Author name cluster

Peng Cao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

1 author row

EAAI Journal 2026 Journal Article

CGMAE: Self-supervised Masked Auto-Encoder with Cross-Graph node alignment for node classification

Ruoxian Song
Peng Cao
Guangqi Wen
Lanting Li
Wei Liang
Weiping Li
Jinzhu Yang
Osmar R. Zaiane

Masked Auto-Encoder (MAE) is widely adopted for node classification by recovering the randomly masked graph structure or node attributes. However, traditional MAE methods face two critical challenges: (1) features learned for reconstruction may not align with the downstream classification task, and (2) masking edges risks distorting inherent semantic relationships, degrading representation quality. To overcome these limitations, we propose a simple yet effective self-supervised M asked A uto- E ncoder with C ross- G raph node alignment (CGMAE) for node classification. It leverages labeled nodes from an auxiliary graph to enhance discriminative feature learning in an unlabeled target graph, bridging the task gap between reconstruction and classification. CGMAE introduces a node-level alignment mechanism to address distribution shifts across graphs. This design jointly learns structural patterns and node attributes through specific encoders, enabling multi-view feature matching to refine node representations. Furthermore, CGMAE innovatively predicts masked target edges using aligned nodes from the auxiliary graph, preserving the semantic relationships during reconstruction. Extensive experiments on six diverse networks (standard, complex, sparse, and large-scale graphs) verify the effectiveness and robustness of the proposed method in self-supervised/unsupervised node classification tasks, with accuracy improvements ranging from 1. 5%/1. 1% to 3. 5%/7. 0% over state-of-the-art methods. Code is available at https: //github. com/songruoxian/CGMAE.

Details DOI

JBHI Journal 2025 Journal Article

An Efficient Transfer Learning With Prompt Learning for Brain Disorders Diagnosis

Liuzeng Zhang
Lanting Li
Peng Cao
Jinzhu Yang
Osmar R. Zaiane
Fei Wang

The limited availability of training data significantly restricts the performance of deep supervised models for brain disease diagnosis. It is crucial to develop a learning framework through cross-disease transfer learning that can extract more information from the limited data. To address this challenge, we concentrate on prompt learning and endeavor to extend its application to the brain networks. Specifically, we propose a novel prompt learning framework called BPformer, which integrates knowledge transferred across diseases via specific prompts while keeping the original architecture of BPformer unchanged. The specific prompts incorporate 1) a mask prompt to determine whether the edges are noisy or discriminating, 2) disorder prompts for modeling consistent and disorder-specific knowledge, and 3) adaptive instance-level prompts to account for inter-individual variations. We evaluate BPformer on the private center Nanjing Medical University dataset, the public Autism Brain Imaging Data Exchange dataset, and the public Alzheimer's Disease Neuroimaging Initiative dataset. We demonstrate the effectiveness of the proposed model across various disease classification tasks, including major depressive disorder, bipolar disorder, alzheimer's disease, and autism spectrum disorder diagnoses. In addition, the proposed method enables disease interpretability and subtype analysis, empowering physicians to provide patients with more accurate and fine-grained treatment plans.

Details DOI

EAAI Journal 2025 Journal Article

Fast and intelligent measurement of the ventilation resistance coefficient for the whole mine based on sparse measurement points

Dong Wang
Jian Liu
Lijun Deng
Peng Cao
Li Liu

Artificial intelligence is playing an important role in mine ventilation engineering, especially in ensuring safe mine production. The mine ventilation resistance coefficient (MVRC) is the core and basic parameter of a mine ventilation system. It is crucial to quickly and accurately obtain the ventilation resistance coefficient (VRC) of the whole mine for the scientific, safe, and intelligent management of the mine ventilation system. To solve the time-consuming and laborious problem of the traditional mine ventilation resistance measurement method, we propose a fast and intelligent measurement method to obtain the whole mine's VRC based on an artificial intelligence differential evolution algorithm and sparse measurement points. The VRC was experimentally measured to verify the validity of the intelligent measurement method and the reliability of the model. The relative error of the air volume at the observation points of the solved results is less than 6 %. The fast intelligent measurement of the MVRC of the Longshou mine was carried out. The results were applied to develop an emergency plan for addressing the insufficient air supply in the ventilation system caused by the collapse of the mine's main blind return shaft and validated through engineering practice. After field practice, the relative error between the predicted and tested air return volume of the 10-row inclined shaft was 3. 23 %. It is verified that the results obtained using this method can solve mine ventilation system problems with relatively high accuracy, significantly reducing both the testing workload and time required for the mine ventilation resistance measurements.

Details DOI

IJCAI Conference 2023 Conference Paper

Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation

Zhiqiang Shen
Peng Cao
Hua Yang
Xiaoli Liu
Jinzhu Yang
Osmar R. Zaiane

Consistency regularization and pseudo labeling-based semi-supervised methods perform co-training using the pseudo labels from multi-view inputs. However, such co-training models tend to converge early to a consensus, degenerating to the self-training ones, and produce low-confidence pseudo labels from the perturbed inputs during training. To address these issues, we propose an Uncertainty-guided Collaborative Mean-Teacher (UCMT) for semi-supervised semantic segmentation with the high-confidence pseudo labels. Concretely, UCMT consists of two main components: 1) collaborative mean-teacher (CMT) for encouraging model disagreement and performing co-training between the sub-networks, and 2) uncertainty-guided region mix (UMIX) for manipulating the input images according to the uncertainty maps of CMT and facilitating CMT to produce high-confidence pseudo labels. Combining the strengths of UMIX with CMT, UCMT can retain model disagreement and enhance the quality of pseudo labels for the co-training segmentation. Extensive experiments on four public medical image datasets including 2D and 3D modalities demonstrate the superiority of UCMT over the state-of-the-art. Code is available at: https: //github. com/Senyh/UCMT.

PDF Details DOI

JBHI Journal 2023 Journal Article

Graph Self-Supervised Learning With Application to Brain Networks Analysis

Guangqi Wen
Peng Cao
Lingwen Liu
Jinzhu Yang
Xizhe Zhang
Fei Wang
Osmar R. Zaiane

The less training data and insufficient supervision limit the performance of the deep supervised models for brain disease diagnosis. It is significant to construct a learning framework that can capture more information in limited data and insufficient supervision. To address these issues, we focus on self-supervised learning and aim to generalize the self-supervised learning to the brain networks, which are non-Euclidean graph data. More specifically, we propose an ensemble masked graph self-supervised framework named BrainGSLs, which incorporates 1) a local topological-aware encoder that takes the partially visible nodes as input and learns these latent representations, 2) a node-edge bi-decoder that reconstructs the masked edges by the representations of both the masked and visible nodes, 3) a signal representation learning module for capturing temporal representations from BOLD signals and 4) a classifier used for the classification. We evaluate our model on three real medical clinical applications: diagnosis of Autism Spectrum Disorder (ASD), diagnosis of Bipolar Disorder (BD) and diagnosis of Major Depressive Disorder (MDD). The results suggest that the proposed self-supervised training has led to remarkable improvement and outperforms state-of-the-art methods. Moreover, our method is able to identify the biomarkers associated with the diseases, which is consistent with the previous studies. We also explore the correlation of these three diseases and find the strong association between ASD and BD. To the best of our knowledge, our work is the first attempt of applying the idea of self-supervised learning with masked autoencoder on the brain network analysis.

Details DOI

JBHI Journal 2023 Journal Article

Image Quality Assessment Guided Collaborative Learning of Image Enhancement and Classification for Diabetic Retinopathy Grading

Qingshan Hou
Peng Cao
Liyu Jia
Leqi Chen
Jinzhu Yang
Osmar R. Zaiane

Diabetic retinopathy (DR) is one of the most serious complications of diabetes and is a prominent cause of permanent blindness. However, the low-quality fundus images increase the uncertainty of clinical diagnosis, resulting in a significant decrease on the grading performance of the fundus images. Therefore, enhancing the image quality is essential for predicting the grade level in DR diagnosis. In essence, we are faced with three challenges: (I) How to appropriately evaluate the quality of fundus images; (II) How to effectively enhance low-quality fundus images for providing reliable fundus images to ophthalmologists or automated analysis systems; (III) How to jointly train the quality assessment and enhancement for improving the DR grading performance. Considering the importance of image quality assessment and enhancement for DR grading, we propose a collaborative learning framework to jointly train the subnetworks of the image quality assessment as well as enhancement, and DR disease grading in a unified framework. The key contribution of the proposed framework lies in modelling the potential correlation of these tasks and the joint training of these subnetworks, which significantly improves the fundus image quality and DR grading performance. Our framework is a general learning model, which may be useful in other medical images with low-quality data. Extensive experimental results have shown that our method outperforms state-of-the-art DR grading methods by a considerable 73. 6% ACC/71. 2% Kappa and 88. 5% ACC/86. 3% Kappa on Messidor and EyeQ benchmark datasets, respectively. In addition, our method significantly enhances the low-quality fundus images while preserving fundus structure features and lesion information. To make the framework more general, we also evaluate the enhancement results in more downstream tasks, such as vessel segmentation.

Details DOI

NeurIPS Conference 2023 Conference Paper

Rank-N-Contrast: Learning Continuous Representations for Regression

Kaiwen Zha
Peng Cao
Jeany Son
Yuzhe Yang
Dina Katabi

Deep regression models typically learn in an end-to-end fashion without explicitly emphasizing a regression-aware representation. Consequently, the learned representations exhibit fragmentation and fail to capture the continuous nature of sample orders, inducing suboptimal results across a wide range of regression tasks. To fill the gap, we propose Rank-N-Contrast (RNC), a framework that learns continuous representations for regression by contrasting samples against each other based on their rankings in the target space. We demonstrate, theoretically and empirically, that RNC guarantees the desired order of learned representations in accordance with the target orders, enjoying not only better performance but also significantly improved robustness, efficiency, and generalization. Extensive experiments using five real-world regression datasets that span computer vision, human-computer interaction, and healthcare verify that RNC achieves state-of-the-art performance, highlighting its intriguing properties including better data efficiency, robustness to spurious targets and data corruptions, and generalization to distribution shifts.

PDF Details

AAAI Conference 2022 Conference Paper

UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-Wise Perspective with Transformer

Haonan Wang
Peng Cao
Jiaqi Wang
Osmar R. Zaiane

Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some skip connection negatively influence the segmentation performance; 2) The original U-Net is worse than the one without any skip connection on some datasets. Based on our findings, we propose a new segmentation framework, named UC- TransNet (with a proposed CTrans module in U-Net), from the channel perspective with attention mechanism. Specifically, the CTrans (Channel Transformer) module is an alternate of the U-Net skip connections, which consists of a sub-module to conduct the multi-scale Channel Cross fusion with Transformer (named CCT) and a sub-module Channelwise Cross-Attention (named CCA) to guide the fused multiscale channel-wise information to effectively connect to the decoder features for eliminating the ambiguity. Hence, the proposed connection consisting of the CCT and CCA is able to replace the original skip connection to solve the semantic gaps for an accurate automatic medical image segmentation. The experimental results suggest that our UCTransNet produces more precise segmentation performance and achieves consistent improvements over the state-of-the-art for semantic segmentation across different datasets and conventional architectures involving transformer or U-shaped framework. Code: https: //github. com/McGregorWwww/UCTransNet.

PDF Details

YNIMG Journal 2020 Journal Article

Longitudinal evaluation of demyelinated lesions in a multiple sclerosis model using ultrashort echo time magnetization transfer (UTE-MT) imaging

Caroline Guglielmetti
Tanguy Boucneau
Peng Cao
Annemie Van der Linden
Peder E.Z. Larson
Myriam M. Chaumeil

Alterations in myelin integrity are involved in many neurological disorders and demyelinating diseases, such as multiple sclerosis (MS). Although magnetic resonance imaging (MRI) is the gold standard method to diagnose and monitor MS patients, clinically available MRI protocols show limited specificity for myelin detection, notably in cerebral grey matter areas. Ultrashort echo time (UTE) MRI has shown great promise for direct imaging of lipids and myelin sheaths, and thus holds potential to improve lesion detection. In this study, we used a sequence combining magnetization transfer (MT) with UTE (“UTE-MT”, TE = 76 μs) and with short TE (“STE-MT”, TE = 3000 μs) to evaluate spatial and temporal changes in brain myelin content in the cuprizone mouse model for MS on a clinical 7 T scanner. During demyelination, UTE-MT ratio (UTE-MTR) and STE-MT ratio (STE-MTR) values were significantly decreased in most white matter and grey matter regions. However, only UTE-MTR detected cortical changes. After remyelination in subcortical and cortical areas, UTE-MTR values remained lower than baseline values, indicating that UTE-MT, but not STE-MT, imaging detected long-lasting changes following a demyelinating event. Next, we evaluated the potential correlations between imaging values and underlying histopathological markers. The strongest correlation was observed between UTE-MTR and percent coverage of myelin basic protein (MBP) immunostaining (r2 = 0. 71). A significant, although lower, correlation was observed between STE-MTR and MBP (r2 = 0. 48), and no correlation was found between UTE-MTR or STE-MTR and gliosis immunostaining. Interestingly, correlations varied across brain substructures. Altogether, our results demonstrate that UTE-MTR values significantly correlate with myelin content as measured by histopathology, not only in white matter, but also in subcortical and cortical grey matter regions in the cuprizone mouse model for MS. Readily implemented on a clinical 7 T system, this approach thus holds great potential for detecting demyelinating/remyelinating events in both white and grey matter areas in humans. When applied to patients with neurological disorders, including MS patient populations, UTE-MT methods may improve the non-invasive longitudinal monitoring of brain lesions, not only during disease progression but also in response to next generation remyelinating therapies.

Details DOI

NeurIPS Conference 2019 Conference Paper

L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise

Yilun Xu
Peng Cao
Yuqing Kong
Yizhou Wang

Accurately annotating large scale dataset is notoriously expensive both in time and in money. Although acquiring low-quality-annotated dataset can be much cheaper, it often badly damages the performance of trained models when using such dataset without particular treatment. Various methods have been proposed for learning with noisy labels. However, most methods only handle limited kinds of noise patterns, require auxiliary information or steps (e. g. , knowing or estimating the noise transition matrix), or lack theoretical justification. In this paper, we propose a novel information-theoretic loss function, L DMI, for training deep neural networks robust to label noise. The core of L DMI is a generalized version of mutual information, termed Determinant based Mutual Information (DMI), which is not only information-monotone but also relatively invariant. To the best of our knowledge, L DMI is the first loss function that is provably robust to instance-independent label noise, regardless of noise pattern, and it can be applied to any existing classification neural networks straightforwardly without any auxiliary information. In addition to theoretical justification, we also empirically show that using L DMI outperforms all other counterparts in the classification task on both image dataset and natural language dataset include Fashion-MNIST, CIFAR-10, Dogs vs. Cats, MR with a variety of synthesized noise patterns and noise amounts, as well as a real-world dataset Clothing1M.

PDF Details

YNIMG Journal 2018 Journal Article

MRI gradient-echo phase contrast of the brain at ultra-short TE with off-resonance saturation

Hongjiang Wei
Peng Cao
Antje Bischof
Roland G. Henry
Peder E.Z. Larson
Chunlei Liu

Larmor-frequency shift or image phase measured by gradient-echo sequences has provided a new source of MRI contrast. This contrast is being used to study both the structure and function of the brain. So far, phase images of the brain have been largely obtained at long echo times as maximum phase signal-to-noise ratio (SNR) is achieved at TE = T2* (∼40 ms at 3T). The structures of the brain, however, are compartmentalized and complex with a wide range of signal relaxation times. At such long TE, the short-T2 components are largely attenuated and contribute minimally to phase contrast. The purpose of this study was to determine whether proton gradient-echo images of the brain exhibit phase contrast at ultra-short TE (UTE). Our data showed that UTE images acquired at 7 T without off-resonance saturation do not contain significant phase contrast between gray and white matter. However, UTE images of the brain can attain strong phase contrast even at a nominal TE of 106 μs by using off-resonance RF saturation pulses, which provide direct saturation of ultra-short-T2 components and indirect saturation of longer-T2 components via magnetization transfer. In addition, phase contrast between gray and white matter acquired at UTE with off-resonance saturation is reversed compared to that of the long-T2 signals acquired at long TEs. This finding opens up a potential new way to manipulate image phase contrast of the brain. By accessing short and ultra-short-T2 species, MRI phase images may further improve the characterization of tissue microstructure in the brain.

Details DOI