文献速递头颈技术与安全CT

基于CT图像的深度学习模型鉴别鼻息肉与内翻性乳头状瘤:一项多中心研究

Deep Learning Model for the Differential Diagnosis of Nasal Polyps and Inverted Papilloma by CT Images: A Multicenter Study.
PubMed 文献 · Acad Radiol · 2024-12-26

回顾性纳入两家医院1791例鼻腔良性肿瘤患者,用3D ResNet、3D Xception和HRNet基于CT图像鉴别鼻息肉与内翻性乳头状瘤。3D Xception模型表现最佳,外部测试集AUC为0.933,敏感度和特异度超过4位放射科医生,并将平均敏感度从0.845提升至0.884、特异度从0.670提升至0.840。

要点

  • 3D Xception模型在外部测试集鉴别鼻息肉与内翻性乳头状瘤的AUC为0.933。
  • 模型辅助使放射科医生平均敏感度从0.845升至0.884、特异度从0.670升至0.840。
  • 模型预测与上皮细胞分化相关,蛋白组学分析纳入70例患者。

核心结论

  • 基于CT图像的深度学习模型有望鉴别鼻息肉与内翻性乳头状瘤,并增强临床医生的判读能力。

研究设计与样本

  • 回顾性纳入两家医院1791例鼻腔良性肿瘤患者,分为训练集、内部测试集和外部测试集,采用3D ResNet、3D Xception和HRNet模型基于CT图像鉴别鼻息肉与内翻性乳头状瘤。

诊断标准与关键数值

  • 3D Xception模型在训练集AUC为0.999(95%CI:0.950-1.000)。
  • 3D Xception模型在内部测试集AUC为0.981(95%CI:0.950-1.000)。
  • 3D Xception模型在外部测试集AUC为0.933(95%CI:0.9099-0.9557)。
  • 最优深度学习模型的敏感度和特异度超过4位放射科医生。
  • 深度学习模型将放射科医生平均敏感度从0.845提升至0.884,平均特异度从0.670提升至0.840。

临床应用与阅片要点

  • 深度学习模型可辅助放射科医生在CT图像上鉴别鼻息肉与内翻性乳头状瘤。
  • 模型预测与上皮细胞分化相关,蛋白组学分析纳入70例患者。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: Nasal polyps (NP) and inverted papilloma (IP) are benign tumors within the nasal cavity, each necessitating distinct treatment approaches. Herein, we investigate the utility of a deep learning (DL) model for distinguishing between NP and IP.

MATERIALS AND METHODS: A total of 1791 patients with nasal benign tumors from two hospitals were retrospectively enrolled. Patients were divided into training, internal test, and external test sets. DL models (3D ResNet, 3D Xception, and HRNet) were employed to identify NP from IP using computed tomography images. Model performance was evaluated via receiver operating characteristic curve analysis, accuracy, sensitivity, and specificity. The best-performing model was compared with radiologists' interpretations. The potential enhancement of radiologists' diagnostic performance using the optimal DL model was investigated. Additionally, proteomics analysis in 70 patients was conducted to elucidate the biological underpinnings of the DL model.

RESULTS: The 3D Xception model emerged as the best-performing DL model, achieving the highest area under the receiver operating characteristic curve of 0.999 (95% confidence interval [CI]: 0.950-1.000) in the training set, 0.981 (95% CI: 0.950-1.000) in the internal test set, and 0.933 (95% CI: 0.9099-0.9557) in the external test set. The sensitivity and specificity of the optimal DL model surpassed those of the four radiologists. Furthermore, the DL model improved average radiologist sensitivity from 0.845 to 0.884 and specificity from 0.670 to 0.840. Proteomic analysis revealed an association between the model predictions and epithelial cell differentiation.

CONCLUSION: DL based on CT images holds promise for distinguishing between NP and IP lesions, thereby augmenting clinicians' interpretation capabilities.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Wang Y, Liu F, Zhang H, et al. Deep Learning Model for the Differential Diagnosis of Nasal Polyps and Inverted Papilloma by CT Images: A Multicenter Study. Acad Radiol. 2024. PMID: 39730250. doi:10.1016/j.acra.2024.12.011

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。