eprintid: 10194835 rev_number: 8 eprint_status: archive userid: 699 dir: disk0/10/19/48/35 datestamp: 2024-07-19 07:10:50 lastmod: 2024-07-19 07:11:05 status_changed: 2024-07-19 07:10:50 type: article metadata_visibility: show sword_depositor: 699 creators_name: Huang, Guangyu creators_name: Yan, Yan creators_name: Xue, Jing-Hao creators_name: Zhu, Wentao creators_name: Luo, Xiongbiao title: Interpretable Heterogeneous Teacher-Student Learning Framework for Hybrid-Supervised Pulmonary Nodule Detection ispublished: inpress divisions: UCL divisions: B04 divisions: C06 divisions: F61 keywords: Heatmap learning, Hybrid-supervised learning, Pseudo label generation, pulmonary nodule detection note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Existing pulmonary nodule detection methods often train models in a fully-supervised setting that requires strong labels (i.e., bounding box labels) as label information. However, manual annotation of bounding boxes in CT images is very time-consuming and labor-intensive. To alleviate the annotation burden, in this paper, we investigate pulmonary nodule detection by leveraging both strong labels and weak labels (i.e., center point labels) for training, and propose a novel hybrid-supervised pulmonary nodule detection (HND) method. The training of HND involves a heterogeneous teacher-student learning framework in two stages. In the first stage, we design a point-based consistency calibration network (PCC-Net) as a teacher, which is pre-trained to generate high-quality pseudo bounding box labels given point-augmented CT images as inputs. In the second stage, we develop an information bottleneck-guided pulmonary nodule detection network (IBD-Net) as a student to perform pulmonary nodule detection. In particular, we introduce information bottleneck to learn reliable pulmonary nodule-specific heatmaps under the guidance of PCC-Net, largely enhancing the model’s interpretability and improving the final detection performance. Based on the above designs, our method can effectively detect pulmonary nodule regions with only a limited number of bounding box labels. Experimental results on the public pulmonary nodule detection dataset LUNA16 show that our HND method achieves an excellent balance between the annotation cost and the detection performance. date: 2024-07-15 date_type: published publisher: Institute of Electrical and Electronics Engineers (IEEE) official_url: http://dx.doi.org/10.1109/tcsvt.2024.3427645 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2298146 doi: 10.1109/tcsvt.2024.3427645 lyricists_name: Xue, Jinghao lyricists_id: JXUEX60 actors_name: Xue, Jinghao actors_id: JXUEX60 actors_role: owner full_text_status: public publication: IEEE Transactions on Circuits and Systems for Video Technology pagerange: 1-1 issn: 1051-8215 citation: Huang, Guangyu; Yan, Yan; Xue, Jing-Hao; Zhu, Wentao; Luo, Xiongbiao; (2024) Interpretable Heterogeneous Teacher-Student Learning Framework for Hybrid-Supervised Pulmonary Nodule Detection. IEEE Transactions on Circuits and Systems for Video Technology p. 1. 10.1109/tcsvt.2024.3427645 <https://doi.org/10.1109/tcsvt.2024.3427645>. (In press). Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10194835/1/GuangyuHuang-TCSVT-2024.pdf