基于磁共振成像的卷积神经网络用于卵巢肿瘤鉴别评估
本研究在单中心451例患者545个卵巢病灶的常规MR图像上构建卷积神经网络区分良恶性,并按7:2:1分为训练、验证和测试集。最终联合模型测试准确度0.87、特异度0.92,高于低年资放射科医师平均的0.64和0.64,与高年资医师平均的0.74和0.70相比亦更高;低年资医师借助模型概率后准确度和特异度提升。
要点
- 联合MR影像与临床变量的最终集成模型测试准确度0.87、特异度0.92。
- 模型与低年资医师平均相比准确度和特异度更高,敏感度无显著差异。
- 低年资医师借助模型概率后准确度0.77、特异度0.81,敏感度无显著变化。
核心结论
- 基于深度学习的AI可辅助放射科医师评估卵巢病灶性质并改善其表现。
研究设计与样本
- 单中心研究,共451例患者的545个病灶(良性379个、恶性166个),按7:2:1分为训练集、验证集和测试集。
- 在常规MR成像上应用卷积神经网络区分卵巢病灶良恶性,最终集成模型结合MR影像与临床变量。
- 模型性能在测试集上与4名低年资和3名高年资放射科医师进行比较。
诊断标准与关键数值
- 最终集成模型测试准确度0.87、特异度0.92、敏感度0.75。
- 低年资医师平均准确度0.64、特异度0.64、敏感度0.63;模型准确度0.87 vs 0.64(p < 0.001)、特异度0.92 vs 0.64(p < 0.001),敏感度0.75 vs 0.63(p = 0.407)。
- 高年资医师平均准确度0.74、特异度0.70、敏感度0.83;模型准确度0.87 vs 0.74(p = 0.033)、特异度0.92 vs 0.70(p < 0.001),敏感度0.75 vs 0.83(p = 0.557)。
- 低年资医师借助模型概率后平均测试准确度0.77 vs 0.64(Δ = 0.13,p < 0.001)、特异度0.81 vs 0.64(Δ = 0.17,p < 0.001),敏感度0.69 vs 0.63(Δ = 0.06,p = 0.302)无变化。
- 借助AI概率后,低年资医师与高年资医师相比特异度0.81 vs 0.70(Δ = 0.11,p = 0.005)更高,准确度0.77 vs 0.74(Δ = 0.03,p = 0.409)和敏感度0.69 vs 0.83(Δ = -0.146,p = 0.097)相近。
临床应用与阅片要点
- 原文未据此给出推荐。
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
OBJECTIVES: There currently lacks a noninvasive and accurate method to distinguish benign and malignant ovarian lesion prior to treatment. This study developed a deep learning algorithm that distinguishes benign from malignant ovarian lesion by applying a convolutional neural network on routine MR imaging.
METHODS: Five hundred forty-five lesions (379 benign and 166 malignant) from 451 patients from a single institution were divided into training, validation, and testing set in a 7:2:1 ratio. Model performance was compared with four junior and three senior radiologists on the test set.
RESULTS: Compared with junior radiologists averaged, the final ensemble model combining MR imaging and clinical variables had a higher test accuracy (0.87 vs 0.64, p < 0.001) and specificity (0.92 vs 0.64, p < 0.001) with comparable sensitivity (0.75 vs 0.63, p = 0.407). Against the senior radiologists averaged, the final ensemble model also had a higher test accuracy (0.87 vs 0.74, p = 0.033) and specificity (0.92 vs 0.70, p < 0.001) with comparable sensitivity (0.75 vs 0.83, p = 0.557). Assisted by the model's probabilities, the junior radiologists achieved a higher average test accuracy (0.77 vs 0.64, Δ = 0.13, p < 0.001) and specificity (0.81 vs 0.64, Δ = 0.17, p < 0.001) with unchanged sensitivity (0.69 vs 0.63, Δ = 0.06, p = 0.302). With the AI probabilities, the junior radiologists had higher specificity (0.81 vs 0.70, Δ = 0.11, p = 0.005) but similar accuracy (0.77 vs 0.74, Δ = 0.03, p = 0.409) and sensitivity (0.69 vs 0.83, Δ = -0.146, p = 0.097) when compared with the senior radiologists.
CONCLUSIONS: These results demonstrate that artificial intelligence based on deep learning can assist radiologists in assessing the nature of ovarian lesions and improve their performance.
KEY POINTS: • Artificial Intelligence based on deep learning can assess the nature of ovarian lesions on routine MRI with higher accuracy and specificity than radiologists. • Assisted by the deep learning model's probabilities, junior radiologists achieved better performance that matched those of senior radiologists.
引用
- Wang R, Cai Y, Lee IK, et al. Evaluation of a convolutional neural network for ovarian tumor differentiation based on magnetic resonance imaging. Eur Radiol. 2020. PMID: 33052463. doi:10.1007/s00330-020-07266-x
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。