Searcharxiv⌕ Search

arXiv subjects

Kenneth K. Y. Wong

Publications and source records attributed to Kenneth K. Y. Wong.

10 recordsLinked to original sources
arXiv2026

Diff4MMLiTS: Advanced Multimodal Liver Tumor Segmentation via Diffusion-Based Image Synthesis and Alignment

Multimodal learning has been demonstrated to enhance performance across various clinical tasks, owing to the diverse perspectives offered by different modalities of data. However, existing multimodal segmentation methods rely on well-registered multimodal data, which is unrealistic for real-world clinical images, particularly for indistinct and diffuse regions such as liver tumors. In this paper, we introduce Diff4MMLiTS, a four-stage multimodal liver tumor segmentation pipeline: pre-registration of the target organs in multimodal CTs; dilation of the annotated modality's mask and followed by its use in inpainting to obtain multimodal normal CTs without tumors; synthesis of strictly aligned multimodal CTs with tumors using the latent diffusion model based on multimodal CT features and randomly generated tumor masks; and finally, training the segmentation model, thus eliminating the need for strictly aligned multimodal data. Extensive experiments on public and internal datasets demonstrate the superiority of Diff4MMLiTS over other state-of-the-art multimodal segmentation methods.

eess.IV↗
arXiv2024

FedLPPA: Learning Personalized Prompt and Aggregation for Federated Weakly-supervised Medical Image Segmentation

Federated learning (FL) effectively mitigates the data silo challenge brought about by policies and privacy concerns, implicitly harnessing more data for deep model training. However, traditional centralized FL models grapple with diverse multi-center data, especially in the face of significant data heterogeneity, notably in medical contexts. In the realm of medical image segmentation, the growing imperative to curtail annotation costs has amplified the importance of weakly-supervised techniques which utilize sparse annotations such as points, scribbles, etc. A pragmatic FL paradigm shall accommodate diverse annotation formats across different sites, which research topic remains under-investigated. In such context, we propose a novel personalized FL framework with learnable prompt and aggregation (FedLPPA) to uniformly leverage heterogeneous weak supervision for medical image segmentation. In FedLPPA, a learnable universal knowledge prompt is maintained, complemented by multiple learnable personalized data distribution prompts and prompts representing the supervision sparsity. Integrated with sample features through a dual-attention mechanism, those prompts empower each local task decoder to adeptly adjust to both the local distribution and the supervision form. Concurrently, a dual-decoder strategy, predicated on prompt similarity, is introduced for enhancing the generation of pseudo-labels in weakly-supervised learning, alleviating overfitting and noise accumulation inherent to local data, while an adaptable aggregation method is employed to customize the task decoder on a parameter-wise basis. Extensive experiments on four distinct medical image segmentation tasks involving different modalities underscore the superiority of FedLPPA, with its efficacy closely parallels that of fully supervised centralized training. Our code and data will be available.

cs.CV↗
arXiv2024

Programming the scalable optical learning operator with spatial-spectral optimization

Electronic computers have evolved drastically over the past years with an ever-growing demand for improved performance. However, the transfer of information from memory and high energy consumption have emerged as issues that require solutions. Optical techniques are considered promising solutions to these problems with higher speed than their electronic counterparts and with reduced energy consumption. Here, we use the optical reservoir computing framework we have previously described (Scalable Optical Learning Operator or SOLO) to program the spatial-spectral output of the light after nonlinear propagation in a multimode fiber. The novelty in the current paper is that the system is programmed through an output sampling scheme, similar to that used in hyperspectral imaging in astronomy. Linear and nonlinear computations are performed by light in the multimode fiber and the high dimensional spatial-spectral information at the fiber output is optically programmed before it reaches the camera. We then used a digital computer to classify the programmed output of the multi-mode fiber using a simple, single layer network. When combining front-end programming and the proposed spatial-spectral programming, we were able to achieve 89.9% classification accuracy on the dataset consisting of chest X-ray images from COVID-19 patients. At the same time, we obtained a decrease of 99% in the number of tunable parameters compared to an equivalently performing digital neural network. These results show that the performance of programmed SOLO is comparable with cutting-edge electronic computing platforms, albeit with a much-reduced number of electronic operations.

physics.optics↗
arXiv2023

YoloCurvSeg: You Only Label One Noisy Skeleton for Vessel-style Curvilinear Structure Segmentation

Weakly-supervised learning (WSL) has been proposed to alleviate the conflict between data annotation cost and model performance through employing sparsely-grained (i.e., point-, box-, scribble-wise) supervision and has shown promising performance, particularly in the image segmentation field. However, it is still a very challenging task due to the limited supervision, especially when only a small number of labeled samples are available. Additionally, almost all existing WSL segmentation methods are designed for star-convex structures which are very different from curvilinear structures such as vessels and nerves. In this paper, we propose a novel sparsely annotated segmentation framework for curvilinear structures, named YoloCurvSeg. A very essential component of YoloCurvSeg is image synthesis. Specifically, a background generator delivers image backgrounds that closely match the real distributions through inpainting dilated skeletons. The extracted backgrounds are then combined with randomly emulated curves generated by a Space Colonization Algorithm-based foreground generator and through a multilayer patch-wise contrastive learning synthesizer. In this way, a synthetic dataset with both images and curve segmentation labels is obtained, at the cost of only one or a few noisy skeleton annotations. Finally, a segmenter is trained with the generated dataset and possibly an unlabeled dataset. The proposed YoloCurvSeg is evaluated on four publicly available datasets (OCTA500, CORN, DRIVE and CHASEDB1) and the results show that YoloCurvSeg outperforms state-of-the-art WSL segmentation methods by large margins. With only one noisy skeleton annotation (respectively 0.14\%, 0.03\%, 1.40\%, and 0.65\% of the full annotation), YoloCurvSeg achieves more than 97\% of the fully-supervised performance on each dataset. Code and datasets will be released at https://github.com/llmir/YoloCurvSeg.

cs.CV↗
arXiv2023

Unifying and Personalizing Weakly-supervised Federated Medical Image Segmentation via Adaptive Representation and Aggregation

Federated learning (FL) enables multiple sites to collaboratively train powerful deep models without compromising data privacy and security. The statistical heterogeneity (e.g., non-IID data and domain shifts) is a primary obstacle in FL, impairing the generalization performance of the global model. Weakly supervised segmentation, which uses sparsely-grained (i.e., point-, bounding box-, scribble-, block-wise) supervision, is increasingly being paid attention to due to its great potential of reducing annotation costs. However, there may exist label heterogeneity, i.e., different annotation forms across sites. In this paper, we propose a novel personalized FL framework for medical image segmentation, named FedICRA, which uniformly leverages heterogeneous weak supervision via adaptIve Contrastive Representation and Aggregation. Concretely, to facilitate personalized modeling and to avoid confusion, a channel selection based site contrastive representation module is employed to adaptively cluster intra-site embeddings and separate inter-site ones. To effectively integrate the common knowledge from the global model with the unique knowledge from each local model, an adaptive aggregation module is applied for updating and initializing local models at the element level. Additionally, a weakly supervised objective function that leverages a multiscale tree energy loss and a gated CRF loss is employed to generate more precise pseudo-labels and further boost the segmentation performance. Through extensive experiments on two distinct medical image segmentation tasks of different modalities, the proposed FedICRA demonstrates overwhelming performance over other state-of-the-art personalized FL methods. Its performance even approaches that of fully supervised training on centralized data. Our code and data are available at https://github.com/llmir/FedICRA.

eess.IV↗
arXiv2023

GlocalFuse-Depth: Fusing Transformers and CNNs for All-day Self-supervised Monocular Depth Estimation

In recent years, self-supervised monocular depth estimation has drawn much attention since it frees of depth annotations and achieved remarkable results on standard benchmarks. However, most of existing methods only focus on either daytime or nighttime images, thus their performance degrades on the other domain because of the large domain shift between daytime and nighttime images. To address this problem, in this paper we propose a two-branch network named GlocalFuse-Depth for self-supervised depth estimation of all-day images. The daytime and nighttime image in input image pair are fed into the two branches: CNN branch and Transformer branch, respectively, where both fine-grained details and global dependency can be efficiently captured. Besides, a novel fusion module is proposed to fuse multi-dimensional features from the two branches. Extensive experiments demonstrate that GlocalFuse-Depth achieves state-of-the-art results for all-day images on the Oxford RobotCar dataset, which proves the superiority of our method.

cs.CV↗
arXiv2019

Behavioral similarity of dissipative solitons in an ultrafast fiber laser

Dissipative solitons are non-dispersive localized waves that exhibit intriguing dynamics. In optical systems, the discovery of new soliton dynamics and how to accurately manipulate dissipative solitons are still largely unexplored and challenging in the ultrafast fiber laser community. Herein, we unveil a new type of dissipative soliton behavior in a net-normal-dispersion bidirectional ultrafast fiber laser. That is, the bidirectional dissipative solitons will always reveal similar spectral and temporal characteristics through common gain and loss modulation, even if the transient instability is involved. The behavioral similarity enables us to accurately design the soliton patterns by introducing seed pulses through loss modulation. As a proof-of-concept application, the precise and flexible manipulation of multi-soliton patterns is demonstrated. These findings will shed new insights into the complex dissipative soliton dynamics, and also beneficial for designing ultrafast lasers with desirable soliton patterns for practical applications.

physics.optics↗
arXiv2017

Panoramic-reconstruction temporal imaging for seamless measurements of slowly-evolved femtosecond pulse dynamics

Single-shot real-time characterization of optical waveforms with sub-picosecond resolution is essential for investigating various ultrafast optical dynamics. However, the finite temporal recording length of current techniques hinders comprehensive understanding of many intriguing ultrafast optical phenomena that evolve over a time scale much longer than their fine temporal details. Inspired by the space-time duality and by stitching of multiple microscopic images to achieve a larger field of view in the spatial domain, here a panoramic-reconstruction temporal imaging (PARTI) system is devised to scale up the temporal recording length without sacrificing the resolution. As a proof-of-concept demonstration, the PARTI system is applied to study the dynamic waveforms of slowly-evolved dissipative Kerr solitons in an ultrahigh-Q microresonator. Two 1.5-ns-long comprehensive evolution portraits are reconstructed with 740-fs resolution and dissipative Kerr soliton transition dynamics, in which a multiplet soliton state evolves into stable singlet soliton state, are depicted.

physics.optics↗
arXiv2013

Asymmetric-detection time-stretch optical microscopy (ATOM) for ultrafast high-contrast cellular imaging in flow

Accelerating imaging speed in optical microscopy is often realized at the expense of image contrast, image resolution, and detection sensitivity- a common predicament for advancing high-speed and high-throughput cellular imaging. We here demonstrate a new imaging approach, called asymmetric-detection time-stretch optical microscopy (ATOM), which can deliver ultrafast label-free high-contrast flow imaging with well delineated cellular morphological resolution and in-line optical image amplification to overcome the compromised imaging sensitivity at high speed. We show that ATOM can separately reveal the enhanced phase-gradient and absorption contrast in microfluidic live-cell imaging at a flow speed as high as ~10 m/s, corresponding to an imaging throughput of ~100,000 cells/sec. ATOM could thus be the enabling platform to meet the pressing need for intercalating optical microscopy in cellular assay, e.g. imaging flow cytometry- permitting high-throughput access to the morphological information of the individual cells simultaneously with a multitude of parameters obtained in the standard assay.

physics.optics↗