no code implementations • 8 Mar 2024 • Zikang Xu, Fenghe Tang, Quan Quan, Qingsong Yao, S. Kevin Zhou
Ensuring fairness in deep-learning-based segmentors is crucial for health equity.
1 code implementation • 27 Feb 2024 • Haoran Lai, Qingsong Yao, Zihang Jiang, Rongsheng Wang, ZhiYang He, Xiaodong Tao, S. Kevin Zhou
The advancement of Zero-Shot Learning in the medical domain has been driven forward by using pre-trained models on large-scale image-text pairs, focusing on image-text alignment.
1 code implementation • 20 Dec 2023 • Rongsheng Wang, Qingsong Yao, Haoran Lai, ZhiYang He, Xiaodong Tao, Zihang Jiang, S. Kevin Zhou
Despite significant advancements in medical vision-language pre-training, existing methods have largely overlooked the inherent entity-specific context within radiology reports and the complex cross-modality contextual relationships between text and images.
1 code implementation • 4 Dec 2023 • Qingsong Yao, Zecheng He, Yuexiang Li, Yi Lin, Kai Ma, Yefeng Zheng, S. Kevin Zhou
Interestingly, this vulnerability is a double-edged sword, which can be exploited to hide AEs.
1 code implementation • 29 Nov 2023 • Haoran Lai, Qingsong Yao, ZhiYang He, Xiaodong Tao, S Kevin Zhou
This work establishes a foundation for robust CAD methods, achieving a balance in identifying a spectrum of thoracic diseases in CXRs.
no code implementations • 13 Sep 2023 • Qingsong Yao
My proposed algorithm essentially generalizes MBGD algorithm to the semiparametric setup.
1 code implementation • 13 Jun 2023 • Heqin Zhu, Quan Quan, Qingsong Yao, Zaiyi Liu, S. Kevin Zhou
However, existing one-shot learning methods are highly specialized in a single domain and suffer domain preference heavily in the situation of multi-domain unlabeled data.
no code implementations • 8 Jun 2023 • Quan Quan, Shang Zhao, Qingsong Yao, Heqin Zhu, S. Kevin Zhou
The augmentation parameters matter to few-shot semantic segmentation since they directly affect the training outcome by feeding the networks with varying perturbated samples.
1 code implementation • 15 Mar 2023 • Zikang Xu, Shang Zhao, Quan Quan, Qingsong Yao, S. Kevin Zhou
Deep learning is becoming increasingly ubiquitous in medical research and applications while involving sensitive information and even critical diagnosis decisions.
no code implementations • 14 Nov 2022 • Quan Quan, Qingsong Yao, Jun Li, S. Kevin Zhou
To the best of our knowledge, we are the first to propose a pixel augmentation method with a pixel granularity for enhancing unsupervised pixel-wise contrastive learning.
no code implementations • 27 Sep 2022 • Zikang Xu, Jun Li, Qingsong Yao, Han Li, S. Kevin Zhou
Machine learning-enabled medical imaging analysis has become a vital part of the automatic diagnosis system.
no code implementations • 12 Mar 2022 • Heqin Zhu, Qingsong Yao, S. Kevin Zhou
In this work, we propose a universal model for multi-domain landmark detection by taking advantage of transformer for modeling long dependencies and develop a domain-adaptive transformer model, named as DATR, which is trained on multiple mixed datasets from different anatomies and capable of detecting landmarks of any image from those anatomies.
no code implementations • 5 Mar 2022 • Yihua Sun, Qingsong Yao, Yuanyuan Lyu, Jianji Wang, Yi Xiao, Hongen Liao, S. Kevin Zhou
Digital chest tomosynthesis (DCT) is a technique to produce sectional 3D images of a human chest for pulmonary disease screening, with 2D X-ray projections taken within an extremely limited range of angles.
no code implementations • 3 Mar 2022 • Qingsong Yao, Jianji Wang, Yihua Sun, Quan Quan, Heqin Zhu, S. Kevin Zhou
Contrastive learning based methods such as cascade comparing to detect (CC2D) have shown great potential for one-shot medical landmark detection.
no code implementations • CVPR 2022 • Quan Quan, Qingsong Yao, Jun Li, S. Kevin Zhou
We herein propose a novel Sample Choosing Policy (SCP) to select "the most worthy" images for annotation, in the context of few-shot medical landmark detection.
no code implementations • 22 Nov 2021 • Qingsong Yao, Zecheng He, S. Kevin Zhou
To the best of our knowledge, Medical Aegis is the first defense in the literature that successfully addresses the strong adaptive adversarial example attacks to medical images.
no code implementations • 8 Oct 2021 • Shakeeb Khan, Xiaoying Lan, Elie Tamer, Qingsong Yao
For such monotone index models with increasing dimension, we propose to use a new class of estimators based on batched gradient descent (BGD) involving nonparametric methods such as kernel estimation or sieve estimation, and study their asymptotic properties.
2 code implementations • 8 Mar 2021 • Heqin Zhu, Qingsong Yao, Li Xiao, S. Kevin Zhou
However, all of those methods are unary in the sense that a highly specialized network is trained for a single task say associated with a particular anatomical region.
2 code implementations • 8 Mar 2021 • Qingsong Yao, Quan Quan, Li Xiao, S. Kevin Zhou
The success of deep learning methods relies on the availability of a large number of datasets with annotations; however, curating such datasets is burdensome, especially for medical images.
1 code implementation • 17 Dec 2020 • Qingsong Yao, Zecheng He, Yi Lin, Kai Ma, Yefeng Zheng, S. Kevin Zhou
Deep neural networks (DNNs) for medical images are extremely vulnerable to adversarial examples (AEs), which poses security concerns on clinical decision making.
no code implementations • 8 Sep 2020 • Qingsong Yao, Li Xiao, Peihang Liu, S. Kevin Zhou
Scarcity of annotated images hampers the building of automated solution for reliable COVID-19 diagnosis and evaluation from CT. To alleviate the burden of data annotation, we herein present a label-free approach for segmenting COVID-19 lesions in CT via pixel-level anomaly modeling that mines out the relevant knowledge from normal CT lung scans.
1 code implementation • 10 Jul 2020 • Qingsong Yao, Zecheng He, Hu Han, S. Kevin Zhou
A comprehensive evaluation on a public dataset for cephalometric landmark detection demonstrates that the adversarial examples generated by ATI-FGSM break the CNN-based network more effectively and efficiently, compared with the original Iterative FGSM attack.
1 code implementation • 4 Sep 2019 • Chao Huang, Hu Han, Qingsong Yao, Shankuan Zhu, S. Kevin Zhou
Instead of a collection of multiple models, it is highly desirable to learn a universal data representation for different tasks, ideally a single model with the addition of a minimal number of parameters steered to each task.