Distinguishing Lymphomatous and Cancerous Lymph Nodes in 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography by Radiomics Analysis

被引:2
|
作者
Zheng, Bo [1 ]
Wu, Jiayi [2 ]
Zhao, Zixuan [2 ]
Ou, Xuejin [2 ]
Cao, Peng [3 ]
Ma, Xuelei [1 ]
机构
[1] Sichuan Univ, West China Hosp, Dept Biotherapy, Dept Oncol, Chengdu 610041, Peoples R China
[2] Sichuan Univ, West China Sch Med, Chengdu 610041, Peoples R China
[3] Sichuan Univ, West China Hosp, Dept Oncol, Chengdu 610041, Peoples R China
关键词
FINE-NEEDLE-ASPIRATION; CELL LUNG-CANCER; TEXTURE ANALYSIS; HODGKIN-DISEASE; PROSTATE-CANCER; FDG-PET; CT; HETEROGENEITY; METASTASIS; IMAGES;
D O I
10.1155/2020/3959236
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
Background. The National Comprehensive Cancer Network guidelines recommend excisional biopsies for the diagnosis of lymphomas. However, resection biopsies in all patients who are suspected of having malignant lymph nodes may cause unnecessary injury and increase medical costs. We investigated the usefulness of 18F-fluorodeoxyglucose positron emission/computed tomography- (18F-FDG-PET/CT-) based radiomics analysis for differentiating between lymphomatous lymph nodes (LLNs) and cancerous lymph nodes (CLNs). Methods. Using texture analysis, radiomic parameters from the 18F-FDG-PET/CT images of 492 lymph nodes (373 lymphomatous lymph nodes and 119 cancerous lymph nodes) were extracted with the LIFEx package. Predictive models were generated from the six parameters with the largest area under the receiver operating characteristics curve (AUC) in PET or CT images in the training set (70% of the data), using binary logistic regression. These models were applied to the test set to calculate predictive variables, including the combination of PET and CT predictive variables (PREcombination). The AUC, sensitivity, specificity, and accuracy were used to compare the differentiating ability of the predictive variables. Results. Compared with the pathological diagnosis of the patient's primary tumor, the AUC, sensitivity, specificity, and accuracy of PREcombination in differentiating between LLNs and CLNs were 0.95, 91.67%, 94.29%, and 92.96%, respectively. Moreover, PREcombination could effectively distinguish LLNs caused by various lymphoma subtypes (Hodgkin's lymphoma and non-Hodgkin's lymphoma) from CLNs, with the AUC, sensitivity, specificity, and accuracy being 0.85 and 0.90, 77.78% and 77.14%, 97.22% and 88.89%, and 90.74% and 83.10%, respectively. Conclusions. Radiomics analysis of 18F-FDG-PET/CT images may provide a noninvasive, effective method to distinguish LLN and CLN and inform the choice between fine-needle aspiration and excision biopsy for sampling suspected lymphomatous lymph nodes.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] The 18F-fluorodeoxyglucose positron emission tomography/computed tomography in breast cancer
    Mihailovic, Jasna
    Ubavic, Milan
    VOJNOSANITETSKI PREGLED, 2017, 74 (06) : 571 - 580
  • [2] Using 18F-fluorodeoxyglucose positron emission tomography/computed tomography to estimate the length of gross tumor and involvement of lymph nodes in esophagogastric junction carcinoma
    Ma, Chi-Luan
    Li, Xiao-Dong
    Sun, Xiao-Rong
    Zhao, Dong-Bo
    Yuan, Yin-Ping
    Yu, Yong-Hua
    JOURNAL OF CANCER RESEARCH AND THERAPEUTICS, 2018, 14 (04) : 896 - 901
  • [3] Diagnostic performance of unenhanced computed tomography and 18F-fluorodeoxyglucose positron emission tomography in indeterminate adrenal tumours
    Delivanis, Danae A.
    Bancos, Irina
    Atwell, Thomas D.
    Schmit, Grant D.
    Eiken, Patrick W.
    Natt, Neena
    Erickson, Dana
    Maraka, Spyridoula
    Young, William F.
    Nathan, Mark A.
    CLINICAL ENDOCRINOLOGY, 2018, 88 (01) : 30 - 36
  • [4] Clinical applications of 18F-fluorodeoxyglucose positron emission tomography/computed tomography in carcinoma of unknown primary
    Hu Man
    Zhao Wei
    Zhang Pin-liang
    Ju Gui-fang
    Fu Zheng
    Zhang Guo-li
    Kong Li
    Yang Yan-qin
    Ma Yi-dong
    Yu Jin-ming
    CHINESE MEDICAL JOURNAL, 2011, 124 (07) : 1010 - 1014
  • [5] 18F-fluorodeoxyglucose positron emission tomography/computed tomography comparison of gastric lymphoma and gastric carcinoma
    Li, Xiao-Feng
    Fu, Qiang
    Dong, You-Wen
    Liu, Jian-Jing
    Song, Xiu-Yu
    Dai, Dong
    Zuo, Cong
    Xu, Wen-Gui
    WORLD JOURNAL OF GASTROENTEROLOGY, 2016, 22 (34) : 7787 - 7796
  • [6] 18F-fluorodeoxyglucose uptake on positron emission tomography in mucinous adenocarcinoma
    Murakami, Shuji
    Saito, Haruhiro
    Karino, Fumi
    Kondo, Tetsuro
    Oshita, Fumihiro
    Ito, Hiroyuki
    Nakayama, Haruhiko
    Yokose, Tomoyuki
    Yamada, Kouzo
    EUROPEAN JOURNAL OF RADIOLOGY, 2013, 82 (11) : E721 - E725
  • [7] Thoracic positron emission tomography: 18F-fluorodeoxyglucose and beyond
    Jaykel, Timothy J.
    Clark, Michael S.
    Adamo, Daniel A.
    Welch, Brain T.
    Thompson, Scott M.
    Young, Jason R.
    Ehman, Eric C.
    JOURNAL OF THORACIC DISEASE, 2020, 12 (11) : 6978 - 6991
  • [8] Incidental focal colorectal 18F-fluorodeoxyglucose uptake on positron emission tomography/computed tomography
    Cho, Soung Hoon
    Kim, Sang Woo
    Kim, Won Chul
    Park, Jae Myung
    Yoo, Ie Ryung
    Kim, Sung Hoon
    Oh, Seong Taek
    WORLD JOURNAL OF GASTROENTEROLOGY, 2013, 19 (22) : 3453 - 3458
  • [9] Diagnostic performance of 18F-fluorodeoxyglucose positron emission tomography/computed tomography in anorectal melanoma
    Bakare, Ajinkya N.
    Agrawal, Archi
    Saklani, Avanish
    Engineer, Reena
    Purandare, Nilendu
    Shah, Sneha
    Puranik, Ameya
    Rangarajan, Venkatesh
    WORLD JOURNAL OF NUCLEAR MEDICINE, 2021, 20 (03) : 215 - 221
  • [10] Clinical application of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics-based machine learning analyses in the field of oncology
    Nakajo, Masatoyo
    Jinguji, Megumi
    Ito, Soichiro
    Tani, Atushi
    Hirahara, Mitsuho
    Yoshiura, Takashi
    JAPANESE JOURNAL OF RADIOLOGY, 2024, 42 (01) : 28 - 55