Recent studies highlighted a practical setting of unsupervised anomaly detection (UAD) that builds a unified model for multi-class images. Despite various advancements addressing this challenging task, the detection performance under the multi-class setting still lags far behind state-of-the-art class-separated models. Our research aims to bridge this substantial performance gap. In this paper, we present Dinomaly, a minimalist reconstruction-based anomaly detection framework that harnesses pure Transformer architectures without relying on complex designs, additional modules, or specialized tricks. Given this powerful framework consisting of only Attentions and MLPs, we found four simple components that are essential to multi-class anomaly detection: (1) Scalable foundation Transformers that extracts universal and discriminative features, (2) Noisy Bottleneck where pre-existing Dropouts do all the noise injection tricks, (3) Linear Attention that naturally cannot focus, and (4) Loose Reconstruction that does not force layer-to-layer and point-by-point reconstruction. Extensive experiments are conducted across popular anomaly detection benchmarks including MVTec-AD, VisA, Real-IAD, etc. Our proposed Dinomaly achieves impressive image-level AUROC of 99.6%, 98.7%, and 89.3% on the three datasets respectively, which is not only superior to state-of-the-art multi-class UAD methods, but also achieves the most advanced class-separated UAD records. Code is available at: https://github.com/guojiajeremy/Dinomaly

Deep learning-based fundus image enhancement has attracted extensive research attention recently, which has shown remarkable effectiveness in improving the visibility of low-quality images. However, these methods are often constrained to specific datasets and degradations, leading to poor generalization capabilities and having challenges in the fine-tuning process. Therefore, a general method for fundus image enhancement is proposed for improved generalizability and flexibility, which decomposes the enhancement task into reconstruction and adaptation phases. In the reconstruction phase, self-supervised training with unpaired data is employed, allowing the utilization of extensive public datasets to improve the generalizability of the model. During the adaptation phase, the model is fine-tuned according to the target datasets and their degradations, utilizing the pre-trained weights from the reconstruction. The proposed method improves the feasibility of latent diffusion models for retinal image enhancement. Adaptation loss and enhancement adaptor are proposed in autoencoders and diffusion networks for fewer paired training data, fewer trainable parameters, and faster convergence compared with training from scratch. The proposed method can be easily fine-tuned and experiments demonstrate the adaptability for different datasets and degradations. Additionally, the reconstruction-adaptation framework can be utilized in different backbones and other modalities, which shows its generality.

Due to the difficulty of collecting multi-label annotations for retinal diseases, fundus images are usually annotated with only one label, while they actually have multiple labels. Given that deep learning requires accurate training data, incomplete disease information may lead to unsatisfactory classifiers and even misdiagnosis. To cope with these challenges, we propose a co-pseudo labeling and active selection method for Fundus Single-Positive multi-label learning, named FSP. FSP trains two networks simultaneously to generate pseudo labels through curriculum co-pseudo labeling and active sample selection. The curriculum co-pseudo labeling adjusts the thresholds according to the model's learning status of each class. Then, the active sample selection maintains confident positive predictions with more precise pseudo labels based on loss modeling. A detailed experimental evaluation is conducted on seven retinal datasets. Comparison experiments show the effectiveness of FSP and its superiority over previous methods. Downstream experiments are also presented to validate the proposed method.

Hybrid level-set method merging edge-region terms has been widely investigated for image segmentation. Nevertheless, the existing models usually meet the issue that each coefficient of edge and region information is tough to choose. It is often determined empirically lacking reliable theory foundation. To alleviate this issue, in this letter, an adaptive edge-region collaborated level-set method is presented, where the internal and external parameters can be selected automatically. For internal parameters, we adopt the local intensity information entropy to overcome the difference in gray-level distribution between target and background. For external parameters, the iterative process of energy function is optimized in terms of the global collaboration of edge-region information. Five representative and recent models are selected as benchmarks to indicate the generalization of our method, which validates that the adaptive parameters can improve the Dice similarity coefficient (DSC) by 0.7%–1.3% with only a small increase in computation time. As a limitation, the proposed method is restricted to applications for single-phase level-set models.

Anomaly detection is an important task for medical image analysis, which can alleviate the reliance of supervised methods on large labelled datasets. Most existing methods use a pixel-wise self-reconstruction framework for anomaly detection. However, there are two challenges of these studies: 1) they tend to overfit learning an identity mapping between the input and output, which leads to failure in detecting abnormal samples; 2) the reconstruction considers the pixel-wise differences which may lead to an undesirable result. To mitigate the above problems, we propose a novel heterogeneous Auto-Encoder (Hetero-AE) for medical anomaly detection. Our model utilizes a convolutional neural network (CNN) as the encoder and a hybrid CNN-Transformer network as the decoder. The heterogeneous structure enables the model to learn the intrinsic information of normal data and enlarge the difference on abnormal samples. To fully exploit the effectiveness of Transformer in the hybrid network, a multi-scale sparse Transformer block is proposed to trade off modelling long-range feature dependencies and high computational costs. Moreover, the multi-stage feature comparison is introduced to reduce the noise of pixel-wise comparison. Extensive experiments on four public datasets (i.e., retinal OCT, chest X-ray, brain MRI, and COVID-19) verify the effectiveness of our method on different imaging modalities for anomaly detection. Additionally, our method can accurately detect tumors in brain MRI and lesions in retinal OCT with interpretable heatmaps to locate lesion areas, assisting clinicians in diagnosing abnormalities efficiently.

Unsupervised anomaly detection (UAD) aims to recognize anomalous images based on the training set that contains only normal images. In medical image analysis, UAD benefits from leveraging the easily obtained normal (healthy) images, avoiding the costly collecting and labeling of anomalous (unhealthy) images. Most advanced UAD methods rely on frozen encoder networks pre-trained using ImageNet for extracting feature representations. However, the features extracted from the frozen encoders that are borrowed from natural image domains coincide little with the features required in the target medical image domain. Moreover, optimizing encoders usually causes pattern collapse in UAD. In this paper, we propose a novel UAD method, namely Encoder-Decoder Contrast (EDC), which optimizes the entire network to reduce biases towards pre-trained image domain and orient the network in the target medical domain. We start from feature reconstruction approach that detects anomalies from reconstruction errors. Essentially, a contrastive learning paradigm is introduced to tackle the problem of pattern collapsing while optimizing the encoder and the reconstruction decoder simultaneously. In addition, to prevent instability and further improve performances, we propose to bring globality into the contrastive objective function. Extensive experiments are conducted across four medical image modalities including optical coherence tomography, color fundus image, brain MRI, and skin lesion image, where our method outperforms all current state-of-the-art UAD methods. Code is available at: https://github.com/guojiajeremy/EDC.

Most advanced unsupervised anomaly detection (UAD) methods rely on modeling feature representations of frozen encoder networks pre-trained on large-scale datasets, e.g. ImageNet. However, the features extracted from the encoders that are borrowed from natural image domains coincide little with the features required in the target UAD domain, such as industrial inspection and medical imaging. In this paper, we propose a novel epistemic UAD method, namely ReContrast, which optimizes the entire network to reduce biases towards the pre-trained image domain and orients the network in the target domain. We start with a feature reconstruction approach that detects anomalies from errors. Essentially, the elements of contrastive learning are elegantly embedded in feature reconstruction to prevent the network from training instability, pattern collapse, and identical shortcut, while simultaneously optimizing both the encoder and decoder on the target domain. To demonstrate our transfer ability on various image domains, we conduct extensive experiments across two popular industrial defect detection benchmarks and three medical image UAD tasks, which shows our superiority over current state-of-the-art methods.

One-shot neural architecture search (NAS) has recently become mainstream in the NAS community because it significantly improves computational efficiency through weight sharing. However, the supernet training paradigm in one-shot NAS introduces catastrophic forgetting, where each step of the training can deteriorate the performance of other architectures that contain partially-shared weights with current architecture. To overcome this problem of catastrophic forgetting, we formulate supernet training for one-shot NAS as a constrained continual learning optimization problem such that learning the current architecture does not degrade the validation accuracy of previous architectures. The key to solving this constrained optimization problem is a novelty search based architecture selection (NSAS) loss function that regularizes the supernet training by using a greedy novelty search method to find the most representative subset. We applied the NSAS loss function to two one-shot NAS baselines and extensively tested them on both a common search space and a NAS benchmark dataset. We further derive three variants based on the NSAS loss function, the NSAS with depth constrain (NSAS-C) to improve the transferability, and NSAS-G and NSAS-LG to handle the situation with a limited number of constraints. The experiments on the common NAS search space demonstrate that NSAS and it variants improve the predictive ability of supernet training in one-shot NAS with remarkable and efficient performance on the CIFAR-10, CIFAR-100, and ImageNet datasets. The results with the NAS benchmark dataset also confirm the significant improvements these one-shot NAS baselines can make.

This article investigates deep neural networks (DNNs)-based lung nodule classification with hyperparameter optimization. Hyperparameter optimization in DNNs is a computationally expensive problem, and a surrogate-assisted evolutionary algorithm has been recently introduced to automatically search for optimal hyperparameter configurations of DNNs, by applying computationally efficient surrogate models to approximate the validation error function of hyperparameter configurations. Different from existing surrogate models adopting stationary covariance functions (kernels) to measure the difference between hyperparameter points, this article proposes a nonstationary kernel that allows the surrogate model to adapt to functions whose smoothness varies with the spatial location of inputs. A multilevel convolutional neural network (ML-CNN) is built for lung nodule classification, and the hyperparameter configuration is optimized by the proposed nonstationary kernel-based Gaussian surrogate model. Our algorithm searches with a surrogate for optimal setting via a hyperparameter importance-based evolutionary strategy, and the experiments demonstrate our algorithm outperforms manual tuning and several well-established hyperparameter optimization methods, including random search, grid search, the tree-structured parzen estimator (TPE) approach, Gaussian processes (GP) with stationary kernels, and the recently proposed hyperparameter optimization via RBF and dynamic (HORD) coordinate search.

As the labeled anomalous medical images are usually difficult to acquire, especially for rare diseases, the deep learning based methods, which heavily rely on the large amount of labeled data, cannot yield a satisfactory performance. Compared to the anomalous data, the normal images without the need of lesion annotation are much easier to collect. In this paper, we propose an anomaly detection framework, namely [Formula: see text], extracting [Formula: see text]elf-supervised and tr [Formula: see text]ns [Formula: see text]ation-consistent features for [Formula: see text]nomaly [Formula: see text]etection. The proposed SALAD is a reconstruction-based method, which learns the manifold of normal data through an encode-and-reconstruct translation between image and latent spaces. In particular, two constraints (i.e., structure similarity loss and center constraint loss) are proposed to regulate the cross-space (i.e., image and feature) translation, which enforce the model to learn translation-consistent and representative features from the normal data. Furthermore, a self-supervised learning module is engaged into our framework to further boost the anomaly detection accuracy by deeply exploiting useful information from the raw normal data. An anomaly score, as a measure to separate the anomalous data from the healthy ones, is constructed based on the learned self-supervised-and-translation-consistent features. Extensive experiments are conducted on optical coherence tomography (OCT) and chest X-ray datasets. The experimental results demonstrate the effectiveness of our approach.

In the context of motor imagery, electroencephalography (EEG) data vary from subject to subject such that the performance of a classifier trained on data of multiple subjects from a specific domain typically degrades when applied to a different subject. While collecting enough samples from each subject would address this issue, it is often too time-consuming and impractical. To tackle this problem, we propose a novel end-to-end deep domain adaptation method to improve the classification performance on a single subject (target domain) by taking the useful information from multiple subjects (source domain) into consideration. Especially, the proposed method jointly optimizes three modules, including a feature extractor, a classifier, and a domain discriminator. The feature extractor learns the discriminative latent features by mapping the raw EEG signals into a deep representation space. A center loss is further employed to constrain an invariant feature space and reduce the intrasubject nonstationarity. Furthermore, the domain discriminator matches the feature distribution shift between source and target domains by an adversarial learning strategy. Finally, based on the consistent deep features from both domains, the classifier is able to leverage the information from the source domain and accurately predict the label in the target domain at the test time. To evaluate our method, we have conducted extensive experiments on two real public EEG data sets, data set IIa, and data set IIb of brain-computer interface (BCI) Competition IV. The experimental results validate the efficacy of our method. Therefore, our method is promising to reduce the calibration time for the use of BCI and promote the development of BCI.

One-Shot Neural Architecture Search (NAS) significantly improves the computational efficiency through weight sharing. However, this approach also introduces multi-model forgetting during the supernet training (architecture search phase), where the performance of previous architectures degrade when sequentially training new architectures with partially-shared weights. To overcome such catastrophic forgetting, the state-of-the-art method assumes that the shared weights are optimal when jointly optimizing a posterior probability. However, this strict assumption is not necessarily held for One-Shot NAS in practice. In this paper, we formulate the supernet training in the One-Shot NAS as a constrained optimization problem of continual learning that the learning of current architecture should not degrade the performance of previous architectures during the supernet training. We propose a Novelty Search based Architecture Selection (\textbf{NSAS}) loss function and demonstrate that the posterior probability could be calculated without the strict assumption when maximizing the diversity of the selected constraints. A greedy novelty search method is devised to find the most representative subset to regularize the supernet training. We apply our proposed approach to two One-Shot NAS baselines, random sampling NAS (RandomNAS) and gradient-based sampling NAS (GDAS). Extensive experiments demonstrate that our method enhances the predictive ability of the supernet in One-Shot NAS and achieves remarkable performance on CIFAR-10, CIFAR-100, and PTB with efficiency.

One-Shot Neural architecture search (NAS) has received wide attentions due to its computational efficiency. Most state-of-the-art One-Shot NAS methods use the validation accuracy based on inheriting weights from the supernet as the stepping stone to search for the best performing architecture, adopting a bilevel optimization pattern with assuming this validation accuracy approximates to the test accuracy after re-training. However, recent works have found that there is no positive correlation between the above validation accuracy and test accuracy for these One-Shot NAS methods, and this reward based sampling for supernet training also entails the rich-get-richer problem. To handle this deceptive problem, this paper presents a new approach, Efficient Novelty-driven Neural Architecture Search, to sample the most abnormal architecture to train the supernet. Specifically, a single-path supernet is adopted, and only the weights of a single architecture sampled by our novelty search are optimized in each step to reduce the memory demand greatly. Experiments demonstrate the effectiveness and efficiency of our novelty search based architecture sampling method.

Recent works on One-Shot Neural Architecture Search (NAS) mostly adopt a bilevel optimization scheme to alternatively optimize the supernet weights and architecture parameters after relaxing the discrete search space into a differentiable space. However, the non-negligible incongruence in their relaxation methods is hard to guarantee the differentiable optimization in the continuous space is equivalent to the optimization in the discrete space. Differently, this paper utilizes a variational graph autoencoder to injectively transform the discrete architecture space into an equivalently continuous latent space, to resolve the incongruence. A probabilistic exploration enhancement method is accordingly devised to encourage intelligent exploration during the architecture search in the latent space, to avoid local optimal in architecture search. As the catastrophic forgetting in differentiable One-Shot NAS deteriorates supernet predictive ability and makes the bilevel optimization inefficient, this paper further proposes an architecture complementation method to relieve this deficiency. We analyze the effectiveness of the proposed method, and a series of experiments have been conducted to compare the proposed method with state-of-the-art One-Shot NAS methods.

Cataract is the clouding of lens, which affects vision and it is the leading cause of blindness in the world's population. Accurate and convenient cataract detection and cataract severity evaluation will improve the situation. Automatic cataract detection and grading methods are proposed in this paper. With prior knowledge, the improved Haar features and visible structure features are combined as features, and multilayer perceptron with discrete state transition (DST-MLP) or exponential DST (EDST-MLP) are designed as classifiers. Without prior knowledge, residual neural networks with DST (DST-ResNet) or EDST (EDST-ResNet) are proposed. Whether with prior knowledge or not, our proposed DST and EDST strategy can prevent overfitting and reduce storage memory during network training and implementation, and neural networks with these strategies achieve state-of-the-art accuracy in cataract detection and grading. The experimental results indicate that combined features always achieve better performance than a single type of feature, and classification methods with feature extraction based on prior knowledge are more suitable for complicated medical image classification task. These analyses can provide constructive advice for other medical image processing applications.

We investigate the matrix function optimization under the orthonormal constraint on the matrix variable. By introducing an index-notation-arrangement-based chain rule (I-Chain rule), we obtain the gradient of the cost function and propose a revisited orthonormal-constraint-based projected gradient method to locate a minimum of an objective/cost function of matrix variables iteratively subject to orthonormal constraint. To guarantee the convergence the proposed method, existing schemes require the gradient can be represented by the multiplication of a symmetrical matrix and the matrix variable itself. This condition has been relaxed in this paper. New techniques are proposed to establish the convergence property of the iterative algorithm. Simulation results show the effectiveness of our framework. This paper allows more extensive applications of matrix function optimization problems in science and engineering.

Bayesian optimization (BO) has been broadly applied to computational expensive problems, but it is still challenging to extend BO to high dimensions. Existing works are usually under strict assumption of an additive or a linear embedding structure for objective functions. This paper directly introduces a supervised dimension reduction method, Sliced Inverse Regression (SIR), to high dimensional Bayesian optimization, which could effectively learn the intrinsic sub-structure of objective function during the optimization. Furthermore, a kernel trick is developed to reduce computational complexity and learn nonlinear subset of the unknowing function when applying SIR to extremely high dimensional BO. We present several computational benefits and derive theoretical regret bounds of our algorithm. Extensive experiments on synthetic examples and two real applications demonstrate the superiority of our algorithms for high dimensional Bayesian optimization.

We focus on the practical challenge of segmenting new retinal fundus images that are dissimilar to existing well-annotated data sets. It is addressed in this paper by a supervised learning pipeline, with its core being the construction of a synthetic fundus image data set using the proposed R-sGAN technique. The resulting synthetic images are realistic-looking in terms of the query images while maintaining the annotated vessel structures from the existing data set. This helps to bridge the mismatch between the query images and the existing well-annotated data set. As a consequence, any known supervised fundus segmentation technique can be directly utilized on the query images, after training on this synthetic data set. Extensive experiments on different fundus image data sets demonstrate the competitiveness of the proposed approach in dealing with a diverse range of mismatch settings.

This paper aims at synthesizing multiple realistic-looking retinal (or neuronal) images from an unseen tubular structured annotation that contains the binary vessel (or neuronal) morphology. The generated phantoms are expected to preserve the same tubular structure, and resemble the visual appearance of the training images. Inspired by the recent progresses in generative adversarial nets (GANs) as well as image style transfer, our approach enjoys several advantages. It works well with a small training set with as few as 10 training examples, which is a common scenario in medical image analysis. Besides, it is capable of synthesizing diverse images from the same tubular structured annotation. Extensive experimental evaluations on various retinal fundus and neuronal imaging applications demonstrate the merits of the proposed approach.

We focus on the challenging problem of filamentary structure segmentation in both 2D and 3D images, including retinal vessels and neurons, among others. Despite the increasing amount of efforts in learning based methods to tackle this problem, there still lack proper data-driven feature construction mechanisms to sufficiently encode contextual labelling information, which might hinder the segmentation performance. This observation prompts us to propose a data-driven approach to learn structured and contextual features in this paper. The structured features aim to integrate local spatial label patterns into the feature space, thus endowing the follow-up tree classifiers capability to grouping training examples with similar structure into the same leaf node when splitting the feature space, and further yielding contextual features to capture more of the global contextual information. Empirical evaluations demonstrate that our approach outperforms state-of-the-arts on well-regarded testbeds over a variety of applications. Our code is also made publicly available in support of the open-source research activities.

The aim of this study is about tracing filamentary structures in both neuronal and retinal images. It is often crucial to identify single neurons in neuronal networks, or separate vessel tree structures in retinal blood vessel networks, in applications such as drug screening for neurological disorders or computer-aided diagnosis of diabetic retinopathy. Both tasks are challenging as the same bottleneck issue of filament crossovers is commonly encountered, which essentially hinders the ability of existing systems to conduct large-scale drug screening or practical clinical usage. To address the filament crossovers' problem, a two-step graph-theoretical approach is proposed in this paper. The first step focuses on segmenting filamentary pixels out of the background. This produces a filament segmentation map used as input for the second step, where they are further separated into disjointed filaments. Key to our approach is the idea that the problem can be reformulated as label propagation over directed graphs, such that the graph is to be partitioned into disjoint sub-graphs, or equivalently, each of the neurons (vessel trees) is separated from the rest of the neuronal (vessel) network. This enables us to make the interesting connection between the tracing problem and the digraph matrix-forest theorem in algebraic graph theory for the first time. Empirical experiments on neuronal and retinal image datasets demonstrate the superior performance of our approach over existing methods.

Fall is one of great threats affecting people with old age. Aimed at the falling issue of aged, the paper explored a pre-impact fall early warning and protection system. This system consists of an early fall alarm, protection airbags, a remote monitoring platform and a guardian's cellphone app. The early fall alarm and airbags are integrated in a belt, convenient for wearing and hip-protection. The inner of early fall alarm has a MEMS sensor, which collects 3-axis accelerated velocity and 3-axis angular velocity. A fall detection algorithm is applied to recognize falls from activities of daily living (ADL). When there is a dangerous movement approaching fall, the early fall alarm will warn the aged to stop the movement. When the fall happens, the early fall alarm will trigger the airbag system, then the airbags in the belt will inflate as soon as possible to reduce the damage to the aged. In addition, the early fall alarm will ring and send message to the guardian's cellphone for help. Meanwhile, the kinematics of the human body during falling time will be stored in TF card and sent to remote monitoring platform for storage. Then the monitoring platform can show the fall location where the fall incident happens in the electronic map. In order to test the reliability of this early fall alarm and protection system, a series of experiments have been designed. The results show that this system can be relatively accurate to detect falls, accomplishing functions including early fall warning and alarming, airbag inflation, statics transferring and storage, real-time location, which has significant benefit for reducing the direct damage and shortening the aiding time.

BACKGROUND: Structural study of retinal blood vessels provides an early indication of diseases such as diabetic retinopathy, glaucoma, and hypertensive retinopathy. These studies require accurate tracing of retinal vessel tree structure from fundus images in an automated manner. However, the existing work encounters great difficulties when dealing with the crossover issue commonly-seen in vessel networks. RESULTS: In this paper, we consider a novel graph-based approach to address this tracing with crossover problem: After initial steps of segmentation and skeleton extraction, its graph representation can be established, where each segment in the skeleton map becomes a node, and a direct contact between two adjacent segments is translated to an undirected edge of the two corresponding nodes. The segments in the skeleton map touching the optical disk area are considered as root nodes. This determines the number of trees to-be-found in the vessel network, which is always equal to the number of root nodes. Based on this undirected graph representation, the tracing problem is further connected to the well-studied transductive inference in machine learning, where the goal becomes that of properly propagating the tree labels from those known root nodes to the rest of the graph, such that the graph is partitioned into disjoint sub-graphs, or equivalently, each of the trees is traced and separated from the rest of the vessel network. This connection enables us to address the tracing problem by exploiting established development in transductive inference. Empirical experiments on public available fundus image datasets demonstrate the applicability of our approach. CONCLUSIONS: We provide a novel and systematic approach to trace retinal vessel trees with the present of crossovers by solving a transductive learning problem on induced undirected graphs.

Cataract is a leading cause of blindness worldwide. Computer-aided cataract detection is two-fold significant. Firstly, it will be helpful in mass screening. Secondly, it can be used as the preprocessing step for computer-aided grading. In this paper, the enhanced texture feature is proposed based on the graders' expertise of cataract and the characteristics of the retro-illumination lens images. The statistics of the enhanced texture feature is used to train the linear discriminant analysis to detect the cataract. The accuracy of 84.8% is achieved on a clinical database that contains 4545 pairs of images. It demonstrates that the proposed method is promising for mass screening and as the preprocessing step for computer-aided grading.

In clinical diagnosis, a grade indicating the severity of nuclear cataract is often manually assigned by a trained ophthalmologist to a patient after comparing the lens' opacity severity in his/her slit-lamp images with a set of standard photos. This grading scheme is often subjective and time-consuming. In this paper, a novel computer-aided diagnosis method via ranking is proposed to facilitate nuclear cataract grading following conventional clinical decision-making process. The grade of nuclear cataract in a slit-lamp image is predicted using its neighboring labeled images in a ranked image list, which is achieved using a learned ranking function. This ranking function is learned via direct optimization on a newly proposed approximation to a ranking evaluation measure. Our proposed method has been evaluated by a large dataset composed of 1000 different cases, which are collected from an ongoing clinical population-based study. Both experimental results and comparison with several existing methods demonstrate the benefit of grading via ranking by our proposed method.

This paper presents a photometric restoration technique that automatically corrects shading within retinal images taken with a fundus camera. The proposed technique is based on the observation that the background of retinal images usually shows flat reflectance variations due to its high similarity in color and texture. It estimates shading through an iterative polynomial interpolation procedure that first estimates a shading image through a horizontal interpolation process and then improves the shading estimation by a vertical interpolation process. Once the shading image is estimated, a reflectance image can accordingly be determined based on the luminance of the retina image under study. Experiments on 161 retinal images of different qualities show promising results.

Computer aided analysis of medical images, a unique type of non-text media, can facilitate clinical diagnosis. As an example, an automatic opacity detection approach is proposed in this paper to grade cortical cataract more objectively. The automatic pupil detection is performed by detecting the strongest edges on the convex hull and ellipse fitting using nonlinear least square method. The cortical opacity is detected by radial edge detection and post-processing. The automatic grades are assigned following Wisconsin cataract grading protocol. The accuracy of pupil detection is 98.2%. The mean error of opacity area detection is 7 percent compared with the result of human grader. And 86.3% accurate grades of cortical cataract are achieved. This is the first time that the spoke-like feature is utilized in the automatic detection of cortical cataract to separate from other opacity types. The encouraging results show that it is probable to apply the proposed approach to clinical diagnosis later.

In this paper, we analyze the convergence of an iterative self-training semi-supervised support vector machine (SVM) algorithm, which is designed for classification in small training data case. This algorithm converges fast and has low computational burden. Its effectiveness is also demonstrated by our data analysis results. Furthermore, we illustrate that this algorithm can be used to significantly reduce training effort and improve adaptability of a brain computer interface (BCI) system, a P300-based speller.

A new approach to automatically extract the main features in color fundus images is proposed. The optic disk is localized by principal component analysis (PCA) and its shape is detected by a modified active shape model (ASM). Exudates are extracted by the combined region growing and edge detection. A fundus coordinate system is further set up based on fovea localization to provide a better description of the features in fundus images. The success rates achieved are 99%, 94%, and 100% for disk localization, disk boundary detection, and fovea localization respectively. The sensitivity and specificity for exudate detection are 100% and 71%. The success of the proposed algorithms can be attributed to utilization of the model-based methods.

Accurate measurement and identification of blood vessels could provide useful information to clinical diagnosis. A piecewise Gaussian model is proposed to describe the intensity distribution of vessel profile in this paper. The characteristic of central reflex is specially considered in the proposed model. The comparison with the single Gaussian model is performed, which shows that the piecewise Gaussian model is a more appropriate model for vessel profile. The obtained model parameters could be utilized in the identification of vessel type. The minimum Mahalanobis distance classifier is employed in the classification. 505 segments of vessels were tested. The success rate is 82.46% and 89.03% for the arteries and veins respectively.

An approach to abnormality detection from colour fundus images for an automated mass screening system is proposed in this paper, which uses the object-based colour difference image. Four colour models, viz. RGB, Luv, Lab and HVC, are evaluated based on hand-labelled feature maps, and Luv and Lab are selected for computing the colour difference because of their good performances in object classification. The object-based colour difference images of bright objects (e.g. exudates) and dark objects (e.g. haemorrhages and blood vessels) are obtained respectively according to the 2D histogram distribution on the L-u plane, and then a watershed transform is performed on the colour difference image to extract object candidates. A pre-thresholding and a post-verification procedure are performed to deal with the over-segmentation problem of the watershed transform.

On the research work leading to automatic analysis of retinal fundus images, the knowledge of the optic disk location is essential, and a new method to locate the optic disk automatically is proposed. The candidate regions are first determined by clustering the brightest pixels in the intensity image. Principal component analysis (PCA) is then applied to these candidate regions. The minimum distance between the original retinal image and its projection onto "disk space" is located as the center of the optic disk. The algorithm has been tested and compared with another commonly used method and the results show that the method proposed here can provide more acceptable automatic location of the optic disk.