Abstract
Background Diagnosis of head and neck (HN) squamous dysplasias and carcinomas is critical for patient care cure and follow-up. It can be challenging, especially for grading intraepithelial lesions. Despite recent simplification in the last WHO grading system, the inter- and intra-observer variability remains substantial, particularly for non-specialized pathologists, exhibiting the need for new tools to support pathologists.
Methods In this study we investigated the potential of deep learning to assist the pathologist with automatic and reliable classification of HN lesions following the 2022 WHO classification system. We created, for the first time, a large-scale database of histological samples (>2000 slides) intended for developing an automatic diagnostic tool. We developed and trained a weakly supervised model performing classification from whole slide images (WSI). We evaluated our model on both internal and external test sets and we defined and validated a new confidence score to assess the predictions which can be used to identify difficult cases.
Results Our model demonstrated high classification accuracy across all lesion types on both internal and external test sets (respectively average AUC: 0.878 (95% CI:[0.834-0.918]) and 0.886 (95% CI: [0.813-0.947])) and the confidence score allowed for accurate differentiation between reliable and uncertain predictions.
Conclusions Our results demonstrate that the model, associated with confidence measurements, can help in the difficult task of classifying head and neck squamous lesions by limiting variability and detecting ambiguous cases, taking us one step closer to a wider adoption of AI-based assistive tools.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
Conflict of interest The authors declare no competing interests.
Ethics Approval and Consent to Participate Our study was approved by the ethics committee of Assistance Publique - Hôpitaux de Paris Centre (CERAPHP. Centre - Institutional Review Board registration #00011928). All the patients were informed by a notification letter of the study and the possibility to refuse the use of their medical data, in line with current legislation. The study was performed in accordance with the Declaration of Helsinki.
Funding ML was supported by a CIFRE PhD fellowship founded by Keen Eye, Paris, France and ANRT (CIFRE 2019/1905). Furthermore, this work was supported by the French government under management of Agence Nationale de la Recherche as part of the “Investissements d’avenir” program, reference ANR-19-P3IA-0001 (PRAIRIE 3IA Institute).
Data Availability Statement The WSI datasets described in the manuscript were subject to hospital regulations and could not be publicly released. Data sharing should be possible with other research teams under formal agreement with Assistance Publique - Hôpitaux de Paris (contact first and last authors for more information).
An external validation has been performed to validate the AI algorithm. Additional results have been added.