Scholarlink

<p>The increase of oral squamous cell carcinoma (OSCC) in many countries is primarily linked to its high mortality rate and poor forecast. The diagnosis of patients with OSCC is usually made by a&#xa0;pathologist who has utilized decades of useful data from tissue biopsy samples. Human error increases while trying to identify the cells via hand from photographs of microscope samples. Previous studies have applied convolutional neural networks (CNNs) with pre-trained models to detect oral diseases to improve accuracy. However, this approach outcomes in a high number of false positives and false negatives, which may lead to inaccurate diagnoses. To detect oral squamous cell carcinoma cancer from histopathological images, we developed the AlexNet deep learning model. We used image preprocessing methods to enhance the quality of histopathology images by utilizing bilateral filtering and color normalization via histogram image enhancement. Additionally, we utilized AlexNet, MobileNetV3, and InceptionV3 for feature extraction, as well as the XGBoost classifier. To emphasize the reliability of our findings, we have expanded on the evaluation metrics (accuracy, precision, recall, and F1 score) achieved by the proposed model, particularly the accuracy of 99%, precision of 98.5%, recall of 98.5%, and F1 score of 99%, highlighting the model’s strength in OSCC detection. These findings highlight the effectiveness of transfer learning in detecting medical images, providing significant advancements in the early detection of OSCC and making a valuable contribution to the field of oral oncology.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Detection of oral squamous cell carcinoma cancer using AlexNet on histopathological images

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月19日

查看全文
  • Nigus Wereta Asnake,
  • Aleka Melese Ayalew,
  • Abebaw Agegne Engda

摘要

The increase of oral squamous cell carcinoma (OSCC) in many countries is primarily linked to its high mortality rate and poor forecast. The diagnosis of patients with OSCC is usually made by a pathologist who has utilized decades of useful data from tissue biopsy samples. Human error increases while trying to identify the cells via hand from photographs of microscope samples. Previous studies have applied convolutional neural networks (CNNs) with pre-trained models to detect oral diseases to improve accuracy. However, this approach outcomes in a high number of false positives and false negatives, which may lead to inaccurate diagnoses. To detect oral squamous cell carcinoma cancer from histopathological images, we developed the AlexNet deep learning model. We used image preprocessing methods to enhance the quality of histopathology images by utilizing bilateral filtering and color normalization via histogram image enhancement. Additionally, we utilized AlexNet, MobileNetV3, and InceptionV3 for feature extraction, as well as the XGBoost classifier. To emphasize the reliability of our findings, we have expanded on the evaluation metrics (accuracy, precision, recall, and F1 score) achieved by the proposed model, particularly the accuracy of 99%, precision of 98.5%, recall of 98.5%, and F1 score of 99%, highlighting the model’s strength in OSCC detection. These findings highlight the effectiveness of transfer learning in detecting medical images, providing significant advancements in the early detection of OSCC and making a valuable contribution to the field of oral oncology.