Given the increasing data requirements of deep learning models and the scarcity of medical imaging data, new data augmentation techniques are receiving particular attention. This paper explores the subfield of tumour synthesis within medical image generation, focusing on the development of synthetic tumours in MR images. This study introduces a novel tumour generation method using diffusion models, designed to inpaint visually convincing 3D synthetic liver tumours into real MRI volumes while generating the corresponding masks using simplex deformation. This approach has been employed successfully to inpaint images with 1000 synthetic tumours. Furthermore, it has shown significant performance improvements when applied in image segmentation tasks. In particular, our method improved the Dice coefficient by 6.7 points on the ATLAS test set without relying on external data. When combined with a pseudo-annotated external dataset, the improvement increased to 10 points. This study not only demonstrates the ability to segment tumours but also paves the way for various synthetic data-based applications in medical imaging.

Triple-negative breast cancer (TNBC) is an aggressive subtype with limited treatment options and a poor prognosis, necessitating accurate early diagnosis to optimize therapeutic interventions. This study aims to develop a predictive method using MRI radiomics and machine learning to distinguish TNBC from other breast cancer subtypes. MRI data from 87 patients with invasive breast cancer were retrospectively analyzed. Manual segmentation of the dynamic contrast-enhanced magnetic resonance imaging (DCE) was performed, and the segmented masks were propagated to T1-weighted (T1), T2-weighted water (T2W), and T2-weighted fat (T2F) scans. Radiomic features were extracted using PyRadiomics, and feature selection was performed using Spearman's correlation, mutual information, and least absolute shrinkage and selection operator (LASSO). The EasyEnsemble classifier, an ensemble of AdaBoost learners trained on balanced bootstrap samples, was employed for the classification. The combination of MRI modalities DCE, T1, T2W, and T2F consistently outperformed individual modalities. LASSO feature selection resulted in the most significant performance improvements, with the highest area under the curve (AUC-score) of$0.93 \pm 0.05$, balanced accuracy of$0.81 \pm 0.04$, and$F$-score of$0.74 \pm 0.05$. These findings demonstrate the potential of MRI radiomics and machine learning to noninvasively enhance the diagnostic capability of TNBC, thereby contributing to improved patient care and personalized treatment strategies.

Fetoscopy laser photocoagulation is a widely adopted procedure for treating Twin-to-Twin Transfusion Syndrome (TTTS). The procedure involves photocoagulation pathological anastomoses to restore a physiological blood exchange among twins. The procedure is particularly challenging, from the surgeon's side, due to the limited field of view, poor manoeuvrability of the fetoscope, poor visibility due to amniotic fluid turbidity, and variability in illumination. These challenges may lead to increased surgery time and incomplete ablation of pathological anastomoses, resulting in persistent TTTS. Computer-assisted intervention (CAI) can provide TTTS surgeons with decision support and context awareness by identifying key structures in the scene and expanding the fetoscopic field of view through video mosaicking. Research in this domain has been hampered by the lack of high-quality data to design, develop and test CAI algorithms. Through the Fetoscopic Placental Vessel Segmentation and Registration (FetReg2021) challenge, which was organized as part of the MICCAI2021 Endoscopic Vision (EndoVis) challenge, we released the first large-scale multi-center TTTS dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms with a focus on creating drift-free mosaics from long duration fetoscopy videos. For this challenge, we released a dataset of 2060 images, pixel-annotated for vessels, tool, fetus and background classes, from 18 in-vivo TTTS fetoscopy procedures and 18 short video clips of an average length of 411 frames for developing placental scene segmentation and frame registration for mosaicking techniques. Seven teams participated in this challenge and their model performance was assessed on an unseen test dataset of 658 pixel-annotated images from 6 fetoscopic procedures and 6 short clips. For the segmentation task, overall baseline performed was the top performing (aggregated mIoU of 0.6763) and was the best on the vessel class (mIoU of 0.5817) while team RREB was the best on the tool (mIoU of 0.6335) and fetus (mIoU of 0.5178) classes. For the registration task, overall the baseline performed better than team SANO with an overall mean 5-frame SSIM of 0.9348. Qualitatively, it was observed that team SANO performed better in planar scenarios, while baseline was better in non-planner scenarios. The detailed analysis showed that no single team outperformed on all 6 test fetoscopic videos. The challenge provided an opportunity to create generalized solutions for fetoscopic scene understanding and mosaicking. In this paper, we present the findings of the FetReg2021 challenge, alongside reporting a detailed literature review for CAI in TTTS fetoscopy. Through this challenge, its analysis and the release of multi-center fetoscopic data, we provide a benchmark for future research in this field.

Deep learning-based methods for cardiac MR segmentation have achieved state-of-the-art results. However, these methods can generate incorrect segmentation results which can lead to wrong clinical decisions in the downstream tasks. Automatic and accurate analysis of downstream tasks, such as myocardial tissue characterization, is highly dependent on the quality of the segmentation results. Therefore, it is of paramount importance to use quality control methods to detect the failed segmentations before further analysis. In this work, we propose a fully automatic uncertainty-based quality control framework for T1 mapping and extracellular volume (ECV) analysis. The framework consists of three parts. The first one focuses on segmentation of cardiac structures from a native and post-contrast T1 mapping dataset (n=295) using a Bayesian Swin transformer-based U-Net. In the second part, we propose a novel uncertainty-based quality control (QC) to detect inaccurate segmentation results. The QC method utilizes image-level uncertainty features as input to a random forest-based classifier/regressor to determine the quality of the segmentation outputs. The experimental results from four different types of segmentation results show that the proposed QC method achieves a mean area under the ROC curve (AUC) of 0.927 on binary classification and a mean absolute error (MAE) of 0.021 on Dice score regression, significantly outperforming other state-of-the-art uncertainty based QC methods. The performance gap is notably higher in predicting the segmentation quality from poor-performing models which shows the robustness of our method in detecting failed segmentations. After the inaccurate segmentation results are detected and rejected by the QC method, in the third part, T1 mapping and ECV values are computed automatically to characterize the myocardial tissues of healthy and cardiac pathological cases. The native myocardial T1 and ECV values computed from automatic and manual segmentations show an excellent agreement yielding Pearson coefficients of 0.990 and 0.975 (on the combined validation and test sets), respectively. From the results, we observe that the automatically computed myocardial T1 and ECV values have the ability to characterize myocardial tissues of healthy and cardiac diseases like myocardial infarction, amyloidosis, Tako-Tsubo syndrome, dilated cardiomyopathy, and hypertrophic cardiomyopathy.

RGB-D saliency detection aims to fuse multi-modal cues to accurately localize salient regions. Existing works often adopt attention modules for feature modeling, with few methods explicitly leveraging fine-grained details to merge with semantic cues. Thus, despite the auxiliary depth information, it is still challenging for existing models to distinguish objects with similar appearances but at distinct camera distances. In this paper, from a new perspective, we propose a novel Hierarchical Depth Awareness network (HiDAnet) for RGB-D saliency detection. Our motivation comes from the observation that the multi-granularity properties of geometric priors correlate well with the neural network hierarchies. To realize multi-modal and multi-level fusion, we first use a granularity-based attention scheme to strengthen the discriminatory power of RGB and depth features separately. Then we introduce a unified cross dual-attention module for multi-modal and multi-level fusion in a coarse-to-fine manner. The encoded multi-modal features are gradually aggregated into a shared decoder. Further, we exploit a multi-scale loss to take full advantage of the hierarchical information. Extensive experiments on challenging benchmark datasets demonstrate that our HiDAnet performs favorably over the state-of-the-art methods by large margins. The source code can be found in https://github.com/Zongwei97/HIDANet/.

Diabetes is one of the major causes of blindness. Diabetic retinopathy (DR) is the most frequent complication of diabetes. One in three people suffering from diabetes would develop diabetic retinopathy. However, the risk of vision loss caused by DR could be prevented by having early treatment. Microaneurysm (MA) is a tiny-red-spot lesion that appears in the fundus image as the first symptom of DR. Automatic detection of MAs is growing research due to the increasing need for efficient and accurate detection. However, MAs detection is prone to false-positive detection because of the imbalance data issue. It is necessary to minimize the number of false-positive, while sensitivity should be as high as possible. In this research, we trained and tested the method in individual dataset to evaluate the sensitivity of the method performance. The proposed method requires less number of data to classify the MAs. This is achieved by maximizing the information extracted from the positive data in each process: maximize the output of CLAHE image enhancement technique, extract MAs candidates in unsupervised approach, enrich the object features by novel local background suppression technique, and apply the cascade learning of two identical unit networks. The cascade learning acts as the filter detection that pushes the classifier to focus learning only on the hard cases. The evaluation shows that the proposed method can reduce the number of false positives significantly. The proposed network is trained and tested with E-Ophta and IDRiD datasets individualy and it can reach the highest (individual) sensitivity with 79.2% for 8 FPI in the FROC evaluation metric.

Road scene analysis is a fundamental task for both autonomous vehicles and ADAS systems. Nowadays, one can find autonomous vehicles that are able to properly detect objects in the scene in good weather conditions; however, some improvements still need to be done when the visibility is altered. People claim that using some non-conventional sensors such as, infra-red or Lidar, combined with classical vision, enhances road scene analysis in optimal weather conditions. In this work, we present the improvements achieved using polarimetric imaging in the complex situation of some adverse weather conditions. This rich modality is known for its ability to describe an object not only by its intensity information, even under poor illumination or strong reflection. The experimental results have shown that, using a new multimodal dataset, polarimetric imaging was able to provide generic features for both good weather conditions and adverse weather conditions, especially fog. By combining polarimetric images with an adapted learning model, the different detection tasks under fog were improved by about 15% to 44%.

Road scene analysis is a fundamental task for both autonomous vehicles and ADAS systems. Nowadays, most of autonomous vehicles are able to properly detect objects in good weather conditions; however, some improvements still need to be done when the visibility is altered. Polarimetric imaging is a rich modality that enables to describe an object by its physical information and has recently shown great performances in enhancing road scenes analysis under adverse weather conditions, especially under fog. Besides, it has been shown in a previous work that this modality could be complementary to classical color images especially for car detection. In this work, four different multimodal fusion schemes as well as different color and polarimetric features combinations are explored to achieve a robust scene analysis. The combination of both modalities could be a great asset to describe road scenes when the visibility is altered. Experimental results have shown that, using a well chosen fusion scheme with an adapted features combination, the detection of objects in road scenes under fog was reinforced. The different detection tasks show a significant improvement when using the adapted fusion scheme and features combination. Thanks to the architecture of the fusion scheme and to the properties of the selected features, these results could be extended to other adverse weather conditions.

Few-shot segmentation presents a significant challenge for semantic scene understanding under limited supervision. Namely, this task targets at generalizing the segmentation ability of the model to new categories given a few samples. In order to obtain complete scene information, we extend the RGB-centric methods to take advantage of complementary depth information. In this paper, we propose a two-stream deep neural network based on metric learning. Our method, known as RDNet, learns class-specific prototype representations within RGB and depth embedding spaces, respectively. The learned prototypes provide effective semantic guidance on the corresponding RGB and depth query image, leading to more accurate performance. Moreover, we build a novel outdoor scene dataset, known as Cityscapes-3i, using labeled RGB images and depth images from the Cityscapes dataset. We also perform ablation studies to explore the effective use of depth information in few-shot segmentation tasks. Experiments on Cityscapes-3ishow that our method achieves excellent results with visual and complementary geometric cues from only a few labeled examples.

Deep learning-based image understanding techniques require a large number of labeled images for training. Few-shot semantic segmentation, on the contrary, aims at generalizing the segmentation ability of the model to new categories given only a few labeled samples. To tackle this problem, we propose a novel prototypical network (MAPnet) with multiscale feature attention. To fully exploit the representative features of target classes, we firstly extract rich contextual information of labeled support images via a multiscale feature enhancement module. The learned prototypes from support features provide further semantic guidance on the query image. Then we adaptively integrate multiple similarity-guided probability maps by attention mechanism, yielding an optimal pixel-wise prediction. Furthermore, the proposed method was validated on the PASCAL-5idataset in terms of 1-way N-shot evaluation. We also test the model with weak annotations, including scribble and bounding box annotations. Both the qualitative and quantitative results demonstrate the advantages of our approach over other state-of-the-art methods.

This paper deals with new augmentation methods for an unconventional imaging modality sensitive to the physics of the observed scene called polarimetry. In nature, polarized light is obtained by reflection or scattering. Robotics applications in urban environments are subject to many obstacles that can be specular and therefore provide polarized light. These areas are prone to segmentation errors using standard modalities but could be solved using information carried by the polarized light. Deep Convolutional Neural Networks (DCNNs) have shown excellent segmentation results, but require a significant amount of data to achieve best performances. The lack of data is usually overcomed by using augmentation methods. However, unlike RGB images, polarization images are not only scalar (intensity) images and standard augmentation techniques cannot be applied straightforwardly. We propose enhancing deep learning models through a regularized augmentation procedure applied to polarimetric data in order to characterize scenes more effectively under challenging conditions. We subsequently observe an average of 18.1 % improvement in IoU between not augmented and regularized training procedures on real world data.

Monocular depth estimation is a recurring subject in the field of computer vision. Its ability to describe scenes via a depth map while reducing the constraints related to the formulation of perspective geometry tends to favor its use. However, despite the constant improvement of algorithms, most methods exploit only colorimetric information. Consequently, robustness to events to which the modality is not sensitive to, like specularity or transparency, is neglected. In response to this phenomenon, we propose using polarimetry as an input for a self-supervised monodepth network. Therefore, we propose exploiting polarization cues to encourage accurate reconstruction of scenes. Furthermore, we include a term of polarimetric regularization to state-of-the-art method to take specific advantage of the data. Our method is evaluated both qualitatively and quantitatively demonstrating that the contribution of this new information as well as an enhanced loss function improves depth estimation results, especially for specular areas.

Cardiac left ventricular (LV) segmentation is a paramount essential step for both diagnosis and treatment of cardiac pathologies such as ischemia, myocardial infarction, arrhythmia and myocarditis. However, this segmentation is challenging due to high variability across patients and the potential lack of contrast between structures. In this work, we propose and evaluate a (2.5D) SegU-Net model based on the fusion of two deep learning segmentation techniques (U-Net and Seg-Net) for automated LGE-MRI (Late gadolinium enhanced magnetic resonance imaging) myocardial disease (infarct core and no-reflow region) quantification in a new multifield expert annotated dataset. Given that the scar tissue represents a small part of the whole MRI slices, we focused on myocardium area. Segmentation results show that this preprocessing step facilitate the learning procedure. In order to solve the class imbalance problem, we propose to apply the Jaccard loss and the Focal Loss as optimization loss function and to integrate a class weights strategy into the objective function. Late combination has been used to merge the output of the best trained models on a different set of hyperparameters. The final network segmentation performances will be useful for future comparison of new methods to the current related work for this task. A total number of 2237 of slices (320 cases) were used for training/validation and 210 slices (35 cases) were used for testing. Experiments on our proposed dataset, using several evaluation metrics such Jaccard distance (IOU), Accuracy and Dice similarity coefficient (DSC), demonstrate efficiency performance in quantifying different zones of myocardium infarction across various patients. As compared to the second intra-observer study, our testing results showed that the SegU-Net prediction model leads to these average Dice coefficients over all segmented tissue classes, respectively: `Back-ground': 0.99999, `Myocardium': 0.99434, `Infarctus': 0.95587, `Noreflow': 0.78187 outperforming seven previously proposed methods.

Automatic depression assessment based on visual cues is a rapidly growing research domain. The present exhaustive review of existing approaches as reported in over sixty publications during the last ten years focuses on image processing and machine learning algorithms. Visual manifestations of depression, various procedures used for data collection, and existing datasets are summarized. The review outlines methods and algorithms for visual feature extraction, dimensionality reduction, decision methods for classification and regression approaches, as well as different fusion strategies. A quantitative meta-analysis of reported results, relying on performance metrics robust to chance, is included, identifying general trends and key unresolved issues to be considered in future studies of automatic depression assessment utilizing visual cues alone or in combination with vocal or verbal cues.

Road scene understanding is a vital task for driving assistance systems. Robust vehicle detection is a precondition for diverse applications particularly for obstacle avoidance and secure navigation. Color images provide limited information about the physical properties of the object. This results in unstable vehicle detection caused mainly from road scene complexity (strong reflexions, noises and radiometric distortions). Instead, polarimetric images, characteristic of the light wave, can robustly describe important physical properties of the object (e.g., the surface geometric structure, material and roughness etc). This modality gives rich physical informations which could be complementary to classical color images features. In order to improve the robustness of the vehicle detection purpose, we propose in this paper a fusion model using polarization information and color image attributes. Our method is based on a feature selection procedure to get the most informative polarization feature and color-based ones. The proposed method, based on the Deformable Part based Models (DPM), has been evaluated on our self-collected database, showing good performances and encouraging results about the use of the polarimetric modality for road scenes analysis.

This article reviews the current state of automatic classification methodologies to identify Diabetic Macular Edema (DME) versus normal subjects based on Spectral Domain OCT (SD-OCT) data. Addressing this classification problem has valuable interest since early detection and treatment of DME play a major role to prevent eye adverse effects such as blindness. The main contribution of this article is to cover the lack of a public dataset and benchmark suited for classifying DME and normal SD-OCT volumes, providing our own implementation of the most relevant methodologies in the literature. Subsequently, 6 different methods were implemented and evaluated using this common benchmark and dataset to produce reliable comparison.

Visual saliency is an attention mechanism which helps to focus on regions of interest instead of processing the whole image or video data. Detecting salient objects in still images has been widely addressed in literature with several formulations and methods. However, visual saliency detection in videos has attracted little attention, although motion information is an important aspect of visual perception. A common approach for obtaining a spatio-temporal saliency map is to combine a static saliency map and a dynamic saliency map. In this paper, we extend a recent saliency detection approach based on principal component analysis (PCA) which have shwon good results when applied to static images. In particular, we explore different strategies to include temporal information into the PCA-based approach. The proposed models have been evaluated on a publicly available dataset which contain several videos of dynamic scenes with complex background, and the results show that processing the spatio-tempral data with multilinear PCA achieves competitive results against state-of-the-art methods.

Timber defects detection is one of the important topics in machine vision applications, since the number and severity of defects determine the quality of the wood and consequently its price. In this paper we propose a method to detect wood defects such as cracks and knots. Firstly we create a dictionary based on the bag-of-words approach in a training step. The dictionary is obtained either using LBP and SURF features alone or with a combination of both features. In the second step an image processing pipeline which associates contrast enhancement, entropy maximization and image filtering is used to detect the potential defect regions and we proposed to use SVM classifier to detect knots and cracks. The proposed algorithm is evaluated on two different datasets which have knots and cracks as groundtruth. The experimental results show that our method achieves a precision of 0.92 and 0.91, and a recall of 0.94 and 0.96 for the Epicea and Pine datasets respectively with multiple features based dictionary.

Visual saliency detection is an important step in many computer vision applications, since it reduces further processing steps to regions of interest. Saliency detection in still images is a well-studied topic. However, videos scenes contain more information than static images, and this additional temporal information is an important aspect of human perception. Therefore, it is necessary to include motion information in order to obtain spatio-temporal saliency map for a dynamic scene. In this paper, we introduce a new spatio-temporal saliency detection method for dynamic scenes based on dynamic textures computed with local binary patterns. In particular, we extract local binary patterns descriptors in two orthogonal planes (LBP-TOP) to describe temporal information, and color features are used to represent spatial information. The obtained three maps are finally fused into a spatio-temporal saliency map. The algorithm is evaluated on a dataset with complex dynamic scenes and the results show that our proposed method outperforms state-of-art methods.

In recent years, automated retina image analysis (ARIA) algorithms have received increasing interest by the medical imaging analysis community. Particular attention has been given to techniques able to automate the pre-screening of Diabetic Retinopathy (DR) using inexpensive retina fundus cameras. With the growing number of diabetics worldwide, these techniques have the potential benefits of broad-based, inexpensive screening. The contribution of this paper is twofold: first, we propose a straightforward pipeline from microaneurysm (an early sign of DR) detection to automatic classification of DR without employing any additional features; then, we quantify the generalisation ability of the MA detection method by employing synthetic examples and, more importantly, we experiment with two public datasets which consist of more than 1,350 images graded as normal or showing signs of DR. With cross-datasets tests, we obtained results better or comparable to other recent methods. Since our experiments are performed only on publicly available datasets, our results are directly comparable with those of other research groups.

Automated detection of small, low level shapes such as circular/spherical objects in images is a challenging computer vision problem. For many applications, especially microbleed detection in Alzheimer's disease, an automatic pre-screening scheme is required to identify potential seeds with high sensitivity and reasonable specificity. A new method is proposed to detect spherical objects in 3D medical images within the multi-scale Laplacian of Gaussian framework. The major contributions are(1)breaking down 3D sphere detection into 1D line profile detection along each coordinate dimension, (2) identifying center of structures bynormalizing the line response profile and (3) employing eigenvalues of the Hessian matrix at optimum scale for the center points to determine spherical objects. The method is validated both on simulated data and susceptibility weighted MRI images with ground truth provided by a medical expert. Validation results demonstrate that the current approach has higher performance in terms of sensitivity and specificity and is effective in detecting adjacent microbleeds, with invariance to intensity, orientation, translation and object scale.

We propose a methodology inspired by Gestalt laws to extract and combine features and we test it on the object category recognition problem. Gestalt is a psycho-visual theory of Perceptual Organization that aims to explain how visual information is organized by our brain. We interpreted its laws of homogeneity and continuation in link with shape and color to devise new features beyond the classical proximity and similarity laws. The shape of the object is analyzed based on its skeleton (good continuation) and as a measure of homogeneity, we propose self-similarity enclosed within shape computed at super-pixel level. Furthermore, we propose a framework to combine these features in different ways and we test it on Caltech 101 database. The results are good and show that such an approach improves objectively the efficiency in the task of object category recognition.

Visual saliency is an important research topic in computer vision applications, which helps to focus on regions of interest instead of processing the whole image. Detecting visual saliency in still images has been widely addressed in literature. However, visual saliency detection in videos is more complicated due to additional temporal information. A spatio-temporal saliency map is usually obtained by the fusion of a static saliency map and a dynamic saliency map. The way both maps are fused plays a critical role in the accuracy of the spatio-temporal saliency map. In this paper, we evaluate the performances of different fusion techniques on a large and diverse dataset and the results show that a fusion method must be selected depending on the characteristics, in terms of color and motion contrasts, of a sequence. Overall, fusion techniques which take the best of each saliency map (static and dynamic) in the final spatio-temporal map achieve best results.

Intravenous (IV) catheterization is the most important phase in medical practices of daily life. It is hard to localize veins in patients who have deep veins, minor age or dark skin; hence multiple attempts become indispensable for proper catheterization in such cases. Near Infrared (NIR) Imaging allow to visualize the veins underneath the skin of persons having non-visibility of veins problem. This paper reports the pre-selection of illuminants that ensure best veins/tissues contrast for patients having different skin tone. The sample subjects have been divided in four different classes based on the Luminance value of their skin tone in order to extract the best illuminant wavelengths range for each class. A multispectral approach has been used which provides the flexibility of wavelength range from visible to NIR (380 to 1040nm). The veins/tissue reflectance contrast obtained helps in determining the best wavelengths range where the contrast is maximum for each of the four classes. Using these results, we are planning to build a prototype system which can automatically select the illuminants based on different physiological characteristics of a subject.

A hybrid framework of probabilistic atlas and statistical shape and appearance model (SSAM) is proposed to achieve 3D prostate segmentation. An initial 3D segmentation of the prostate is obtained by registering the probabilistic atlas to the test dataset with deformable Demons registration. The initial results obtained are used to initialize multiple SSAMs corresponding to the apex, central and base regions of the prostate gland to incorporate local variabilities. Multiple mean parametric models of shape and appearance are derived from principal component analysis of prior shape and intensity information of the prostate from the training data. The parameters are then modified with the prior knowledge of the optimization space to achieve 2D segmentation. The 2D labels are registered to the 3D labels generated using probabilistic atlas to constrain the pose variation and generate valid 3D shapes. The proposed method achieves a mean Dice similarity coefficient value of 0.89±0.11 and mean Hausdorff distance of 3.05±2.25 mm when validated with 15 prostate volumes of a public dataset in a leave-one-out validation framework.

This paper presents a novel method to identify the 2D axial Magnetic Resonance (MR) slice from a pre-acquired MR prostate volume that closely corresponds to the 2D axial Transrectal Ultrasound (TRUS) slice obtained during prostate biopsy. The shape-context representations of the segmented prostate contours in both the imaging modalities are used to establish point correspondences using Bhattacharyya distance. Thereafter, Chi-square distance is used to find the prostate shape similarities between the MR slices and the TRUS slice. Normalized mutual information and correlation coefficient between the TRUS and MR slices are computed to find the information theoretic similarities between the TRUS-MR slices. The maximum of the weighted likelihood function of the afore-mentioned statistical similarity measures finally yields the MR slice that closely resembles the TRUS slice acquired during the biopsy procedure. The method is evaluated for 20 patient datasets and close matches with the ground truth are obtained for 16 cases.

Diabetic macular edema (DME) is a common vision threatening complication of diabetic retinopathy. In a large scale screening environment DME can be assessed by detecting exudates (a type of bright lesions) in fundus images. In this work, we introduce a new methodology for diagnosis of DME using a novel set of features based on colour, wavelet decomposition and automatic lesion segmentation. These features are employed to train a classifier able to automatically diagnose DME. We present a new publicly available dataset with ground-truth data containing 169 patients from various ethnic groups and levels of DME. This and other two publicly available datasets are employed to evaluate our algorithm. We are able to achieve diagnosis performance comparable to retina experts on the MESSIDOR (an independently labelled dataset with 1200 images) with cross-dataset testing (e.g., the classifier was trained on an independent dataset and tested on MESSIDOR). Our algorithm is robust to segmentation uncertainties, does not need ground truth at lesion level, and is computationally efficient, as it generates a diagnosis on an average of 9.3 seconds per image on an 2.6 GHz platform with an unoptimised Matlab implementation.

Prostate volume estimation from segmented prostate contours in Trans Rectal Ultrasound (TRUS) images aids in diagnosis and treatment of prostate diseases, including prostate cancer. However, accurate, computationally efficient and automatic segmentation of the prostate in TRUS images is a challenging task owing to low Signal-To-Noise-Ratio (SNR), speckle noise, micro-calcifications and heterogeneous intensity distribution inside the prostate region. In this paper, we propose a probabilistic framework for propagation of a parametric model derived from Principal Component Analysis (PCA) of prior shape and posterior probability values to achieve the prostate segmentation. The proposed method achieves a mean Dice similarity coefficient value of 0.96±0.01, and a mean absolute distance value of 0.80±0.24 mm when validated with 24 images from 6 datasets in a leave-one-patient-out validation framework. Our proposed model is automatic, and performs accurate prostate segmentation in presence of intensity heterogeneity and imaging artifacts.

Retinal fundus images acquired with non-mydriatic digital fundus cameras are a versatile tool for the diagnosis of various retinal diseases. Even with relative ease of use, the images produced sometimes suffer from reflectance artefacts mainly due to the nerve fibre layer (NFL) or camera lens related reflections. We propose a technique that employs multiple fundus images to obtain a single higher quality image without these reflectance artefacts, which also compensates for a sub-optimal illumination. The removal of bright artefacts, can have great benefits for the reduction of false positives in the detection of retinal lesions by automatic systems or manual inspection. The fundus images are acquired by changing the stare point of the patient but keeping the camera fixed. Between each shot, the apparent shape and position of all the retinal structures that do not exhibit isotropic reflectance (e.g. bright artefacts) change. This physical effect is exploited by our algorithm.

In this paper, we present a novel approach exploiting fluorescence imaging to estimate the shape of transparent objects. Classical inspection systems require users to coat transparent objects with some powder before measurement. Methods suggested in literature through non contact measurement do not effectively deal with the refraction problem, thus, providing inaccuracies. The proposed method handles the scanning of transparent objects without using any powder and solving the refraction problem using UV environment. A classical triangulation method based on stereovision scheme using fixed stereoscopic visible range cameras with a fixed UV (Ultra Violet) laser source is implemented. Transparent object surface irradiated by UV laser emits fluorescence i.e. a visible white light in a diffused manner. Images consisting of fluorescent points are thereafter analyzed to extract 3D information of the transparent object surface with a stereovision scheme. The object is moved for scanning different parts and the above procedure is repeated.

This paper introduces a novel 3D measurement scheme based on UV laser triangulation to ascertain the shape of transparent objects. Transparent objects are extremely difficult to scan with traditional 3D scanners because of the refraction problem observed in the visible range. Therefore, the object surface needs to be preliminary powdered before being digitized with commercial scanners. Our approach consists of using non contact measurement scheme while dealing with the refraction problem in visible environment. The object shape is computed by classical triangulation method based on stereovision constraint. The proposed acquisition system is composed of two classical visible range cameras and a UV laser source. The exploitation of the UV laser for triangulation system characterizes the novelty of the proposed approach. The fluorescence generated by the UV radiation enables to acquire 3D data of transparent surface with a classical stereovision scheme.

The first and perhaps most important phase of a surgical procedure is the insertion of an intravenous (IV) catheter. Currently, this is performed manually by trained personnel. In some visions of future operating rooms, however, this process is to be replaced by an automated system. Experiments to determine the best NIR wavelengths to optimize vein contrast for physiological differences such as skin tone and/or the presence of hair on the arm or wrist surface are presented. For illumination our system is composed of a mercury arc lamp coupled to a 10 nm bandpass spectrometer. A structured lighting system is also coupled to our multispectral system in order to provide 3D information of the patient arm orientation. Images of each patient arm are acquired under every possible combination of illuminants and the optimal combination of wavelengths for a given subject to maximize vein contrast using linear discriminant analysis is determined.

In this paper, we present a 3D light propagation model to simulate multispectral reflectance images of large skin surface areas. In particular, we aim to simulate more accurately the effects of various physiological properties of the skin in the case of subcutaneous vein imaging compared to existing models. Our method combines a Monte Carlo light propagation model, a realistic three-dimensional model of the skin using parametric surfaces and a vision system for data acquisition. We describe our model in detail, present results from the Monte Carlo modeling and compare our results with those obtained with a well established Monte Carlo model and with real skin reflectance images.

In this letter, we address the problem of the influence of neighbor edges and their effect on the edge delocalization while extracting a neighbor contour by a derivative approach. The properties to be fulfilled by the regularization operators to minimize or suppress this side effect are deduced, and the best detectors are pointed out. The study is carried out in 1-D for discrete signal. We show that among the derivative filters, one of them can correctly detect our model edges without being influenced by a neighboring transition, whatever their separation distance is and their respective amplitude is. A model of contour and close transitions is presented and used throughout this letter. The noise effect on the edge delocalization is recalled through one of the Canny criteria. Different derivative filters are applied onto synthetic images, and their performances are compared

In the last decade, the accessibility of inexpensive and powerful computers has allowed true digital holography to be used for industrial inspection. This technique allows capturing a complex image of a scene (i.e. containing magnitude and phase), and reconstructing the phase and magnitude information. Digital holograms give a new dimension to texture analysis since the topology information can be used as an additional way to extract features. This new technique can be used to extend previous work on image segmentation of patterned wafers for defect detection. This paper presents a combination of features obtained from Gabor filters on different complex images. The combination enables to cope with the intensity variations occurring during the holography and provides final results which are independent from the selected training samples.

The accessibility of inexpensive and powerful computers has allowed true digital holography to be used for industrial inspection using microscopy. This technique allows the capture of a complex image (i.e., one containing magnitude and phase), and the reconstruction of the phase and magnitude information. Digital holograms give a new dimension to texture analysis, since the topology information can be used as an additional way to extract features. This new technique can be used to extend previous work on the image segmentation of patterned wafers for defect detection. The paper presents a comparison between the features obtained using Gabor filtering on complex images under illumination and focus variations.

Thermal imaging is a powerful tool used by progressive companies across a wide range of industries and applications ranging from predictive maintenance to product development quality assurance. In cosmetic industry product quality control is an important stage of production. This paper deals with an active thermography vision system. It is used to detect the presence of glue occlusion in plastic lids. The experimental set-up is described. The images are processed so as to remove the noise and a segmentation stage is done using Wen's threshold, followed by an erosion filter, 100 percent of the defects were detected by this prototype.