Gloria Bueno

Face recognition using Histograms of Oriented Gradients

Face recognition has been a long standing problem in computer vision. Recently, Histograms of Oriented Gradients (HOGs) have proven to be an effective descriptor for object recognition in general and face recognition in particular. In this paper, we investigate a simple but powerful approach to make robust use of HOG features for face recognition. The three main contributions of this work are: First, in order to compensate for errors in facial feature detection due to occlusions, pose and illumination changes, we propose to extract HOG descriptors from a regular grid. Second, fusion of HOG descriptors at different scales allows to capture important structure for face recognition. Third, we identify the necessity of performing dimensionality reduction to remove noise and make the classification process less prone to overfitting. This is particularly important if HOG features are extracted from overlapping cells. Finally, experimental results on four databases illustrate the benefits of our approach.

Review of imaging solutions for integrated quantitative immunohistochemistry in the Pathology daily practice

Immunohistochemistry (IHC) plays an essential role in Pathology. In order to improve reproducibility and standardization of the results interpretation, IHC quantification methods have been developed. IHC interpretation based in whole slide imaging or virtual microscopy is of special interest. The objective of this work is to review the different computer-based programs for automatic immunohistochemistry and Fluorescence In Situ Hybridization (FISH) evaluation. Scanning solutions and image analysis software in immunohistochemistry were studied, focusing especially on systems based in virtual slides. Integrated scanning and image analysis systems are available (Bacus TMAScore, Dako ACIS III, Genetix Ariol, Aperio Image Analysis, 3DHistech Mirax HistoQuant, Bioimagene Pathiam). Other image analysis software systems (Definiens TissueMap, SlidePath Tissue Image Analysis) can be applied to several virtual slide formats. Fluorescence is the preferred approach in HistoRx AQUA, since it allows for a better compartmentalization of signals. Multispectral imaging using CRi Nuance allows multiple antibodies immunohistochemistry, and different stain unmixing. Most current popular automated image analysis solutions are aimed to brightfield immunohistochemistry, but fluorescence and FISH solutions may become more important in the near future. Automated quantitative tissue microarrays (TMA) analysis is essential to provide high-throughput analysis. Medical informatics standards in images (DICOM) and workflow (IHE) under development will foster the use of image analysis in Pathology Departments.

Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer

Importance Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Objective Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin–stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists’ diagnoses in a diagnostic setting. Design, Setting, and Participants Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). Exposures Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. Main Outcomes and Measures The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. Results The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; P < .001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC). Conclusions and Relevance In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

A joint physics-based statistical deformable model for multimodal brain image analysis

A probabilistic deformable model for the representation of multiple brain structures is described. The statistically learned deformable model represents the relative location of different anatomical surfaces in brain magnetic resonance images (MRIs) and accommodates their significant variability across different individuals. The surfaces of each anatomical structure are parameterized by the amplitudes of the vibration modes of a deformable spherical mesh. For a given MRI in the training set, a vector containing the largest vibration modes describing the different deformable surfaces is created. This random vector is statistically constrained by retaining the most significant variation modes of its Karhunen-Loeve expansion on the training population. By these means, the conjunction of surfaces are deformed according to the anatomical variability observed in the training set. Two applications of the joint probabilistic deformable model are presented: isolation of the brain from MRI using the probabilistic constraints embedded in the model and deformable model-based registration of three-dimensional multimodal (magnetic resonance/single photon emission computed tomography) brain images without removing nonbrain structures. The multi-object deformable model may be considered as a first step toward the development of a general purpose probabilistic anatomical atlas of the brain.

Three-dimensional segmentation of anatomical structures in MR images on large data bases

In this paper an image-based method founded on mathematical morphology is presented in order to facilitate the segmentation of cerebral structures over large data bases of 3D magnetic resonance images (MRIs). The segmentation is described as an immersion simulation, applied to the modified gradient image, modeled by a generated 3D-region adjacency graph (RAG). The segmentation relies on two main processes: homotopy modification and contour decision. The first one is achieved by a marker extraction stage where homogeneous 3D-regions are identified. This stage uses contrasted regions from morphological reconstruction and labeled flat regions constrained by the RAG. Then, the decision stage intends to precisely locate the contours of regions detected by the marker extraction. This decision is performed by a 3D extension of the watershed transform. The method has been applied on a data base of 3D brain MRIs composed of fifty patients. Results are illustrated by segmenting the ventricles, corpus callosum, cerebellum, hippocampus, pons, medulla and midbrain on our data base and the approach is validated on two phantom 3D MRIs.

USING SET OF EXPERIENCE KNOWLEDGE STRUCTURE TO EXTEND A RULE SET OF CLINICAL DECISION SUPPORT SYSTEM FOR ALZHEIMER'S DISEASE DIAGNOSIS

In this article we present an experience-based clinical decision support system (CDSS) for the diagnosis of Alzheimers disease, which enables the discovery of new knowledge in the system and the generation of new rules that drive reasoning. In order to evolve an initial set of production rules given by medical experts we make use of the Set of Experience Knowledge Structure (SOEKS). An illustrative case of our system is also presented.

Smile Detection for User Interfaces

Perceptual User Interfaces (PUIs) aim at facilitating humancomputer interaction with the aid of human-like capacities (computer vision, speech recognition, etc.). In PUIs, the human face is a central element, since it conveys not only identity but also other important information, particularly with respect to the user’s mood or emotional state. This paper describes both a face detector and a smile detector for PUIs. Both are suitable for real-time interaction. The face detector provides eye, mouth and nose locations in frontal or nearly-frontal poses, whereas the smile detector is able to give a smile intensity measure. Experiments confirm that they are competitive with respect to extant detectors. These two detectors are used in an unobtrusive application that allows to interact with an Instant Messaging (IM) client.Perceptual User Interfaces (PUIs) aim at facilitating human-computer interaction with the aid of human-like capacities (computer vision, speech recognition, etc.). In PUIs, the human face is a central element, since it conveys not only identity but also other important information, particularly with respect to the users mood or emotional state. This paper describes both a face detector and a smile detector for PUIs. Both are suitable for real-time interaction. The face detector provides eye, mouth and nose locations in frontal or nearly-frontal poses, whereas the smile detector is able to give a smile intensity measure. Experiments confirm that they are competitive with respect to extant detectors. These two detectors are used in an unobtrusive application that allows to interact with an Instant Messaging (IM) client.

Automated pollen identification using microscopic imaging and texture analysis

Pollen identification is required in different scenarios such as prevention of allergic reactions, climate analysis or apiculture. However, it is a time-consuming task since experts are required to recognize each pollen grain through the microscope. In this study, we performed an exhaustive assessment on the utility of texture analysis for automated characterisation of pollen samples. A database composed of 1800 brightfield microscopy images of pollen grains from 15 different taxa was used for this purpose. A pattern recognition-based methodology was adopted to perform pollen classification. Four different methods were evaluated for texture feature extraction from the pollen image: Haralicks gray-level co-occurrence matrices (GLCM), log-Gabor filters (LGF), local binary patterns (LBP) and discrete Tchebichef moments (DTM). Fishers discriminant analysis and k-nearest neighbour were subsequently applied to perform dimensionality reduction and multivariate classification, respectively. Our results reveal that LGF and DTM, which are based on the spectral properties of the image, outperformed GLCM and LBP in the proposed classification problem. Furthermore, we found that the combination of all the texture features resulted in the highest performance, yielding an accuracy of 95%. Therefore, thorough texture characterisation could be considered in further implementations of automatic pollen recognition systems based on image processing techniques.

Autofocus evaluation for brightfield microscopy pathology

An essential and indispensable component of automated microscopy framework is the automatic focusing system, which determines the in-focus position of a given field of view by searching the maximum value of a focusing function over a range of z-axis positions. The focus function and its computation time are crucial to the accuracy and efficiency of the system. Sixteen focusing algorithms were analyzed for histological and histopathological images. In terms of accuracy, results have shown an overall high performance by most of the methods. However, we included in the evaluation study other criteria such as computational cost and focusing curve shape which are crucial for real-time applications and were used to highlight the best practices.

Breast density classification to reduce false positives in CADe systems

This paper describes a novel weighted voting tree classification scheme for breast density classification. Breast parenchymal density is an important risk factor in breast cancer. Moreover, it is known that mammogram interpretation is more difficult when dense tissue is involved. Therefore, automated breast density classification may aid in breast lesion detection and analysis. Several classification methods have been compared and a novel hierarchical classification procedure of combined classifiers with linear discriminant analysis (LDA) is proposed as the best solution to classify the mammograms into the four BIRADS tissue classes. The classification scheme is based on 298 texture features. Statistical analysis to test the normality and homoscedasticity of the data was carried out for feature selection. Thus, only features that are influenced by the tissue type were considered. The novel classification techniques have been incorporated into a CADe system to drive the detection algorithms and tested with 1459 images. The results obtained on the 322 screen-film mammograms (SFM) of the mini-MIAS dataset show that 99.75% of samples were correctly classified. On the 1137 full-field digital mammograms (FFDM) dataset results show 91.58% agreement. The results of the lesion detection algorithms were obtained from modules integrated within the CADe system developed by the authors and show that using breast tissue classification prior to lesion detection leads to an improvement of the detection results. The tools enhance the detectability of lesions and they are able to distinguish their local attenuation without local tissue density constraints.