Fang Yu-Jen, Huang Chien-Wei, Karmakar Riya, Mukundan Arvind, Tsao Yu-Ming, Yang Kai-Yao, Wang Hsiang-Chen
Department of Internal Medicine, National Taiwan University Hospital, Yun-Lin Branch, No. 579, Sec. 2, Yunlin Rd., Dou-Liu 64041, Taiwan.
Department of Internal Medicine, National Taiwan University College of Medicine, No. 1, Jen Ai Rd., Sec. 1, Taipei 10051, Taiwan.
Cancers (Basel). 2024 Jan 29;16(3):572. doi: 10.3390/cancers16030572.
Esophageal carcinoma (EC) is a prominent contributor to cancer-related mortality since it lacks discernible features in its first phases. Multiple studies have shown that narrow-band imaging (NBI) has superior accuracy, sensitivity, and specificity in detecting EC compared to white light imaging (WLI). Thus, this study innovatively employs a color space linked to décor to transform WLIs into NBIs, offering a novel approach to enhance the detection capabilities of EC in its early stages. In this study a total of 3415 WLI along with the corresponding 3415 simulated NBI images were used for analysis combined with the YOLOv5 algorithm to train the WLI images and the NBI images individually showcasing the adaptability of advanced object detection techniques in the context of medical image analysis. The evaluation of the model's performance was based on the produced confusion matrix and five key metrics: precision, recall, specificity, accuracy, and F1-score of the trained model. The model underwent training to accurately identify three specific manifestations of EC, namely dysplasia, squamous cell carcinoma (SCC), and polyps demonstrates a nuanced and targeted analysis, addressing diverse aspects of EC pathology for a more comprehensive understanding. The NBI model effectively enhanced both its recall and accuracy rates in detecting dysplasia cancer, a pre-cancerous stage that might improve the overall five-year survival rate. Conversely, the SCC category decreased its accuracy and recall rate, although the NBI and WLI models performed similarly in recognizing the polyp. The NBI model demonstrated an accuracy of 0.60, 0.81, and 0.66 in the dysplasia, SCC, and polyp categories, respectively. Additionally, it attained a recall rate of 0.40, 0.73, and 0.76 in the same categories. The WLI model demonstrated an accuracy of 0.56, 0.99, and 0.65 in the dysplasia, SCC, and polyp categories, respectively. Additionally, it obtained a recall rate of 0.39, 0.86, and 0.78 in the same categories, respectively. The limited number of training photos is the reason for the suboptimal performance of the NBI model which can be improved by increasing the dataset.
食管癌（EC）是癌症相关死亡率的一个重要因素，因为它在早期阶段缺乏明显特征。多项研究表明，与白光成像（WLI）相比，窄带成像（NBI）在检测食管癌方面具有更高的准确性、敏感性和特异性。因此，本研究创新性地采用一种与装饰相关的色彩空间将白光图像转换为窄带图像，为提高食管癌早期检测能力提供了一种新方法。在本研究中，总共3415张白光图像以及相应的3415张模拟窄带图像被用于分析，并结合YOLOv5算法分别对白光图像和窄带图像进行训练，展示了先进目标检测技术在医学图像分析中的适应性。模型性能的评估基于生成的混淆矩阵和五个关键指标：训练模型的精确率、召回率、特异性、准确率和F1分数。该模型经过训练以准确识别食管癌的三种特定表现，即发育异常、鳞状细胞癌（SCC）和息肉，展示了细致入微且有针对性的分析，涉及食管癌病理学的多个方面，以实现更全面的理解。窄带成像模型在检测发育异常癌（一种可能提高总体五年生存率的癌前阶段）时有效地提高了召回率和准确率。相反，鳞状细胞癌类别降低了其准确率和召回率，尽管窄带成像和白光成像模型在识别息肉方面表现相似。窄带成像模型在发育异常、鳞状细胞癌和息肉类别中的准确率分别为0.60、0.81和0.66。此外，它在相同类别中的召回率分别为0.40、0.73和0.76。白光成像模型在发育异常、鳞状细胞癌和息肉类别中的准确率分别为0.56、0.99和0.65。此外，它在相同类别中的召回率分别为0.39、0.86和0.78。训练照片数量有限是窄带成像模型性能欠佳的原因，增加数据集可以改善这一情况。
