相关论文: SIMPLER: H&E-Informed Representation Learning for …
Hyperspectral imaging (HSI) unlocks the huge potential to a wide variety of applications relied on high-precision pathology image segmentation, such as computational pathology and precision medicine. Since hyperspectral pathology images…
Hyperspectral image (HSI) reconstruction aims to recover 3D HSI from its degraded 2D measurements. Recently great progress has been made in deep learning-based methods, however, these methods often struggle to accurately capture…
Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…
As the rapid development of computer vision and the emergence of powerful network backbones and architectures, the application of deep learning in medical imaging has become increasingly significant. Unlike natural images, medical images…
Emerging unsupervised implicit neural representation (INR) methods, such as NeRP, NeAT, and SCOPE, have shown great potential to address sparse-view computed tomography (SVCT) inverse problems. Although these INR-based methods perform well…
While the Segment Anything Model (SAM) excels in semantic segmentation for general-purpose images, its performance significantly deteriorates when applied to medical images, primarily attributable to insufficient representation of medical…
We introduce SPECTRE, a fully transformer-based foundation model for volumetric computed tomography (CT). Our Self-Supervised & Cross-Modal Pretraining for CT Representation Extraction (SPECTRE) approach utilizes scalable 3D Vision…
Increased levels of tumor infiltrating lymphocytes (TILs) in cancer tissue indicate favourable outcomes in many types of cancer. Manual quantification of immune cells is inaccurate and time consuming for pathologists. Our aim is to leverage…
Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and corresponding voxel-level labels. However, obtaining segmentations of…
In this communication, a fast reconstruction algorithm is proposed for fluorescence \textit{blind} structured illumination microscopy (SIM) under the sample positivity constraint. This new algorithm is by far simpler and faster than…
Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) as efficient learners for CIL. MAEs were originally designed…
Vision Transformer shows great superiority in medical image segmentation due to the ability in learning long-range dependency. For medical image segmentation from 3D data, such as computed tomography (CT), existing methods can be broadly…
CLIP embeddings have demonstrated remarkable performance across a wide range of multimodal applications. However, these high-dimensional, dense vector representations are not easily interpretable, limiting our understanding of the rich…
Neural networks possess incredible capabilities for extracting abstract features from data. Electromagnetic computing harnesses wave propagation to execute computational operations. Metasurfaces, composed of subwavelength meta-atoms, are…
As the therapeutic target for Inflammatory Bowel Disease (IBD) shifts toward histologic remission, the accurate assessment of microscopic inflammation has become increasingly central for evaluating disease activity and response to…
Virtual immunohistochemistry (IHC) staining from hematoxylin and eosin (H&E) images can accelerate diagnostics by providing preliminary molecular insight directly from routine sections, reducing the need for repeat sectioning when tissue is…
Hyperspectral unmixing (HU) plays a fundamental role in a wide range of hyperspectral applications. It is still challenging due to the common presence of outlier channels and the large solution space. To address the above two issues, we…
Hyperspectral images (HSIs) contain rich spectral and spatial information. Motivated by the success of transformers in the field of natural language processing and computer vision where they have shown the ability to learn long range…
Accurate tumor segmentation and classification in breast ultrasound (BUS) imaging remain challenging due to low contrast, speckle noise, and diverse lesion morphology. This study presents a multi-task deep learning framework that jointly…
We present experimental demonstration of tilt-mirror assisted transmission structured illumination microscopy (tSIM) that offers a large field of view super resolution imaging. An assembly of custom-designed tilt-mirrors are employed as the…