ABSTRACT
Lymphoma is a common malignancy that endangers human life and health, and accurate identification of lymphoma from PET/CT images has great value in clinical treatment. Efficient and accurate discrimination of lymphomas is an important and challenging research task. However, deep networks may lose important features such as texture structure of the target while acquiring rich image information and even misclassify small-scale targets. Traditional machine learning methods rely heavily on manually designed features and require the design of reasonable and effective feature combinations. To this end, we propose a new bidirectional feature fusion method with a lymphoma subtype classification model for PET/CT images. Firstly, deep learning latent features and machine learning explicit features of PET/CT images are extracted based on convolutional neural networks and prior knowledge, where the explicit features include distribution features and radiomics features. In the latent features extraction stage, we propose a new feature channel compression method based on squeeze-and-excitation normalization. Then, the latent features and explicit features are effectively fused based on the proposed bidirectional feature selection method. Finally, a classifier is constructed by introducing deep learning and machine learning methods for lymphoma classification. To validate the effectiveness of the model, we designed multiple sets of comparison experiments and ablation experiments to classify lymphoma subtypes, including non-lymphoma, Hodgkin's lymphoma, diffuse large B-cell lymphoma and other non-Hodgkin's lymphoma on the lymphoma dataset. The accuracy and recall of the classification reached 0.831 and 0.819, respectively. To validate the generalization of the model, we set experiments on the lung cancer PET/CT dataset, and our model improved the accuracy of classification by 0.045 compared with the resnet18 network. The experiments show that the proposed method in this paper has better classification on lymphoma dataset and can be applied to other tumors.
- Serfling, S., "Improved cancer detection in Waldeyer's tonsillar ring by 68Ga-FAPI PET/CT imaging." European Journal of Nuclear Medicine and Molecular Imaging 48.4 (2021): 1178-1187.Google ScholarCross Ref
- Meulepas, Johanna M., "Radiation exposure from pediatric CT scans and subsequent cancer risk in the Netherlands." JNCI: Journal of the National Cancer Institute 111.3 (2019): 256-263.Google ScholarCross Ref
- Priya, R. Mohana, and P. Venkatesan. "An efficient image segmentation and classification of lung lesions in pet and CT image fusion using DTWT incorporated SVM." Microprocessors and Microsystems 82 (2021): 103958.Google Scholar
- Evangelista, Laura, "PET/MRI in prostate cancer: a systematic review and meta-analysis." European journal of nuclear medicine and molecular imaging 48.3 (2021): 859-873.Google Scholar
- Alongi, Pierpaolo, "Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: An explorative study on machine learning feature classification in 94 patients." European Radiology 31.7 (2021): 4595-4605.Google ScholarCross Ref
- Zhang, Jianyuan, "Value of pre-therapy 18F-FDG PET/CT radiomics in predicting EGFR mutation status in patients with non-small cell lung cancer." European journal of nuclear medicine and molecular imaging 47.5 (2020): 1137-1146.Google Scholar
- Qin, RuoXi, "Fine-grained lung cancer classification from PET and CT images based on multidimensional attention mechanism." Complexity 2020 (2020).Google Scholar
- Kawauchi, Keisuke, "A convolutional neural network-based system to classify patients using FDG PET/CT examinations." BMC cancer 20.1 (2020): 1-10.Google Scholar
- Apostolopoulos, Ioannis D., "Automatic classification of solitary pulmonary nodules in PET/CT imaging employing transfer learning techniques." Medical & Biological Engineering & Computing 59.6 (2021): 1299-1310.Google ScholarCross Ref
- Nobashi, Tomomi, "Performance comparison of individual and ensemble CNN models for the classification of brain 18F-FDG-PET scans." Journal of Digital Imaging 33.2 (2020): 447-455.Google ScholarCross Ref
- Barrington, Sally F., and Judith Trotman. "The role of PET in the first-line treatment of the most common subtypes of non-Hodgkin lymphoma." The Lancet Haematology 8.1 (2021): e80-e93.Google ScholarCross Ref
- Georgi, Thomas W., "Automatic classification of lymphoma lesions in FDG-PET–Differentiation between tumor and non-tumor uptake." PloS one 17.4 (2022): e0267275.Google ScholarCross Ref
- Lippi, Marco, "Texture analysis and multiple-instance learning for the classification of malignant lymphomas." Computer methods and programs in biomedicine 185 (2020): 105153.Google Scholar
- Chaddad A. Automated feature extraction in brain tumor by magnetic resonance imaging using gaussian mixture models[J]. International Journal of Biomedical Imaging, (2015).Google ScholarDigital Library
- Chaddad A, Zinn P O, Colen R R. Brain tumor identification using Gaussian Mixture Model features and Decision Trees classifier[C]. 2014 48th annual conference on information sciences and systems (CISS). IEEE, 2014: 1-4.Google Scholar
- Iantsen A, Visvikis D, Hatt M. Squeeze-and-excitation normalization for automated delineation of head and neck primary tumors in combined PET and CT images[C]. 3D Head and Neck Tumor Segmentation in PET/CT Challenge. Springer, Cham, 2020: 37-43.Google Scholar
- Kumar R L, Kakarla J, Isunuri B V, Multi-class brain tumor classification using residual network and global average pooling[J]. Multimedia Tools and Applications, 2021, 80(9): 13429-13438.Google ScholarDigital Library
- Gárate-Escamila A K, El Hassani A H, Andrès E. Classification models for heart disease prediction using feature selection and PCA[J]. Informatics in Medicine Unlocked, 2020, 19: 100330.Google ScholarCross Ref
- Kaiming H, Xiangyu Z, Shaoqing R. Jian S, “Deep Residual Learning for Image Recognition” [J]. Computer Vision and Pattern Recognition (CVPR), 2015.Google Scholar
- Khan S H, Sohail A, Khan A, Classification and Region Analysis of COVID-19 Infection using Lung CT Images and Deep Convolutional Neural Networks[J]. Computer Vision and Pattern Recognition, 2020.Google Scholar
- Gao X, Qian Y, Gao A. COVID-VIT: Classification of COVID-19 from CT chest images based on vision transformer models[J]. Computer Vision and Pattern Recognition, 2021.Google Scholar
- Mobiny A, Nguyen H V. Fast CapsNet for Lung Cancer Screening[J]. Computer Vision and Pattern Recognition, 2018.Google ScholarCross Ref
- X. Yao, Z. Zhu, C. Kang, S. -H. Wang, J. M. Gorriz and Y. -D. Zhang, AdaD-FNN for Chest CT-Based COVID-19 Diagnosis[J]. in IEEE Transactions on Emerging Topics in Computational Intelligence, 2022.Google Scholar
Index Terms
Classification of lymphoma subtypes in PET/CT images based on a bidirectional feature fusion method
Recommendations
Variational Bayes Inference Based Segmentation of Heterogeneous Lymphoma Volumes in Dual-Modality PET-CT Images
DICTA '11: Proceedings of the 2011 International Conference on Digital Image Computing: Techniques and ApplicationsAccurate segmentation of heterogeneous carcinoma lesions in medical images is vital to the treatment planning, assessment of therapy response and other oncological applications. With current state-of-the-art imaging modalities, the CT images enhance the ...
Colour Feature Extraction and Polynomial Algorithm for Classification of Lymphoma Images
Progress in Pattern Recognition, Image Analysis, Computer Vision, and ApplicationsAbstractLymphomas are neoplasms that originate in the lymphatic system and represent one of the most common types of cancer found in the World population. The feature analysis may contribute toward results of higher relevance in the classification of the ...
Improved Multi-modal Patch Based Lymphoma Segmentation with Negative Sample Augmentation and Label Guidance on PET/CT Scans
Multiscale Multimodal Medical ImagingAbstractLymphoma is a cancer of the lymphatic system, and it can affect many organs throughout the body. Positron emission tomography (PET)/computed tomography (CT) are primary imaging methods to assess lymphoma types and monitor their treatment, where ...
Comments