Search Results for author:
Found 25 papers, 16 papers with code
Advancing Deformable Medical Image Registration with Multi-axis Cross-covariance Attention
However, the high computation and memory loads of SA (growing quadratically with the spatial resolution) hinder transformers from processing subtle textural information in high-resolution image features, e. g., at the full and half image resolutions.
Language-guided Medical Image Segmentation with Target-informed Multi-level Contrastive Alignments
TMCA enables target-informed cross-modality alignments and fine-grained text guidance to bridge the pattern gaps in language-guided segmentation.
3DPX: Single Panoramic X-ray Analysis Guided by 3D Oral Structure Reconstruction
3DPX consists of (i) a novel progressive reconstruction network to improve 2D-to-3D reconstruction and, (ii) a contrastive-guided bidirectional multimodality alignment module for 3D-guided 2D PX classification and segmentation tasks.
SGSeg: Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance
Segmentation of infected areas in chest X-rays is pivotal for facilitating the accurate delineation of pulmonary structures and pathological anomalies.
3DPX: Progressive 2D-to-3D Oral Image Reconstruction with Hybrid MLP-CNN Networks
Panoramic X-ray (PX) is a prevalent modality in dental practice for its wide availability and low cost.
Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration
However, due to the high computation/memory loads of self-attention, transformers are typically used at downsampled feature resolutions and cannot capture fine-grained long-range dependence at the full image resolution.
Dynamic Traceback Learning for Medical Report Generation
Automated medical report generation has the potential to significantly reduce the workload associated with the time-consuming process of medical reporting.
Enhancing medical vision-language contrastive learning via inter-matching relation modelling
These learned image representations can be transferred to and benefit various downstream medical vision tasks such as disease classification and segmentation.
Full-resolution MLPs Empower Medical Dense Prediction
This textural information is crucial for medical dense prediction as it can differentiate the subtle human anatomy in medical images.
AutoFuse: Automatic Fusion Networks for Deformable Medical Image Registration
However, DNN-based registration needs to explore the spatial information of each image and fuse this information to characterize spatial correspondence.
Merging-Diverging Hybrid Transformer Networks for Survival Prediction in Head and Neck Cancer
In view of this, we propose a merging-diverging learning framework for survival prediction from multi-modality images.
Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registration
Recently, Non-Iterative Coarse-to-finE (NICE) registration methods have been proposed to perform coarse-to-fine registration in a single network and showed advantages in both registration accuracy and runtime.
AdaMSS: Adaptive Multi-Modality Segmentation-to-Survival Learning for Survival Outcome Prediction from PET/CT Images
Instead of adopting MTL, we propose a novel Segmentation-to-Survival Learning (SSL) strategy, where our AdaMSS is trained for tumor segmentation and survival prediction sequentially in two stages.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
Brain Tumor Sequence Registration with Non-iterative Coarse-to-fine Networks and Dual Deep Supervision
In this study, we focus on brain tumor sequence registration between pre-operative and follow-up Magnetic Resonance Imaging (MRI) scans of brain glioma patients, in the context of Brain Tumor Sequence Registration challenge (BraTS-Reg 2022).
Radiomics-enhanced Deep Multi-task Learning for Outcome Prediction in Head and Neck Cancer
Recently, deep learning methods have been proposed to perform end-to-end outcome prediction so as to remove the reliance on manual segmentation.
Non-iterative Coarse-to-fine Registration based on Single-pass Deep Cumulative Learning
Recently, iterative deep registration methods have been used to alleviate this limitation, where the transformations are iteratively learned in a coarse-to-fine manner.
The Brain Tumor Sequence Registration (BraTS-Reg) Challenge: Establishing Correspondence Between Pre-Operative and Follow-up MRI Scans of Diffuse Glioma Patients
Registration of longitudinal brain MRI scans containing pathologies is challenging due to dramatic changes in tissue appearance.
DeepMTS: Deep Multi-task Learning for Survival Prediction in Patients with Advanced Nasopharyngeal Carcinoma using Pretreatment PET/CT
However, the models using the whole target regions will also include non-relevant background information, while the models using segmented tumor regions will disregard potentially prognostic information existing out of primary tumors (e. g., local lymph node metastasis and adjacent tissue invasion).
Enhancing Medical Image Registration via Appearance Adjustment Networks
In this study, we propose an Appearance Adjustment Network (AAN) to enhance the adaptability of DLRs to appearance variations.
Prediction of 5-year Progression-Free Survival in Advanced Nasopharyngeal Carcinoma with Pretreatment PET/CT using Multi-Modality Deep Learning-based Radiomics
Methods: A total of 257 patients (170/87 in internal/external cohorts) with advanced NPC (TNM stage III or IVa) were enrolled.
SPA: Stochastic Probability Adjustment for System Balance of Unsupervised SNNs
Spiking neural networks (SNNs) receive widespread attention because of their low-power hardware characteristic and brain-like signal response mechanism, but currently, the performance of SNNs is still behind Artificial Neural Networks (ANNs).
High-quality Panorama Stitching based on Asymmetric Bidirectional Optical Flow
For photos taken from a distant perspective, the parallax among them is relatively small, and the obtained panoramic image can be nearly seamless and undistorted.
Spiking Inception Module for Multi-layer Unsupervised Spiking Neural Networks
This module is trained through STDP-based competitive learning and outperforms the baseline modules on learning capability, learning efficiency, and robustness.
High-parallelism Inception-like Spiking Neural Networks for Unsupervised Feature Learning
Most STDP-based SNNs adopted a slow-learning Fully-Connected (FC) architecture and used a sub-optimal vote-based scheme for spike decoding.
