Search

Breast density is a strong risk factor for breast cancer. In this paper, we present an automated approach for breast density segmentation in mammographic images based on a supervised pixel-based classification and using textural and morphological features. The objective of the paper is not only to show the feasibility of an automatic algorithm for breast density segmentation but also to prove its potential application to the study of breast density evolution in longitudinal studies. The database used here contains three complete screening examinations, acquired 2 years apart, of 130 different patients. The approach was validated by comparing manual expert annotations with automatically obtained estimations. Transversal analysis of the breast density analysis of craniocaudal (CC) and mediolateral oblique (MLO) views of both breasts acquired in the same study showed a correlation coefficient of ρ = 0.96 between the mammographic density percentage for left and right breasts, whereas a comparison of both mammographic views showed a correlation of ρ = 0.95. A longitudinal study of breast density confirmed the trend that dense tissue percentage decreases over time, although we noticed that the decrease in the ratio depends on the initial amount of breast density This work was partially funded by the Spanish R+D+I grant no. TIN2012-37171-C02-01

Contains fulltext : 136858.pdf (Publisher’s version ) (Open Access) This paper describes an evaluation framework that allows a standardized and quantitative comparison of IVUS lumen and media segmentation algorithms. This framework has been introduced at the MICCAI 2011 Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop, comparing the results of eight teams that participated. We describe the available data-base comprising of multi-center, multi-vendor and multi-frequency IVUS datasets, their acquisition, the creation of the reference standard and the evaluation measures. The approaches address segmentation of the lumen, the media, or both borders; semi- or fully-automatic operation; and 2-D vs. 3-D methodology. Three performance measures for quantitative analysis have been proposed. The results of the evaluation indicate that segmentation of the vessel lumen and media is possible with an accuracy that is comparable to manual annotation when semi-automatic methods are used, as well as encouraging results can be obtained also in case of fully-automatic segmentation. The analysis performed in this paper also highlights the challenges in IVUS segmentation that remains to be solved.

L'aterosclerosi és una malaltia inflamatòria que afecta artèries grans i mitjanes. Això es produeix a causa de l'acumulació de placa a les parets. Aquest procés d'acumulació és lent i es produeix al llarg de dècades, podent arribar, en casos extrems, al trencament de la placa (la qual cosa pot produir trombes que obstrueixin el reg sanguini). S'està duent a terme una investigació per poder realitzar l'estudi tensional d'artèries afectades a partir de seccions transversals per tal de poder predir amb més precisió si aquestes tenen perill de trencament o no. En el marc de la investigació esmentada, en aquest estudi es pretén determinar quins són els paràmetres mínims necessaris per poder caracteritzar la configuració de cada secció i estudiar l'estat tensional de les artèries amb la mínima quantitat d'informació possible. Per això, en primer lloc, s'han homogeneïtzat les dades geomètriques de les seccions transversals a partir de diferents mètodes, com el mètode del conjunt de nivells (Level Set method). Un cop fet això, s'han utilitzat diferents algorismes, tant lineals (ACP) com no lineals (kACP), per a la reducció dimensional de les variables que diferenciïn les seccions d'artèries estables de les inestables i així poder representar les dades amb la menor quantitat de paràmetres possible. S'ha arribat a la conclusió que aquells paràmetres que tenen un paper més important a l'hora de poder diferenciar entre les seccions d'un grup i d'un altre són l'àrea de la secció arterial, el seu índex de remodelització, la càrrega de la placa i l'angle de les calcificacions. Tot això tenint en compte que només s'han utilitzat les dades geomètriques de seccions transversals d'artèries. La aterosclerosis es una enfermedad inflamatoria que afecta a arterias grandes y medianas. Esto se produce debido a la acumulación de placa en las paredes. Este proceso de acumulación es lento y se produce a lo largo de décadas, pudiendo llegar, en casos extremos, a la rotura de la placa (lo que puede producir trombos que obstruyan el riego sanguíneo). Se está llevando a cabo una investigación para poder realizar el estudio tensional de arterias afectadas a partir de secciones transversales para poder predecir con mayor precisión si éstas tienen peligro de rotura o no. En el marco de dicha investigación, en el presente estudio se pretende determinar cuáles son los parámetros mínimos necesarios para poder caracterizar la configuración de cada sección y estudiar el estado tensional de las arterias con la mínima cantidad de información posible. Por eso, en primer lugar, se han homogeneizado los datos geométricos de las secciones transversales a partir de diferentes métodos, como el método del conjunto de niveles (Level Set method). Una vez hecho esto, se han utilizado diferentes algoritmos, tanto lineales (ACP) como no lineales (kACP), para la reducción dimensional de las variables que diferencien las secciones de arterias estables de las inestables y así poder representar los datos con la menor cantidad de parámetros posible. Se ha llegado a la conclusión de que aquellos parámetros que tienen un papel más importante a la hora de poder diferenciar entre las secciones de un grupo y otro son el área de la sección arterial, su índice de remodelización, la carga de la placa y el ángulo de las calcificaciones. Todo esto teniendo en cuenta que sólo se han utilizado los datos geométricos de secciones transversales de arterias. Atherosclerosis is an inflammatory disease that affects large and medium arteries. This occurs due to the accumulation of plaque on its walls. This accumulation process is slow and occurs over decades, and can lead, in extreme cases, to rupture of the plaque (which can produce thrombi that obstruct the blood supply). An investigation is being carried out in order to carry out the tension study of affected arteries from their cross sections to predict with greater precision if they are in danger of rupture or not. Within the framework of this research, the present study intends to determine the minimum parameters necessary to be able to characterize the configuration of each section and study the tension state of the arteries with the minimum amount of information possible. To do this, first, the geometric data of the cross-sections have been homogenized using different methods, such as the Level Set method. Once this is done, different algorithms have been used, both linear (PCA) and non-linear (kPCA), for the dimensional reduction of the variables that differentiate the sections of stable arteries from unstable ones and thus be able to represent the data with the least amount of parameters possible. It has been concluded that those parameters that play a more important role when it comes to being able to differentiate between the sections of one group and another are the area of the arterial section, its remodeling index, the plaque load and the angle of calcifications. All this taking into account that only the geometric data of cross-sections of arteries have been taken into account.

MRI; Deep learning; Multiple sclerosis Resonancia magnética; Aprendizaje profundo; Esclerosis múltiple Ressonància magnètica; Aprenentatge profund; Esclerosi múltiple The assessment of disease activity using serial brain MRI scans is one of the most valuable strategies for monitoring treatment response in patients with multiple sclerosis (MS) receiving disease-modifying treatments. Recently, several deep learning approaches have been proposed to improve this analysis, obtaining a good trade-off between sensitivity and specificity, especially when using T1-w and T2-FLAIR images as inputs. However, the need to acquire two different types of images is time-consuming, costly and not always available in clinical practice. In this paper, we investigate an approach to generate synthetic T1-w images from T2-FLAIR images and subsequently analyse the impact of using original and synthetic T1-w images on the performance of a state-of-the-art approach for longitudinal MS lesion detection. We evaluate our approach on a dataset containing 136 images from MS patients, and 73 images with lesion activity (the appearance of new T2 lesions in follow-up scans). To evaluate the synthesis of the images, we analyse the structural similarity index metric and the median absolute error and obtain consistent results. To study the impact of synthetic T1-w images, we evaluate the performance of the new lesion detection approach when using (1) both T2-FLAIR and T1-w original images, (2) only T2-FLAIR images, and (3) both T2-FLAIR and synthetic T1-w images. Sensitivities of 0.75, 0.63, and 0.81, respectively, were obtained at the same false-positive rate (0.14) for all experiments. In addition, we also present the results obtained when using the data from the international MSSEG-2 challenge, showing also an improvement when including synthetic T1-w images. In conclusion, we show that the use of synthetic images can support the lack of data or even be used instead of the original image to homogenize the contrast of the different acquisitions in new T2 lesions detection algorithms. AC holds an FPI grant from the Ministerio de Ciencia, Innovación y Universidades with reference number PRE2018-083507. This work has been supported by DPI2020-114769RB-I00 from the Ministerio de Ciencia, Innovación y Universidades. The authors gratefully acknowledge the support of the NVIDIA Corporation with their donation of the TITAN X GPU used in this research. This work has been also supported by ICREA Academia Program.

The tear film lipid layer is heterogeneous among the population. Its classification depends on its thickness and can be done using the interference pattern categories proposed by Guillon. The interference phenomena can be characterised as a colour texture pattern, which can be automatically classified into one of these categories. From a photography of the eye, a region of interest is detected and its low-level features are extracted, generating a feature vector that describes it, to be finally classified in one of the target categories. This paper presents an exhaustive study about the problem at hand using different texture analysis methods in three colour spaces and different machine learning algorithms. All these methods and classifiers have been tested on a dataset composed of 105 images from healthy subjects and the results have been statistically analysed. As a result, the manual process done by experts can be automated with the benefits of being faster and unaffected by subjective factors, with maximum accuracy over 95%. This paper has been partially funded by the Ministerio de Ciencia e Innovación of the Gobierno de España and FEDER funds of the European Union through the research project PI10/00578; and by the Consellería de Industria of the Xunta de Galicia through the Research Project 10/CSA918054PR SI

The present paper describes the design and usage of an Internet medical image search engine based on the queryby-example paradigm and the multimedia standard ISO-15938-12:2008. The system, which allows combining Content Based Information Retrieval (CBIR) techniques such as “query by image” with traditional XML metadata filtering, is applied to annotate and query Optical Biopsies-OB (in the present case Confocal endomicroscopy-CEM). The OB-CEM are taken by endoscopists, not trained in microscopic morphology which is the domain of the surgical pathology. To gain diagnostic confidence the endoscopists could consult the images to a pathologist or could use the system proposed in the paper. That is, to search for similar images to compare the diagnosis.

In recent years, some convolutional neural networks (CNNs) have been proposed to segment sub-cortical brain structures from magnetic resonance images (MRIs). Although these methods provide accurate segmentation, there is a reproducibility issue regarding segmenting MRI volumes from different image domains – e.g., differences in protocol, scanner, and intensity profile. Thus, the network must be retrained from scratch to perform similarly in different imaging domains, limiting the applicability of such methods in clinical settings. In this paper, we employ the transfer learning strategy to solve the domain shift problem. We reduced the number of training images by leveraging the knowledge obtained by a pretrained network, and improved the training speed by reducing the number of trainable parameters of the CNN. We tested our method on two publicly available datasets – MICCAI 2012 and IBSR – and compared them with a commonly used approach: FIRST. Our method showed similar results to those obtained by a fully trained CNN, and our method used a remarkably smaller number of images from the target domain. Moreover, training the network with only one image from MICCAI 2012 and three images from IBSR datasets was sufficient to significantly outperform FIRST with (p

Accurate brain tissue segmentation in magnetic resonance imaging (MRI) has attracted the attention of medical doctors and researchers since variations in tissue volume and shape permit diagnosing and monitoring neurological diseases. Several proposals have been designed throughout the years comprising conventional machine learning strategies as well as convolutional neural networks (CNNs) approaches. In particular, in this paper, we analyze a sub-group of deep learning methods producing dense predictions. This branch, referred in the literature as fully CNN (FCNN), is of interest as these architectures can process an input volume in less time than CNNs. Our study focuses on understanding the architectural strengths and weaknesses of literature-like approaches. We implement eight FCNN architectures inspired by robust state-of-the-art methods on brain segmentation related tasks and use them within a standard pipeline. We evaluate them using the IBSR18, MICCAI2012, and iSeg2017 datasets as they contain infant and adult data and exhibit different voxel spacing, image quality, number of scans, and available imaging modalities. The discussion is driven in four directions: comparison between 2D and 3D approaches, the relevance of multiple imaging sequences, the effect of patch size, and the impact of patch overlap as a sampling strategy for training and testing models. Besides the aforementioned analysis, we show that the methods under evaluation can yield top performance on the three data collections. A public version is accessible to download from our research website to encourage other researchers to explore the evaluation framework This work was supported in part by the La Fundació la Marató de TV3 and in part by the Retos de Investigació under Grant TIN2014-55710-R, Grant TIN2015-73563-JIN, and Grant DPI2017-86696-R from the Ministerio de Ciencia y Tecnología. The work of J. Bernal and K. Kushibar was supported by the Catalan Government under Grant FI-DGR2017, Grant 2017FI B00476, and Grant 2017FI B00372. The work of M. Cabezas was supported by the Juan de la Cierva–Incorporación Grant from the Spanish Government under Grant IJCI-2016-29240

Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) has been recognized as an effective tool for Breast Cancer (BC) diagnosis. Automatic BC analysis from DCE-MRI depends on features extracted particularly from lesions, hence, lesions need to be accurately segmented as a prior step. Due to the time and experience required to manually segment lesions in 4D DCE-MRI, automating this task is expected to reduce the workload, reduce observer variability and improve diagnostic accuracy. In this paper we propose an automated method for breast lesion segmentation from DCE-MRI based on a U-Net framework. The contributions of this work are the proposal of a modified U-Net architecture and the analysis of the input DCE information. In that sense, we propose the use of an ensemble method combining three U-Net models, each using a different input combination, outperforming all individual methods and other existing approaches. For evaluation, we use a subset of 46 cases from the TCGA-BRCA dataset, a challenging and publicly available dataset not reported to date for this task. Due to the incomplete annotations provided, we complement them with the help of a radiologist in order to include secondary lesions that were not originally segmented. The proposed ensemble method obtains a mean Dice Similarity Coefficient (DSC) of 0.680 (0.802 for main lesions) which outperforms state-of-the art methods using the same dataset, demonstrating the effectiveness of our method considering the complexity of the dataset This work was partially supported by the project ICEBERG: Image Computing for Enhancing Breast Cancer Radiomics (RTI2018-096 333-B-I00, Spanish Ministry) Open Access funding provided thanks to the CRUE-CSIC agreement with Elsevier

Medical support systems used to assist in the diagnosis of prostate lesions generally related to prostate segmentation is one of the majors focus of interest in recent literature. The main problem encountered in the diagnosis of a prostate study is the localization of a Regions of Interest (ROI) containing a tumor tissue. In this paper, a new GUI tool based on a semi-automatic prostate segmentation is presented. The main rationale behind this tool and the focus of this article is facilitate the time consuming segmentation process used for annotating images in the clinical practice, enabling the radiologists to use novel and easy to use semi-automatic segmentation techniques instead of manual segmentation. In this work, a detailed specification of the proposed segmentation algorithm using an Active Contour Models (ACM) aided with a Gradient Vector Flow (GVF) component is defined. The purpose is to help the manual segmentation process of the main ROIs of prostate gland zones. Finally, an experimental case of use and a discussion part of the results are presented.

In recent years, the use of Convolutional Neural Networks (CNNs) in medical imaging has shown improved performance in terms of mass detection and classification compared to current state-of-the-art methods. This paper proposes a fully automated framework to detect masses in Full-Field Digital Mammograms (FFDM). This is based on the Faster Region-based Convolutional Neural Network (Faster-RCNN) model and is applied for detecting masses in the large-scale OPTIMAM Mammography Image Database (OMI-DB), which consists of 80,000 FFDMs mainly from Hologic and General Electric (GE) scanners. This research is the first to benchmark the performance of deep learning on OMI-DB. The proposed framework obtained a True Positive Rate (TPR) of 0.93 at 0.78 False Positive per Image (FPI) on FFDMs from the Hologic scanner. Transfer learning is then used in the Faster R-CNN model trained on Hologic images to detect masses in smaller databases containing FFDMs from the GE scanner and another public dataset INbreast (Siemens scanner). The detection framework obtained a TPR of 0.91±0.06 at 1.69 FPI for images from the GE scanner and also showed higher performance compared to state-of-the-art methods on the INbreast dataset, obtaining a TPR of 0.99±0.03 at 1.17 FPI for malignant and 0.85±0.08 at 1.0 FPI for benign masses, showing the potential to be used as part of an advanced CAD system for breast cancer screening This work is partially supported by SMARTER project funded by the Ministry of Economy and Competitiveness of Spain, under project reference DPI2015-68442-R, and the ICEBERG project (Ref. RTI2018- 096333-B-I00) funded by the Ministry of Science, Innovation and Universities. R. Agarwal is funded by the support of the Secretariat of Universities and Research, Ministry of Economy and Knowledge, Government of Catalonia Ref. ECO/1794/2015 FIDGR-2016

The study of the colonic volume is a procedure with strong relevance to gastroenterologists. Depending on the clinical protocols, the volume analysis has to be performed on MRI of the unprepared colon without contrast administration. In such circumstances, existing measurement procedures are cumbersome and time-consuming for the specialists. The algorithm presented in this paper permits a quasi-automatic segmentation of the unprepared colon on T2-weighted MRI scans. The segmentation algorithm is organized as a three-stage pipeline. In the first stage, a custom tubularity filter is run to detect colon candidate areas. The specialists provide a list of points along the colon trajectory, which are combined with tubularity information to calculate an estimation of the colon medial path. In the second stage, we delimit the region of interest by applying custom segmentation algorithms to detect colon neighboring regions and the fat capsule containing abdominal organs. Finally, within the reduced search space, segmentation is performed via 3D graph-cuts in a three-stage multigrid approach. Our algorithm was tested on MRI abdominal scans, including different acquisition resolutions, and its results were compared to the colon ground truth segmentations provided by the specialists. The experiments proved the accuracy, efficiency, and usability of the algorithm, while the variability of the scan resolutions contributed to demonstrate the computational scalability of the multigrid architecture. The system is fully applicable to the colon measurement clinical routine, being a substantial step towards a fully automated segmentation.

Sub-cortical brain structure segmentation in Magnetic Resonance Images (MRI) has attracted the interest of the research community for a long time as morphological changes in these structures are related to different neurodegenerative disorders. However, manual segmentation of these structures can be tedious and prone to variability, highlighting the need for robust automated segmentation methods. In this paper, we present a novel convolutional neural network based approach for accurate segmentation of the sub-cortical brain structures that combines both convolutional and prior spatial features for improving the segmentation accuracy. In order to increase the accuracy of the automated segmentation, we propose to train the network using a restricted sample selection to force the network to learn the most difficult parts of the structures. We evaluate the accuracy of the proposed method on the public MICCAI 2012 challenge and IBSR 18 datasets, comparing it with different traditional and deep learning state-of-the-art methods. On the MICCAI 2012 dataset, our method shows an excellent performance comparable to the best participant strategy on the challenge, while performing significantly better than state-of-the-art techniques such as FreeSurfer and FIRST. On the IBSR 18 dataset, our method also exhibits a significant increase in the performance with respect to not only FreeSurfer and FIRST, but also comparable or better results than other recent deep learning approaches. Moreover, our experiments show that both the addition of the spatial priors and the restricted sampling strategy have a significant effect on the accuracy of the proposed method. In order to encourage the reproducibility and the use of the proposed method, a public version of our approach is available to download for the neuroimaging community Kaisar Kushibar and Jose Bernal hold FI-DGR2017 grant from the Catalan Government with reference numbers 2017FI_B00372 and 2017FI_B00476, respectively. This work has been partially supported by La Fundació la Marató de TV3, by Retos de Investigación TIN2014-55710-R, TIN2015-73563-JIN, and DPI2017-86696-R from the Ministerio de Ciencia y Tecnologia

The aim of this paper is to evaluate the spatial glandular volumetric tissue distribution as well as the density measures provided by Volpara™ using a dataset composed of repeated pairs of mammograms, where each pair was acquired in a short time frame and in a slightly changed position of the breast. Materials and methods We conducted a retrospective analysis of 99 pairs of repeatedly acquired full-field digital mammograms from 99 different patients. The commercial software Volpara™ Density Maps (Volpara Solutions, Wellington, New Zealand) is used to estimate both the global and the local glandular tissue distribution in each image. The global measures provided by Volpara™, such as breast volume, volume of glandular tissue, and volumetric breast density are compared between the two acquisitions. The evaluation of the local glandular information is performed using histogram similarity metrics, such as intersection and correlation, and local measures, such as statistics from the difference image and local gradient correlation measures. Results Global measures showed a high correlation (breast volume R = 0.99, volume of glandular tissue R = 0.94, and volumetric breast density R = 0.96) regardless the anode/filter material. Similarly, histogram intersection and correlation metric showed that, for each pair, the images share a high degree of information. Regarding the local distribution of glandular tissue, small changes in the angle of view do not yield significant differences in the glandular pattern, whilst changes in the breast thickness between both acquisition affect the spatial parenchymal distribution. Conclusions This study indicates that Volpara™ Density Maps is reliable in estimating the local glandular tissue distribution and can be used for its assessment and follow-up. Volpara™ Density Maps is robust to small variations of the acquisition angle and to the beam energy, although divergences arise due to different breast compression conditions This work was partially funded by the Ministry of Economy and Competitiveness of Spain grant under project reference DPI2015-68442-R and by Universitat de Girona by UdG grant MPCUdG2016/022. Eloy Garcıa holds a FPI grant BES-2013-065314. Oliver Diaz is funded by the SCARtool project (H2020-MSCA-IF-2014, reference 657875), a research funded by the European Union within the Marie Sklodowska-Curie Innovative Training Networks

In this paper, an UWB Tapered Slot Vivaldi Antenna (TSA) is presented. The proposed TSA is optimized in order to increase the bandwidth and ensure a good impedance matching at low and bandwidth frequencies while respecting the low profile. The overall size of simulated antenna is 45×40×0.8 mm 3 . This antenna is designed in order to be used in bio medical application and some other radar based microwave imaging. This work was supported by the Moroccan Ministry of Higher Education (MESRSFC) and the CNRST under grant number PPR2/2015/36.

Specialists have used confocal microscopy in the ex-vivo modality to identify Basal Cell Carcinoma tumors with an overall sensitivity of 96.6% and specificity of 89.2% (Chung et al., 2004). However, this technology hasn’t established yet in the standard clinical practice because most pathologists lack the knowledge to interpret its output. In this paper we propose a combination of deep learning and computer vision techniques to digitally stain confocal microscopy images into H&E-like slides, enabling pathologists to interpret these images without specific training. We use a fully convolutional neural network with a multiplicative residual connection to denoise the confocal microscopy images, and then stain them using a Cycle Consistency Generative Adversarial Network

Magnetic resonance imaging (MRI) synthesis has attracted attention due to its various applications in the medical imaging domain. In this paper, we propose generating synthetic multiple sclerosis (MS) lesions on MRI images with the final aim to improve the performance of supervised machine learning algorithms, therefore, avoiding the problem of the lack of available ground truth. We propose a two-input two-output fully convolutional neural network model for MS lesion synthesis in MRI images. The lesion information is encoded as discrete binary intensity level masks passed to the model and stacked with the input images. The model is trained end-to-end without the need for manually annotating the lesions in the training set. We then perform the generation of synthetic lesions on healthy images via registration of patient images, which are subsequently used for data augmentation to increase the performance for supervised MS lesion detection algorithms. Our pipeline is evaluated on MS patient data from an in-house clinical dataset and the public ISBI2015 challenge dataset. The evaluation is based on measuring the similarities between the real and the synthetic images as well as in terms of lesion detection performance by segmenting both the original and synthetic images individually using a state-of-the-art segmentation framework. We also demonstrate the usage of synthetic MS lesions generated on healthy images as data augmentation. We analyze a scenario of limited training data (one-image training) to demonstrate the effect of the data augmentation on both datasets. Our results significantly show the effectiveness of the usage of synthetic MS lesion images. For the ISBI2015 challenge, our one-image model trained using only a single image plus the synthetic data augmentation strategy showed a performance similar to that of other CNN methods that were fully trained using the entire training set, yielding a comparable human expert rater performance.

Methods The aim of the paper is twofold. First, we present Starviewer, a DICOM viewer developed in C++ with a core component built on top of open-source libraries. The viewer supports extensions that implement functionalities and front-ends for specific use cases. Second, we propose an adaptable evaluation framework based on a set of criteria weighted according to user needs. The framework can consider different user profiles and allow criteria to be decomposed in subcriteria and grouped in more general categories making a multi-level hierarchical structure that can be analysed at different levels of detail to make scores interpretation more comprehensible. Results Different examples to illustrate Starviewer functionalities and its extensions are presented. In addition, the proposed evaluation framework is used to compare Starviewer with four open-source viewers regarding their functionalities for daily clinical practice. In a range from 0 to 10, the final scores are: Horos (7.7), Starviewer (6.2), Weasis (6.0), Ginkgo CADx (4.1), and medInria (3.8). Conclusions Starviewer provides basic and advanced features for daily image diagnosis needs as well as a modular design that enables the development of custom extensions. The evaluation framework is useful to understand and prioritize new development goals, and can be easily adapted to express different needs by altering the weights. Moreover, it can be used as a complement to maturity models.

With recent advances in the field of deep learning, the use of convolutional neural networks (CNNs) in medical imaging has become very encouraging. The aim of our paper is to propose a patch-based CNN method for automated mass detection in full-field digital mammograms (FFDM). In addition to evaluating CNNs pretrained with the ImageNet dataset, we investigate the use of transfer learning for a particular domain adaptation. First, the CNN is trained using a large public database of digitized mammograms (CBIS-DDSM dataset), and then the model is transferred and tested onto the smaller database of digital mammograms (INbreast dataset). We evaluate three widely used CNNs (VGG16, ResNet50, InceptionV3) and show that the InceptionV3 obtains the best performance for classifying the mass and nonmass breast region for CBIS-DDSM. We further show the benefit of domain adaptation between the CBIS-DDSM (digitized) and INbreast (digital) datasets using the InceptionV3 CNN. Mass detection evaluation follows a fivefold cross-validation strategy using free-response operating characteristic curves. Results show that the transfer learning from CBIS-DDSM obtains a substantially higher performance with the best true positive rate (TPR) of 0.98 ± 0.02 at 1.67 false positives per image (FPI), compared with transfer learning from ImageNet with TPR of 0.91 ± 0.07 at 2.1 FPI. In addition, the proposed framework improves upon mass detection results described in the literature on the INbreast database, in terms of both TPR and FPI This work is partially supported by SMARTER project funded by Ministry of Economy and Competitiveness of Spain, under project reference DPI2015-68442-R.A. is funded by the support of the Secretariat of Universities and Research, Ministry of Economy and Knowledge, Government of Catalonia Ref. ECO/1794/2015 FIDGR-2016

A recent trend in digital mammography is computer-aided diagnosis systems, which are computerised tools designed to assist radiologists. Most of these systems are used for the automatic detection of abnormalities. However, recent studies have shown that their sensitivity is significantly decreased as the density of the breast increases. This dependence is method specific. In this paper we propose a new approach to the classification of mammographic images according to their breast parenchymal density. Our classification uses information extracted from segmentation results and is based on the underlying breast tissue texture. Classification performance was based on a large set of digitised mammograms. Evaluation involves different classifiers and uses a leave-one-out methodology. Results demonstrate the feasibility of estimating breast density using image processing and analysis techniques.

Malaria is a well known disease that affects nearly half of the population of the world. Besides, it has been widely accepted that microcirculation plays an important role in malaria pathogenesis. The use of Cytocam-IDF imaging technique, allows capturing cell?s movement in human blood vessels in a non-invasive form. In order to analyse the relationship between blood flow heterogeneity and Malaria, this work presents a method for tracking individual red blood cells inside vessels from both healthy and unhealthy individuals. The design and evaluation of this method have been based on the specific characteristics presented by the data provided. La malaria es una conocida enfermedad que afecta a casi la mitad de la población del mundo. Además, se ha demostrado repetidamente que la microcirculación juega un papel importante en la patogénesis de la malaria. El uso de la técnica de imagen Cytocam-IDF, permite capturar el movimiento de las células en los vasos sanguíneos humanos de una forma no invasiva. Con el fin de analizar la relación entre la heterogeneidad del flujo sanguíneo y la Malaria, este trabajo presenta un método para el seguimiento de los glóbulos rojos dentro de venas de individuos tanto sanos como afectados por la enfermedad. El diseño y la evaluación de este método se han basado en las características específicas presentadas por las imágenes proporcionadas. La malària és una malaltia ben coneguda que afecta gairebé la meitat de la població del món. A més, s'ha acceptat àmpliament que la microcirculació té un paper important en la patogènesi de la Malària. L'ús de la tècnica d'imatge Cytocam-IDF, permet la captura de moviment de cèl·lules dins els vasos sanguinis humans d'una forma no invasiva. Per tal d'analitzar la relació entre l'heterogeneïtat del flux sanguini i la Malària, aquest treball presenta un mètode per al seguiment dels glòbuls vermelles dins les venes de persones, tant sanes com infectades per la malaltia. El disseny i l'avaluació d'aquest mètode s'han basat en les característiques específiques presentades per les dades proporcionades.

In recent years, Convolutional Neural Networks (ConvNets) have rapidly emerged as a widespread machine learning technique in a number of applications especially in the area of medical image classification and segmentation. In this paper, we propose a novel approach that uses ConvNet for classifying brain medical images into healthy and unhealthy brain images. The unhealthy images of brain tumors are categorized also into low grades and high grades. In particular, we use the modified version of the Alex Krizhevsky network (AlexNet) deep learning architecture on magnetic resonance images as a potential tumor classification technique. The classification is performed on the whole image where the labels in the training set are at the image level rather than the pixel level. The results showed a reasonable performance in characterizing the brain medical images with an accuracy of 91.16%.

Digital mammograms may present an overexposed area in the peripheral part of the breast, which is visually shown as a darker area with lower contrast. This has a direct impact on image quality and affects image visualisation and assessment. This paper presents an automatic method to enhance the overexposed peripheral breast area providing a more homogeneous and improved view of the whole mammogram. The method automatically restores the overexposed area by equalising the image using information from the intensity of non-overexposed neighbour pixels. The correction is based on a multiplicative model and on the computation of the distance map from the breast boundary. A total of 334 digital mammograms were used for evaluation. Mammograms before and after enhancement were evaluated by an expert using visual comparison. In 90.42% of the cases, the enhancement obtained improved visualisation compared to the original image in terms of contrast and detail. Moreover, results show that lesions found in the peripheral area after enhancement presented a more homogeneous intensity distribution. Hence, peripheral enhancement is shown to improve visualisation and will play a role in further development of CAD systems in mammography This work was partially funded by the Spanish R+D+I Grant no. TIN2012-37171-C02-01. M. Tortajada holds a UdG BR-GR10 grant

Objectives: In this paper, we present ProstateAnalyzer, a new web-based medical tool for prostate cancer diagnosis. ProstateAnalyzer allows the visualization and analysis of magnetic resonance images (MRI) in a single framework. Methods: ProstateAnalyzer recovers the data from a PACS server and displays all the associated MRI images in the same framework, usually consisting of 3D T2-weighted imaging for anatomy, dynamic contrast-enhanced MRI for perfusion, diffusion-weighted imaging in the form of an apparent diffusion coefficient (ADC) map and MR Spectroscopy. ProstateAnalyzer allows annotating regions of interest in a sequence and propagates them to the others. Results: From a representative case, the results using the four visualization platforms are fully detailed, showing the interaction among them. The tool has been implemented as a Java-based applet application to facilitate the portability of the tool to the different computer architectures and software and allowing the possibility to work remotely via the web. Conclusion: ProstateAnalyzer enables experts to manage prostate cancer patient data set more efficiently. The tool allows delineating annotations by experts and displays all the required information for use in diagnosis. According to the current European Society of Urogenital Radiology guidelines, it also includes the PI-RADS structured reporting scheme This work was partially funded by the Spanish R+D+I Grant no. TIN2012-37171-C02-01

Scattering is one of the main issues left in planar mammography examinations, as it degrades the quality of the image and complicates the diagnostic process. Although widely used, anti-scatter grids have been found to be inefficient, increasing the dose delivered, the equipment price and not eliminating all the scattered radiation. Alternative scattering reduction methods, based on post-processing algorithms using Monte Carlo (MC) simulations, are being developed to substitute anti-scatter grids. Idealized detectors are commonly used in the simulations for the purpose of simplification. In this study, the scatter distribution of three detector geometries is analyzed and compared: Case 1 makes use of idealized detector geometry, Case 2 uses a scintillator plate and Case 3 uses a more realistic detector simulation, based on the structure of an indirect mammography X-ray detector. This paper demonstrates that common configuration simplifications may introduce up to 14% of underestimation of the scatter in simulation results Oliver Díaz is supported by the European Union within the Marie Sklodowska-Curie Innovative Training Networks (H2020-MSCA-IF-2014 SCARtool project, reference 657875) and the Ministry of Economy Competitiveness of Spain, under project reference DPI2015- and 68442-R

Minimally invasive surgical and diagnostic systems rely on endoscopic images of internal organs to assist medical tasks. Specular highlights are common on those images due to the strong reflectivity of the mucus layer on the organs and the relatively high intensity of the light source. This is a significant source of error that can affect the systems’ performance. In this paper, we propose a segmentation method of the specular regions based on an automatic color-adaptive threshold and a gradient-based edge detector. The segmented regions are then recovered using a robust mask-specific Sobolev inpainting approach. Experimental results demonstrate the precision and efficiency of the proposed method. In contrast to the existing approaches, the proposed solution does not require manual threshold selection or complex computations to achieve accurate results. Moreover, our method has a real-time performance and can be generalized to various applications.

Aquest estudi busca investigar el paper del circuit frontoestriat com a biomarcador dels d'eficits en les funcions executives observades en la malaltia de Huntington utilitzant dos estratègies diferents (i.e. general linear model and support vector machines)

Breast cancer is the most frequently diagnosed cancer in women. However, the exact cause(s) of breast cancer still remains unknown. Early detection, precise identification of women at risk, and application of appropriate disease prevention measures are by far the most effective way to tackle breast cancer. There are more than 70 common genetic susceptibility factors included in the current non-image-based risk prediction models (e.g., the Gail and the Tyrer-Cuzick models). Image-based risk factors, such as mammographic densities and parenchymal patterns, have been established as biomarkers but have not been fully incorporated in the risk prediction models used for risk stratification in screening and/or measuring responsiveness to preventive approaches. Within computer aided mammography, automatic mammographic tissue segmentation methods have been developed for estimation of breast tissue composition to facilitate mammographic risk assessment. This paper presents a comprehensive review of automatic mammographic tissue segmentation methodologies developed over the past two decades and the evidence for risk assessment/density classification using segmentation. The aim of this review is to analyse how engineering advances have progressed and the impact automatic mammographic tissue segmentation has in a clinical environment, as well as to understand the current research gaps with respect to the incorporation of image-based risk factors in non-image-based risk prediction models.

In computer-assisted beating heart surgeries, accurate tracking of the heart’s motion is of huge importance and there is a continuous need to eliminate any source of error that might disturb the tracking process. One source of error is the specular reflection that appears on the glossy surface of the heart. In this paper, we propose a robust solution for the detection and removal of specular highlights. A hybrid color attributes and wavelet based edge projection approach is applied to accurately identify the affected regions. These regions are then recovered using a dynamic search-based inpainting with adaptive windowing. Experimental results demonstrate the precision and efficiency of the proposed method. Moreover, it has a real-time performance and can be generalized to various other applications.

This paper proposes a new technique for the analysis of renal biopsies stained with Sirius red and digitized under non-polarized light. The renal interstitial space, the cortex area and the tubules should be segmented to allow the estimation of the renal cortical interstitial volume fraction and the parameters characterizing the tubule distribution. In this paper, a totally automatic algorithm is proposed that relies on mathematic morphology tools. The proposed algorithm has been assessed in a large number of biopsies leading to similar results to those obtained by the manual approach.

Purpose: Atheromatic plaque progression is affected, among others phenomena, by biomechanical, biochemical, and physiological factors. In this paper, the authors introduce a novel framework able to provide both morphological (vessel radius, plaque thickness, and type) and biomechanical (wall shear stress and Von Mises stress) indices of coronary arteries. Methods: First, the approach reconstructs the three-dimensional morphology of the vessel from intravascular ultrasound(IVUS) and Angiographic sequences, requiring minimal user interaction. Then, a computational pipeline allows to automatically assess fluid-dynamic and mechanical indices. Ten coronary arteries are analyzed illustrating the capabilities of the tool and confirming previous technical and clinical observations. Results: The relations between the arterial indices obtained by IVUS measurement and simulations have been quantitatively analyzed along the whole surface of the artery, extending the analysis of the coronary arteries shown in previous state of the art studies. Additionally, for the first time in the literature, the framework allows the computation of the membrane stresses using a simplified mechanical model of the arterial wall. Conclusions: Circumferentially (within a given frame), statistical analysis shows an inverse relation between the wall shear stress and the plaque thickness. At the global level (comparing a frame within the entire vessel), it is observed that heavy plaque accumulations are in general calcified and are located in the areas of the vessel having high wall shear stress. Finally, in their experiments the inverse proportionality between fluid and structural stresses is observed.

Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2013, Director: Simone Balocco i Francesco Ciompi, Coronary heart disease is the leading cause of mortality and obesity in developed countries, luckily in recent decades have developed various forms of medical imaging extraction useful for diagnosis and monitoring of patients with these problems. IVUS images are the most important in this field since they allow observing the arteries from the inside and take useful measures for the treatment of the disease. To assist doctors work an automatic lumen area segmentation system is being developed, which is the area where the blood flows in the arteries. In this paper we try to study its performance and try to optimize this system to bring it a little more accurate segmentation to be useful in medical practice.

Fiber tracking is the most popular technique for creating white matter connectivity maps from diffusion tensor imaging (DTI). This approach requires a seeding process which is challenging because it is not clear how and where the seeds have to be placed. On the other hand, to enhance the interpretation of fiber maps, segmentation and clustering techniques are applied to organize fibers into anatomical structures. In this paper, we propose a new approach to automatically obtain bundles of fibers grouped into anatomical regions. This method applies an information-theoretic split-and-merge algorithm that considers fractional anisotropy and fiber orientation information to automatically segment white matter into volumes of interest (VOIs) of similar FA and eigenvector orientation. For each VOI, a number of planes and seeds is automati- cally placed in order to create the fiber bundles. The proposed approach avoids the need for the user to define seeding or selection regions. The whole process requires less than a minute and minimal user interaction. The agreement between the automated and manual approaches has been measured for 10 tracts in a DTI brain atlas and found to be almost perfect (kappa > 0.8) and substantial (kappa > 0.6). This method has also been evaluated on real DTI data considering 5 tracts. Agreement was substantial (kappa > 0.6) in most of the cases This work has been supported by TIN2010-21089-C03-01 and 2009 SGR 643 and FIS PS09/00596 of I+D+I 2009-2012

Living systems have fairly high concentration of ions, and as a result they conduct electricity, and therefore may impair the quality of magnetic resonance imaging. This paper will show both by calculated value and experimental data that magnetic resonance signal depend on the object being imaged, and the distribution of the conductivity. The conductivity effect in magnetic resonance imaging only change the signal intensity and does not cause blurring.

In this paper we present a knowledge-based approach for the automatic detection of microcalcifications and clusters in mammographic images. Our proposal is based on using local features extracted from a bank of filters to obtain a local description of the microcalcifications morphology. The developed approach performs an initial training step in order to automatically learn and select the most salient features, which are subsequently used in a boosted classifier to perform the detection of individual microcalcifications. Subsequently, the microcalcification detection method is extended in order to detect clusters. The validity of our approach is extensively demonstrated using two digitised databases and one full-field digital database. The experimental evaluation is performed in terms of ROC analysis for the microcalcification detection and FROC analysis for the cluster detection, resulting in better than 80% sensitivity at 1 false positive cluster per image We would like to thank the reviewers for their critical evaluation of the manuscript. This study has been supported by the Ministerio de Ciencia e Innovacion under grants TIN2011-23704 and AYA2010-21782-C03-02. A.Torrent holds a FPU grant AP2007-01934. M. Tortajada holds a UdG grant BRGR10-04

This paper presents a novel method for non-rigid registration of transrectal ultrasound and magnetic resonance prostate images based on a non-linear regularized framework of point correspondences obtained from a statistical measure of shape-contexts. The segmented prostate shapes are represented by shape-contexts and the Bhattacharyya distance between the shape representations is used to find the point correspondences between the 2D fixed and moving images. The registration method involves parametric estimation of the non-linear diffeomorphism between the multimodal images and has its basis in solving a set of non-linear equations of thin-plate splines. The solution is obtained as the least-squares solution of an over-determined system of non-linear equations constructed by integrating a set of non-linear functions over the fixed and moving images. However, this may not result in clinically acceptable transformations of the anatomical targets. Therefore, the regularized bending energy of the thin-plate splines along with the localization error of established correspondences should be included in the system of equations. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate mid-gland ultrasound and magnetic resonance images. The results obtained in terms of Dice similarity coefficient show an average of 0.980 ± 0.004, average 95% Hausdorff distance of 1.63 ± 0.48. mm and mean target registration and target localization errors of 1.60 ± 1.17. mm and 0.15 ± 0.12. mm respectively This work is a part of the PROSCAN Project of the VICOROB laboratory of University of Girona, Catalunya, Spain. The authors thank VALTEC 08-1-0039 of Generalitat de Catalunya, Spanish Science and Innovation grant nb. TIN2011-23704, Spain and Conseil Regional de Bourgogne, France for funding this research. The research is also partially supported by the Grant CNK80370 of the National Innovation Office (NIH) and Hungarian Scientific Research Fund (OTKA); the European Union and co-financed by the European Regional Development Fund within the Project TAMOP-4.2.1/B-09/1/KONV-2010-0005

Ultrasound contrast is gaining acceptance worldwide as an adjunct to conventional ultrasound imaging. It has clinical applications as diverse as liver disease detection and characterization, myocardial perfusion and wall motion studies, and cerebral vascularity and perfusion imaging. This paper will focus on imaging techniques used for transcranial ultrasound contrast imaging. The interaction of ultrasound with the microbubbles in the contrast agent is complex and nonlinear. This has led to the development of a variety of imaging modes to improve contrast detection over noncontrast optimized modes. This article presents several of these imaging methods in such a way as to help clinical and research users of ultrasound contrast understand this rapidly developing field. Copyright © 2009 S. Karger AG, Basel ABSTRACT FROM AUTHOR] Copyright of Cerebrovascular Diseases is the property of Karger AG and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) 27 14 24 14-24

This paper presents a comparison of two clustering based algorithms and one region based algorithm for segmenting fatty and dense tissue in mammographic images. This is a crucial step in order to obtain a quantitative measure of the density of the breast. The first algorithm is a multiple thresholding algorithm based on the excess entropy, the second one is based on the Fuzzy C-Means clustering algorithm, and the third one is based on a statistical analysis of the breast. The performance of the algorithms is exhaustively evaluated using a database of full-field digital mammograms containing 150 CC and 150 MLO images and ROC analysis (ground-truth provided by an expert). Results demonstrate that the use of region information is useful to obtain homogeneous region segmentation, although clustering algorithms obtained better sensitivity

Inter patient shape, size and intensity variations of the prostate in transrectal ultrasound (TRUS) images challenge automatic segmentation of the prostate. In this paper we propose a variational model driven by Mumford-Shah (MS) functional for segmenting the prostate. Parametric representation of the implicit curve is derived from principal component analysis (PCA) of the signed distance representation of the labeled training data to impose shape prior. Posterior probability of the prostate region determined from random forest classification facilitates initialization and propagation of our model in a MS energy minimization framework. The proposed method achieves mean Dice similarity coefficient (DSC) value of 0.97±0.01, with a mean Hausdorff distance (HD) value of 1.73±0.24 mm when validated with 24 images from 6 datasets in a leave-one-patient-out validation framework. The model achieves statistically significant t-test p-value

In this paper a Terahertz T ime-Domain measurement system has been used to perform Tomographic imaging of pharmaceutical compounds with coating. Measurements on paracetamol and ibuprofene samples are done both in transmission and reflection geometries and their capabilities are compared. Results of the contrast reconstructions provide information of the relative permittivity of the pharmaceutical compounds. T he interfaces between materials with different permittivities are detected, thus allowing characterization of different layers of the compound.