Search

Finding new ways to cost-effectively facilitate population screening and improve cancer diagnoses at an early stage supported by data-driven AI models provides unprecedented opportunities to reduce cancer related mortality. This work presents the INCISIVE project initiative towards enhancing AI solutions for health imaging by unifying, harmonizing, and securely sharing scattered cancer-related data to ensure large datasets which are critically needed to develop and evaluate trustworthy AI models. The adopted solutions of the INCISIVE project have been outlined in terms of data collection, harmonization, data sharing, and federated data storage in compliance with legal, ethical, and FAIR principles. Experiences and examples feature breast cancer data integration and mammography collection, indicating the current progress, challenges, and future directions. This research received funding mainly from the European Union’s Horizon 2020 research and innovation program under grant agreement no 952179. It was also partially funded by the Ministry of Economy, Industry, and Competitiveness of Spain under contracts PID2019-107255GB and 2017-SGR-1414. Peer Reviewed Article signat per 30 autors/es: Ivan Lazic (1), Ferran Agullo (2), Susanna Ausso (3), Bruno Alves (4), Caroline Barelle (4), Josep Ll. Berral (2), Paschalis Bizopoulos (5), Oana Bunduc (6), Ioanna Chouvarda (7), Didier Dominguez (3), Dimitrios Filos (7), Alberto Gutierrez-Torre (2), Iman Hesso (8), Nikša Jakovljević (1), Reem Kayyali (8), Magdalena Kogut-Czarkowska (9), Alexandra Kosvyra (7), Antonios Lalas (5) , Maria Lavdaniti (10,11), Tatjana Loncar-Turukalo (1),Sara Martinez-Alabart (3), Nassos Michas (4,12), Shereen Nabhani-Gebara (8), Andreas Raptopoulos (6), Yiannis Roussakis (13), Evangelia Stalika (7,11), Chrysostomos Symvoulidis (6,14), Olga Tsave (7), Konstantinos Votis (5) Andreas Charalambous (15) / (1) Faculty of Technical Sciences, University of Novi Sad, 21000 Novi Sad, Serbia; (2) Barcelona Supercomputing Center, 08034 Barcelona, Spain; (3) Fundació TIC Salut Social, Ministry of Health of Catalonia, 08005 Barcelona, Spain; (4) European Dynamics, 1466 Luxembourg, Luxembourg; (5) Centre for Research and Technology Hellas, 57001 Thessaloniki, Greece; (6) Telesto IoT Solutions, London N7 7PX, UK: (7) School of Medicine, Faculty of Health Sciences, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece; (8) Department of Pharmacy, Kingston University London, London KT1 2EE, UK; (9) Timelex BV/SRL, 1000 Brussels, Belgium; (10) Nursing Department, International Hellenic University, 57400 Thessaloniki, Greece; (11) Hellenic Cancer Society, 11521 Athens, Greece; (12) European Dynamics, 15124 Athens, Greece; (13) German Oncology Center, Department of Medical Physics, Limassol 4108, Cyprus; (14) Department of Digital Systems, University of Piraeus, 18534 Piraeus, Greece; (15) Department of Nursing, Cyprus University of Technology, Limassol 3036, Cyprus

BACKGROUND: We assessed the long-term risk of screen-detected and interval breast cancer in women with a first or second false-positive screening result. METHODS: Joint analysis had been performed using individual-level data from three population-based screening programs in Europe (Copenhagen in Denmark, Norway, and Spain). Overall, 75,513 screened women aged 50-69 years from Denmark (1991-2010), 556,640 from Norway (1996-2008), and 517,314 from Spain (1994-2010) were included. We used partly conditional Cox hazards models to assess the association between false-positive results and the risk of subsequent screen-detected and interval cancer. RESULTS: During follow-up, 1,149,467 women underwent 3,510,450 screening exams, and 10,623 screen-detected and 5700 interval cancers were diagnosed. Compared to women with negative tests, those with false-positive results had a two-fold risk of screen-detected (HR = 2.04, 95% CI: 1.93-2.16) and interval cancer (HR = 2.18, 95% CI: 2.02-2.34). Women with a second false-positive result had over a four-fold risk of screen-detected and interval cancer (HR = 4.71, 95% CI: 3.81-5.83 and HR = 4.22, 95% CI: 3.27-5.46, respectively). Women remained at an elevated risk for 12 years after the false-positive result. CONCLUSIONS: Women with prior false-positive results had an increased risk of screen-detected and interval cancer for over a decade. This information should be considered to design personalised screening strategies based on individual risk.

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 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

BACKGROUND: In Spain, women invited to breast screening are not usually informed about potential harms of screening. The objective of the InforMa study is to assess the effect of receiving information about the benefits and harms of breast screening on informed choice and other decision-making outcomes, in women approaching the age of invitation to mammography screening. METHODS: Two-stage randomised controlled trial. In the first stage, 40 elementary territorial units of the public healthcare system were selected and randomised to intervention or control. In the second stage, women aged 49-50 years were randomly selected. The target sample size was 400 women. Women in the intervention arm received a decision aid (DA) with detailed information on the benefits and harms of screening. Women in the control arm received a standard leaflet that did not mention harms and recommended accepting the invitation to participate in the Breast Cancer Screening Program (BCSP). The primary outcome was informed choice, defined as adequate knowledge and intentions consistent with attitudes. Secondary outcomes included decisional conflict, worry about breast cancer, time perspective, opinions about the DA or the leaflet, and participation in the BCSP. RESULTS: In the intervention group, 23.2% of 203 women made an informed choice compared to only 0.5% of 197 women in the control group (p < 0.001). Attitudes and intentions were similar in both study groups with a high frequency of women intending to be screened, 82.8% vs 82.2% (p = 0.893). Decisional conflict was significantly lower in the intervention group. No differences were observed in confidence in the decision, anxiety, and participation in BCSP. CONCLUSIONS: Women in Spain lack knowledge on the benefits and harms of breast screening. Providing quantitative information on benefits and harms has produced a considerable increase in knowledge and informed choice, with a high acceptance of the informative materials. TRIAL REGISTRATION: Trial identifier NCT03046004 at ClinicalTrials.gov registry. Registered on February 4 2017. Trial name: InforMa study. This study was supported by the research grant “Women participation in decisions and strategies on early detection of breast cancer” (PI14/00113) from the Instituto de Salud Carlos III and cofunded by Fondo Europeo de Desarrollo Regional (FEDER) “Una manera de hacer Europa.” Anna Pons received a grant for PhD students from the Lleida Biomedical Research Institute (IRBLleida). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

DOI: 10.1155/2016/1370259 Texture analysis methods are widely used to characterize breast masses in mammograms. Texture gives information about the spatial arrangement of the intensities in the region of interest. This information has been used in mammogram analysis applications such as mass detection, mass classification, and breast density estimation. In this paper, we study the effect of factors such as pixel resolution, integration scale, preprocessing, and feature normalization on the performance of those texture methods for mass classification. The classification performance was assessed considering linear and nonlinear support vector machine classifiers. To find the best combination among the studied factors, we used three approaches: greedy, sequential forward selection (SFS), and exhaustive search. On the basis of our study, we conclude that the factors studied affect the performance of texture methods, so the best combination of these factors should be determined to achieve the best performance with each texture method. SFS can be an appropriate way to approach the factor combination problem because it is less computationally intensive than the other methods.

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.

Breast magnetic resonance imaging (MRI) and X-ray mammography are two image modalities widely used for early detection and diagnosis of breast diseases in women. The combination of these modalities, traditionally done using intensity-based registration algorithms, leads to a more accurate diagnosis and treatment, due to the capability of co-localizing lesions and susceptibles areas between the two image modalities. In this work, we present the first attempt to register breast MRI and X-ray mammographic images using intensity gradients as the similarity measure. Specifically, a patient-specific biomechanical model of the breast, extracted from the MRI image, is used to mimic the mammographic acquisition. The intensity gradients of the glandular tissue are directly projected from the 3D MRI volume to the 2D mammographic space, and two different gradient-based metrics are tested to lead the registration, the normalized cross-correlation of the scalar gradient values and the gradient correlation of the vectoral gradients. We compare these two approaches to an intensity-based algorithm, where the MRI volume is transformed to a synthetic computed tomography (pseudo-CT) image using the partial volume effect obtained by the glandular tissue segmentation performed by means of an Expectation-Maximization algorithm. This allows us to obtain the digitally reconstructed radiographies by a direct intensity projection. The best results are obtained using the scalar gradient approach along with a transversal isotropic material model, obtaining a target registration error (TRE), in millimeters, of 5.65 ± 2.76 for CC- and of 7.83 ± 3.04 for MLO-mammograms, while the TRE is 7.33 ± 3.62 in the 3D MRI. We also evaluate the effect of the glandularity of the breast as well as the landmark position on the TRE, obtaining moderated correlation values (0.65 and 0.77 respectively), concluding that these aspects need to be considered to increase the accuracy in further approaches This research has been partially supported from the University of Girona (MPC UdG 2016/022 grant), the European Union within the Marie Sklodowska-Curie Innovative Training Networks (SCARtool project H2020-MSCA-IF-2014, reference 657875) and the Ministry of Economy and Competitiveness of Spain, under project SMARTER (DPI2015-68442-R) and the FPI grant BES-2013-065314

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

OBJECTIVE: To analyse mammography screening in Spanish women aged 45 to 69 according sociodemographic variables and to describe the role of population-based breast cancer screening programmes in terms of variability of said screening. METHODS: Cross-sectional study of the 2011 National Health Survey. The study population includes women living in Spain between late 2011 and early 2012. The weighted sample analysed corresponds to 3,086 women aged 45 to 69. The dependent variables were mammograms and when the last mammogram was performed and why. Independent variables were age, social class, occupational status, country of origin, area of origin (rural/urban), health cover and years the programme had been in place. Logistic regression models were performed, with odds ratio (OR) adjusted according to age and 95% confidence intervals (95% CI). RESULTS: Approximately 91.9% indicated that they had had a mammogram before. The women who had had their last mammography screening in the previous 1 to 2 years were associated with the highest social class (OR: 1.69; 95% CI: 1.03-2.75). The reason for performing the last periodic mammogram via a population-based programme was associated with women aged between 60 and 69 years (OR: 1.51; 95% CI: 1.04-2.19). CONCLUSIONS: The results show that there are still inequalities in preventive practices. Possible risk groups need to be identified in order to promote the implementation of specific actions. Objetivo: Analizar según variables sociodemográficas el control mamográfico que realizan las mujeres españolas de 45 a 69 años de edad y describir el papel que desempeñan los programas poblacionales de cribado del cáncer de mama en cuanto a la variabilidad de los controles mamográficos. Métodos: Estudio transversal a partir de la Encuesta Nacional de Salud de 2011. La población de estudio son las mujeres residentes en España entre finales de 2011 y principios de 2012. La muestra ponderada analizada corresponde a 3.086 mujeres de 45 a 69 años de edad. Las variables dependientes fueron la realización de mamografías, la última mamografía y el motivo de su realización. Las variables independientes fueron la edad, la clase social, la situación laboral, el país de origen, el ámbito de procedencia, la cobertura sanitaria y los años de implantación del programa. Se realizaron modelos de regresión logística, obteniendo odds ratio (OR) ajustadas por edad y sus intervalos de confianza del 95% (IC95%). Resultados: Un 91,9% indicó que se había realizado una mamografía alguna vez. Las mujeres que se habían realizado el último control mamográfico entre 1 y 2 años antes se asociaron a la clase social más alta (OR: 1,69;IC95%: 1,03-2,75). El motivo de realizar la última mamografía periódica por un programa poblacional se asoció a las mujeres cuya edad era de 60-69 años (OR: 1,51; IC95%: 1,04-2,19). Conclusión: Los resultados indican que existen desigualdades sociales en la realización de prácticas preventivas. Debemos identificar posibles grupos de riesgo con el fin de impulsar la implementación de acciones específicas.

Background The decision to participate or not in breast cancer screening is complex due to the trade-off between the expected benefit of breast cancer mortality reduction and the major harm of overdiagnosis. It seems ethically necessary to inform women so that they can actively participate in decision-making and make an informed choice based on their values and preferences. The objective of this study is to assess the effects of receiving information about the benefits and harms of screening on decision-making, in women approaching the age of invitation to mammography screening. Methods A two-stage, randomized controlled trial (RCT). In the first stage, 40 Basic Health Areas (BHAs) will be selected and randomized to intervention or control. In the second stage, women within each BHA will be randomly selected (n = 400). Four breast cancer screening programs (BCSPs) of the Spanish public health system, three in Catalonia and one in the Canary Islands will participate in the study. Women in the intervention arm will receive a leaflet with detailed information on the benefits and harms of screening using mammography. Women in the control arm will receive a standard leaflet that does not mention harms and recommends accepting the invitation to participate in the biennial examinations of the BCSP. The primary outcome is informed choice, a dichotomous variable that combines knowledge, attitudes, and intentions. Secondary outcomes include decisional conflict; confidence in the decision made; anxiety about screening participation; worry about breast cancer; anticipated regret; time perspective; perceived importance of benefits/harms of screening; perceived risk of breast cancer; and leaflet acceptability. Primary and secondary outcomes are assessed 2–3 weeks after the intervention. Discussion This is the first RCT that assesses the effect of informing about the benefits and harms of breast cancer screening in Spain in women facing the decision to be screened using mammography. It aims to assess the impact of information on several decisional outcomes and to contribute to paving the road towards shared decision-making in breast cancer screening in our country. Trial registration ClinicalTrials.gov registry, ID: NCT03046004. Retrospectively registered on 4 February 2017. Trial name: InforMa study. Electronic supplementary material The online version of this article (doi:10.1186/s13063-017-2161-7) contains supplementary material, which is available to authorized users.

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 The usual practice in breast cancer screening programmes for mammogram interpretation is to perform double reading. However, little is known about its cost-effectiveness in the context of digital mammography. Our purpose was to evaluate the cost-effectiveness of double reading versus single reading of digital mammograms in a population-based breast cancer screening programme. Methods Data from 28,636 screened women was used to establish a decision-tree model and to compare three strategies: 1) double reading; 2) double reading for women in their first participation and single reading for women in their subsequent participations; and 3) single reading. We calculated the incremental cost-effectiveness ratio (ICER), which was defined as the expected cost per one additionally detected cancer. We performed a deterministic sensitivity analysis to test the robustness of the ICER. Results The detection rate of double reading (5.17 parts per thousand) was similar to that of single reading (4.78 parts per thousand; P = .768). The mean cost of each detected cancer was (sic)8,912 for double reading and (sic)8,287 for single reading. The ICER of double reading versus single reading was (sic)16,684. The sensitivity analysis showed variations in the ICER according to the sensitivity of reading strategies. The strategy that combines double reading in first participation with single reading in subsequent participations was ruled out due to extended dominance. Conclusions From our results, double reading appears not to be a cost-effective strategy in the context of digital mammography. Double reading would eventually be challenged in screening programmes, as single reading might entail important net savings without significantly changing the cancer detection rate. These results are not conclusive and should be confirmed in prospective studies that investigate long-term outcomes like quality adjusted life years (QALYs).

DOI: 10.1155/2016/1370259 Texture analysis methods are widely used to characterize breast masses in mammograms. Texture gives information about the spatial arrangement of the intensities in the region of interest. This information has been used in mammogram analysis applications such as mass detection, mass classification, and breast density estimation. In this paper, we study the effect of factors such as pixel resolution, integration scale, preprocessing, and feature normalization on the performance of those texture methods for mass classification. The classification performance was assessed considering linear and nonlinear support vector machine classifiers. To find the best combination among the studied factors, we used three approaches: greedy, sequential forward selection (SFS), and exhaustive search. On the basis of our study, we conclude that the factors studied affect the performance of texture methods, so the best combination of these factors should be determined to achieve the best performance with each texture method. SFS can be an appropriate way to approach the factor combination problem because it is less computationally intensive than the other methods.

Women with false‐positive results are commonly referred back to routine screening. Questions remain regarding their long‐term outcome of breast cancer. We assessed the risk of screen‐detected breast cancer in women with false‐positive results. We conducted a joint analysis using individual level data from the population‐based screening programs in Copenhagen and Funen in Denmark, Norway, and Spain. Overall, 150,383 screened women from Denmark (1991–2008), 612,138 from Norway (1996–2010), and 1,172,572 from Spain (1990–2006) were included. Poisson regression was used to estimate the relative risk (RR) of screen‐detected cancer for women with false‐positive versus negative results. We analyzed information from 1,935,093 women 50–69 years who underwent 6,094,515 screening exams. During an average 5.8 years of follow‐up, 230,609 (11.9%) women received a false‐positive result and 27,849 (1.4%) were diagnosed with screen‐detected cancer. The adjusted RR of screen‐detected cancer after a false‐positive result was 2.01 (95% CI: 1.93–2.09). Women who tested false‐positive at first screen had a RR of 1.86 (95% CI: 1.77–1.96), whereas those who tested false‐positive at third screening had a RR of 2.42 (95% CI: 2.21–2.64). The RR of breast cancer at the screening test after the false‐positive result was 3.95 (95% CI: 3.71–4.21), whereas it decreased to 1.25 (95% CI: 1.17–1.34) three or more screens after the false‐positive result. Women with false‐positive results had a twofold risk of screen‐detected breast cancer compared to women with negative tests. The risk remained significantly higher three or more screens after the false‐positive result. The increased risk should be considered when discussing stratified screening strategies.

Treball de fi de grau en Sistemes Audiovisuals Tutor: Gemma Piella Fenoy This project investigates the feasibility of using the scattering transform for breast cancer detection from mammograms. The Scattering Transform is a recently introduced descriptor that follows the scheme of a neural network, whose filters are wavelets followed by a modulus operator. We built a classification scheme that involves a feature extraction and a classification stages. For the first stage, we have used the Scattering Transform for extracting discriminant features robust to small deformations in the image. Moreover, we have also used another descriptor as a reference, the Scale-Invariant Feature Transform, widely used in classification problem. For the second stage, we have trained two models, a generative (based on affine spaces) and a discriminative (based on support vector machines). We tested our pattern recognition system on 1590 mammograms (964 normal cases,/n425 cancer cases and 201 benign cases), achieving more than 90% of accuracy. These results confirm that the Scattering Transform is a powerful tool to describe mammograms. Aquest projecte investiga la factibilitat d’utilitzar la transformada scattering en /nproblemes de detecció de càncer de mama mitjançant l’ús de mamografies. /nLa transformada scattering és un nou descriptor/nque segueix l’esquema d’una xarxa /nneuronal on els filtres són /nwavelets/nseguides d’un operador de mòdul. /nHem construït un esquema de classificació format per una etapa d’extracció de /ncaracterístiques i una altra de classificació. Per la primera etapa, hem utilitzat la /ntransformada scattering per extreure característiques discriminants robustes a petites /ndeformacions de la imatge. A més, també hem utilitzat un altre descriptor comú en /nproblemes de classificació, el /nScale-Invariant Feature Transform, que ens ha servit com /na referència. Per la segona etapa, hem entrenat dos models,/nun generatiu (basat en espais /na/nfins) i un altre /ndiscriminatiu (/nbasat en màquines de suport /nvectorial). /nHem testejat el nostre sistema de reconeixement de patrons amb 1590 mamografies /n(694 casos normals, 425 casos cancerígens i 201 casos benignes) i hem obtingut /nmés /nd’un 90% d’encert. /nAquests resultats confirmen/nque /nla transformada scattering és una /nbona eina per descriure mamografies.

It has been shown that the accuracy of mammographic abnormality detection methods is strongly dependent on the breast tissue characteristics, where a dense breast drastically reduces detection sensitivity. In addition, breast tissue density is widely accepted to be an important risk indicator for the development of breast cancer. Here, we describe the development of an automatic breast tissue classification methodology, which can be summarized in a number of distinct steps: 1) the segmentation of the breast area into fatty versus dense mammographic tissue; 2) the extraction of morphological and texture features from the segmented breast areas; and 3) the use of a Bayesian combination of a number of classifiers. The evaluation, based on a large number of cases from two different mammographic data sets, shows a strong correlation ( and 0.67 for the two data sets) between automatic and expert-based Breast Imaging Reporting and Data System mammographic density assessment.

Breast density measurement is an important aspect in breast cancer diagnosis as dense tissue has been related to the risk of breast cancer development. The purpose of this study is to develop a method to automatically compute breast density in breast MRI. The framework is a combination of image processing techniques to segment breast and fibroglandular tissue. Intra- and interpatient signal intensity variability is initially corrected. The breast is segmented by automatically detecting body-breast and air-breast surfaces. Subsequently, fibroglandular tissue is segmented in the breast area using expectation-maximization. A dataset of 50 cases with manual segmentations was used for evaluation. Dice similarity coefficient (DSC), total overlap, false negative fraction (FNF), and false positive fraction (FPF) are used to report similarity between automatic and manual segmentations. For breast segmentation, the proposed approach obtained DSC, total overlap, FNF, and FPF values of 0.94, 0.96, 0.04, and 0.07, respectively. For fibroglandular tissue segmentation, we obtained DSC, total overlap, FNF, and FPF values of 0.80, 0.85, 0.15, and 0.22, respectively. The method is relevant for researchers investigating breast density as a risk factor for breast cancer and all the described steps can be also applied in computer aided diagnosis systems This work was supported by the Spanish Science and Innovation under Grant TIN2012-37171-C02-01. The work of A. Gubern-Merida was supported by the FPU under Grant AP2009-2835

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 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

The massive growth in applications of radiological imaging and image-guided treatments has met a worldwide shortage of trained radiologists. Therefore, several computer-based radiology training environments, which combine traditional learning opportunities with advanced e-learning platforms, have recently been developed with the goal of supporting the acquisition of radiological expertise. However, the quantity and quality of clinical experience arises as the main issue to ensure the success for such learning environments when training radiologists to interpret medical images. In this sense, MamoDB is a research web-based tool which has been customized in order to incorporate learning capabilities for training and guidance of newly employed or resident radiologists. MamoDB allows panels of experts to collaborate at different hospitals and research centres by means of integrating a Picture Archiving and Communication System (PACS) to store the Digital Imaging and Communications in Medicine (DICOM) files as well as a database with the eXtended Markup Language (XML) files containing the experts’ annotations for each clinical case

Introduction: Early detection of breast cancer (BC) with mammography may cause overdiagnosis and overtreatment, detecting tumors which would remain undiagnosed during a lifetime. The aims of this study were: first, to model invasive BC incidence trends in Catalonia (Spain) taking into account reproductive and screening data; and second, to quantify the extent of BC overdiagnosis. Methods: We modeled the incidence of invasive BC using a Poisson regression model. Explanatory variables were: age at diagnosis and cohort characteristics (completed fertility rate, percentage of women that use mammography at age 50, and year of birth). This model also was used to estimate the background incidence in the absence of screening. We used a probabilistic model to estimate the expected BC incidence if women in the population used mammography as reported in health surveys. The difference between the observed and expected cumulative incidences provided an estimate of overdiagnosis. Results: Incidence of invasive BC increased, especially in cohorts born from 1940 to 1955. The biggest increase was observed in these cohorts between the ages of 50 to 65 years, where the final BC incidence rates more than doubled the initial ones. Dissemination of mammography was significantly associated with BC incidence and overdiagnosis. Our estimates of overdiagnosis ranged from 0.4% to 46.6%, for women born around 1935 and 1950, respectively. Conclusions: Our results support the existence of overdiagnosis in Catalonia attributed to mammography usage, and the limited malignant potential of some tumors may play an important role. Women should be better informed about this risk. Research should be oriented towards personalized screening and risk assessment tools.

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

We present a new approach to model and classify breast parenchymal tissue. Given a mammogram, first, we will discover the distribution of the different tissue densities in an unsupervised manner, and second, we will use this tissue distribution to perform the classification. We achieve this using a classifier based on local descriptors and probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature. We studied the influence of different descriptors like texture and SIFT features at the classification stage showing that textons outperform SIFT in all cases. Moreover we demonstrate that pLSA automatically extracts meaningful latent aspects generating a compact tissue representation based on their densities, useful for discriminating on mammogram classification. We show the results of tissue classification over the MIAS and DDSM datasets. We compare our method with approaches that classified these same datasets showing a better performance of our proposal.

Objectives: To objectively evaluate automatic volumetric breast density assessment in Full-Field Digital Mammograms (FFDM) using measurements obtained from breast Magnetic Resonance Imaging (MRI). Material and Methods: A commercially available method for volumetric breast density estimation on FFDM is evaluated by comparing volume estimates obtained from 186 FFDM exams including mediolateral oblique (MLO) and cranial-caudal (CC) views to objective reference standard measurements obtained from MRI. Results: Volumetric measurements obtained from FFDM show high correlation with MRI data. Pearson’s correlation coefficients of 0.93, 0.97 and 0.85 were obtained for volumetric breast density, breast volume and fibroglandular tissue volume, respectively. Conclusions: Accurate volumetric breast density assessment is feasible in Full-Field Digital Mammograms and has potential to be used in objective breast cancer risk models and personalized screening The research leading to these results has received funding from the European Union's Seventh Framework Programme FP7 under grant agreement no 306088 and has been supported by the Spanish Science and Innovation grant nb. TIN2012-37171-C02-01. Albert Gubern-Merida holds a FPU grant AP2009-2835. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript

OBJECTIVE: To compare accuracy measures for mammographic screening in Norway, Spain, and the US. METHODS: Information from women aged 50-69 years who underwent mammographic screening 1996-2009 in the US (898,418 women), Norway (527,464), and Spain (517,317) was included. Screen-detected cancer, interval cancer, and the false-positive rates, sensitivity, specificity, positive predictive value (PPV) for recalls (PPV-1), PPV for biopsies (PPV-2), 1/PPV-1 and 1/PPV-2 were computed for each country. Analyses were stratified by age, screening history, time since last screening, calendar year, and mammography modality. RESULTS: The rate of screen-detected cancers was 4.5, 5.5, and 4.0 per 1000 screening exams in the US, Norway, and Spain respectively. The highest sensitivity and lowest specificity were reported in the US (83.1 % and 91.3 %, respectively), followed by Spain (79.0 % and 96.2 %) and Norway (75.5 % and 97.1 %). In Norway, Spain and the US, PPV-1 was 16.4 %, 9.8 %, and 4.9 %, and PPV-2 was 39.4 %, 38.9 %, and 25.9 %, respectively. The number of women needed to recall to detect one cancer was 20.3, 6.1, and 10.2 in the US, Norway, and Spain, respectively. CONCLUSIONS: Differences were found across countries, suggesting that opportunistic screening may translate into higher sensitivity at the cost of lower specificity and PPV. KEY POINTS: • Positive predictive value is higher in population-based screening programmes in Spain and Norway. • Opportunistic mammography screening in the US has lower positive predictive value. • Screening settings in the US translate into higher sensitivity and lower specificity. • The clinical burden may be higher for women screened opportunistically. This work was partially supported by grants from Instituto de Salud Carlos III FEDER (PI11/01296), BELE Study, the National Institutes of Health (T32CA09168), and the National Cancer Institute-funded Breast Cancer Surveillance Consortium (HHSN261201100031C). The collection of US cancer and vital status data used in this study was supported in part by several state public health departments and cancer registries

Breast cancer is the second cause of death among women cancers. Computer Aided Detection has been demon- strated an useful tool for early diagnosis, a crucial as- pect for a high survival rate. In this context, several re- search works have incorporated texture features in mam- mographic image segmentation and description such as Gray-Level co-occurrence matrices, Local Binary Pat- terns, and many others. This paper presents an approach for breast density classi¯cation based on segmentation and texture feature extraction techniques in order to clas- sify digital mammograms according to their internal tis- sue. The aim of this work is to compare di®erent texture descriptors on the same framework (same algorithms for segmentation and classi¯cation, as well as same images). Extensive results prove the feasibility of the proposed ap- proach.

In order to develop applications for z;isual interpretation of medical images, the early detection and evaluation of microcalcifications in digital mammograms is verg important since their presence is often associated with a high incidence of breast cancers. Accurate classification into benign and malignant groups would help improve diagnostic sensitivity as well as reduce the number of unnecessa y biopsies. The challenge here is the selection of the useful features to distinguish benign from malignant micro calcifications. Our purpose in this work is to analyse a microcalcification evaluation method based on a set of shapebased features extracted from the digitised mammography. The segmentation of the microcalcifications is performed using a fixed-tolerance region growing method to extract boundaries of calcifications with manually selected seed pixels. Taking into account that shapes and sizes of clustered microcalcifications have been associated with a high risk of carcinoma based on digerent subjective measures, such as whether or not the calcifications are irregular, linear, vermiform, branched, rounded or ring like, our efforts were addressed to obtain a feature set related to the shape. The identification of the pammeters concerning the malignant character of the microcalcifications was performed on a set of 146 mammograms with their real diagnosis known in advance from biopsies. This allowed identifying the following shape-based parameters as the relevant ones: Number of clusters, Number of holes, Area, Feret elongation, Roughness, and Elongation. Further experiments on a set of 70 new mammogmms showed that the performance of the classification scheme is close to the mean performance of three expert radiologists, which allows to consider the proposed method for assisting the diagnosis and encourages to continue the investigation in the sense of adding new features not only related to the shape