Capsules for biomedical image segmentation

•First ever capsule network for image segmentation.•Reduced memory burden: locally-constrained routing and transformation matrix sharing.•Introduced novel deconvolutional capsules to create encoder-decoder architecture.•Extended the reconstruction regularization to the segmentation task.•Outperforme...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Medical image analysis Ročník 68; s. 101889
Hlavní autoři:	LaLonde, Rodney, Xu, Ziyue, Irmakci, Ismail, Jain, Sanjay, Bagci, Ulas
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Netherlands Elsevier B.V 01.02.2021 Elsevier BV
Témata:	Ablation Capsule network Capsules Coders Computed tomography Datasets Encoders-Decoders Experiments Humans Image processing Image Processing, Computer-Assisted Image reconstruction Image segmentation Lung segmentation Lungs Magnetic Resonance Imaging Medical imaging Muscles Neural Networks, Computer Parameters Pre-clinical imaging Regularization Routing Thigh MRI segmentation Thorax Tomography Tomography, X-Ray Computed Lung segmentation Pre-clinical imaging Capsule network Thigh MRI segmentation
ISSN:	1361-8415, 1361-8423, 1361-8423
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•First ever capsule network for image segmentation.•Reduced memory burden: locally-constrained routing and transformation matrix sharing.•Introduced novel deconvolutional capsules to create encoder-decoder architecture.•Extended the reconstruction regularization to the segmentation task.•Outperformed existing methods across five clinical and preclinical datasets for lung segmentation from CT scans. [Display omitted] Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. This is made possible via the introduction of locally-constrained routing and transformation matrix sharing, which reduces the parameter/memory burden and allows for the segmentation of objects at large resolutions. To compensate for the loss of global information in constraining the routing, we propose the concept of “deconvolutional” capsules to create a deep encoder-decoder style network, called SegCaps. We extend the masked reconstruction regularization to the task of segmentation and perform thorough ablation experiments on each component of our method. The proposed convolutional-deconvolutional capsule network, SegCaps, shows state-of-the-art results while using a fraction of the parameters of popular segmentation networks. To validate our proposed method, we perform experiments segmenting pathological lungs from clinical and pre-clinical thoracic computed tomography (CT) scans and segmenting muscle and adipose (fat) tissue from magnetic resonance imaging (MRI) scans of human subjects’ thighs. Notably, our experiments in lung segmentation represent the largest-scale study in pathological lung segmentation in the literature, where we conduct experiments across five extremely challenging datasets, containing both clinical and pre-clinical subjects, and nearly 2000 computed-tomography scans. Our newly developed segmentation platform outperforms other methods across all datasets while utilizing less than 5% of the parameters in the popular U-Net for biomedical image segmentation. Further, we demonstrate capsules’ ability to generalize to unseen handling of rotations/reflections on natural images.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Authors’ Contributions
ISSN:	1361-8415 1361-8423 1361-8423
DOI:	10.1016/j.media.2020.101889