文献速递胸部骨肌技术与安全CT

基于患者CT图像与临床信息通过卷积神经网络自动检测和分类肋骨骨折

Automatic detection and classification of rib fractures based on patients' CT images and clinical information via convolutional neural network.
PubMed 文献 · Eur Radiol · 2020-11-17

本研究回顾性收集1020例参与者的CT图像和临床信息,构建Faster R-CNN模型融合跨模态数据自动检测和分类肋骨骨折。与单用CT图像相比,联合临床信息在新鲜、愈合及陈旧骨折中均提升检测与分类性能;与经验丰富的放射科医生相比,CNN模型灵敏度更高、精确率相当且诊断时间更短。

要点

  • CNN模型联合临床信息与CT图像可自动检测并分类新鲜、愈合及陈旧肋骨骨折。
  • 与单用CT图像相比,联合临床信息在新鲜、愈合及陈旧骨折中均提升检测与分类性能。
  • 与经验丰富的放射科医生相比,CNN模型灵敏度更高、精确率相当、诊断时间更短。

核心结论

  • 结合CT图像与临床信息的CNN模型可在实际临床实践中以良好性能和可行性自动检测并分类肋骨骨折。

研究设计与样本

  • 回顾性研究,共收集1020例参与者的CT图像和临床信息(年龄、性别、病史),分为单中心训练集760例(年龄55.8±13.4岁,男性500例)、单中心测试集134例(年龄53.1±14.3岁,男性90例)及两个来自不同医院的多中心独立测试集(62例,年龄57.97±11.88岁,男性41例;64例,年龄57.40±13.36岁,男性35例)。

诊断标准与关键数值

  • 采用Faster R-CNN模型融合CT图像与临床信息,并用结果合并技术将2D推断转换为3D病灶结果;诊断性能基于ROC曲线、fROC曲线、精确率、召回率(灵敏度)、F1分数和诊断时间评估;分类性能以AUC、灵敏度和特异度评估。

临床应用与阅片要点

  • 与经验丰富的放射科医生相比,CNN模型在新鲜、愈合及陈旧骨折三类的平均灵敏度分别为0.95>0.77、0.89>0.61和0.80>0.55,平均精确率分别为0.91>0.87、0.84>0.77和0.95>0.70,诊断时间平均缩短126.15秒。

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

OBJECTIVE: To develop a convolutional neural network (CNN) model for the automatic detection and classification of rib fractures in actual clinical practice based on cross-modal data (clinical information and CT images).

MATERIALS: In this retrospective study, CT images and clinical information (age, sex and medical history) from 1020 participants were collected and divided into a single-centre training set (n = 760; age: 55.8 ± 13.4 years; men: 500), a single-centre testing set (n = 134; age: 53.1 ± 14.3 years; men: 90), and two independent multicentre testing sets from two different hospitals (n = 62, age: 57.97 ± 11.88, men: 41; n = 64, age: 57.40 ± 13.36, men: 35). A Faster Region-based CNN (Faster R-CNN) model was applied to integrate CT images and clinical information. Then, a result merging technique was used to convert 2D inferences into 3D lesion results. The diagnostic performance was assessed on the basis of the receiver operating characteristic (ROC) curve, free-response ROC (fROC) curve, precision, recall (sensitivity), F1-score, and diagnosis time. The classification performance was evaluated in terms of the area under the ROC curve (AUC), sensitivity, and specificity.

RESULTS: The CNN model showed improved performance on fresh, healing, and old fractures and yielded good classification performance for all three categories when both clinical information and CT images were used compared to the use of CT images alone. Compared with experienced radiologists, the CNN model achieved higher sensitivity (mean sensitivity: 0.95 > 0.77, 0.89 > 0.61 and 0.80 > 0.55), comparable precision (mean precision: 0.91 > 0.87, 0.84 > 0.77, and 0.95 > 0.70), and a shorter diagnosis time (average reduction of 126.15 s).

CONCLUSIONS: A CNN model combining CT images and clinical information can automatically detect and classify rib fractures with good performance and feasibility in actual clinical practice.

KEY POINTS: • The developed convolutional neural network (CNN) performed better in fresh, healing, and old fractures and yielded a good classification performance in three categories, if both (clinical information and CT images) were used compared to CT images alone. • The CNN model had a higher sensitivity and matched precision in three categories than experienced radiologists with a shorter diagnosis time in actual clinical practice.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Zhou QQ, Tang W, Wang J, et al. Automatic detection and classification of rib fractures based on patients' CT images and clinical information via convolutional neural network. Eur Radiol. 2020. PMID: 33201278. doi:10.1007/s00330-020-07418-z

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。