Most advances in medical lesion detection network are limited to subtle modification on the conventional detection network designed for natural images. However, there exists a vast domain gap between medical images and natural images where the medical image detection often suffers from several domain-specific challenges, such as high lesion/background similarity, dominant tiny lesions, and severe class imbalance. Is a hand-crafted detection network tailored for natural image undoubtedly good enough over a discrepant medical lesion domain? Is there more powerful operations, filters, and sub-networks that better fit the medical lesion detection problem to be discovered? In this paper, we introduce a novel ElixirNet that includes three components: 1) TruncatedRPN balances positive and negative data for false positive reduction; 2) Auto-lesion Block is automatically customized for medical images to incorporates relation-aware operations among region proposals, and leads to more suitable and efficient classification and localization. 3) Relation transfer module incorporates the semantic relationship and transfers the relevant contextual information with an interpretable graph, thus alleviates the problem of lack of annotations for all types of lesions. Experiments on DeepLesion and Kits19 prove the effectiveness of ElixirNet, achieving improvement of both sensitivity and precision over FPN with fewer parameters.
A flexural support technique for lightweighted Primary Mirror Assembly (PMA) of a space telescope is presented in this article. The proposed three-point flexural mount based on a cartwheel flexure can maintain the surface figure of the PMA in a horizontal optical testing layout. The on-orbit surface error of the PMA causes significant degradation in image quality. On-ground optical testing cannot determine the zero-gravity figure of the PMA due to surface distortion by gravity. We unveiled the crucial fact that through a delicate mounting structure design, the surface figure can remain constant precisely without inducing distinguishable astigmatism when PMA rotates with respect to the optical axis, and the figure can be considered as the zero-gravity surface figure on the orbit. A design case is described to show the lightweight design of a SiC mirror and the optimal flexural mounting. Topology optimization and integrated opto-mechanical analysis using the finite element method are utilized in the design process. The Primary Mirror and mounting structures were fabricated and assembled. After the PMA mirror surface was polished to λ/50 RMS, optical testing in different clocking configurations was performed, respectively, through rotating the PMA by multiple angles. Test results show that the surface figure remained invariant, indicating that gravity release on the orbit will not cause an additional surface error. Vibration tests including sweep sine and random vibration were also performed to validate the mechanical design. The requirements for the mounting technique in space were qualified.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.