arXiv subjects

Kaiyang Cheng

Publications and source records attributed to Kaiyang Cheng.

3 recordsLinked to original sources

arXiv2021

Adversarial Robust Training of Deep Learning MRI Reconstruction Models

Deep Learning (DL) has shown potential in accelerating Magnetic Resonance Image acquisition and reconstruction. Nevertheless, there is a dearth of tailored methods to guarantee that the reconstruction of small features is achieved with high fidelity. In this work, we employ adversarial attacks to generate small synthetic perturbations, which are difficult to reconstruct for a trained DL reconstruction network. Then, we use robust training to increase the network's sensitivity to these small features and encourage their reconstruction. Next, we investigate the generalization of said approach to real world features. For this, a musculoskeletal radiologist annotated a set of cartilage and meniscal lesions from the knee Fast-MRI dataset, and a classification network was devised to assess the reconstruction of the features. Experimental results show that by introducing robust training to a reconstruction network, the rate of false negative features (4.8\%) in image reconstruction can be reduced. These results are encouraging, and highlight the necessity for attention to this problem by the image reconstruction community, as a milestone for the introduction of DL reconstruction in clinical practice. To support further research, we make our annotations and code publicly available at https://github.com/fcaliva/fastMRI_BB_abnormalities_annotation.

eess.IV↗

arXiv2019

Adversarial Policy Gradient for Deep Learning Image Augmentation

The use of semantic segmentation for masking and cropping input images has proven to be a significant aid in medical imaging classification tasks by decreasing the noise and variance of the training dataset. However, implementing this approach with classical methods is challenging: the cost of obtaining a dense segmentation is high, and the precise input area that is most crucial to the classification task is difficult to determine a-priori. We propose a novel joint-training deep reinforcement learning framework for image augmentation. A segmentation network, weakly supervised with policy gradient optimization, acts as an agent, and outputs masks as actions given samples as states, with the goal of maximizing reward signals from the classification network. In this way, the segmentation network learns to mask unimportant imaging features. Our method, Adversarial Policy Gradient Augmentation (APGA), shows promising results on Stanford's MURA dataset and on a hip fracture classification task with an increase in global accuracy of up to 7.33% and improved performance over baseline methods in 9/10 tasks evaluated. We discuss the broad applicability of our joint training strategy to a variety of medical imaging tasks.

cs.CV↗

arXiv2017

Implementing Quantum Search Algorithm with Metamaterials

Metamaterials, artificially structured electromagnetic (EM) materials, have enabled the realization of many unconventional electromagnetic properties not found in nature, such as negative refractive index, magnetic response, invisibility cloaking and so on. Based on these man-made materials with novel EM properties, various devices have been designed and realized. However, quantum analog devices based on metamaterials have not been achieved so far. Here we designed and printed metamaterials to perform quantum search algorithm. The structures, comprising of an array of two-dimensional (2D) sub-wavelength air holes with different radii perforated on the dielectric layer, have been fabricated by using 3D printing technique. When an incident wave enters in the designed metamaterials, the profile of beam wavefront is processed iteratively as it propagates through the metamaterial periodically. After roundtrips, precisely the same as the efficiency of quantum search algorithm, searched items will be found with the incident wave all focusing on the marked positions. Such a metamaterial-based quantum searching simulator may lead to remarkable achievements in wave-based signal processors.

physics.optics↗