Centre for Computational Biology (CBIO), Mines Paris, PSL University, Paris, France.
Keen Eye, Paris, France.
Histopathology. 2024 Jan;84(2):343-355. doi: 10.1111/his.15067. Epub 2023 Oct 23.
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 intraobserver variability remains substantial, particularly for nonspecialized pathologists, exhibiting the need for new tools to support pathologists.
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 that can be used to identify difficult cases.
Our model demonstrated high classification accuracy across all lesion types on both internal and external test sets (respectively average area under the curve [AUC]: 0.878 (95% confidence interval [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.
Our results demonstrate that the model, associated with confidence measurements, can help in the difficult task of classifying HN squamous lesions by limiting variability and detecting ambiguous cases, taking us one step closer to a wider adoption of AI-based assistive tools.
头颈部（HN）鳞状上皮发育不良和癌的诊断对患者的治疗、治愈和随访至关重要。尽管最近在最后一个世卫组织分级系统中进行了简化，但仍存在显著的观察者间和观察者内变异性，特别是对于非专业病理学家，这表明需要新的工具来支持病理学家。
在这项研究中，我们研究了深度学习在辅助病理学家根据 2022 年世卫组织分类系统自动可靠地分类 HN 病变方面的潜力。我们首次创建了一个包含大量组织学样本（>2000 张幻灯片）的大型数据库，旨在开发一种自动诊断工具。我们开发并训练了一个从全切片图像（WSI）进行分类的弱监督模型。我们在内部和外部测试集上评估了我们的模型，并定义和验证了一个新的置信度评分，以评估可以用于识别困难病例的预测。
我们的模型在内部和外部测试集上的所有病变类型上均表现出较高的分类准确性（分别为平均曲线下面积[AUC]：0.878（95%置信区间[CI]：[0.834-0.918]）和 0.886（95% CI：[0.813-0.947]）），并且置信度评分允许可靠地区分可靠和不确定的预测。
我们的结果表明，该模型与置信度测量相结合，可以通过限制变异性和检测模棱两可的病例来帮助完成分类 HN 鳞状病变的困难任务，使我们更接近更广泛地采用基于人工智能的辅助工具。
