Pheng-Ann Heng

The Chinese University of Hong Kong | CUHK

Background Deep learning (DL) is promising to detect glaucoma. However, patients’ privacy and data security are major concerns when pooling all data for model development. We developed a privacy-preserving DL model using the federated learning (FL) paradigm to detect glaucoma from optical coherence tomography (OCT) images. Methods This is a multic...

In medical image analysis, anomaly detection in weakly supervised settings has gained significant interest due to the high cost associated with expert-annotated pixel-wise labeling. Current methods primarily rely on auto-encoders and flow-based healthy image reconstruction to detect anomalies. However, these methods have limitations in terms of hig...

Despite great progress in semi-supervised learning (SSL) that leverages unlabeled data to improve the performance over fully supervised models, existing SSL approaches still fail to exhibit good results when faced with a severe class imbalance problem in medical image segmentation. In this work, we propose a novel Mean-teacher based class imbalance...

In medical image analysis, imbalanced noisy dataset classification poses a long-standing and critical problem since clinical large-scale datasets often attain noisy labels and imbalanced distributions through annotation and collection. Current approaches addressing noisy labels and long-tailed distributions separately may negatively impact real-wor...

Cross-domain distribution shift is a common problem for medical image analysis because medical images from different devices usually own varied domain distributions. Test-time adaptation (TTA) is a promising solution by efficiently adapting source-domain distributions to target-domain distributions at test time with unsupervised manners, which has...

Purpose The purpose of this study was to develop an artificial intelligence (AI) system for the identification of disease status and recommending treatment modalities for retinopathy of prematurity (ROP). Methods This retrospective cohort study included a total of 24,495 RetCam images from 1075 eyes of 651 preterm infants who received RetCam exami...

Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demanding. Unfortunately, the resultant noisy bounding boxes could cause corrupt supervision signals and thus diminish detection performance. Motivated by the observation that t...

Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for both 2D and 3D computer vision. However, existing MAE-style methods can only learn from the data of a single modality, i.e., either images or point clouds, which neglect the implicit semantic and geometric correlation between 2D and 3D. In this paper, we expl...

High-accuracy Dichotomous Image Segmentation (DIS) aims to pinpoint category-agnostic foreground objects from natural scenes. The main challenge for DIS involves identifying the highly accurate dominant area while rendering detailed object structure. However, directly using a general encoder-decoder architecture may result in an oversupply of high-...

We propose a novel approach for RGB-D salient instance segmentation using a dual-branch cross-modal feature calibration architecture called CalibNet. Our method simultaneously calibrates depth and RGB features in the kernel and mask branches to generate instance-aware kernels and mask features. CalibNet consists of three simple modules, a dynamic i...

Robotic bin packing is very challenging, especially when considering practical needs such as object variety and packing compactness. This paper presents SDF-Pack, a new approach based on signed distance field (SDF) to model the geometric condition of objects in a container and compute the object placement locations and packing orders for achieving...

Purpose: Segmentation of liver vessels from CT images is indispensable prior to surgical planning and aroused a broad range of interest in the medical image analysis community. Due to the complex structure and low-contrast background, automatic liver vessel segmentation remains particularly challenging. Most of the related researches adopt FCN, U-...

Deep learning (DL)-based rib fracture detection has shown promise of playing an important role in preventing mortality and improving patient outcome. Normally, developing DL-based object detection models requires huge amount of bounding box annotation. However, annotating medical data is time-consuming and expertise-demanding, making obtaining a la...

Despite that the segment anything model (SAM) achieved impressive results on general-purpose semantic segmentation with strong generalization ability on daily images, its demonstrated performance on medical image segmentation is less precise and not stable, especially when dealing with tumor segmentation tasks that involve objects of small sizes, i...

Convolutional Neural Networks (CNNs) have shown remarkable progress in medical image segmentation. However, lesion segmentation remains a challenge to state-of-the-art CNN-based algorithms due to the variance in scales and shapes. On the one hand, tiny lesions are hard to be delineated precisely from the medical images which are often of low resolu...

Artificial intelligence has deeply revolutionized the field of medicinal chemistry with many impressive applications, but the success of these applications requires a massive amount of training samples with high-quality annotations, which seriously limits the wide usage of data-driven methods. In this paper, we focus on the reaction yield predictio...

Semi-supervised learning (SSL) methods assume that labeled data, unlabeled data and test data are from the same distribution. Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers). Most previous works focused o...

Video dehazing aims to recover haze-free frames with high visibility and contrast. This paper presents a novel framework to effectively explore the physical haze priors and aggregate temporal information. Specifically, we design a memory-based physical prior guidance module to encode the prior-related features into long-range memory. Besides, we fo...

Masked Image Modeling (MIM) has achieved impressive representative performance with the aim of reconstructing randomly masked images. Despite the empirical success, most previous works have neglected the important fact that it is unreasonable to force the model to reconstruct something beyond recovery, such as those masked objects. In this work, we...

Data augmentation is an effective regularization strategy for mitigating overfitting in deep neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud data is relatively limited. While mixing-based augmentation has shown promise for point clouds, previous methods mix point clouds either on block level or point level, wh...

Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers. One key issue is to generate consistent trajectory predictions without colliding. To overcome the challenge, we propose an efficient masked autoencoder for trajectory prediction (Traj-MAE) that better represents the compl...

Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. Recently proposed evidential neural networks explicitly account for different uncertainties by treating the network's outputs as evidence to parameterize the Dirichlet distribution, and achieve impressive performance in uncertainty estimation. Howeve...

Multi-label classification (MLC) can attach multiple labels on single image, and has achieved promising results on medical images. But existing MLC methods still face challenging clinical realities in practical use, such as: (1) medical risks arising from misclassification, (2) sample imbalance problem among different diseases, (3) inability to cla...

Deep convolutional neural networks (ConvNets) have achieved state-of-the-art performance in various medical image analysis tasks. The success is partially attributed to a large amount of labeled data. However, some medical images, such as a rare disease case actinic keratosis, are rare and are difficult to obtain a large amount of labeled data in h...

The generalization capacity of deep models is crucial for real-world clinical deployment, where domain shifts usually exist due to changes of image acquisition conditions. This chapter presents domain generalization methods for medical image segmentation with meta learning technique, aiming to generalize the deep models learned from multiple source...

Puncture robots pave a new way for stable, accurate and safe percutaneous liver tumor puncture operation. However, affected by respiratory motion, intraoperative accurate location of the tumor and its surrounding anatomical structures remains a difficult problem in existing robot-assisted puncture operations. In this paper, a dual-arm robotic needl...

Kinesthetic feedback, the feeling of restriction or resistance when hands contact objects, is essential for natural freehand interaction in VR. However, inducing kinesthetic feedback using mechanical hardware can be cumbersome and hard to control in commodity VR systems. We propose the kine-appendage concept to compensate for the loss of kinesthe...

In subcellular biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures. However, fluorescence staining is slow, expensive, and harmful to cells. In this paper, we treat it as a deep learning task termed subcellular structure prediction (SSP), aiming to predict the 3D fluorescent...

Automated detecting lung infections from computed tomography (CT) data plays an important role for combating coronavirus 2019 (COVID-19). However, there are still some challenges for developing AI system: 1) most current COVID-19 infection segmentation methods mainly relied on 2-D CT images, which lack 3-D sequential constraint; 2) existing 3-D CT...

Deep simulations have gained widespread attention owing to their excellent acceleration performances. However, these methods cannot provide effective collision detection and response strategies. We propose a deep interactive physical simulation framework that can effectively address tool-object collisions. The framework can predict the dynamic info...

Domain generalization aims to learn knowledge invariant across different distributions while semantically meaningful for downstream tasks from multiple source domains, to improve the model's generalization ability on unseen target domains. The fundamental objective is to understand the underlying "invariance" behind these observational distribution...

Video instance shadow detection aims to simultaneously detect, segment, associate, and track paired shadow-object associations in videos. This work has three key contributions to the task. First, we design SSIS-Track, a new framework to extract shadow-object associations in videos with paired tracking and without category specification; especially,...

Automated detecting lung infections from computed tomography (CT) data plays an important role for combating COVID-19. However, there are still some challenges for developing AI system. 1) Most current COVID-19 infection segmentation methods mainly relied on 2D CT images, which lack 3D sequential constraint. 2) Existing 3D CT segmentation methods f...

Contemporary methods have shown promising results on cardiac image segmentation, but merely in static learning, i.e., optimizing the network once for all, ignoring potential needs for model updating. In real-world scenarios, new data continues to be gathered from multiple institutions over time and new demands keep growing to pursue more satisfying...

Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels. We consider an extreme of this weakly supervised learning problem, called single positive multi-label learning (SPML), where each multi-label training image has only one positive label. Traditionally, all unannotated labels are...

Graph neural networks (GNNs) have drawn more and more attention from material scientists and demonstrated a strong capacity to establish connections between the structure and properties. However, with only unrelaxed structures provided as input, few GNN models can predict the thermodynamic properties of relaxed configurations with an acceptable lev...

Contemporary methods have shown promising results on cardiac image segmentation, but merely in static learning, i.e ., optimizing the network once for all, ignoring potential needs for model updating. In real-world scenarios, new data continues to be gathered from multiple institutions over time and new demands keep growing to pursue more satisfy...

Supervised deep learning has achieved prominent success in various diabetic macular edema (DME) recognition tasks from optical coherence tomography (OCT) volumetric images. A common problematic issue that frequently occurs in this field is the shortage of labeled data due to the expensive fine-grained annotations, which increases substantial diffic...

Most of the existing object detection works are based on the bounding box annotation: each object has a precise annotated box. However, for rib fractures, the bounding box annotation is very labor-intensive and time-consuming because radiologists need to investigate and annotate the rib fractures on a slice-by-slice basis. Although a few studies ha...

Deep learning models were frequently reported to learn from shortcuts like dataset biases. As deep learning is playing an increasingly important role in the modern healthcare system, it is of great need to combat shortcut learning in medical data as well as develop unbiased and trustworthy models. In this paper, we study the problem of developing d...

Despite recent progress on semi-supervised federated learning (FL) for medical image diagnosis, the problem of imbalanced class distributions among unlabeled clients is still unsolved for real-world use. In this paper, we study a practical yet challenging problem of class imbalanced semi-supervised FL (imFed-Semi), which allows all clients to have...

Medical data often follow imbalanced distributions, which poses a long-standing challenge for computer-aided diagnosis systems built upon medical image classification. Most existing efforts are conducted by applying re-balancing methods for the collected training samples, which improves the predictive performance for the minority class but at the c...

Graph neural networks (GNNs) have drawn more and more attention from material scientists and demonstrated a high capacity to establish connections between the structure and properties. However, with only unrelaxed structures provided as input, few GNN models can predict the thermodynamic properties of relaxed configurations with an acceptable level...

Deep learning shows great potential in generation tasks thanks to deep latent representation. Generative models are classes of models that can generate observations randomly with respect to certain implied parameters. Recently, the diffusion Model becomes a raising class of generative models by virtue of its power-generating ability. Nowadays, grea...

Purpose: Real-time surgical workflow analysis has been a key component for computer-assisted intervention system to improve cognitive assistance. Most existing methods solely rely on conventional temporal models and encode features with a successive spatial-temporal arrangement. Supportive benefits of intermediate features are partially lost from...

Background There is no simple model to screen for Alzheimer's disease, partly because the diagnosis of Alzheimer's disease itself is complex—typically involving expensive and sometimes invasive tests not commonly available outside highly specialised clinical settings. We aimed to develop a deep learning algorithm that could use retinal photographs...

Artificial intelligence has deeply revolutionized the field of medicinal chemistry with many impressive applications, but the success of these applications requires a massive amount of training samples with high-quality annotations, which seriously limits the wide usage of data-driven methods. In this paper, we focus on the reaction yield predictio...

Surgical scene segmentation is fundamentally crucial for prompting cognitive assistance in robotic surgery. However, pixel-wise annotating surgical video in a frame-by-frame manner is expensive and time consuming. To greatly reduce the labeling burden, in this work, we study semi-supervised scene segmentation from robotic surgical video, which is p...

Purpose: To evaluate the ability of fine-grained annotations to overcome shortcut learning in deep learning (DL)-based diagnosis using chest radiographs. Materials and methods: Two DL models were developed using radiograph-level annotations (disease present: yes or no) and fine-grained lesion-level annotations (lesion bounding boxes), respective...

This paper formulates a new problem, instance shadow detection, which aims to detect shadow instance and the associated object instance that cast each shadow in the input image. To approach this task, we first compile a new dataset with the masks for shadow instances, object instances, and shadow-object associations. We then design an evaluation me...

Most of the existing object detection works are based on the bounding box annotation: each object has a precise annotated box. However, for rib fractures, the bounding box annotation is very labor-intensive and time-consuming because radiologists need to investigate and annotate the rib fractures on a slice-by-slice basis. Although a few studies ha...

Federated learning, which trains a generic model for different institutions without sharing their data, is a new trend to avoid training with centralized data, which is often impossible due to privacy issues. The Federated Tumor Segmentation (FeTS) Challenge 2021 has two tasks for participants. Task 1 aims at effective weight aggregation methods gi...

Domain generalization typically requires data from multiple source domains for model learning. However, such strong assumption may not always hold in practice, especially in medical field where the data sharing is highly concerned and sometimes prohibitive due to privacy issue. This paper studies the important yet challenging single domain generali...

Domain generalization typically requires data from multiple source domains for model learning. However, such strong assumption may not always hold in practice, especially in medical field where the data sharing is highly concerned and sometimes prohibitive due to privacy issue. This paper studies the important yet challenging single domain generali...

Despite recent progress on semi-supervised federated learning (FL) for medical image diagnosis, the problem of imbalanced class distributions among unlabeled clients is still unsolved for real-world use. In this paper, we study a practical yet challenging problem of class imbalanced semi-supervised FL (imFed-Semi), which allows all clients to have...

This paper formulates a new problem, instance shadow detection, which aims to detect shadow instance and the associated object instance that cast each shadow in the input image. To approach this task, we first compile a new dataset with the masks for shadow instances, object instances, and shadow-object associations. We then design an evaluation me...

PurposeWe aim to develop a multi-task three-dimensional (3D) deep learning (DL) model to detect glaucomatous optic neuropathy (GON) and myopic features (MF) simultaneously from spectral-domain optical coherence tomography (SDOCT) volumetric scans.Methods Each volumetric scan was labelled as GON according to the criteria of retinal nerve fibre layer...

Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre. Previous works rely on conventional aggregation modules (e.g., dilated convolution, convolutional LSTM), which only make use of the local context. In this paper, we propose a novel framework STswinCL that explores the comple...

Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some noisy-labeled images, the network training procedure would suffer from difficulties, leading to a sub-optimal classifie...

Automatic laparoscope motion control is fundamentally important for surgeons to efficiently perform operations. However, its traditional control methods based on tool tracking without considering information hidden in surgical scenes are not intelligent enough, while the latest supervised imitation learning (IL)-based methods require expensive sens...

Parkinson’s disease (PD) is treated effectively by deep brain stimulation (DBS) of the subthalamic nucleus (STN), using an electrode inserted into the head of a PD patient. The electrode has multiple electrical contacts along its length, so the best may be chosen for selectively stimulating the STN. Neurosurgeons usually determine the optimal stimu...

Due to the difficulty of collecting exhaustive multi-label annotations, multi-label training data often contains partial labels. We consider an extreme of this problem, called single positive multi-label learning (SPML), where each multi-label training image has only one positive label. Traditionally, all unannotated labels are assumed as negative...

Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre. Previous works rely on conventional aggregation modules (e.g., dilated convolution, convolutional LSTM), which only make use of the local context. In this paper, we propose a novel framework STswinCL that explores the comple...

Deep learning models were frequently reported to learn from shortcuts like dataset biases. As deep learning is playing an increasingly important role in the modern healthcare system, it is of great need to combat shortcut learning in medical data as well as develop unbiased and trustworthy models. In this paper, we study the problem of developing d...

Industrial bin picking is a challenging task that requires accurate and robust segmentation of individual object instances. Particularly, industrial objects can have irregular shapes, that is, thin and concave, whereas in bin-picking scenarios, objects are often closely packed with strong occlusion. To address these challenges, we formulate a novel...

Background and Objectives:Soft body cutting simulation is the core module of virtual surgical training systems. By making full use of the powerful computing resources of modern computers, the existing methods have already met the needs of real-time interaction. However, there is still a lack of high realism. The main reason is that most current met...

Cardiac image segmentation is a fundamental step in cardiovascular disease diagnosis, where many deep learning models have achieved promising performance. However, when deploying these well-trained models for real clinical usage, the network will inevitably produce inferior results due to domain shifts, motion artifacts, etc. How to avoid the poten...

Objectives: We proposed a new approach to train deep learning model for aneurysm rupture prediction which only uses a limited amount of labeled data. Method: Using segmented aneurysm mask as input, a backbone model was pretrained using a self-supervised method to learn deep embeddings of aneurysm morphology from 947 unlabeled cases of angiograph...

Surgical instrument segmentation -- in general a pixel classification task -- is fundamentally crucial for promoting cognitive intelligence in robot-assisted surgery (RAS). However, previous methods are struggling with discriminating instrument types and instances. To address the above issues, we explore a mask classification paradigm that produces...

Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some noisy-labeled images, the network training procedure would suffer from difficulties, leading to a sub-optimal classifie...

Unsupervised domain adaptation for object detection aims to generalize the object detector trained on the labelrich source domain to the unlabeled target domain. Recently, existing works adopt the instance-level alignment or pixel-level alignment to perform domain transfer, which can effectively avoid the negative transfer due to the diverse backgr...

To realize a higher-level autonomy of surgical knot tying in minimally invasive surgery (MIS), automated suture grasping, which bridges the suture stitching and looping procedures, is an important yet challenging task needs to be achieved. This paper presents a holistic framework with image-guided and automation techniques to robotize this operatio...

Our new concept, Kine-Appendage, compensates for absence of kinesthetic feedback in VR through transformations of virtual appendages.