Hong-Yu Zhou

Prof. Dr. Hong-Yu Zhou


Research Focus & Metrics

Academic Career Length

35Years (1992-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 July 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
HZHong-Yu Zhou
Hong-Yu Zhou
JGJiansen Guo
Jiansen Guo
YZYinghao Zhang
Yinghao Zhang
XHXiaoguang Han
Xiaoguang Han
LYLequan Yu
Lequan Yu
YYYizhou Yu
Yizhou Yu
Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional neural networks to learn more contextualized visual representations. However, most of recently proposed transformer-based segmentation approaches simply treated transformers as assisted modules to help encode global context into convolutional representations. To address this issue, we introduce nnFormer (i.e., not-another transFormer), a 3D transformer for volumetric medical image segmentation. nnFormer not only exploits the combination of interleaved convolution and self-attention operations, but also introduces local and global volume-based self-attention mechanism to learn volume representations. Moreover, nnFormer proposes to use skip attention to replace the traditional concatenation/summation operations in skip connections in U-Net like architecture. Experiments show that nnFormer significantly outperforms previous transformer-based counterparts by large margins on three public datasets. Compared to nnUNet, the most widely recognized convnet-based 3D medical segmentation model, nnFormer produces significantly lower HD95 and is much more computationally efficient. Furthermore, we show that nnFormer and nnUNet are highly complementary to each other in model ensembling. Codes and models of nnFormer are available at https://git.io/JSf3i.

3 October 2024
Verified
Book Chapter
Closed access
PDF file
JLJiarun Liu
Jiarun Liu
HYHao Yang
Hao Yang
HZHong-Yu Zhou
Hong-Yu Zhou
YXYan Xi
Yan Xi
LYLequan Yu
Lequan Yu
SWShanshan Wang
Shanshan Wang

12 June 2023 in Nature Biomedical Engineering
Verified
Journal Article
Open access
PDF file
HZHong-Yu Zhou
Hong-Yu Zhou
YYYizhou Yu
Yizhou Yu
CWChengdi Wang
Chengdi Wang
SZShu Zhang
Shu Zhang
YGYuanxu Gao
Yuanxu Gao
WLWeimin Li
Weimin Li
During the diagnostic process, clinicians leverage multimodal information, such as the chief complaint, medical images and laboratory test results. Deep-learning models for aiding diagnosis have yet to meet this requirement of leveraging multimodal information. Here we report a transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. Rather than learning modality-specific features, the model leverages embedding layers to convert images and unstructured and structured text into visual tokens and text tokens, and uses bidirectional blocks with intramodal and intermodal attention to learn holistic representations of radiographs, the unstructured chief complaint and clinical history, and structured clinical information such as laboratory test results and patient demographic information. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary disease (by 12% and 9%, respectively) and in the prediction of adverse clinical outcomes in patients with COVID-19 (by 29% and 7%, respectively). Unified multimodal transformer-based models may help streamline the triaging of patients and facilitate the clinical decision-making process.

1 October 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
JLJian-Hao Luo
Jian-Hao Luo
HZHao Zhang
Hao Zhang
HZHong-Yu Zhou
Hong-Yu Zhou
CXChen-Wei Xie
Chen-Wei Xie
JWJianxin Wu
Jianxin Wu
WLWeiyao Lin
Weiyao Lin
This paper aims at accelerating and compressing deep neural networks to deploy CNN models into small devices like mobile phones or embedded gadgets. We focus on filter level pruning, i.e., the whole filter will be discarded if it is less important. An effective and unified framework, ThiNet (stands for "Thin Net"), is proposed in this paper. We formally establish filter pruning as an optimization problem, and reveal that we need to prune filters based on statistics computed from its next layer, not the current layer, which differentiates ThiNet from existing methods. We also propose "gcos" (Group COnvolution with Shuffling), a more accurate group convolution scheme, to further reduce the pruned model size. Experimental results demonstrate the effectiveness of our method, which has advanced the state-of-the-art. Moreover, we show that the original VGG-16 model can be compressed into a very small model (ThiNet-Tiny) with only 2.66MB model size, but still preserve AlexNet level accuracy. This small model is evaluated on several benchmarks with different vision tasks (e.g., classification, detection, segmentation), and shows excellent generalization ability.

2 January 2025 in Nature Medicine
Verified
Journal Article
Closed access
PDF file
SJShreya Johri
Shreya Johri
JJJaehwan Jeong
Jaehwan Jeong
BTBenjamin A. Tran
Benjamin A. Tran
DSDaniel I. Schlessinger
Daniel I. Schlessinger
SWShannon Wongvibulsin
Shannon Wongvibulsin
PRPranav Rajpurkar
Pranav Rajpurkar

19 August 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CCChaoqi Chen
Chaoqi Chen
YWYushuang Wu
Yushuang Wu
QDQiyuan Dai
Qiyuan Dai
HZHong-Yu Zhou
Hong-Yu Zhou
MXMutian Xu
Mutian Xu
YYYizhou Yu
Yizhou Yu
Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (e.g., social network analysis and recommender systems), computer vision (e.g., object detection and point cloud learning), and natural language processing (e.g., relation extraction and sequence learning), to name a few. With the emergence of Transformers in natural language processing and computer vision, graph Transformers embed a graph structure into the Transformer architecture to overcome the limitations of local neighborhood aggregation while avoiding strict structural inductive biases. In this paper, we present a comprehensive review of GNNs and graph Transformers in computer vision from a task-oriented perspective. Specifically, we divide their applications in computer vision into five categories according to the modality of input data, i.e., 2D natural images, videos, 3D data, vision + language, and medical images. In each category, we further divide the applications according to a set of vision tasks. Such a task-oriented taxonomy allows us to examine how each task is tackled by different GNN-based approaches and how well these approaches perform. Based on the necessary preliminaries, we provide the definitions and challenges of the tasks, in-depth coverage of the representative approaches, as well as discussions regarding insights, limitations, and future directions.