Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks127 from public data
- 1,373
- Convolutional Neural Networks-Based MRI Image Analysis for the Alzheimer’s Disease Prediction From Mild Cognitive Impairment390
A deep learning approach based on convolutional neural networks, designed to accurately predict MCI-to-AD conversion with magnetic resonance imaging (MRI) data, outperforms others with higher accuracy and AUC, while keeping a good balance between the sensitivity and specificity.
- Diagnosis of Alzheimer’s Disease via Multi-Modality 3D Convolutional Neural Network291
A convolutional neural network to integrate all the multi-modality information included in both T1-MR and FDG-PET images of the hippocampal area, for the diagnosis of AD is proposed and yields a state-of-the-art performance.
- 220
- Multiple instance learning for classification of dementia in brain MRI214
The proposed multiple instance learning (MIL) method for Alzheimer's disease and its prodromal stage mild cognitive impairment can achieve similar or improved results, providing an alternative framework for the detection and prediction of neurodegenerative diseases.
- Segmentation of MR images via discriminative dictionary learning and sparse coding: Application to hippocampus labeling209
A novel method for the automatic segmentation of brain MRI images by using discriminative dictionary learning and sparse coding techniques, which can learn dictionaries offline and perform segmentations online, enabling a significant speed-up in the segmentation stage.
- PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report161
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones and proposes solutions that significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.
- Discriminative dictionary learning for abdominal multi-organ segmentation154
An automated segmentation method is presented for multi-organ segmentation in abdominal CT images and achieves a promising segmentation performance with Dice overlap values of 94.9%, 93.6%, 71.1%, and 92.5% for liver, kidneys, pancreas, and spleen, respectively.
- 140
- 137
- Bidirectional Mapping of Brain MRI and PET With 3D Reversible GAN for the Diagnosis of Alzheimer’s Disease124
The experimental results show that the structural and functional information of brain tissue can be mapped well and that the image synthesized by the proposed method is close to the real image, demonstrating the effectiveness of the proposed framework.
- Image Super-Resolution Using Knowledge Distillation95
The proposed method significantly improves the SR performance of a student network without changing its structure, which means that the computational time and the memory consumption do not increase during the testing stage while theSR performance is significantly improved.
- Multiclass diagnosis of stages of Alzheimer's disease using linear discriminant analysis scoring for multimodal data92
The results showed that the proposed framework for AD multiclass diagnosis with a linear discriminant analysis (LDA) scoring method achieved a better performance than the method that did not score multimodal data and the methods in previous studies, thereby indicating that the LDA scoring strategy is an efficient way for multimodalities fusion inAD multiclass classification.
- NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results85
This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field.
- Predicting Alzheimer’s Disease Conversion From Mild Cognitive Impairment Using an Extreme Learning Machine-Based Grading Method With Multimodal Data78
An extreme learning machine (ELM)-based grading method is developed to efficiently fuse multimodal data and predict MCI-to-AD conversion, resulting in an accurate prediction of MCI-to-AD conversion.
- 56
- 47
- CoTrFuse: a novel framework by fusing CNN and transformer for medical image segmentation45
The proposed CoTrFuse network is a network that combines the strengths of both CNN and Transformer that outperforms several state-of-the-art segmentation methods, indicating its superiority in medical image segmentation.
- 42
- Graph Reasoning-Based Emotion Recognition Network41
This paper proposes a novel framework based on the graph convolutional network for emotion recognition by utilizing the semantic relationships of different regions to achieve superior performance over state-of-the-art approaches for the emotion recognition on the CEAR and AFEW datasets.
- 39
- A Super-resolution Guided Network for Improving Automated Thyroid Nodule Segmentation36
A novel framework to improve the accuracy of thyroid nodules segmentation and provide a new way of ultrasound image segmentation that outperforms most state-of-the-art methods and can provide doctors with reliable auxiliary diagnosis information in clinical practice.
- 33
- Supervoxel Classification Forests for Estimating Pairwise Image Correspondences32
A general method for establishing pairwise correspondences, which is a fundamental problem in image analysis, and the quality of the correspondences is determined in a label propagation setting, demonstrating the potential of supervoxel classification forests for estimating image correspondences.
- N-Net: A novel dense fully convolutional neural network for thyroid nodule segmentation31
A novel N-shape dense fully convolutional neural network for medical image segmentation, referred to as N-Net, which outperforms several state-of-the-art methods in the thyroid nodule segmentation tasks.
- 30
- 26
- 26
- Functional density and edge maps: Characterizing functional architecture in individuals and improving cross-subject registration26
The results suggest that the proposed functional density and edge maps are promising features in characterizing the functional architecture in individuals and provide an alternative way to explore the functional variation across subjects.
- Multi-Atlas Segmentation Using Partially Annotated Data: Methods and Annotation Strategies25
This work re-examines the labelling problem common in many existing approaches and formulates its solution in terms of a Markov Random Field energy minimisation problem on a graph connecting atlases and the target image to provide a unifying framework for multi-atlas segmentation.
- Saliency-CCE: Exploiting colour contextual extractor and saliency-based biomedical image segmentation24
A novel dual-task framework for white blood cell (WBC) and skin lesion (SL) saliency detection and segmentation in biomedical images, called Saliency-CCE is proposed, which outperform representative state-of-the-art SOD and biomedical image segmentation approaches.
- A Deep Learning Quantification Algorithm for HER2 Scoring of Gastric Cancer24
This is the first study to provide a deep learning quantification algorithm for HER2 scoring of gastric cancer to assist the pathologist's diagnosis and the effectiveness of the proposed method is demonstrated.
- A novel framework for segmentation of small targets in medical images23
A segmentation framework termed STS-Net is introduced, specifically designed for small target segmentation, which leverages the established capacity of convolutional neural networks to acquire effective image representations.
- Ntire 2025 Image Shadow Removal Challenge Report22
This work examines the findings of the NTIRE 2025 Shadow Removal Challenge, with 17 teams successfully submitting their solutions during the final evaluation phase, and one focusing on reconstruction fidelity and the other on visual perception through a user study.
- 22
- 21
- Stain Style Transfer Using Transitive Adversarial Networks21
A novel network that is referred to as Transitive Adversarial Networks (TAN) to transfer the color information among slides from different hospitals or centers is proposed, demonstrating the effectiveness of the proposed TAN method in stain style transfer.
- Deep learning-based prediction of HER2 status and trastuzumab treatment efficacy of gastric adenocarcinoma based on morphological features15
An algorithm is explored that utilizes hematoxylin and eosin (H&E) staining to accurately predict HER2 status and assess the response to trastuzumab in GAC, potentially facilitating clinical decision-making.
- LightR-YOLOv5: A compact rotating detector for SARS-CoV-2 antigen-detection rapid diagnostic test results14
LightR-YOLOv5, a compact rotating SARS-CoV-2 antigen-detection RDT results detector is proposed and a new data augmentation approach, Single-Copy–Paste, is proposed for increasing data samples for the specific task of RDT result detection while achieving a small improvement in model accuracy.
- Multi-atlas Segmentation as a Graph Labelling Problem: Application to Partially Annotated Atlas Data14
This paper revisits the problem of multi-atlas segmentation and forms its solution in terms of graph-labelling using a Markov Random Field formulation and provides an extension to an existing continuous MRF optimisation method to solve the proposed problem formulation.
- Spatially Aware Patch-Based Segmentation (SAPS): An Alternative Patch-Based Segmentation Framework14
This paper presents a novel alternative framework which combines the use of kNN search structures such as ball trees and a spatially weighted label fusion scheme to search patches in large regional areas to overcome the problem of limited search windows.
- A Multi-Scale Densely Connected Convolutional Neural Network for Automated Thyroid Nodule Classification13
The proposed n-ClsNet achieves an average accuracy (ACC) score of 93.8% in the thyroid nodule classification task, which outperforms several representative state-of-the-art classification methods.
- 11
- 11
- 11
- Improved generative adversarial networks using the total gradient loss for the resolution enhancement of fluorescence images11
This work developed a post-processing method for FI resolution enhancement by employing improved generative adversarial networks, and proposed total gradient loss for network training to overcome the drawback of fake texture generation.
- 11
- UniMRISegNet: Universal 3D Network for Various Organs and Cancers Segmentation on Multi-Sequence MRI10
- 10
- 10
- 9
- 9
- 9
- A blind image super-resolution network guided by kernel estimation and structural prior knowledge8
This work proposes a two stage blind super-resolution network that is based on kernel estimation strategy and is capable of integrating structural texture as prior knowledge and outperforms the state-of-the-art methods in terms of fidelity and recovery of clear details.
- Weakly Supervised Classification for Nasopharyngeal Carcinoma With Transformer in Whole Slide Images8
- 7
- A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image Classifications7
A parameterized GAN (ParaGAN) that effectively controls the changes of synthetic samples among domains and highlights the attention regions for downstream classification is proposed that can consistently outperform the existing augmentation methods with explainable classification on two small-scale medical datasets.
- 7
- Unpaired Stain Style Transfer Using Invertible Neural Networks Based on Channel Attention and Long-Range Residual7
An unsupervised color normalization method based on channel attention and long-range residual, using a technology called invertible neural networks (INN) to transfer the stain style while preserving the tissue semantics between different hospitals or centers, resulting in a virtual stained sample in the sense that no actual stains are used.
- Compact StereoNet: Stereo Disparity Estimation via Knowledge Distillation and Compact Feature Extractor7
An efficient convolutional neural architecture for stereo disparity estimation is proposed and a novel adaptive $Smooth_{L1}$ (ASL) Loss for calculating the similarity between the contextual features of the teacher network and those of the student network is presented, resulting in a more robust distillation process.
- MBVCNN: Joint convolutional neural networks method for image recognition7
Aiming at the problem of objects in image recognition rectangle, but objects which are input into convolutional neural networks square, the object recognition model was put forward which was based on BING method to realize object estimate and built joint convolution neural networks, which achieve multiple size image input.
- 7
- 6
- 6
- Distance guided generative adversarial network for explainable medical image classifications6
A distance-guided GAN (DisGAN) that controls the variation degrees of generated samples in the hyperplane space that can apply to different classification architectures and has the potential to extend to multi-class classification.
- 5
- Comprehensive Mendelian randomization analysis of low-density lipoprotein cholesterol and multiple cancers5
Analyses using both the HMGCR and PCSK9 genes have shown that LDL-C may be a potential risk factor for breast and prostate cancer, while analyses of the HMGCR gene have also suggested that LDL-C may increase the risk of thyroid cancer and decrease the risk of colorectal cancer.
- Toward Real World Stereo Image Super-Resolution via Hybrid Degradation Model and Discriminator for Implied Stereo Image Information5
A novel approach is proposed that integrates a implicit stereo information discriminator and a hybrid degradation model that ensures effective enhancement while preserving disparity consistency, and demonstrates impressive performance on synthetic and real datasets.
- 5
- 4
- 4
- ScribbleVS: Scribble-Supervised Medical Image Segmentation via Dynamic Competitive Pseudo Label Selection4
This work introduces ScribbleVS, a framework designed to learn from scribble annotations, and introduces a Regional Pseudo Labels Diffusion Module to expand the scope of supervision and reduce the impact of noise present in pseudo labels.
- Dual-Decoder Consistency via Pseudo-Labels Guided Data Augmentation for Semi-Supervised Medical Image Segmentation4
A novel semi-supervised learning method, Dual-Decoder Consistency via Pseudo-Labels Guided Data Augmentation (DCPA), for medical image segmentation that uses distinct decoders for student and teacher networks while maintain the same encoder.
- 4
- Deep Learning Framework for Detecting Positive Lymph Nodes of Gastric Cancer on Histopathological Images4
The results demonstrated that the proposed framework can not only reduce pathological workload to a certain extent, but can also assist in identifying positive lymph nodes and determining the N staging of gastric cancer in patients.
- 4
- Enhancement Mask for Hippocampus Detection and Segmentation4
A two-stage 3D fully convolutional neural network that efficiently detects and segments the hippocampal structures and has remarkable benefits for accelerating training process and obtaining more accurate segmentation results.
- 3
- 3
- 3
- 3
- E2-RealSR: efficient and effective real-world super-resolution network based on partial degradation modulation3
This work proposes an efficient and effective real-world image super-resolution network (E2-RealSR) based on partial degradation modulation, which is consisted of a small regression and a lightweight super-resolution network.
- 3
- 3
- 3
- 3
- 3
- Multi-angle Dual-task Consistency for Semi-Supervised Medical Image Segmentation3
A novel Multi-angle Dual-task Consistency Network (MDC-Net) for semi-supervised medical image segmentation that overcomes the problem of incomplete segmentation caused by noise in pseudo labels, but also enforces geometric constraints and makes the model more robust.
- Multi-atlas propagation via a manifold graph on a database of both labeled and unlabeled images3
This work presents a framework for multi-atlas based segmentation in situations where the authors have a small number of segmented atlas images, but a large database of unlabeled images is also available.
- Implicit Neural Representation-Based MRI Reconstruction Method With Sensitivity Map Constraints2
This work proposes INR-CRISTAL, a joint image and sensitivity estimation framework that introduces explicit regularization on sensitivity maps to leverage their inherent smoothness and designs a frequency-adaptive sinusoidal representation network (FA-SIREN) that enables dynamic frequency modulation at each layer, improving the adaptability to heterogeneous spectral components within complex signals.
- 2
- VariMix: A variety-guided data mixing framework for explainable medical image classifications2
A variety-guided data mixing framework (VariMix), which exploits an absolute difference map (ADM) to address the label mismatch problems of mixed medical images and demonstrates the superiority of VariMix compared with the existing GAN- and Mixup-based methods on four public datasets using Swin Transformer V2 and ConvNeXt architectures.
- 2
- 2
- Multi-stage network for single image Demoireing2
This work proposes a multi-stage and multi-patch network, which can recover non-homogeneous moire images by aggregating the features of different spatial regions of patches in different stages and introduces a novel Atrous Fusion Module in different atrous rates to learn multi-scale information.
- Crowd Counting with Dilated Inception Convolution2
The proposed lightweight crowd density map estimation architecture with Dilated Inception Convolution Neural Network (DICNN) not only extracts scale-aware informative features, but also effectively reduces the number of parameters of the CNN architecture.
- 2
- 2
- 2
- MSAN-Net: An End-to-End Multi-Scale Attention Network for Universal Industrial Defect Detection1
Extensive experiments showed that MSAN-Net was outperformed existing SOTA models in industrial defect detection tasks, significantly improving detection accuracy for multi-class defects in complex scenarios, reducing reliance on manual inspection, and effectively lowering scrap losses caused by defects, thus providing a reliable solution for intelligent quality inspection in the electronics manufacturing industry.
- 1
- 1
- 1
- GLNet: low-light image enhancement via grayscale priors1
Two novel and general approaches are presented, which propose a new loss function to constrain the ratio between the corresponding RGB pixel values on the low- light image and the high-light image, and a new framework named GLNet, which uses the dense residual connection block to obtain the deep features of theLow-light images, and design a gray scale channel network branch to guide the texture restoration on the RGB channels by enhancing the grayscale image.
- Enhanced multi-stage network for defocus deblurring using dual-pixel images1
Experimental results show that the proposed enhanced multi-stage network for defocus deblurring using dual-pixel Images can achieve better accuracy than state-of-the-art approaches on the public DPD dataset.
- 1
- Modified gray level difference-based thresholding segmentation and its application in X-Ray welding image1
A modified gray level difference-based transition region extraction and thresholding algorithm is presented for segmentation of the images that have been corrupted by intensity inhomogeneities or noise.
- A Watermarking Algorithm for Color Halftone Image Based on MBVQ1
Experimental results show that the new digital watermarking algorithm presented has a good transparent watermark, furthermore, it is robust against various signal processing such as random alternation, text addition and geometric shear.
- –
- Innovative Quantitative Analysis for Disease Progression Assessment in Familial Cerebral Cavernous Malformations–
A quantitative statistical framework for FCCM, which comprises an efficient annotation module, an FCCM lesion segmentation module, and an FCCM lesion quantitative statistics module, which provides a quantitative assessment method for disease progression and drug efficacy study, but also considerably reduces the manual measurement and statistical workload of lesions.
- A Patch-Based Hankel Low-Rank Method for MRI Reconstruction–
A patch-based Hankel low rank method is proposed by utilizing the low-rankness of a series of k-space patches to accelerate Hankel low-rank reconstruction without sacrificing reconstruction quality.
- IP23-34 DEEP LEARNING-BASED PROSTATE CANCER POSTOPERATIVE BIOCHEMICAL RECURRENCE PREDICTION MODEL: AN INTERNATIONAL MULTICENTER STUDY–
The rate of acquisition of urinary incontinence at 12 months after RARP was 80%, and age and BMI were identi fi ed as signi fi cant risk factors for postoperative urinary incontinence.
- ASteISR: Adapting Single Image Super-resolution Pre-trained Model for Efficient Stereo Image Super-resolution–
This paper introduces the concept of stereo adapters and spatial adapters which are incorporated into the pre-trained SISR transformer network and proposes a efficient method for transferring a pre-trained single-image super-resolution transformer network to the domain of stereo image super-resolution (SteISR) through a parameter-efficient fine-tuning (PEFT) method.
- –
- –
- –
- –
- –
- –
- –
- Distance Guided Generative Adversarial Network for Explainable Binary Classifications–
A distance guided GAN (DisGAN) which controls the variation degrees of generated samples in the hyperplane space which can apply to different classification architectures and has potential to extend to multi-class classification.
- –
- –
- –
- –
- –
- Edge Detection Combined Local Gray Level Difference and Competitive Fuzzy Logic–
From the experimental result, it can be seen that the edge detection method proposed in this paper is superior to Canny method and Log method under the noisy condition.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.