illustrating once more the difficulty to obtain objective and robust grading of head and neck dysplasia and the need for new tools to help pathologists make reliable diagnoses. We developed and trained a weakly supervised deep learning model that was able to accurately grade head and neck dysplasia, offering a first tool for assisted diagnosis.…”

Section: Discussionsupporting

confidence: 90%

“…The classification of head and neck dysplasias has been a highly controversial issue for many years. Indeed, since the first classification proposed by Kleinsasser in 1963 (5), many different classifications have been proposed by expert pathologists without achieving a strong consensus (6,7). Each of them had different terminologies and methods of grading, but their reproducibility was always low to moderate (6,(8)(9)(10)(11)(12) (Table 1).…”

Section: Introductionmentioning

confidence: 99%

“…Indeed, since the first classification proposed by Kleinsasser in 1963 (5), many different classifications have been proposed by expert pathologists without achieving a strong consensus (6,7). Each of them had different terminologies and methods of grading, but their reproducibility was always low to moderate (6,(8)(9)(10)(11)(12) (Table 1). Nevertheless, higher grades were associated with a higher risk of transformation into carcinoma, confirming their significance (13).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Diagnosis with Confidence: Deep Learning for Reliable Classification of Squamous Lesions of the Upper Aerodigestive Tract

Lubrano

Bellahsen-Harrar

Berlemont³

et al. 2022

Preprint

View full text Add to dashboard Cite

Diagnosis of head and neck squamous dysplasia and carcinomas is critical for patient care, cure and follow-up. It can be challenging, especially for intraepithelial lesions. Even though the last WHO classification simplified the grading of dysplasia with only two grades (except for oral or oropharyngeal lesions), the inter and intra-observer variability remains substantial, especially for non-specialized pathologists. In this study we investigated the potential of deep learning to assist the pathologist with automatic and reliable classification of head and neck squamous lesions following the 2022 WHO classification system for the hypopharynx, larynx, trachea and parapharyngeal space. We created, for the first time, a large scale database of histological samples intended for developing an automatic diagnostic tool. We developed and trained a weakly supervised model performing classification from whole slides images. A dual blind review was carried out to define a gold standard test set on which our model was able to classify lesions with high accuracy on every class (average AUC: 0.878 (95% CI: [0.834-0.918])). Finally, we defined a confidence score for the model predictions, which can be used to identify ambiguous or difficult cases. When the algorithm is applied as a screening tool, such cases can then be submitted to pathologists in priority. Our results demonstrate that the model, associated with confidence measurements, can help in the difficult task of classifying head and neck squamous lesions.

show abstract

Section: Discussionsupporting

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosis with Confidence: Deep Learning for Reliable Classification of Squamous Lesions of the Upper Aerodigestive Tract

Lubrano

Bellahsen-Harrar

Berlemont³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Aufgenommen wurden Fälle mit gutartigen Stimmlippenveränderungen, Dysplasien und Plattenepithelkarzinomen der Stimmlippen. Der verwendete histopathologische Befund enthielt eine Diagnose auf der Grundlage der Klassifikation von Kopf-Hals-Tumoren von 2005 oder (je nach Erstellungsdatum) 2017 gemäß WHO (Weltgesundheitsorganisation) und diente als Goldstandard [ 11 ]. Für die statistische Auswertung der Ergebnisse wurde jeder Befund je nach histologischer Dignität einer der folgenden Diagnosegruppen zugeordnet: Diagnosegruppe A (benigne Läsion oder geringgradige bzw.…”

Section: Materials Und Methodenunclassified

Kontaktendoskopie mit Narrow Band Imaging zur Erkennung perpendikulärer Gefäßveränderungen bei benignen Läsionen, Dysplasien und Karzinomen der Stimmlippen

Schöninger

Voigt-Zimmermann

Kropf

et al. 2021

HNO

View full text Add to dashboard Cite

Zusammenfassung Hintergrund Perpendikuläre Gefäßveränderungen (PGV) sind Marker der tumorinduzierten Neoangiogenese der Stimmlippen. Die Kontaktendoskopie mit Narrow Band Imaging (KE-NBI) ermöglicht eine detaillierte Analyse solcher Gefäßveränderungen. Ziel der Arbeit In dieser Arbeit wurde das Potenzial der KE-NBI bei der Diagnostik benigner, dysplastischer und maligner Veränderungen der Stimmlippen untersucht. Außerdem sollte bei der Detektion von PGV die Aussagekraft des KE-NBI im Vergleich zur Weißlichtendoskopie (WLE) und zur alleinigen Narrow-Band-Imaging-Endoskopie (NBI) bestimmt werden. Material und Methoden Dazu befundeten 3 Untersucher histopathologisch verifizierte benigne, dysplastische oder maligne Läsionen der Stimmlippen (n = 60) jeweils im Modus WLE, NBI und KE-NBI. Die Läsionen wurden auf PGV hin untersucht und ihre Dignität beurteilt. Ermittelt wurden der Anteil der Läsionen mit detektierten PGV sowie die diagnostische Güte für jeden Modus und die Interratervariabilität bei der Erkennung von höhergradigen Dysplasien und Karzinomen. Ergebnisse Die KE-NBI zeigte sich den anderen Modi bei der Detektion von PGV und hinsichtlich Sensitivität und Genauigkeit bei der Erkennung von höhergradigen Dysplasien und Karzinomen überlegen. Die Autoren sahen eine deutliche Assoziation dieser pathologischen Veränderungen mit PGV. Schlussfolgerung Mittels KE-NBI werden PGV häufiger und zuverlässiger als mit den anderen Methoden erkannt. Die Assoziation dieser Gefäßveränderungen mit höhergradigen Dysplasien und Karzinomen der Stimmlippen wurde bestätigt. Im Vergleich zu WLE und NBI zeigte sich eine erhöhte diagnostische Güte. Somit kann die KE-NBI durch bessere Detektion der PGV die endoskopische Differenzierung zwischen benignen und malignen Läsionen der Stimmlippen verbessern.

show abstract

“…While the rate of malignant transformation varies widely with estimates as low as 1.7% and as high as 46.3% [3] , early diagnosis and treatment of vocal cord leukoplakia may prevent progression and malignancy [4] . The 2017 World Health Organization Classification of Head and Neck Tumors proposed a two-tier classification system for dysplasia, with reasonably clear histopathological criteria for the two groups: 1) low-grade (LG) dysplasia including squamous hyperplasia and mild dysplasia, and 2) high-grade (HG) dysplasia including moderate and severe dysplasia and carcinoma in situ [5,6] . In response to this classification, some otolaryngologists proposed that patients in the LG group of vocal cord leukoplakia with a low malignancy risk would generally require a conservative treatment or watchand-wait policy, whereas patients in the HG group of vocal cord leukoplakia would demand both surgical treatment and close follow-up to monitor possible progression to a more aggressive pathology [7] .…”

Section: Introductionmentioning

confidence: 99%

Applying Deep Learning with Convolutional Neural Networks to Laryngoscopic Imaging for Real-time Automated Segmentation and Classification of Vocal Cord Leukoplakia

Luo

Ren

et al. 2021

Preprint

View full text Add to dashboard Cite

Objectives The study was to apply deep learning (DL) with convolutional neural networks (CNNs) to laryngoscopic imaging for assisting in real-time automated segmentation and classification of vocal cord leukoplakia. Methods This was a single-center retrospective diagnostic study included 216 patients who underwent laryngoscope and pathological examination from October 1, 2018 through October 1, 2019. Lesions were classified as nonsurgical group (NSG) and surgical group (SG) according to pathology. All selected images of vocal cord leukoplakia were annotated independently by 2 expert endoscopists and divided into a training set, a validation set, and a test set in a ratio of 6:2:2 for training the model. Results Among the 260 lesions identified in 216 patients, 2220 images from narrow band imaging (NBI) and 2144 images from white light imaging (WLI) were selected. For segmentation, the average intersection-over-union (IoU) value exceeded 70%. For classification, the model was able to classify the surgical group (SG) by laryngoscope with a sensitivity of 0.93 and specificity of 0.94 in WLI, and a sensitivity of 0.99 and specificity of 0.97 in NBI. Moreover, this model achieved a mean average precision (mAP) of 0.81 in WLI and 0.92 in NBI with an IoU> 0.5. Conclusions The study found that a model developed by applying DL with CNNs to laryngoscopic imaging results in high sensitivity, specificity, and mAP for automated segmentation and classification of vocal cord leukoplakia. This finding shows promise for the application of DL with CNNs in assisting in accurate diagnosis of vocal cord leukoplakia from WLI and NBI.

show abstract

Laryngeal Dysplasia: Persisting Dilemmas, Disagreements and Unsolved Problems—A Short Review

Cited by 14 publications

References 33 publications

Diagnosis with Confidence: Deep Learning for Reliable Classification of Squamous Lesions of the Upper Aerodigestive Tract

Diagnosis with Confidence: Deep Learning for Reliable Classification of Squamous Lesions of the Upper Aerodigestive Tract

Kontaktendoskopie mit Narrow Band Imaging zur Erkennung perpendikulärer Gefäßveränderungen bei benignen Läsionen, Dysplasien und Karzinomen der Stimmlippen

Applying Deep Learning with Convolutional Neural Networks to Laryngoscopic Imaging for Real-time Automated Segmentation and Classification of Vocal Cord Leukoplakia

Contact Info

Product

Resources

About