Štifanić Jelena, Štifanić Daniel, Anđelić Nikola, Car Zlatan
Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka, Croatia.
Faculty of Engineering, Catholic University of Croatia, Ilica 244, 10000 Zagreb, Croatia.
Biology (Basel). 2025 Jul 22;14(8):909. doi: 10.3390/biology14080909.
Oral cancer is typically diagnosed through histological examination; however, the primary issue with this type of procedure is tumor heterogeneity, where a subjective aspect of the examination may have a direct effect on the treatment plan for a patient. To reduce inter- and intra-observer variability, artificial intelligence algorithms are often used as computational aids in tumor classification and diagnosis. This research proposes a two-step approach for automatic multiclass grading using oral histopathology images (the first step) and Grad-CAM visualization (the second step) to assist clinicians in diagnosing oral squamous cell carcinoma. The Xception architecture achieved the highest classification values of 0.929 (±σ = 0.087) AUC and 0.942 (±σ = 0.074) AUC. Additionally, Grad-CAM provided visual explanations of the model's predictions by highlighting the precise areas of histopathology images that influenced the model's decision. These results emphasize the potential of integrated AI algorithms in medical diagnostics, offering a more precise, dependable, and effective method for disease analysis.
口腔癌通常通过组织学检查来诊断；然而，这类程序的主要问题是肿瘤异质性，检查中的主观因素可能会直接影响患者的治疗方案。为了减少观察者间和观察者内的变异性，人工智能算法常被用作肿瘤分类和诊断的计算辅助工具。本研究提出了一种两步法，用于使用口腔组织病理学图像进行自动多类分级（第一步）和Grad-CAM可视化（第二步），以协助临床医生诊断口腔鳞状细胞癌。Xception架构实现了最高分类值，AUC为0.929（±σ = 0.087），AUC为0.942（±σ = 0.074）。此外，Grad-CAM通过突出影响模型决策的组织病理学图像的精确区域，为模型的预测提供了可视化解释。这些结果强调了集成人工智能算法在医学诊断中的潜力，为疾病分析提供了一种更精确、可靠和有效的方法。
