Wei Xiao, Chanjuan Liu, Ke Jiang, Linyun Ye, Jinxing Gao, Quanbing Wang
Zhejiang Provincial JianDe First People's Hospital, HangZhou, Zhejiang, China.
graduate school, Bengbu Medical College, Bengbu, AnHui, China.
Sci Rep. 2024 Nov 19;14(1):28675. doi: 10.1038/s41598-024-79250-0.
Early Diagnosis of oral cancer is very important and can save you from some oral malignancies. However, while this approach aids in the rapid healing of patients and the preservation of their lives, there are several causes for poor and wrong diagnosis of oral cancer. In recent years, the use of computer-aided design diagnosis tools as an auxiliary tool alongside clinicians has greatly benefited in more accurate identification of this malignancy. The current study proposes a new approach for identifying oral cancer patients based on image processing and deep learning. The current study employs a recently integrated model of an improved tunicate swarm algorithm to produce an efficient tool for improving a convolutional neural network and delivering an accurate cancer diagnostic system. The approach is then implemented on the oral cancer pictures dataset. The approach is then validated by comparing it to other published papers using various measurement markers. The proposed model achieved an accuracy of 98.70% and a recall of 93.71% in detecting oral cancerous lesions from photographic images. The model also achieved an F1-score of 90.08% and a precision of 96.42%. The final results demonstrate that the offered approach can produce more exact results and can be used in conjunction with clinicians to help in diagnosing oral cancer.
口腔癌的早期诊断非常重要，它能使你免受一些口腔恶性肿瘤的侵害。然而，尽管这种方法有助于患者快速康复并挽救他们的生命，但口腔癌诊断不佳和错误诊断的原因有多种。近年来，将计算机辅助设计诊断工具作为临床医生的辅助工具使用，在更准确地识别这种恶性肿瘤方面大有裨益。当前的研究提出了一种基于图像处理和深度学习来识别口腔癌患者的新方法。当前的研究采用了一种最近整合的改进型樽海鞘群算法模型，以生成一种有效的工具来改进卷积神经网络并提供一个准确的癌症诊断系统。然后将该方法应用于口腔癌图片数据集。接着通过使用各种测量指标与其他已发表的论文进行比较来验证该方法。所提出的模型在从摄影图像中检测口腔癌病变方面，准确率达到了98.70%，召回率达到了93.71%。该模型还实现了90.08%的F1分数和96.42%的精确率。最终结果表明，所提供的方法能够产生更准确的结果，并且可以与临床医生结合使用，以帮助诊断口腔癌。
