Dense regression activation maps for lesion segmentation in CT scans of COVID-19 patients

• Published in: Medical image analysis Vol. 86; p. 102771
• Main Authors: Xie, Weiyi, Jacobs, Colin, Charbonnier, Jean-Paul, van Ginneken, Bram
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.05.2023
• Subjects: Algorithms; Class activation map; Computed tomography; COVID-19; COVID-19 - diagnostic imaging; Dense regression activation map; Humans; Image Processing, Computer-Assisted - methods; Medical imaging; Neural Networks, Computer; Tomography, X-Ray Computed - methods; Weakly-supervised semantic segmentation; COVID-19; Medical imaging; Computed tomography; Dense regression activation map; Weakly-supervised semantic segmentation; Class activation map
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2023.102771

Automatic lesion segmentation on thoracic CT enables rapid quantitative analysis of lung involvement in COVID-19 infections. However, obtaining a large amount of voxel-level annotations for training segmentation networks is prohibitively expensive. Therefore, we propose a weakly-supervised segmentation method based on dense regression activation maps (dRAMs). Most weakly-supervised segmentation approaches exploit class activation maps (CAMs) to localize objects. However, because CAMs were trained for classification, they do not align precisely with the object segmentations. Instead, we produce high-resolution activation maps using dense features from a segmentation network that was trained to estimate a per-lobe lesion percentage. In this way, the network can exploit knowledge regarding the required lesion volume. In addition, we propose an attention neural network module to refine dRAMs, optimized together with the main regression task. We evaluated our algorithm on 90 subjects. Results show our method achieved 70.2% Dice coefficient, substantially outperforming the CAM-based baseline at 48.6%. We published our source code at https://github.com/DIAGNijmegen/bodyct-dram. •We propose a weakly-supervised segmentation method based on regression training.•Our framework produces high-resolution segmentation maps.•We study the difference between class and regression activation maps.