Convolutional neural network-based program to predict lymph node metastasis of non-small cell lung cancer using 18F-FDG PET

被引:1
作者
Kidera, Eitaro [1 ,2 ]
Koyasu, Sho [2 ]
Hirata, Kenji [3 ]
Hamaji, Masatsugu [4 ]
Nakamoto, Ryusuke [2 ]
Nakamoto, Yuji [2 ]
机构
[1] Kishiwada City Hosp, Dept Radiol, Kishiwada, Japan
[2] Kyoto Univ, Grad Sch Med, Dept Diagnost Imaging & Nucl Med, 54 Shogoin Kawahara Cho,Sakyo Ku, Kyoto 6068507, Japan
[3] Hokkaido Univ, Grad Sch Med, Dept Diagnost Imaging, Sapporo, Japan
[4] Kyoto Univ, Kyoto Univ Hosp, Dept Thorac Surg, Kyoto, Japan
关键词
Deep learning; Lymph node metastasis; Non-small cell lung cancer; Positron emission tomography; POSITRON-EMISSION-TOMOGRAPHY; ARTIFICIAL-INTELLIGENCE; OUTCOMES;
D O I
10.1007/s12149-023-01866-5
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Purpose To develop a convolutional neural network (CNN)-based program to analyze maximum intensity projection (MIP) images of 2-deoxy-2-[F-18]fluoro-d-glucose (FDG) positron emission tomography (PET) scans, aimed at predicting lymph node metastasis of non-small cell lung cancer (NSCLC), and to evaluate its effectiveness in providing diagnostic assistance to radiologists.Methods We obtained PET images of NSCLC from public datasets, including those of 435 patients with available N-stage information, which were divided into a training set (n = 304) and a test set (n = 131). We generated 36 maximum intensity projection (MIP) images for each patient. A residual network (ResNet-50)-based CNN was trained using the MIP images of the training set to predict lymph node metastasis. Lymph node metastasis in the test set was predicted by the trained CNN as well as by seven radiologists twice: first without and second with CNN assistance. Diagnostic performance metrics, including accuracy and prediction error (the difference between the truth and the predictions), were calculated, and reading times were recorded.Results In the test set, 67 (51%) patients exhibited lymph node metastases and the CNN yielded 0.748 predictive accuracy. With the assistance of the CNN, the prediction error was significantly reduced for six of the seven radiologists although the accuracy did not change significantly. The prediction time was significantly reduced for five of the seven radiologists with the median reduction ratio 38.0%.Conclusion The CNN-based program could potentially assist radiologists in predicting lymph node metastasis by increasing diagnostic confidence and reducing reading time without affecting diagnostic accuracy, at least in the limited situations using MIP images.
引用
收藏
页码:71 / 80
页数:10
相关论文
共 50 条
  • [31] Effects of Tracer Uptake Time in Non-Small Cell Lung Cancer 18F-FDG PET Radiomics
    Kolinger, Guilherme D.
    Garc, David Vallez
    Kramer, Gerbrand Maria
    Frings, Virginie
    Zwezerijnen, Gerben J. C.
    Smit, Egbert F.
    de Langen, Adrianus Johannes
    Buvat, Irene
    Boellaard, Ronald
    JOURNAL OF NUCLEAR MEDICINE, 2022, 63 (06) : 919 - 924
  • [32] Influx rate constant of 18F-FDG increases in metastatic lymph nodes of non-small cell lung cancer patients
    Yang, Min
    Lin, Zhong
    Xu, Zeqing
    Li, Dan
    Lv, Weize
    Yang, Shuai
    Liu, Ye
    Cao, Ying
    Cao, Qingdong
    Jin, Hongjun
    EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2020, 47 (05) : 1198 - 1208
  • [33] Impact of Point Spread Function Reconstruction on Thoracic Lymph Node Staging With 18F-FDG PET/CT in Non-Small Cell Lung Cancer
    Lasnon, Charline
    Hicks, Rodney J.
    Beauregard, Jean-Mathieu
    Milner, Alvin
    Paciencia, Maria
    Guizard, Anne-Valerie
    Bardet, Stephane
    Gervais, Radj
    Lemoel, Gabriel
    Zalcman, Gerard
    Aide, Nicolas
    CLINICAL NUCLEAR MEDICINE, 2012, 37 (10) : 971 - 976
  • [34] Repeat 18F-FDG PET for monitoring neoadjuvant chemotherapy in patients with stage III non-small cell lung cancer
    Eschmann, S. M.
    Friedel, G.
    Paulsen, F.
    Reimold, M.
    Hehr, T.
    Budach, W.
    Dittmann, H.
    Langen, H. -J.
    Bares, R.
    LUNG CANCER, 2007, 55 (02) : 165 - 171
  • [35] Prognostic value of metabolic tumor burden on 18F-FDG PET in nonsurgical patients with non-small cell lung cancer
    Liao, Shengri
    Penney, Bill C.
    Wroblewski, Kristen
    Zhang, Hao
    Simon, Cassie A.
    Kampalath, Rony
    Shih, Ming-Chi
    Shimada, Naoko
    Chen, Sheng
    Salgia, Ravi
    Appelbaum, Daniel E.
    Suzuki, Kenji
    Chen, Chin-Tu
    Pu, Yonglin
    EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2012, 39 (01) : 27 - 38
  • [36] Diagnostic value of 18F-FDG PET/CT for lymph node metastasis of esophageal squamous cell carcinoma
    Yamada, Hiroyuki
    Hosokawa, Masao
    Itoh, Kazuo
    Takenouchi, Toshinao
    Kinoshita, Yoshihiro
    Kikkawa, Tomohiro
    Sakashita, Keita
    Uemura, Shion
    Nishida, Yasunori
    Kusumi, Takaya
    Sasaki, Shigeyuki
    SURGERY TODAY, 2014, 44 (07) : 1258 - 1265
  • [37] 18F-FDG avid volumes on pre-radiotherapy FDG PET as boost target delineation in non-small cell lung cancer
    Gao, Ang
    Wang, Shijiang
    Fu, Zheng
    Sun, Xindong
    Yu, Jinming
    Meng, Xue
    INTERNATIONAL JOURNAL OF CLINICAL AND EXPERIMENTAL MEDICINE, 2015, 8 (05): : 7561 - 7568
  • [38] Standardized visual reading of F18-FDG-PET in patients with non-small cell lung cancer scheduled for preoperative thoracic lymph node staging
    Rogasch, Julian M. M.
    Apostolova, Ivayla
    Steffen, Ingo G.
    Steinkrueger, Ferdinand L. G. A.
    Genseke, Philipp
    Riedel, Sandra
    Wertzel, Heinz
    Achenbach, H. Jost
    Kalinski, Thomas
    Schultz, Meinald
    Schreiber, Jens
    Amthauer, Holger
    Furth, Christian
    EUROPEAN JOURNAL OF RADIOLOGY, 2016, 85 (08) : 1345 - 1350
  • [39] Metabolic parameters using 18F-FDG PET/CT correlate with occult lymph node metastasis in squamous cell lung carcinoma
    Kim, Do-Hoon
    Song, Bong-Il
    Hong, Chae Moon
    Jeong, Shin Young
    Lee, Sang-Woo
    Lee, Jaetae
    Ahn, Byeong-Cheol
    EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2014, 41 (11) : 2051 - 2057
  • [40] Chemotherapy response evaluation with 18F-FDG PET in patients with non-small cell lung cancer
    de Geus-Oei, Lioe-Fee
    van der Heijden, Henricus F. M.
    Visser, Eric P.
    Hermsen, Rick
    van Hoorn, Bas A.
    Timmer-Bonte, Johanna N. H.
    Willemsen, Antoon T.
    Pruim, Jan
    Corstens, Frans H. M.
    Krabbe, Paul F. M.
    Oyen, Wim J. G.
    JOURNAL OF NUCLEAR MEDICINE, 2007, 48 (10) : 1592 - 1598