25 research outputs found
Doctor Imitator: Hand-Radiography-based Bone Age Assessment by Imitating Scoring Methods
No full textBone age assessment is challenging in clinical practice due to the
complicated bone age assessment process. Current automatic bone age assessment
methods were designed with rare consideration of the diagnostic logistics and
thus may yield certain uninterpretable hidden states and outputs. Consequently,
doctors can find it hard to cooperate with such models harmoniously because it
is difficult to check the correctness of the model predictions. In this work,
we propose a new graph-based deep learning framework for bone age assessment
with hand radiographs, called Doctor Imitator (DI). The architecture of DI is
designed to learn the diagnostic logistics of doctors using the scoring methods
(e.g., the Tanner-Whitehouse method) for bone age assessment. Specifically, the
convolutions of DI capture the local features of the anatomical regions of
interest (ROIs) on hand radiographs and predict the ROI scores by our proposed
Anatomy-based Group Convolution, summing up for bone age prediction. Besides,
we develop a novel Dual Graph-based Attention module to compute
patient-specific attention for ROI features and context attention for ROI
scores. As far as we know, DI is the first automatic bone age assessment
framework following the scoring methods without fully supervised hand
radiographs. Experiments on hand radiographs with only bone age supervision
verify that DI can achieve excellent performance with sparse parameters and
provide more interpretability.Comment: Original Title: "Doctor Imitator: A Graph-based Bone Age Assessment
Framework Using Hand Radiographs" @inproceedings{chen2020doctor,
title={Doctor imitator: A graph-based bone age assessment framework using
hand radiographs}, author={Chen, Jintai and Yu, Bohan and Lei, Biwen and
Feng, Ruiwei and Chen, Danny Z and Wu, Jian}, booktitle={MICCAI}, year={2020}
Experimental determination on the critical angle of seismic incidence of curved bridge
No full textThe shaking table model test mainly focuses on the study of seismic response law, aseismic performance and seismic damping and isolation effect of bridges with a single or multi-platform shaking table. Basically, the plane principal axis direction is adopted for the seismic input of structural models. Little research effort considering multi-angle seismic input has been reported in the structural model test. In this paper we designed and conducted a small-scale shaking table model test to study the seismic response law of the curved girder bridges with seismic input at different angles, and provided experimental verification for the theoretical method of the most unfavorable angle of seismic input. The experimental results show that the variation trend of component response to variation of the seismic input direction is consistent with that of the numerical analysis, which indicates that the designed device is effective
Typical Earthquake Damage and Seismic Isolation Technology for Bridges Subjected to Near-Fault Ground Motions
No full textDevelopment and Application of Thought of Balance between Force and Displacement in Seismic Isolation Design of Bridges Subjected to Near-Fault Ground Motions
No full textLong-term statin use before primary percutaneous coronary intervention improves treatment outcomes of acute myocardial infarction
No full textImpact of seismic excitation direction on the fragility analysis of horizontally curved concrete bridges
No full text
