arXiv subjects

Xinjian Chen

Publications and source records attributed to Xinjian Chen.

12 recordsLinked to original sources

arXiv2026

Clinician-Friendly Foundation Models for Ophthalmic Image Diagnostics without Fine-Tuning or Technical Barriers

Artificial intelligence (AI) shows remarkable potential in medical imaging diagnostics, yet most current models require retraining when applied across different clinical settings, limiting their scalability. We developed GlobeReady, a deployment-oriented platform powered by the RetiGlobe foun- dation model and local feature augmentation. RetiGlobe was pretrained in two stages: 1) self-supervised learning using DINOv2 on 38 million synthetic ophthalmic images, and 2) contrastive learning using CLIP on 475,845 real image-text pairs spanning diverse ethnicities, imaging devices, and geographic regions worldwide. We evaluate GlobeReady on 488,448 ophthalmic images, including color fundus photographs (CFPs) and optical coherence tomography scans, from multi-centres in China, Singapore, Vietnam and the UK. Prospective testing included usability assessment with 31 ophthalmologists. Exploratory analyses evaluated domain generalisability, Bayesian uncertainty quantification, out-of-distribution (OOD) detection, and feature-based case retrieval.

cs.CV↗

arXiv2026

HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA

Retrieval-Augmented Generation (RAG) significantly improves document-based question answering by integrating external documents during generation. However, retrieval accuracy can degrade when the knowledge base contains many semantically and structurally similar documents. We introduce HiQA, a practical hierarchical contextual augmentation framework for multi-document question answering (MDQA). HiQA enriches text chunks with cascading document metadata, such as document titles and section paths, so that retrieval can use both local content and document structure. The framework also uses a multi-route retriever that combines semantic, lexical, and keyword/entity signals. We further introduce MasQA, a benchmark designed to evaluate MDQA systems in realistic similar-document settings. Experiments show that HiQA improves retrieval and answer quality on MasQA and remains competitive on public MDQA benchmarks, while its benefits are strongest for structured, domain-specific, highly similar document collections.

cs.CL↗

arXiv2025

Enhancing Diagnostic Accuracy in Rare and Common Fundus Diseases with a Knowledge-Rich Vision-Language Model

Previous foundation models for fundus images were pre-trained with limited disease categories and knowledge base. Here we introduce a knowledge-rich vision-language model (RetiZero) that leverages knowledge from more than 400 fundus diseases. For RetiZero's pretraining, we compiled 341,896 fundus images paired with texts, sourced from public datasets, ophthalmic literature, and online resources, encompassing a diverse range of diseases across multiple ethnicities and countries. RetiZero exhibits remarkable performance in several downstream tasks, including zero-shot disease recognition, image-to-image retrieval, AI-assisted clinical diagnosis,few-shot fine-tuning, and internal- and cross-domain disease identification. In zero-shot scenarios, RetiZero achieves Top-5 accuracies of 0.843 for 15 diseases and 0.756 for 52 diseases. For image retrieval, it achieves Top-5 scores of 0.950 and 0.886 for the same sets, respectively. AI-assisted clinical diagnosis results show that RetiZero's Top-3 zero-shot performance surpasses the average of 19 ophthalmologists from Singapore, China, and the United States. RetiZero substantially enhances clinicians' accuracy in diagnosing fundus diseases, in particularly rare ones. These findings underscore the value of integrating the RetiZero into clinical settings, where various fundus diseases are encountered.

eess.IV↗

arXiv2024

AI-based Automatic Segmentation of Prostate on Multi-modality Images: A Review

Prostate cancer represents a major threat to health. Early detection is vital in reducing the mortality rate among prostate cancer patients. One approach involves using multi-modality (CT, MRI, US, etc.) computer-aided diagnosis (CAD) systems for the prostate region. However, prostate segmentation is challenging due to imperfections in the images and the prostate's complex tissue structure. The advent of precision medicine and a significant increase in clinical capacity have spurred the need for various data-driven tasks in the field of medical imaging. Recently, numerous machine learning and data mining tools have been integrated into various medical areas, including image segmentation. This article proposes a new classification method that differentiates supervision types, either in number or kind, during the training phase. Subsequently, we conducted a survey on artificial intelligence (AI)-based automatic prostate segmentation methods, examining the advantages and limitations of each. Additionally, we introduce variants of evaluation metrics for the verification and performance assessment of the segmentation method and summarize the current challenges. Finally, future research directions and development trends are discussed, reflecting the outcomes of our literature survey, suggesting high-precision detection and treatment of prostate cancer as a promising avenue.

eess.IV↗

arXiv2024

Enhancing Diagnostic Reliability of Foundation Model with Uncertainty Estimation in OCT Images

Inability to express the confidence level and detect unseen classes has limited the clinical implementation of artificial intelligence in the real-world. We developed a foundation model with uncertainty estimation (FMUE) to detect 11 retinal conditions on optical coherence tomography (OCT). In the internal test set, FMUE achieved a higher F1 score of 96.76% than two state-of-the-art algorithms, RETFound and UIOS, and got further improvement with thresholding strategy to 98.44%. In the external test sets obtained from other OCT devices, FMUE achieved an accuracy of 88.75% and 92.73% before and after thresholding. Our model is superior to two ophthalmologists with a higher F1 score (95.17% vs. 61.93% &71.72%). Besides, our model correctly predicts high uncertainty scores for samples with ambiguous features, of non-target-category diseases, or with low-quality to prompt manual checks and prevent misdiagnosis. FMUE provides a trustworthy method for automatic retinal anomalies detection in the real-world clinical open set environment.

eess.IV↗

arXiv2023

Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification

Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies. We established an uncertainty-inspired open-set (UIOS) model, which was trained with fundus images of 9 retinal conditions. Besides assessing the probability of each category, UIOS also calculated an uncertainty score to express its confidence. Our UIOS model with thresholding strategy achieved an F1 score of 99.55%, 97.01% and 91.91% for the internal testing set, external target categories (TC)-JSIEC dataset and TC-unseen testing set, respectively, compared to the F1 score of 92.20%, 80.69% and 64.74% by the standard AI model. Furthermore, UIOS correctly predicted high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images. UIOS provides a robust method for real-world screening of retinal anomalies.

cs.LG↗

arXiv2020

Accurate Retinal Vessel Segmentation via Octave Convolution Neural Network

Retinal vessel segmentation is a crucial step in diagnosing and screening various diseases, including diabetes, ophthalmologic diseases, and cardiovascular diseases. In this paper, we propose an effective and efficient method for vessel segmentation in color fundus images using encoder-decoder based octave convolution networks. Compared with other convolution networks utilizing standard convolution for feature extraction, the proposed method utilizes octave convolutions and octave transposed convolutions for learning multiple-spatial-frequency features, thus can better capture retinal vasculatures with varying sizes and shapes. To provide the network the capability of learning how to decode multifrequency features, we extend octave convolution and propose a new operation named octave transposed convolution. A novel architecture of convolutional neural network, named as Octave UNet integrating both octave convolutions and octave transposed convolutions is proposed based on the encoder-decoder architecture of UNet, which can generate high resolution vessel segmentation in one single forward feeding without post-processing steps. Comprehensive experimental results demonstrate that the proposed Octave UNet outperforms the baseline UNet achieving better or comparable performance to the state-of-the-art methods with fast processing speed. Specifically, the proposed method achieves 0.9664 / 0.9713 / 0.9759 / 0.9698 accuracy, 0.8374 / 0.8664 / 0.8670 / 0.8076 sensitivity, 0.9790 / 0.9798 / 0.9840 / 0.9831 specificity, 0.8127 / 0.8191 / 0.8313 / 0.7963 F1 score, and 0.9835 / 0.9875 / 0.9905 / 0.9845 Area Under Receiver Operating Characteristic curve, on DRIVE, STARE, CHASE_DB1, and HRF datasets, respectively.

eess.IV↗

arXiv2020

Low Tensor Train- and Low Multilinear Rank Approximations for De-speckling and Compression of 3D Optical Coherence Tomography Images

This paper proposes low tensor-train (TT) rank and low multilinear (ML) rank approximations for de-speckling and compression of 3D optical coherence tomography (OCT) images for a given compression ratio (CR). To this end, we derive the alternating direction method of multipliers based algorithms for the related problems constrained with the low TT- and low ML rank. Rank constraints are implemented through the Schatten-p (Sp) norm, p e {0, 1/2, 2/3, 1}, of unfolded matrices. We provide the proofs of global convergence towards a stationary point for both algorithms. Rank adjusted 3D OCT image tensors are finally approximated through tensor train- and Tucker alternating least squares decompositions. We comparatively validate the low TT- and low ML rank methods on twenty-two 3D OCT images with the JPEG2000 and 3D SPIHT compression methods, as well as with no compression 2D bilateral filtering (BF), 2D median filtering (MF), and enhanced low-rank plus sparse matrix decomposition (ELRpSD) methods. For the CR<10, the low Sp TT rank method with pe{0, 1/2, 2/3} yields either highest or comparable signal-to-noise ratio (SNR), and comparable or better contrast-to-noise ratio (CNR), mean segmentation errors (SEs) of retina layers and expert-based image quality score (EIQS) than original image and image compression methods. It compares favorably in terms of CNR, fairly in terms of SE and EIQS with the no image compression methods. Thus, for CR<10 the low S2/3 TT rank approximation can be considered a good choice for visual inspection based diagnostics. For 2<CR<60, the low S1 ML rank method compares favorably in terms of SE with image compression methods and with 2D BF and ELRpSD. It is slightly inferior to 2D MF. Thus, for 2<CR<60, the low S1 ML rank approximation can be considered a good choice for segmentation based diagnostics either on-site or in the remote mode of operation.

math.NA↗

arXiv2018

Non-rigid image registration using spatially region-weighted correlation ratio and GPU-acceleration

Objective: Non-rigid image registration with high accuracy and efficiency is still a challenging task for medical image analysis. In this work, we present the spatially region-weighted correlation ratio (SRWCR) as a novel similarity measure to improve the registration performance. Methods: SRWCR is rigorously deduced from a three-dimension joint probability density function combining the intensity channels with an extra spatial information channel. SRWCR estimates the optimal functional dependence between the intensities for each spatial bin, in which the spatial distribution modeled by a cubic B-spline function is used to differentiate the contribution of voxels. We also analytically derive the gradient of SRWCR with respect to the transformation parameters and optimize it using a quasi-Newton approach. Furthermore, we propose a GPU-based parallel mechanism to accelerate the computation of SRWCR and its derivatives. Results: The experiments on synthetic images, public 4-D thoracic computed tomography (CT) dataset, retinal optical coherence tomography (OCT) data, and clinical CT and positron emission tomography (PET) images confirm that SRWCR significantly outperforms some state-of-the-art techniques such as spatially encoded mutual information and Robust PaTch-based cOrrelation Ration. Conclusion: This study demonstrates the advantages of SRWCR in tackling the practical difficulties due to distinct intensity changes, serious speckle noise, or different imaging modalities. Significance: The proposed registration framework might be more reliable to correct the non-rigid deformations and more potential for clinical applications.

stat.ME↗

arXiv2017

A Hierarchical Image Matting Model for Blood Vessel Segmentation in Fundus images

In this paper, a hierarchical image matting model is proposed to extract blood vessels from fundus images. More specifically, a hierarchical strategy utilizing the continuity and extendibility of retinal blood vessels is integrated into the image matting model for blood vessel segmentation. Normally the matting models require the user specified trimap, which separates the input image into three regions manually: the foreground, background and unknown regions. However, since creating a user specified trimap is a tedious and time-consuming task, region features of blood vessels are used to generate the trimap automatically in this paper. The proposed model has low computational complexity and outperforms many other state-ofart supervised and unsupervised methods in terms of accuracy, which achieves a vessel segmentation accuracy of 96:0%, 95:7% and 95:1% in an average time of 10:72s, 15:74s and 50:71s on images from three publicly available fundus image datasets DRIVE, STARE, and CHASE DB1, respectively.

cs.CV↗

arXiv2016

Gaze2Segment: A Pilot Study for Integrating Eye-Tracking Technology into Medical Image Segmentation

This study introduced a novel system, called Gaze2Segment, integrating biological and computer vision techniques to support radiologists' reading experience with an automatic image segmentation task. During diagnostic assessment of lung CT scans, the radiologists' gaze information were used to create a visual attention map. This map was then combined with a computer-derived saliency map, extracted from the gray-scale CT images. The visual attention map was used as an input for indicating roughly the location of a object of interest. With computer-derived saliency information, on the other hand, we aimed at finding foreground and background cues for the object of interest. At the final step, these cues were used to initiate a seed-based delineation process. Segmentation accuracy of the proposed Gaze2Segment was found to be 86% with dice similarity coefficient and 1.45 mm with Hausdorff distance. To the best of our knowledge, Gaze2Segment is the first true integration of eye-tracking technology into a medical image segmentation task without the need for any further user-interaction.

cs.CV↗

arXiv2010

Ball-Scale Based Hierarchical Multi-Object Recognition in 3D Medical Images

This paper investigates, using prior shape models and the concept of ball scale (b-scale), ways of automatically recognizing objects in 3D images without performing elaborate searches or optimization. That is, the goal is to place the model in a single shot close to the right pose (position, orientation, and scale) in a given image so that the model boundaries fall in the close vicinity of object boundaries in the image. This is achieved via the following set of key ideas: (a) A semi-automatic way of constructing a multi-object shape model assembly. (b) A novel strategy of encoding, via b-scale, the pose relationship between objects in the training images and their intensity patterns captured in b-scale images. (c) A hierarchical mechanism of positioning the model, in a one-shot way, in a given image from a knowledge of the learnt pose relationship and the b-scale image of the given image to be segmented. The evaluation results on a set of 20 routine clinical abdominal female and male CT data sets indicate the following: (1) Incorporating a large number of objects improves the recognition accuracy dramatically. (2) The recognition algorithm can be thought as a hierarchical framework such that quick replacement of the model assembly is defined as coarse recognition and delineation itself is known as finest recognition. (3) Scale yields useful information about the relationship between the model assembly and any given image such that the recognition results in a placement of the model close to the actual pose without doing any elaborate searches or optimization. (4) Effective object recognition can make delineation most accurate.

cs.CV↗