Image Projection Network: 3D to 2D Image Segmentation in OCTA Images

• Published in: IEEE transactions on medical imaging Vol. 39; no. 11; pp. 3343 - 3354
• Main Authors: Li, Mingchao, Chen, Yerui, Ji, Zexuan, Xie, Keren, Yuan, Songtao, Chen, Qiang, Li, Shuo
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 3D to 2D; Angiography; Biomedical imaging; biomedical volumetric image segmentation; Blood vessels; End to end; Image processing; image projection network; Image segmentation; optical coherence tomography angiography; Projection; Retina; Retinal images; Retinal vessels; Semantics; Three-dimensional displays; Two dimensional displays

We present an image projection network (IPN), which is a novel end-to-end architecture and can achieve 3D-to-2D image segmentation in optical coherence tomography angiography (OCTA) images. Our key insight is to build a projection learning module (PLM) which uses a unidirectional pooling layer to co...