ABSTRACT
Accurate lymph node detection based on CT images is an important pre-step in Lymphadenectomy, which is crucial for the subsequent treatment of patients. However, many interfering factors such as organs, tissues, and blood vessels in CT images lead a large number of false positive objects with the existing detection methods, which hinders the clinical application. In this study, we propose an effective and fast 2.5D framework algorithm for false positive reduction (FPR). Specifically, considering the globular shape of the lymph nodes, the axial, coronal and sagittal slices from CT data of lymph nodes are used as 2.5D inputs to the network to mine the three-dimensional spatial information of lymph nodes. In addition, multi-scale inputs are used to address the challenges posed by changes in the volume of the lymph nodes, and use stacking learning to fuse the results of models at various scales. Compared to 3D networks, it greatly decreases computational costs and running time. Based on the public dataset, we add 20 additional cases of CT data to construct a new dataset CTLymph for FPR. The proposed method achieves an AUC of 0.941, reducing the number of false positive lymph nodes from 25 to 4. The result shows that our proposed model achieves superior performance and outperforms several state-of-the-art methods.
- Einstein, D.M., Singer, A.A., Chilcote, W.A., and Desai, R.K., ”Abdominal lymphadenopathy: spectrum of CT findings,” Radiographics 11(3), 457-472 (1991).Google ScholarCross Ref
- Eisenhauer, E., Therasse, P., Bogaerts, J., Schwartz, L., Sargent, D., Ford, R., Dancey, J., Arbuck, S., Gwyther, S., and Mooney, M., ”New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1),”European Journal of Cancer 45(2), 228-247 (2009).Google ScholarCross Ref
- Nakamura Yoshihiko ”Investigation of optimal feature value set in false positive reduction process for automated ab-dominal lymph node detection method”. 9414(2015): 94143N-94143N-7.Google Scholar
- Lin L , Tan Y , Schwartz L H , Hybrid detection of lung nodules on CT scan images[J]. Medical Physics, 2015, 42(9).Google Scholar
- Hyunjun Eun ”Single-view 2D CNNs with fully automatic nonnodule categorization for false positive reduction in pulmo-nary nodule detection”. Computer Methods and Programs in Biomedicine 165(2018): 215-224.Google ScholarCross Ref
- Bum-Chae Kim ”Multi-scale gradual integration CNN for false positive reduction in pulmonary nodule detection”. Neural Networks 115(2019): 1-10.Google ScholarDigital Library
- Roth H R, Lu L, Seff A, A new 2.5 D representation for lymph node detection using random sets of deep convolutional neural network observations[C]. International conference on medical image computing and computer-assisted intervention. Springer, Cham, 2014: 520-527.Google Scholar
- Z. Pan , ”Multi-context 3D Resnet for Small-size False Positive Reduction in Pelvic Lymph Node Detection,” 2021 IEEE International Conference on Bio-informatics and Biomedicine (BIBM), 2021, pp. 1773-1780, doi: 10.1109/BIBM52615.2021.9669701.Google ScholarCross Ref
- Jin Hongsheng ”A deep 3D residual CNN for false-positive reduction in pulmonary nodule detection.”. Medical physics 45.5(2018):2097-2107.Google Scholar
- K. He, X. Zhang, S. Ren and J. Sun, ”Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 9, pp. 19041916, 1 Sept. 2015, doi: 10.1109/TPAMI.2015.2389824.Google ScholarDigital Library
- Cherry K M, Wang S, Turkbey E B, Abdominal lymphade-nopathy detection using random forest[C]. Medical Imaging 2014: ComputerAided Diagnosis. International Society for Otics and Photonics, 2014, 9035: 90351G.Google Scholar
- Liu J, Zhao J, Hoffman J, Mediastinal lymph node detection on thoracic CT scans using spatial prior from multi-atlas label fusion[C]. Medical Imaging 2014: Computer-Aided Diagnosis. International Society for Optics and Photonics, 2014, 9035: 90350M.Google Scholar
- R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh and D. Batra, ”Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 618-626, doi: 10.1109/ICCV.2017.74.Google ScholarCross Ref
- Zuo, Wangxia “An Embedded Multi-branch 3D Convolution Neural Network for False Positive Reduction in Lung Nodule Detection.” Journal of digital imaging vol. 33,4 (2020): 846-857.Google ScholarCross Ref
- Meng X, Peng Y, Guo Y. An adaptive multi-scale network with nonorthogonal multi-union input for reducing false positive of lymph nodes[J]. Biocybernetics and Biomedical Engineering, 2021, 41(1): 265277.Google ScholarCross Ref
- K. He, X. Zhang, S. Ren and J. Sun, ”Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.Google ScholarCross Ref
- Liu Jianfang ”Improving CT detection sensitivity for nodal metastases in oesophageal cancer with combination of smaller size and lymph node axial ratio.”. European radiology 28.1(2018): 188-195.Google Scholar
- Haixin Peng and Yinjun Peng. ”Spatio-temporal context based recurrent visual attention model for lymph node detection”. International Journal of Im-aging Systems and Technology 30.4(2020): 1220-1242.Google ScholarCross Ref
Index Terms
- Multi-scale 2.5D Integrated Model for False Positive Reduction in Abdominal Lymph Node Detection
Recommendations
A 3D Multi-scale Virtual Adversarial Network for False Positive Reduction in Pulmonary Nodule Detection
ICIAI '19: Proceedings of the 2019 3rd International Conference on Innovation in Artificial IntelligenceLung cancer is a high-mortality disease. Using Computer-based Automatic Detection (CADe) systems can detect pulmonary nodules to assist early diagnosis. An effective CADe system based on deep learning is often trained with sufficient labeled samples. ...
An intelligent system of pelvic lymph node detection
AbstractComputed tomography (CT) scanning is a fast and painless procedure that can capture clear imaging information beneath the abdomen and is widely used to help diagnose and monitor disease progress. The pelvic lymph node is a key indicator of ...
An end-to-end framework for pulmonary nodule detection and false positive reduction from CT Images
ISICDM 2020: The Fourth International Symposium on Image Computing and Digital MedicineThe automatic pulmonary nodule detection in thoracic computed tomography (CT) scans plays a crucial role in the early diagnosis of lung cancer. The automated lung nodule detection is challenging due to the high variance in appearance and shape of the ...
Comments