Early Detection of Residual/Recurrent Lung Malignancies on Post-Radiation FDG PET/CT

被引:0
作者
Chen, Liyuan [1 ]
Lowe, Avanka [2 ]
Wang, Jing [1 ]
机构
[1] Univ Texas Southwestern Med Ctr, Dept Radiat Oncol, 2280 Inwood Rd, Dallas, TX 75235 USA
[2] Univ Arizona, Tucson & Banner Univ Med Ctr, Dept Med Imaging, Coll Med, 1501 N Cambell Ave, Tucson, AZ 85724 USA
关键词
PET/CT; lung malignancies detection; CNN; radiomics; evidential reasoning; RADIATION-THERAPY; CANCER; RADIOTHERAPY;
D O I
10.3390/a17100435
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Positron Emission Tomography/Computed Tomography (PET/CT) using Fluorodeoxyglucose (FDG) is an important imaging modality for assessing treatment outcomes in patients with pulmonary malignant neoplasms undergoing radiation therapy. However, distinguishing between benign post-radiation changes and residual or recurrent malignancies on PET/CT images is challenging. Leveraging the potential of artificial intelligence (AI), we aimed to develop a hybrid fusion model integrating radiomics and Convolutional Neural Network (CNN) architectures to improve differentiation between benign post-radiation changes and residual or recurrent malignancies on PET/CT images. We retrospectively collected post-radiation PET/CTs with identified labels for benign changes or residual/recurrent malignant lesions from 95 lung cancer patients who received radiation therapy. Firstly, we developed separate radiomics and CNN models using handcrafted and self-learning features, respectively. Then, to build a more reliable model, we fused the probabilities from the two models through an evidential reasoning approach to derive the final prediction probability. Five-folder cross-validation was performed to evaluate the proposed radiomics, CNN, and fusion models. Overall, the hybrid fusion model outperformed the other two models in terms of sensitivity, specificity, accuracy, and the area under the curve (AUC) with values of 0.67, 0.72, 0.69, and 0.72, respectively. Evaluation results on the three AI models we developed suggest that handcrafted features and learned features may provide complementary information for residual or recurrent malignancy identification in PET/CT.
引用
收藏
页数:12
相关论文
共 24 条
  • [1] TEXTURAL FEATURES CORRESPONDING TO TEXTURAL PROPERTIES
    AMADASUN, M
    KING, R
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1989, 19 (05): : 1264 - 1274
  • [2] PET/CT Radiomics in Lung Cancer: An Overview
    Bianconi, Francesco
    Palumbo, Isabella
    Spanu, Angela
    Nuvoli, Susanna
    Fravolini, Mario Luca
    Palumbo, Barbara
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (05):
  • [3] PET/CT reading for relapse in non-small cell lung cancer after chemoradiotherapy in the PET-Plan trial cohort
    Brose, Alexander
    Michalski, Kerstin
    Ruf, Juri
    Tosch, Marco
    Eschmann, Susanne M.
    Schreckenberger, Mathias
    Koenig, Jochem
    Nestle, Ursula
    Miederer, Matthias
    [J]. CANCER IMAGING, 2023, 23 (01)
  • [4] Changing profiles of cancer burden worldwide and in China: a secondary analysis of the global cancer statistics 2020
    Cao, Wei
    Chen, Hong-Da
    Yu, Yi-Wen
    Li, Ni
    Chen, Wan-Qing
    [J]. CHINESE MEDICAL JOURNAL, 2021, 134 (07) : 783 - 791
  • [5] RADIATION SENSITIVITY OF HUMAN-LUNG CANCER CELL-LINES
    CARMICHAEL, J
    DEGRAFF, WG
    GAMSON, J
    RUSSO, D
    GAZDAR, AF
    LEVITT, ML
    MINNA, JD
    MITCHELL, JB
    [J]. EUROPEAN JOURNAL OF CANCER & CLINICAL ONCOLOGY, 1989, 25 (03): : 527 - 534
  • [6] Attention Guided Lymph Node Malignancy Prediction in Head and Neck Cancer
    Chen, Liyuan
    Dohopolski, Michael
    Zhou, Zhiguo
    Wang, Kai
    Wang, Rongfang
    Sher, David
    Wang, Jing
    [J]. INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 2021, 110 (04): : 1171 - 1179
  • [7] Combining many-objective radiomics and 3D convolutional neural network through evidential reasoning to predict lymph node metastasis in head and neck cancer
    Chen, Liyuan
    Zhou, Zhiguo
    Sher, David
    Zhang, Qiongwen
    Shah, Jennifer
    Nhat-Long Pham
    Jiang, Steve
    Wang, Jing
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2019, 64 (07)
  • [8] Accurate segmenting of cervical tumors in PET imaging based on similarity between adjacent slices
    Chen, Liyuan
    Shen, Chenyang
    Zhou, Zhiguo
    Maquilan, Genevieve
    Thomas, Kimberly
    Folkert, Michael R.
    Albuquerque, Kevin
    Wang, Jing
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2018, 97 : 30 - 36
  • [9] Use of PET to monitor the response of lung cancer to radiation treatment
    Erdi, YE
    Macapinlac, H
    Rosenzweig, KE
    Humm, JL
    Larson, SM
    Erdi, AK
    Yorke, ED
    [J]. EUROPEAN JOURNAL OF NUCLEAR MEDICINE, 2000, 27 (07) : 861 - 866
  • [10] The predictive value of [18F]FDG PET/CT radiomics combined with clinical features for EGFR mutation status in different clinical staging of lung adenocarcinoma
    Gao, Jianxiong
    Niu, Rong
    Shi, Yunmei
    Shao, Xiaoliang
    Jiang, Zhenxing
    Ge, Xinyu
    Wang, Yuetao
    Shao, Xiaonan
    [J]. EJNMMI RESEARCH, 2023, 13 (01)