Antonio Foncubierta

IBM Research - Thomas J. Watson Research Center · Cognitive Healthcare and Life Sciences

Content--based medical image retrieval has been proposed as a technique that allows not only for easy access to images from the relevant literature and electronic health records but also for training physicians, for research and clinical decision support. The bag--of--visual--words approach is a widely used technique that tries to shorten the sema...

Information retrieval algorithms have changed the way we manage and use various data sources, such as images, music or multimedia collections. First, free text information of documents from varying sources became accessible in addition to structured data in databases, initially for exact search and then for more probabilistic models. Novel approach...

Texture-based computerized analysis of high-resolution computed tomography images from patients with interstitial lung diseases is introduced to assist radiologists in image interpretation. The cornerstone of our approach is to learn lung texture signatures using a linear combination of N-th order Riesz templates at multiple scales. The weights of...

Health and life sciences’ research fields like personalized medicine, drug discovery, pharmacovigilance and systems biology make an intensive use of graphical information to represent knowledge in the form of domain-specific diagrams, such as molecular pathway‘s. The aim is to provide added value to written text in scientific literature and related...

Health providers currently construct their differential diagnosis for a given medical case most often based on textbook knowledge and clinical experience. Data mining of the large amount of medical records generated daily in hospitals is only very rarely done, limiting the reusability of these cases. As part of the VISCERAL project, the Retrieval b...

While a growing number of benchmark studies compare the performance of algorithms for automated organ segmentation or lesion detection in images with restricted fields of view, few efforts have been made so far towards benchmarking these and related routines for the automated identification of bones, inner organs and relevant substructures visible...

The Bag--of--Visual--Words (BoVW) is a visual description technique that aims at shortening the semantic gap by partitioning a low--level feature space into regions of the feature space that potentially correspond to visual concepts and by giving more value to this space. In this paper we present a conceptual analysis of three major properties of l...

Variations in the shape and appearance of anatomical structures in medical images are often relevant radiological signs of disease. Automatic tools can help automate parts of this manual process. A cloud-based evaluation framework is presented in this paper including results of benchmarking current state-of-the-art medical imaging algorithms for an...

The results of the VISCERAL 3D case retrieval benchmark were presented during the Multimodal Retrieval in the Medical Domain (MRMD) 2015 workshop in Vienna, Austria on March 29, 2015. The main task for the participanta was to find and rank similar medical cases from a large multimodal (semantic RadLex terms extracted from text and visual 3D data) d...

The workshop Multimodal Retrieval in the Medical Domain (MRMD) dealt with various approaches of information retrieval in the medical domain including modalities such as text, structured data, semantic information, images, and videos. The goal was to bring together researchers of the various domains to combine approaches and compare experience. The...

Pulmonary embolism (PE) affects up to 600,000 patients and contributes to at least 100,000 deaths every year in the United States alone. Diagnosis of PE can be difficult as most symptoms are unspecific and early diagnosis is essential for successful treatment. Computed Tomography (CT) images can show morphological anomalies that suggest the existen...

Medical images contain a large amount of visual information about structures and anomalies in the human body. To make sense of this information, human interpretation is often essential. On the other hand, computer-based approaches can exploit information contained in the images by numerically measuring and quantifying specific visual features. Anno...

Content-based medical image retrieval has been proposed as a technique that allows not only for easy access to images from the relevant literature and electronic health records but also for training physicians, for research and clinical decision support. The bag-of-visual-words approach is a widely used technique that tries to shorten the semantic...

The workshop Multimodal Retrieval in the Medical Domain (MRMD) took place in connection with the European Conference of Information Retrieval (ECIR) in Vienna, Austria on March 29, 2015. The workshop included two invited presentations and seven accepted scientific papers. A session on the VISCERAL (VISual Concept Extraction in RAdioLogy) Retrieval...

Searching for medical image content is a regular task for many physicians, especially in radiology. Retrieval of medical images from the scientific literature can benefit from automatic modality classification to focus the search and filter out non–relevant items. Training datasets are often unevenly distributed regarding the classes resulting some...

This is an overview paper describing the data and evaluation scheme of the VISCERAL Segmentation Challenge at ISBI 2015. The challenge was organized on a cloud-based virtualmachine environment, where each participant could develop and submit their algorithms. The dataset contains up to 20 anatomical structures annotated in a training and a test set...

Since the birth of modern medical imaging in the XIXth century the use of images to support clinical decisions has grown and evolved in many aspects. Medical images consist not only of radiography–based approaches. Medical imaging modalities are nowadays based on visible light, magnetic fields, ultrasound, temperature, and a myriad of energy source...

To help managing the large amount of biomedical images produced, image information retrieval tools have been developed to help accessing the right information at the right moment. To provide a test bed for image retrieval evaluation the ImageCLEFmed benchmark proposes a biomedical classification task that focuses on determining the image modality o...

Pulmonary embolism (PE) affects up to 600,000 patients and contributes to at least 100,000 deaths every year in the United States alone. Diagnosis of PE can be difficult as most symptoms are unspecific. Computed Tomography (CT) angiography is the reference for diagnosing PE. CT angiography produces grayscale images with darker areas representing an...

We propose a texture learning approach that exploits local organizations of scales and directions. First, linear combinations of Riesz wavelets are learned using kernel support vector machines. The resulting texture “signatures” are modeling optimal class–wise discriminatory properties. The visualization of the obtained signatures allows verifying...

In this paper, a novel 3D retrieval model to retrieve medical volumes using 2D images as input is proposed. The main idea consists of applying a multi{scale detection of saliency of image regions. Then, the 3D volumes with the regions for each of the scales are associated with a set of projections onto the three canonical planes.The 3D shape is ind...

We propose a texture learning approach that exploits local organizations of scales and directions. First, linear combinations of Riesz wavelets are learned using kernel support vector machines. The resulting texture "signatures" are modeling optimal class–wise discriminatory properties. The visualization of the obtained signatures allows verifying...

Three-dimensional computerized characterization of biomedical solid textures is key to large-scale and high-throughput screening of imaging data. Such data increasingly become available in the clinical and research environments with an ever increasing spatial resolution. In this text we exhaustively analyze the state-of-the-art in 3-D biomedical te...

To help managing the large amount of biomedical images produced, image information retrieval tools have been developed to help accessing the right information at the right moment. To provide a test bed for image retrieval evaluation the ImageCLEFmed benchmark proposes a biomedical classification task that focuses on determining the image modality o...

Epilepsy is a disorder of the brain that can lead to acute crisis and temporary loss of brain functions. Surgery is used to remove focal lesions that remain resistant to treatment. An accurate localization of epileptogenic lesions has a strong influence on the outcome of epilepsy surgery. Magnetic resonance imaging (MRI) is clinically used for lesi...

Distinct texture classes are often sharing several visual concepts. Texture instances from different classes are sharing regions in the feature hyperspace, which results in ill-defined classification configurations. In this work, we detect rotation-covariant visual concepts using steerable Riesz wavelets and bags of visual words. In a first step, K...

Pulmonary embolism is an avoidable cause of death if treated immediately but delays in diagnosis and treatment lead to an increased risk. Computer-assisted image analysis of both unenhanced and contrast-enhanced computed tomography (CT) have proven useful for diagnosis of pulmonary embolism. Dual energy CT provides additional information over the s...

We propose rotation-covariant texture analysis of 4D dual- energy computed tomography (DECT) as a diagnosis aid tool for acute pulmonary embolism in emergency radiology. The cornerstone of the proposed approach is to align 3D Riesz directional filters along bronchovascular structures to enable rotation-covariant comparisons of the parenchymal textu...

Journal images represent an important part of the knowledge stored in the medical literature. Figure classification has received much attention as the information of the image types can be used in a variety of contexts to focus image search and filter out unwanted information or ”noise”, for example non–clinical images. A major problem in figure cl...

When physicians are searching for articles in the medical literature, images of the articles can help determining relevance of the article content for a specific information need. The visual image representation can be an advantage in effectiveness (quality of found articles) and also in efficiency (speed of determining relevance or irrelevance) as...

Volumetric medical images contain an enormous amount of visual information that can discourage the exhaustive use of local descriptors for image analysis, comparison and retrieval. Distinctive features and patterns that need to be analyzed for finding diseases are most often local or regional, often in only very small parts of the image. Separating...

The Khresmoi project is developing a multilingual multimodal search and access system for medical and health information and documents. This scientific demonstration presents the current state of the Khresmoi integrated system, which includes components for text and image annotation, semantic search, search by image similarity and machine translati...

As in many other scientific domains where computer--based tools need to be evaluated, also medical imaging often requires the expensive generation of manual ground truth. For some specific tasks medical doctors can be required to guarantee high quality and valid results, whereas other tasks such as the image modality classification described in thi...

Pulmonary embolism is a common condition with high short---term morbidity. Pulmonary embolism can be treated successfully but diagnosis remains difficult due to the large variability of symptoms, which are often non---specific including breath shortness, chest pain and cough. Dual energy CT produces 4---dimensional data by acquiring variation of at...

Interstitial lung diseases (ILDs) are regrouping over 150 heterogeneous disorders of the lung parenchyma. High---Resolution Computed Tomography (HRCT) plays an important role in diagnosis, as standard chest x---rays are often non---specific for ILDs. Assessment of ILDs is considerd hard for clinicians because the diseases are rare, patterns often l...

Khresmoi is a European Integrated Project developing a multilingual multimodal search and access system for medical and health information and documents. It addresses the challenges of searching through huge amounts of medical data, including general medical information available on the internet, as well as radiology data in hospital archives. It i...

To summarize excellent research in the field of medical sensor, signal and imaging informatics published in the year 2011. Synopsis of the articles selected for the IMIA (International Medical Informatics Association) Yearbook 2012 through a manual initial selection and a peer review process to find the best paper in this domain published in 2011....

Comparing several series of images is not always easy as corresponding slices often need to be selected manually. Particularly two situations were identified in this context: (1) patients with a large number of image series over time (such as patients with monitored cancers) frequently need to compare the series, for example to compare tumor growth...

Segmentation of the various parts of the brain is a challenging area in medical imaging and it is a prerequisite for many image analysis tasks useful for clinical research. Advances have been made in generating brain image templates that can be registered to automatically segment regions of interest in the human brain. However, these methods may fa...

BACKGROUND Radiology is strongly connected with image use and search. However, the management and reuse of the overwhelming amount of medical image data produced by hospitals is not yet satisfactory. Search by using patient IDs or keywords does not allow exploiting the full richness of large databases of images with attached diagnoses due to scarce...

We develop a texture analysis framework to assist radiologists in interpreting high-resolution computed tomography (HRCT) images of the lungs of patients affected with interstitial lung diseases (ILD). Novel texture descriptors based on the Riesz transform are proposed to analyze lung texture without any assumption on prevailing scales and orientat...

PurposeThe main purpose of the paper is to evaluate an automated method for blood vessels segmentation in color fundus images, due to its important role in the diagnosis of several pathologies such as diabetes. The final objective is to introduce the algorithm into a Computer Aided Diagnosis (CAD) tool that would be available in those local medical...

The main purpose of the paper is to evaluate an automated method for blood vessels segmentation in color fundus images, due to its important role in the diagnosis of several pathologies such as diabetes. The final objective is to introduce the algorithm into a Computer Aided Diagnosis (CAD) tool that would be available in those local medical center...

The continuous growth of the available throughput, specially in the uplink of mobile phone networks is opening the doors to new services and business opportunities without references in the past. In more concrete, new standards HSDPA/HSUPA, introduced to complement and enhance 3G networks, together with the advances in audio and specially video cod...