Abstract：
BACKGROUND: We aimed to develop a diagnostic deep learning model using contrast-enhanced CT images and to investigate whether cervical lymphadenopathies can be diagnosed with these deep learning methods without radiologist interpretations and histopathological examinations.
METHODS: A total of 400 patients who underwent surgery for lymphadenopathy in the neck between 2010 and 2022 were retrospectively analyzed. They were examined in four groups of 100 patients: the granulomatous diseases group, the lymphoma group, the squamous cell tumor group, and the reactive hyperplasia group. The diagnoses of the patients were confirmed histopathologically. Two CT images from all the patients in each group were used in the study. The CT images were classified using ResNet50, NASNetMobile, and DenseNet121 architecture input.
RESULTS: The classification accuracies obtained with ResNet50, DenseNet121, and NASNetMobile were 92.5%, 90.62, and 87.5, respectively.
CONCLUSIONS: Deep learning is a useful diagnostic tool in diagnosing cervical lymphadenopathy. In the near future, many diseases could be diagnosed with deep learning models without radiologist interpretations and invasive examinations such as histopathological examinations. However, further studies with much larger case series are needed to develop accurate deep-learning models.
METHODS: A total of 400 patients who underwent surgery for lymphadenopathy in the neck between 2010 and 2022 were retrospectively analyzed. They were examined in four groups of 100 patients: the granulomatous diseases group, the lymphoma group, the squamous cell tumor group, and the reactive hyperplasia group. The diagnoses of the patients were confirmed histopathologically. Two CT images from all the patients in each group were used in the study. The CT images were classified using ResNet50, NASNetMobile, and DenseNet121 architecture input.
RESULTS: The classification accuracies obtained with ResNet50, DenseNet121, and NASNetMobile were 92.5%, 90.62, and 87.5, respectively.
CONCLUSIONS: Deep learning is a useful diagnostic tool in diagnosing cervical lymphadenopathy. In the near future, many diseases could be diagnosed with deep learning models without radiologist interpretations and invasive examinations such as histopathological examinations. However, further studies with much larger case series are needed to develop accurate deep-learning models.
摘要：
背景：我们旨在开发一种使用对比增强CT图像的诊断深度学习模型，并研究使用这些深度学习方法是否可以在没有放射科医生解释和组织病理学检查的情况下诊断出颈部淋巴结病变。
方法：对2010年至2022年因颈部淋巴结肿大而接受手术治疗的400例患者进行回顾性分析。他们在四组100名患者中进行了检查：肉芽肿性疾病组，淋巴瘤组，鳞状细胞肿瘤组，和反应性增生组。患者的诊断在组织病理学上得到证实。研究中使用了每组所有患者的两张CT图像。CT图像使用ResNet50，NASNetMobile，和DenseNet121架构输入。
结果：使用ResNet50、DenseNet121和NASNetMobile获得的分类准确率为92.5%，分别为90.62和87.5。
结论：深度学习是诊断颈淋巴结病的有用诊断工具。在不久的将来,许多疾病可以通过深度学习模型来诊断，而无需放射科医生的解释和侵入性检查，如组织病理学检查。然而,需要进一步研究更大的案例系列来开发准确的深度学习模型。
方法：对2010年至2022年因颈部淋巴结肿大而接受手术治疗的400例患者进行回顾性分析。他们在四组100名患者中进行了检查：肉芽肿性疾病组，淋巴瘤组，鳞状细胞肿瘤组，和反应性增生组。患者的诊断在组织病理学上得到证实。研究中使用了每组所有患者的两张CT图像。CT图像使用ResNet50，NASNetMobile，和DenseNet121架构输入。
结果：使用ResNet50、DenseNet121和NASNetMobile获得的分类准确率为92.5%，分别为90.62和87.5。
结论：深度学习是诊断颈淋巴结病的有用诊断工具。在不久的将来,许多疾病可以通过深度学习模型来诊断，而无需放射科医生的解释和侵入性检查，如组织病理学检查。然而,需要进一步研究更大的案例系列来开发准确的深度学习模型。
