Y Dinesh, Ramalingam Karthikeyan, Ramani Pratibha, Mohan Deepak Ramya
Oral Pathology and Microbiology, Saveetha Dental College and Hospitals, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, IND.
Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, IND.
Cureus. 2023 Aug 24;15(8):e44018. doi: 10.7759/cureus.44018. eCollection 2023 Aug.
Artificial intelligence in oncology has gained a lot of interest in recent years. Early detection of Oral squamous cell carcinoma (OSCC) is crucial for early management to attain a better prognosis and overall survival. Machine learning (ML) has also been used in oral cancer studies to explore the discrimination between clinically normal and oral cancer.
A dataset comprising 360 clinical intra-oral images of OSCC, Oral Potentially Malignant Disorders (OPMDs) and clinically healthy oral mucosa were used. Clinicians trained the machine learning model with the clinical images (n=300). Roboflow software (Roboflow Inc, USA) was used to classify and annotate images along with Multi-class annotation and object detection models trained by two expert oral pathologists. The test dataset (n=60) of new clinical images was again evaluated by two clinicians and Roboflow. The results were tabulated and Kappa statistics was performed using SPSS v23.0 (IBM Corp., Armonk, NY). Results: Training dataset clinical images (n=300) were used to train the clinicians and Roboflow algorithm. The test dataset (n=60) of new clinical images was again evaluated by the clinicians and Roboflow. The observed outcomes revealed that the Mean Average Precision (mAP) was 25.4%, precision 29.8% and Recall 32.9%. Based on the kappa statistical analysis the 0.7 value shows a moderate agreement between the clinicians and the machine learning model. The test dataset showed the specificity and sensitivity of the Roboflow machine learning model to be 75% and 88.9% respectively. Conclusion: In conclusion, machine learning showed promising results in the early detection of suspected lesions using clinical intraoral images and aids general dentists and patients in the detection of suspected lesions such as OPMDs and OSCC that require biopsy and immediate treatment.
近年来，肿瘤学中的人工智能引起了广泛关注。口腔鳞状细胞癌（OSCC）的早期检测对于早期治疗以获得更好的预后和总体生存率至关重要。机器学习（ML）也已用于口腔癌研究，以探索临床正常组织与口腔癌之间的差异。
使用了一个包含360张OSCC、口腔潜在恶性疾病（OPMDs）临床口腔内图像以及临床健康口腔黏膜图像的数据集。临床医生使用临床图像（n = 300）训练机器学习模型。Roboflow软件（美国Roboflow公司）用于对图像进行分类和注释，同时由两名专业口腔病理学家训练多类注释和目标检测模型。新临床图像的测试数据集（n = 60）再次由两名临床医生和Roboflow进行评估。结果制成表格，并使用SPSS v
23.0（IBM公司，纽约州阿蒙克）进行Kappa统计分析。结果：训练数据集临床图像（n = 300）用于训练临床医生和Roboflow算法。新临床图像的测试数据集（n = 60）再次由临床医生和Roboflow进行评估。观察结果显示，平均精度均值（mAP）为25.4%，精确率为29.8%，召回率为32.9%。基于kappa统计分析，0.7的值表明临床医生和机器学习模型之间存在中度一致性。测试数据集显示Roboflow机器学习模型的特异性和敏感性分别为75%和88.9%。结论：总之，机器学习在使用临床口腔内图像早期检测可疑病变方面显示出有前景的结果，并有助于普通牙医和患者检测需要活检和立即治疗的可疑病变，如OPMDs和OSCC。
