Diagnosis of acute appendicitis based on abdominal plain computed tomography scan：a radiomics study

Qubie Xuelei; Wang Kexin; Liu Xiang; Zhang Yaofeng; Zhang Xiaodong; Wang Xiaoying

doi:10.13406/j.cnki.cyxb.003567

您当前的位置：

首页 >

文章列表页 >

Diagnosis of acute appendicitis based on abdominal plain computed tomography scan：a radiomics study

Medical imaging | 更新时间：2025-10-21

- Diagnosis of acute appendicitis based on abdominal plain computed tomography scan：a radiomics study
- Journal of Chongqing Medical University Vol. 49, Issue 8, Pages: 1039-1044(2024)
- 作者机构：
  
  1.北京大学第一医院医学影像科,北京 100034
  2.首都医科大学基础医学院,北京 100069
  3.北京赛迈特锐医学科技有限公司,北京 100011
- 作者简介：
- 基金信息：
- DOI：10.13406/j.cnki.cyxb.003567
  CLC： R445
- Received：03 August 2023，
  
  Revised：2023-11-21，
  
  Accepted：01 March 2024，
  
  Published：28 August 2024
- 稿件说明：
移动端阅览
曲别雪蕾,王可欣,刘想,等.基于腹部CT平扫图像对急性阑尾炎的诊断：影像组学研究[J].重庆医科大学学报,2024,49(8):1039-1044.

Qubie Xuelei,Wang Kexin,Liu Xiang,et al.Diagnosis of acute appendicitis based on abdominal plain computed tomography scan：a radiomics study[J].Journal of Chongqing Medical University,2024,49(8):1039-1044.
曲别雪蕾,王可欣,刘想,等.基于腹部CT平扫图像对急性阑尾炎的诊断：影像组学研究[J].重庆医科大学学报,2024,49(8):1039-1044. DOI： 10.13406/j.cnki.cyxb.003567.

Qubie Xuelei,Wang Kexin,Liu Xiang,et al.Diagnosis of acute appendicitis based on abdominal plain computed tomography scan：a radiomics study[J].Journal of Chongqing Medical University,2024,49(8):1039-1044. DOI： 10.13406/j.cnki.cyxb.003567.

摘要

目的

探索使用影像组学模型在腹部CT平扫图像上诊断急性阑尾炎的可行性。

方法

回顾性收集2015年5月至2021年8月北京大学第一医院经手术病理确诊的急性阑尾炎患者的术前腹部CT扫描的影像和临床数据210例，以及同期因其他急腹症行腹部CT平扫的患者210例用于影像组学模型训练。420例患者的CT检查采集于4台不同CT扫描设备。由2位影像科医生手工标注阑尾区域。将数据按7∶3的比例随机分为训练集和测试集。使用特征提取102种图像特征后，使用Pearson相关分析进行特征降维，以递归特征消除法选择最相关的20种特征训练支持向量机（support vector machine，SVM）进行二分类，得到影像组学模型。得到影像组学模型后，对测试集进行预测结果，以受试者工作特征曲线（receiver operating characteristic，ROC）评价影像组学模型的效能。

结果

经过特征降维、特征选择后，共有3种形态特征、3种一级特征和14种纹理特征用于训练SVM模型。测试集中SVM模型正确预测114例（阑尾炎60例，非阑尾炎54例），错误预测12例（阑尾炎3例，非阑尾炎9例）敏感度为95.2%，特异度为85.7%，准确率为90.5%，ROC曲线下面积为0.931（95%CI=0.887~0.976）。

结论

基于腹部CT平扫图像的影像组学模型可用于急性阑尾炎的预测，未来有望用于急腹症CT检查的流程优化。

Abstract

Objective

To investigate the feasibility of a radiomics model in the diagnosis of acute appendicitis based on abdominal plain computed tomography（CT） scan.

Methods

A retrospective analysis was performed for the preoperative abdominal CT imaging data and clinical data of 210 patients with acute appendicitis confirmed by surgery in our hospital from May 2015 to August 2021，and 210 patients who underwent abdominal plain CT scan due to other acute abdominal diseases during the same period of time were enrolled for the training of the radiomics model. CT scan data of the 420 patients were collected from 4 different CT devices，and the region of the appendix was manually annotated by two radiologists. The data were randomly divided into training set and test set at a ratio of 7∶3. After 102 types of image features were extracted，the Pearson correlation analysis was used for feature dimension reduction，and the recursive feature elimination method was used to select 20 most relevant features for the training and binary classification of support vector machine（SVM） to obtain a radiomics model. After the radiomics model was obtained，the test set was used to predict the results，and the receiver operating characteristic（ROC） curve was used to evaluate the performance of the radiomics model.

Results

After feature dimension reduction and feature selection，3 shape-based features，3 first-order features，and 14 texture features were used to train the SVM model. In the test set，the SVM model had correct prediction in 114 cases（60 appendicitis cases and 54 non-appendicitis cases） and wrong prediction in 12 cases（3 appendicitis cases and 9 non-appendicitis cases），with a sensitivity of 95.2%，a specificity of 85.7%，an accuracy of 90.5%，and an area under the ROC curve of 0.931（95%CI： 0.887-0.976）.

Conclusion

The radiomics model based on abdominal plain CT scan images can be used for the prediction of acute appendicitis and is expected to be used to optimize the workflow of CT examination for acute abdominal disease in the future.

关键词

Keywords

references

Ferris M ， Quan S ， Kaplan BS ， et al . The global incidence of appendicitis：a systematic review of population-based studies [J ] . Ann Surg ， 2017 ， 266 （ 2 ）： 237 - 241 ．

Expert Panel on Gastrointestinal Imaging ： Garcia EM ， Camacho MA ， et al . ACR appropriateness criteria ® right lower quadrant pain-suspected appendicitis [J ] . J Am Coll Radiol ， 2018 ， 15 （ 11 Suppl ）： S373- S387．

Coward S ， Kareemi H ， Clement F ， et al . Incidence of appendicitis over time：a comparative analysis of an administrative healthcare database and a pathology-proven appendicitis registry [J ] . PLoS One ， 2016 ， 11 （ 11 ）： e0165161 ．

Paulson EK ， Kalady MF ， Pappas TN . Clinical practice. suspected appendicitis [J ] . N Engl J Med ， 2003 ， 348 （ 3 ）： 236 - 242 ．

Fersahoğlu MM ， Çiyiltepe H ， Ergin A ， et al . Effective use of CT by surgeons in acute appendicitis diagnosis [J ] . Ulus Travma Acil Cerrahi Derg ， 2021 ， 27 （ 1 ）： 43 - 49 ．

Caruso D ， Polici M ， Zerunian M ， et al . Radiomics in oncology，part 1：technical principles and gastrointestinal application in CT and MRI [J ] . Cancers ， 2021 ， 13 （ 11 ）： 2522 ．

Federle MP . CT of the acute（emergency） abdomen [J ] . Eur Radiol ， 2005 ， 15 Suppl 4 ： S100 - S104 ．

沈俊杰，汤军保 . 多层螺旋CT诊断急性阑尾炎临床价值分析 [J ] . 医学影像学杂志， 2022 ， 32 （ 8 ）： 1430 - 1432 ．

Shen JJ ， Tang JB . Value of multi-slice spiral CT in the diagnosis of acute appendicitis of different pathological types [J ] . J Med Imag ， 2022 ， 32 （ 8 ）： 1430 - 1432 ．

Eurboonyanun K ， Rungwiriyawanich P ， Chamadol N ， et al . Accuracy of nonenhanced CT vs contrast-enhanced CT for diagnosis of acute appendicitis in adults [J ] . Curr Probl Diagn Radiol ， 2021 ， 50 （ 3 ）： 315 - 320 ．

Rud B ， Vejborg TS ， Rappeport ED ， et al . Computed tomography for diagnosis of acute appendicitis in adults [J ] . Cochrane Database Syst Rev ， 2019 ， 2019 （ 11 ）： CD009977 ．

Cartwright SL ， Knudson MP . Evaluation of acute abdominal pain in adults [J ] . Am Fam Physician ， 2008 ， 77 （ 7 ）： 971 - 978 ．

朱丽娜，高　歌，刘义，等 . CAD整合入前列腺多参数MRI结构化报告：低经验读片者诊断效能研究 [J ] . 放射学实践， 2020 ， 35 （ 10 ）： 1282 - 1287 ．

Zhu LN ， Gao G ， Liu Y ， et al . Integrating computer-aided diagnosis with prostate multiparametric MRI structured reports：low-experience radiologists performance study [J ] . Radiol Pract ， 2020 ， 35 （ 10 ）： 1282 - 1287 ．

Cui YP ， Sun ZN ， Ma S ， et al . Automatic detection and scoring of kidney stones on noncontrast CT images using S. T. O. N. E. nephrolithometry：combined deep learning and thresholding methods [J ] . Mol Imaging Biol ， 2021 ， 23 （ 3 ）： 436 - 445 ．

Mashayekhi R ， Parekh VS ， Faghih M ， et al . Radiomic features of the pancreas on CT imaging accurately differentiate functional abdominal pain，recurrent acute pancreatitis，and chronic pancreatitis [J ] . Eur J Radiol ， 2020 ， 123 ： 108778 ．

Zwanenburg A ， Vallières M ， Abdalah MA ， et al . The image biomarker standardization initiative：standardized quantitative radiomics for high-throughput image-based phenotyping [J ] . Radiology ， 2020 ， 295 （ 2 ）： 328 - 338 ．

Hatt M ， Le Rest CC ， Tixier F ， et al . Radiomics：data are also images [J ] . J Nucl Med ， 2019 ， 60 Suppl 2 ： S38 - S44 ．

Mayerhoefer ME ， Materka A ， Langs G ， et al . Introduction to radiomics [J ] . J Nucl Med ， 2020 ， 61 （ 4 ）： 488 - 495 ．

Sidey-Gibbons JAM ， Sidey-Gibbons CJ . Machine learning in medicine：a practical introduction [J ] . BMC Med Res Methodol ， 2019 ， 19 （ 1 ）： 64 ．

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Advances in the application of ultrasound combined with radiomics and artificial intelligence in the diagnosis and prognostic evaluation of gastrointestinal stromal tumors

Machine learning combined with computed tomography radiomics in predicting vertebral fragility fractures in patients with type 2 diabetes mellitus

Research progress on artificial intelligence in screening and precise diagnosis and treatment of cervical cancer

Diagnosis of Alzheimer's disease based on whole-brain radiomics

Predictive value of a nomogram based on enhanced T1WI radiomics and clinico-MRIomics for aggressive histological types of endometrial cancer before surgery

Related Author

He Xuemei

Liu Yang

Zhong Jian

Liu Qiao

Zeng Yan

Li Siyi

Zhou Daiquan

Hong Yuqin

Related Institution

Department of Ultrasound，The First Affiliated Hospital of Chongqing Medical University

Department of Radiology,The Third Affiliated Hospital of Chongqing Medical University

Department of Endocrinology,The Third Affiliated Hospital of Chongqing Medical University

Department of Pathology and Pathophysiology，School of Biology & Basic Medical Sciences， Suzhou Medical College of Soochow University

Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University

⁰