Alba Garcia Seco de Herrera

Evaluating performance of biomedical image retrieval systems--an overview of the medical image retrieval task at ImageCLEF 2004-2013.

Medical image retrieval and classification have been extremely active research topics over the past 15 years. Within the ImageCLEF benchmark in medical image retrieval and classification, a standard test bed was created that allows researchers to compare their approaches and ideas on increasingly large and varied data sets including generated ground truth. This article describes the lessons learned in ten evaluation campaigns. A detailed analysis of the data also highlights the value of the resources created.

General Overview of ImageCLEF at the CLEF 2015 Labs

This paper presents an overview of the ImageCLEF 2015 evaluation campaign, an event that was organized as part of the CLEF labs 2015. ImageCLEF is an ongoing initiative that promotes the evaluation of technologies for annotation, indexing and retrieval for providing information access to databases of images in various usage scenarios and domains. In 2015, the 13th edition of ImageCLEF, four main tasks were proposed: 1 automatic concept annotation, localization and sentence description generation for general images; 2 identification, multi-label classification and separation of compound figures from biomedical literature; 3 clustering of x-rays from all over the body; and 4 prediction of missing radiological annotations in reports of liver CT images. The x-ray task was the only fully novel task this year, although the other three tasks introduced modifications to keep up relevancy of the proposed challenges. The participation was considerably positive in this edition of the lab, receiving almost twice the number of submitted working notes papers as compared to previous years.

Different gray matter patterns in chronic schizophrenia and chronic bipolar disorder patients identified using voxel-based morphometry

Gray matter (GM) volume deficits have been described in patients with schizophrenia (Sz) and bipolar disorder (BD), but to date, few studies have directly compared GM volumes between these syndromes with methods allowing for whole-brain comparisons. We have used structural magnetic resonance imaging (MRI) and voxel-based morphometry (VBM) to compare GM volumes between 38 Sz and 19 BD chronic patients. We also included 24 healthy controls. The results revealed a widespread cortical (dorsolateral and medial prefrontal and precentral) and cerebellar deficit as well as GM deficits in putamen and thalamus in Sz when compared to BD patients. Besides, a subcortical GM deficit was shown by Sz and BD groups when compared to the healthy controls, although a putaminal reduction was only evident in the Sz patients. In this comparison, the BD patients showed a limited cortical and subcortical GM deficit. These results support a partly different pattern of GM deficits associated to chronic Sz and chronic BD, with some degree of overlapping.

Assessing the scholarly impact of imageCLEF

Systematic evaluation has an important place in information retrieval research starting with the Cranfield tests and currently with TREC (Text REtrieval Conference) and other evaluation campaigns. Such benchmarks are often mentioned to have an important impact in advancing a research field and making techniques comparable. Still, their exact impact is hard to measure. This paper aims at assessing the scholarly impact of the ImageCLEF image retrieval evaluation initiative. To this end, the papers in the proceedings published after each evaluation campaign and their citations are analysed using Scopus and Google Scholar. A significant impact of ImageCLEF could be shown through this bibliometric analysis. The differences between the employed analysis methods, each with its advantages and limitations, are also discussed.

Optimized voxel brain morphometry: association between brain volumes and the response to atypical antipsychotics

To date, few studies have addressed the relationship between brain structure alterations and responses to atypical antipsychotics in schizophrenia. To this end, in this study, magnetic resonance imaging (MRI) and voxel-based morphometry (VBM) were used to assess the relationship between the brain volumes of gray (GM) and white (WM) matters and the clinical response to risperidone or olanzapine in 30 schizophrenia patients. In comparison with healthy controls, the patients in this study showed a bilateral decrease in the anteromedial cerebellar hemispheres, the rectal gyrus and the insula, together with bilateral increases in GM in the basal ganglia. Both patient groups had a significantly smaller volume of WM in a region encompassing the internal and external capsules as compared to the controls. We found an inverse association between striatal size and the degree of clinical improvement, and a direct association between the degree of insular volume deficit and its improvement. The non-responder patient group showed a significant decrease in their left rectal gyrus as compared with the responder group. This study reveals a pattern of structural alterations in schizophrenia associated with the response to risperidone or olanzapine.

Overview of ImageCLEF 2017: information extraction from images

This paper presents an overview of the ImageCLEF 2017 evaluation campaign, an event that was organized as part of the CLEF (Conference and Labs of the Evaluation Forum) labs 2017. ImageCLEF is an ongoing initiative (started in 2003) that promotes the evaluation of technologies for annotation, indexing and retrieval for providing information access to collections of images in various usage scenarios and domains. In 2017, the 15th edition of ImageCLEF, three main tasks were proposed and one pilot task: (1) a LifeLog task about searching in LifeLog data, so videos, images and other sources; (2) a caption prediction task that aims at predicting the caption of a figure from the biomedical literature based on the figure alone; (3) a tuberculosis task that aims at detecting the tuberculosis type from CT (Computed Tomography) volumes of the lung and also the drug resistance of the tuberculosis; and (4) a remote sensing pilot task that aims at predicting population density based on satellite images. The strong participation of over 150 research groups registering for the four tasks and 27 groups submitting results shows the interest in this benchmarking campaign despite the fact that all four tasks were new and had to create their own community.

Bag---of---Colors for biomedical document image classification

The number of biomedical publications has increased noticeably in the last 30 years. Clinicians and medical researchers regularly have unmet information needs but require more time for searching than is usually available to find publications relevant to a clinical situation. The techniques described in this article are used to classify images from the biomedical open access literature into categories, which can potentially reduce the search time. Only the visual information of the images is used to classify images based on a benchmark database of ImageCLEF 2011 created for the task of image classification and image retrieval. We evaluate particularly the importance of color in addition to the frequently used texture and grey level features. Results show that bags---of---colors in combination with the Scale Invariant Feature Transform (SIFT) provide an image representation allowing to improve the classification quality. Accuracy improved from 69.75% of the best system in ImageCLEF 2011 using visual information, only, to 72.5% of the system described in this paper. The results highlight the importance of color for the classification of biomedical images.

Comparing fusion techniques for the ImageCLEF 2013 medical case retrieval task

Retrieval systems can supply similar cases with a proven diagnosis to a new example case under observation to help clinicians during their work. The ImageCLEFmed evaluation campaign proposes a framework where research groups can compare case-based retrieval approaches. This paper focuses on the case-based task and adds results of the compound figure separation and modality classification tasks. Several fusion approaches are compared to identify the approaches best adapted to the heterogeneous data of the task. Fusion of visual and textual features is analyzed, demonstrating that the selection of the fusion strategy can improve the best performance on the case-based retrieval task.

Medical image retrieval using bag of meaningful visual words: unsupervised visual vocabulary pruning with PLSA

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 gap by learning meaningful features from the dataset and describing documents and images in terms of the histogram of these features. Visual vocabularies are often redundant, over--complete and noisy. Larger than required vocabularies lead to high--dimensional feature spaces, which present important disadvantages with the curse of dimensionality and computational cost being the most obvious ones. In this work a visual vocabulary pruning technique is presented. It enormously reduces the amount of required words to describe a medical image dataset with no significant effect on the accuracy. Results show that a reduction of up to 90% can be achieved without impact on the system performance. Obtaining a more compact representation of a document enables multimodal description as well as using classifiers requiring low--dimensional representations.

Medical image modality classification using discrete Bayesian networks

We propose and evaluate a pipeline for the use of visual descriptors extracted from medical images as input in discrete Bayesian Network Classifiers.We compare the results obtained thanks to our pipeline with other proposals in the scenario of the ImageCLEFmed 2013 competition.When coping with classification problems including large number of classes, hierarchical approaches are supplementary for increasing the baseline accuracy.The proposed discretization and feature subset selection techniques allow for a proper integration of any combination of visual descriptors. Moreover, the resulting number of variables does not necessarily increase when integrating new descriptors.In contrast to other participants proposals, we present a generalist classification system (ranking 3rd out of 8) that has not been optimized to the competition problem.The use of probabilistic classifiers allows us for a deep result analysis, which let us identify the weak points in the discrimination capabilities. In this paper we propose a complete pipeline for medical image modality classification focused on the application of discrete Bayesian network classifiers. Modality refers to the categorization of biomedical images from the literature according to a previously defined set of image types, such as X-ray, graph or gene sequence. We describe an extensive pipeline starting with feature extraction from images, data combination, pre-processing and a range of different classification techniques and models. We study the expressive power of several image descriptors along with supervised discretization and feature selection to show the performance of discrete Bayesian networks compared to the usual deterministic classifiers used in image classification. We perform an exhaustive experimentation by using the ImageCLEFmed 2013 collection. This problem presents a high number of classes so we propose several hierarchical approaches. In a first set of experiments we evaluate a wide range of parameters for our pipeline along with several classification models. Finally, we perform a comparison by setting up the competition environment between our selected approaches and the best ones of the original competition. Results show that the Bayesian Network classifiers obtain very competitive results. Furthermore, the proposed approach is stable and it can be applied to other problems that present inherent hierarchical structures of classes.