深度学习在超声上鉴别肝脏良恶性实性病变
本研究纳入596例患者的911幅肝脏实性病变超声图像(恶性535幅、良性376幅),用ResNet50架构深度学习模型区分良恶性,并与两位专家判读比较。模型在全数据集测试准确度0.84(95%CI 0.74-0.90),高于专家1的0.80(95%CI 0.70-0.87)和专家2的0.73(95%CI 0.63-0.82);在不确定诊断数据集上模型准确度0.79(95%CI 0.69-0.87),高于专家平均的0.68(p=0.025)。作者认为深度学习可改善良恶性鉴别,表现与专家放射科医生相当。
要点
- 模型在全数据集测试准确度0.84(95%CI 0.74-0.90),专家1为0.80、专家2为0.73。
- 在Code Abdomen评为诊断不确定的病变中,模型准确度0.79,高于专家平均0.68(p=0.025)。
- 模型基于超声图像区分肝脏实性病变良恶性,表现与专家放射科医生相当。
核心结论
- 本研究提出的深度学习算法可改善超声捕获的肝脏实性病变良恶性鉴别,表现与专家放射科医生相当;深度学习工具可能用于提高临床工作流程的准确性和效率。
研究设计与样本
- 研究纳入596例符合标准患者的911幅肝脏实性病变超声图像,其中恶性535幅、良性376幅;训练集含660个病变并在训练中动态增强至330,000幅图像,测试集含79幅图像;采用ResNet50架构神经网络以ImageNet预训练权重微调;纳入经组织病理学或MRI明确诊断的非囊性肝脏病变;训练与评估使用两个独立数据集,一个含全部病变,一个含基于Code Abdomen评分系统判定为诊断不确定的病变。
诊断标准与关键数值
- 全数据集:模型测试准确度0.84(95%CI 0.74-0.90),专家1为0.80(95%CI 0.70-0.87),专家2为0.73(95%CI 0.63-0.82)。
- 不确定诊断数据集:模型测试准确度0.79(95%CI 0.69-0.87),专家1为0.70(95%CI 0.59-0.78),专家2为0.66(95%CI 0.55-0.75)。
- 不确定诊断数据集上,模型与全部专家平均相比测试准确度更高(0.79 vs. 0.68,p=0.025)。
临床应用与阅片要点
- 作者认为深度学习工具可能用于提高临床工作流程的准确性和效率。
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
PURPOSE: The ability to reliably distinguish benign from malignant solid liver lesions on ultrasonography can increase access, decrease costs, and help to better triage patients for biopsy. In this study, we used deep learning to differentiate benign from malignant focal solid liver lesions based on their ultrasound appearance.
METHODS: Among the 596 patients who met the inclusion criteria, there were 911 images of individual liver lesions, of which 535 were malignant and 376 were benign. Our training set contained 660 lesions augmented dynamically during training for a total of 330,000 images; our test set contained 79 images. A neural network with ResNet50 architecture was fine-tuned using pre-trained weights on ImageNet. Non-cystic liver lesions with definite diagnosis by histopathology or MRI were included. Accuracy of the final model was compared with expert interpretation. Two separate datasets were used in training and evaluation, one with all lesions and one with lesions deemed to be of uncertain diagnosis based on the Code Abdomen rating system.
RESULTS: Our model trained on the complete set of all lesions achieved a test accuracy of 0.84 (95% CI 0.74-0.90) compared to expert 1 with a test accuracy of 0.80 (95% CI 0.70-0.87) and expert 2 with a test accuracy of 0.73 (95% CI 0.63-0.82). Our model trained on the uncertain set of lesions achieved a test accuracy of 0.79 (95% CI 0.69-0.87) compared to expert 1 with a test accuracy of 0.70 (95% CI 0.59-0.78) and expert 2 with a test accuracy of 0.66 (95% CI 0.55-0.75). On the uncertain dataset, compared to all experts averaged, the model had higher test accuracy (0.79 vs. 0.68, p = 0.025).
CONCLUSION: Deep learning algorithms proposed in the current study improve differentiation of benign from malignant ultrasound-captured solid liver lesions and perform comparably to expert radiologists. Deep learning tools can potentially be used to improve the accuracy and efficiency of clinical workflows.
引用
- Xi IL, Wu J, Guan J, et al. Deep learning for differentiation of benign and malignant solid liver lesions on ultrasonography. Abdom Radiol (NY). 2021. PMID: 32681268. doi:10.1007/s00261-020-02564-w
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。