Diffuse large B‐cell lymphoma segmentation in PET‐CT images via hybrid learning for feature fusion. Issue 7 (22nd June 2021)

• Record Type: Journal Article
• Authors: Yuan, Cheng; Zhang, Miao; Huang, Xinyun; Xie, Wei; Lin, Xiaozhu; Zhao, Weili; Li, Biao; Qian, Dahong
• Is Part Of: Medical physics. Volume 48:Issue 7(2021)
• Page Start: 3665
• Page End: 3678
• Publication Date: 2021-06-22
• Subjects: feature‐level fusion -- lymphoma segmentation -- multimodality imaging -- spatial convolution; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1002/mp.14847
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: Diffuse large B‐cell lymphoma (DLBCL) is an aggressive type of lymphoma with high mortality and poor prognosis that especially has a high incidence in Asia. Accurate segmentation of DLBCL lesions is crucial for clinical radiation therapy. However, manual delineation of DLBCL lesions is tedious and time‐consuming. Automatic segmentation provides an alternative solution but is difficult for diffuse lesions without the sufficient utilization of multimodality information. Our work is the first study focusing on positron emission tomography and computed tomography (PET‐CT) feature fusion for the DLBCL segmentation issue. We aim to improve the fusion performance of complementary information contained in PET‐CT imaging with a hybrid learning module in the supervised convolutional neural network. Methods: First, two encoder branches extract single‐modality features, respectively. Next, the hybrid learning component utilizes them to generate spatial fusion maps which can quantify the contribution of complementary information. Such feature fusion maps are then concatenated with specific‐modality (i.e., PET and CT) feature maps to obtain a representation of the final fused feature maps in different scales. Finally, the reconstruction part of our network creates a prediction map of DLBCL lesions by integrating and up‐sampling the final fused feature maps from encoder blocks in different scales. Results: The ability of our method was evaluated to detect foreground and segment lesions in three independent body regions (nasopharynx, chest, and abdomen) of a set of 45 PET‐CT scans. Extensive ablation experiments compared our method to four baseline techniques for multimodality fusion (input‐level (IL) fusion, multichannel (MC) strategy, multibranch (MB) strategy, and quantitative weighting (QW) fusion). The results showed that our method achieved a high detection accuracy (99.63% in the nasopharynx, 99.51% in the chest, and 99.21% in the abdomen) and had the superiority in segmentation performance with the mean dice similarity coefficient (DSC) of 73.03% and the modified Hausdorff distance (MHD) of 4.39 mm, when compared with the baselines (DSC: IL: 53.08%, MC: 63.59%, MB: 69.98%, and QW: 72.19%; MHD: IL: 12.16 mm, MC: 6.46 mm, MB: 4.83 mm, and QW: 4.89 mm). Conclusions: A promising segmentation method has been proposed for the challenging DLBCL lesions in PET‐CT images, which improves the understanding of complementary information by feature fusion and may guide clinical radiotherapy. The statistically significant analysis based on P ‐value calculation has indicated a degree of significant difference between our proposed method and other baselines (almost metrics: P < 0.05). This is a preliminary research using a small sample size, and we will collect data continually to achieve the larger verification study.