Breast cancer is the most common cancer to affect women and the leading cause of cancer deaths in women in Europe. However, breast cancer mortality rates in most European countries are decreasing since 1990, as a consequence of the combined effects of earlier detection and treatment improvements. Breast conservative surgery (BCS) combined with radiotherapy has become the treatment of choice for the majority of women presenting with early breast cancer. With identical overall survival compared to mastectomy, BCS is usually linked to a better cosmetic outcome. In turn, this is an important endpoint for breast cancer treatment and is closely related to psychosocial recovery and quality of life (QOL). However, at least 30% of the cases have fair/poor aesthetic outcomes after BCS. Postoperative deformities after BCS and radiotherapy are difficult to treat and are a source of patient dissatisfaction. Thus, many women will live for many years with the potentially disfiguring aesthetic consequences of their treatment. When a woman faces a breast cancer diagnosis, and surgery is proposed, two options are available: breast conservative surgery or mastectomy. The decision as to which type of surgery to offer patients is subjective and based almost exclusively on the judgment and experience of the clinician. This clinical judgment takes into account several factors as tumor resection/breast volume ratio (TRBVR), tumor location or glandular density. Among these, TRBVR is considered the most important and presents a major impact on aesthetic outcome. However, there is a gap in scientific research regarding objective ways to access breast volume and tumor/breast volume ratio, a measurement that could ultimately help in the selection of the optimal BCS technique. Several methods have been described for breast volume assessment; however, these methods are not easy to perform routinely. A reliable and easy method to calculate breast volume and tumor/breast volume ratio has not yet been described. The BCCT.plan project aims to provide objective tools to personalize surgical planning. This tool will enable alternative surgical strategies to be explored and the consequences of the available options, with respect to the appearance of the breast under analysis. Using a combination of 3D reconstruction with images of the external shape of the patient, together with simple measures of the tumor (size and location), and glandular density, taken from radiological exams, we will develop a simple 3D model of the breast. Naturally, there is a need to create a database containing radiological examinations, annotated by radiology professionals, and breast surface information, to develop the methods for 3D model creation. Some of these methods relate to automatic algorithms that allow the information fusion of several medical image modalities and the identification and classification of suspicious malignant regions. In this sense, the database would assist in the method development and validation. The breast surface information will be acquired through aggregated photography and depth sensors (RGBD), adopting recent developments in low cost 3D technology. This modalities and surface combination will enable the development of a standardized and reproducible analysis tool which will be based on the aesthetic outcome evaluation of both 3-dimensional shape of the reconstructed breast and its volume after BCS, obtaining a prediction of the respective aesthetic result. This project will support surgical planning personalization, by assessing the risk of deformities after breast conserving surgery, for each patient’s TRBVR. It will serve as a decision support tool to communicate the available options to the patient and to enable standardized evaluation and a safe outcome of the procedure. The project will demonstrate the ability of virtual tools to empower patients and have a direct impact on their care. This will aid surgeon-patient communication concerning the type of breast surgery recommended, and will empower patients to take an active role in a shared decision making process. These tools will also enable the objective evaluation of the patient's aesthetic appearance after treatment.

The emergent clinical scenarios that are envisioned in this project will give rise to large amounts of data coming from different sources, including ubiquitous sensing, clinical data from electronic health records, and diverse devices being increasingly used for medical imaging and biomedical signal monitoring. In this context, the use computer-aided detection and diagnosis (CAD) tools will gain increased importance in order to be able to deal with the data processing and analysis in a tractable way, so that clinical research and practice can take advantage of the gathered information, giving rise to more effective workflows. Nowadays CAD tools aim to assist clinicians in the stages of clinical practice, either for screening, objective detection, measurement and characterization of relevant information from images and signals, or providing support for diagnosis, prognosis and decisions (e.g. treatment, surgery, ...) by easing the integration of the available information. Medical researchers are now building analytic tools that can turn raw data into actionable intelligence. Some are mining existing databases of medical treatments and outcomes to gather statistical evidence. Others are looking to the patient specific data to find cues about the state of the patient. Medical imaging, especially x-ray, ultrasonography and magnetic resonance imaging, are crucial in treatment and diagnosis, since effective decisions depend on correct diagnosis. Though medical/clinical judgment may be sufficient in the treatment of many conditions, the use of diagnostic imaging services is paramount in confirming, correctly assessing and documenting the course of the disease as well as in assessing response to treatment. Although research on Computer-Aided Diagnosis (CAD) and quantitative medical image analysis of lesions has been ongoing for decades, major gains must be made before such detection and analysis are universally accepted for use in the clinical arena. Currently, use of computers in the medical image interpretation process is mainly reserved as an aid to the radiologist, serving only to register or enhance images and give secondary interpretations. Although computer-aided detection (CADe) is widely used to assist radiologists with the reading, there is a need to improve performance of existing CADe algorithms, particularly with respect to sensitivity and the false-positive rates. In addition, the current acquisition modes of some medical imaging devices, like ultrasound, are very operator dependent, and their automatic analysis is still in its infancy. Apart from the improvement of the currently used tools, new features and challenges are envisioned for the future CADe applications. For example, novel ways to present CADe results to clinicians should be investigated to improve its potential use in the clinical decision, as well as with better explanatory capabilities of the diagnostics and prognostics. Furthermore, new screening technologies are emerging, and there is a growing need for CADe applications for these new modalities, as well as for incorporation of biomechanical modelling into the analysis chain to account for motion and correlation across multiple views and modalities (i.e., image fusion) - multimodal data integration for personalized health. One of the primary aims of this research line is not merely to follow trends or evaluate the latest imaging technology, but to develop new capabilities for future research and development as well as potential commercial clinical outcomes. We will face the problem of a faster evolution of modalities, with increased complexity, requiring a faster evolution and adaption of CAD tools. This requires research on innovative methodologies for CAD development, that allow to switch from ad hoc engineering approaches, driven by the automation of direct expert knowledge, to more automated approaches, driven by the intrinsic structure of data, knowledge discovery and expert supervision. Problems tackled will be generic in that appropriate outcomes can be applied universally to medical imaging (e.g. radiology) practice as a whole. Such research may be termed “Generic Enabling Research (GER)”. In order to tackle the specific objectives of this research line, we approach the problem from a number of different inter-related work packages, each with its own requirements and objectives.

PICTURE (Patient Information Combined for the Assessment of Specific Surgical Outcomes in Breast Cancer) is a FP7 funded by the European Commission with a budget of 2.2M EUR for 2013/15. Breast cancer is an increasingly treatable disease, and 10-year survival now exceeds 80%. When a woman faces a breast cancer diagnosis, and surgery is proposed, two options are available: breast-conserving surgery or mastectomy. Given the high breast cancer survival rate, many women will live for many years with the potentially disfiguring aesthetic consequences of their surgical and therapeutic treatment. The cosmetic outcome of surgery is a function of many factors including tumour size and location, the volume of the breast, its density, and the dose and distribution of radiotherapy. A good aesthetic outcome is an important endpoint for breast cancer treatment and is closely related to psychosocial recovery and quality of life. The PICTURE project aims to address these issues by providing objective tools, tailored to the individual patient, to predict the aesthetic outcome of breast conserving surgery. Using a combination of 3D photography and routinely acquired radiological images (i.e. mammography, ultrasound and MRI, when available), together with information about the tumour (size, location, shape etc.) we will develop techniques to biomechanically model the anatomy of the breast and the effect of surgical removal of cancerous tissue. This digital patient representation and associated predictive tools will enable alternative surgical strategies to be explored and the consequences of the available options, with respect to the appearance of the breast, to be visualised. This will aid communication with the patient of the type of breast surgery recommended by the surgeon, and will empower patients to take an active role in a shared decision making process. We will also develop tools to enable the patient's aesthetic appearance after treatment to be objectively evaluated. Current techniques use subjective methods, such as assessment by an expert panel, or computer analysis of 2-dimensional photography to estimate, for instance, breast asymmetry. By adopting recent developments in low cost 3D photography and depth sensing technology, we will develop a standardised, reproducible analysis tool which will base the aesthetic outcome evaluation on both the 3-dimensional shape of the reconstructed breast and its volume. This will establish standardised quality assurance and evaluation procedures, enabling institutions across Europe to be compared and factors that have a positive or negative impact on surgical outcome identified. In PICTURE, VCMI is leading the Workpackages of 'Aesthetic Quantification', 'Image Processing and Image Analysis', and 'Knowledge Management'.

SARA (Asset Management System for Road Networks), funded by the Portuguese Agency for Innovation (ADI), with a budget of 1.4M EUR for 2012/14.

The project SARA – System to Manage Assets in Road Networks is a joint research initiative that benefits from the expertise of two INESC TEC Units – the Information and Computer Graphics Systems Unit (USIG) and the Telecommunications and Multimedia Unit (UTM). The aim is to create an innovative solution to efficiently manage road network assets.

The project SARA will provide a system to represent, register and update assets in a spatio-temporal context. With this system, it will be possible to integrate and develop decision-support tools and methodologies, thus contributing to a significant evolution of current activities in this area.

The main objective is to provide the necessary instruments to road network managers that will help them implement the most suitable conservation strategies according to the available economic resources and predefined quality standards. All this is based on the knowledge of the evolution of the network’s elements throughout time.

As part of the project, UTM will be creating computational vision algorithms to detect and classify road networks and pavement pathologies based on the semi-automatic recognition of images. Additionally, the Unit will develop graphic tools for result visualisation and to correct these elements and pathologies.

USIG, on the other hand, will be responsible for spatio-temporal modelling and for developing tools to edit instances in geographical entities (assets) and the occurrence of pathologies. The Unit will also implement decision-support modules to help create intervention scenarios and to help define conservation strategies and policies for the road networks.

With a duration of two years, the SARA has recently applied to NSRF funding through company MonteAdriano – Engenharia e Construção, S.A, a group in the construction sector which participates in businesses related to road concession and parking lots.

3d BCT (3D Models for Aesthetic Evaluation and Prediction of Breast Cancer Interventions) project (PTDC/SAU-ENB/114951/2009), funded by the Portuguese Foundation for Science and Technology (FCT), with a budget of 69K EUR for 2011/14. In 3d BCT we investigate new methods to reconstruct 3D data from one or more uncalibrated views of the breast of the patient. We research a model fitting method, allowing the system to automatically fit a generic deformable model to patient specific three-dimensional (3D) breast surface measurements using a physically-based framework. This can be used to quantitatively and reliably assess the aesthetic outcome of breast reconstructive surgery. In addition this will also allow the surgeon to quantitatively analyze the degrees of various deformities and asymmetries in the shape of the breast. Finally, a model creation mode will allow a surgeon to interactively adjust the shape of the breast by varying key shape variables, analogous to the aesthetic and structural elements surgeons inherently vary manually during breast reconstruction. Our contribution will be a set of global deformations with very intuitive parameters that a physician can apply to a generic geometric primitive in order to model the breast of a patient for pre-operative planning purposes and for communicating and demonstrating this plan to the patient.

SINPATCO (Sistema Inteligente para Diagnóstico de Patologias da Coluna Vertebral) project, for 2010/11, under the Programme MOBILE CNPq - FEUP. Project of international scientific collaboration with the Universidade Federal do Ceará. The focus of the project is in the application of machine learning techniques, specifically neural networks and kernel methods, in Traumato-Orthopedics clinic.

INCT MACC (Instituto Nacional de Ciência e Tecnologia Medicina Assistida por Computação Científica), for 2009/12. Project led by Laboratório Nacional de Computação Científica - LNCC, Brazil and involving 33 institutions, designed to strengthen scientific and technological excellence on scientific computation for medicine (http://macc.lncc.br/contexto.php).

Semantic PACS (Picture Archiving and Communication System with Semantic Search Engine) project (project nº 003472), funded by the Portuguese Agency for Innovation (ADI), with a budget of 320K EUR for 2009/11. Semantic PACS aims to develop a software module to integrate with PACS that supports automatic, semantic based, description and search methods directly over medical images. In opposition with existent systems, this solution will make possible to generate on-the-fly diagnosis reports based on the similarity of medical images archived in the system.

NeTS (Next Generation Network Operations and Management) project (CMU-PT/RNQ/0029/2009), funded by the Portuguese Foundation for Science and Technology (FCT), with a budget of 390K EUR for 2011/13 under the Cooperation Agreement between Portugal and Carnegie Mellon University. The goal of NeTS is to develop a novel network operation and management framework that departs from conventional approaches through a cross-disciplinary research collaboration based on hierarchical network abstraction modeling, structure learning of probabilistic graphical models for machine learning, and wavelet and kernel-based signal processing technologies.

ASSIST is a contracted project that started in the end of 2012. It aims to study and develop algorithms and technologies to use video for the analysis of patterns in the movement of groups of people in limited spaces. The project aims to develop an accessible and flexible system for the national social economical context, but with high export potential.

The RobotVigil – Robot Vigilante (surveillance robot) - is a project funded by the Quadro de Referência Estratégico Nacional (QREN), 15/SI/2009, Proj. no 7905, proposed in the context of the development of new solutions supported by new generation networks. The project is composed of several companies, CleverHouse, Strong and SinePower, and two research entities, INESC Porto and Faculdade de Engenharia da Universidade do Porto. The project aims to research, develop, integrate and assess technologies that allow the development of solutions and services for security and remote surveillance, supported by new generation networks and new image processing and computer vision algorithms.

Living Usability Lab for Next Generation Networks is a Portuguese industry-academia collaborative R&D project funded by the Quadro de Referência Estratégico Nacional (QREN), 15/SI/2009, Proj. no 7900. The project is active in the field of live usability testing, focusing on the development of technologies and services to support healthy, productive and active citizens. The project adopts the principles of universal design and natural user interfaces (speech, gesture) making use of the benefits of next generation networks and distributed computing. Therefore, it will impact the general population, including the elderly and citizens with permanent or situational special needs. Website: http://www.livinglab.pt

OMR (Optical Recognition System for Handwritten Music Scores) project (PTDC/EIA/71225/2006), funded by the Portuguese Foundation for Science and Technology (FCT), with a budget of 50K EUR for 2007/10. In OMR we investigate and develop algorithms to recognise handwritten music scores to obtain a digital, easy-to-manage version of the original scores. We have developed a fully functional prototype system comprising the creation of a database of music scores and a web application mainly featuring: Addition of music scores to the system, performing their recognition and conversion to MusicXML in an integrated manner, allowing the user to confirm and correct the conversion results at the last stage of this process; Complete maintenance of a fully navigable music scores archive, including both the original version and the digital version obtained from the optical recognition; Browsing and searching the database, as well as the MusicXML contents; Visualization, downloading and edition of the selected music scores; Complete system management. Additional information is available at the project website: http://www.inescporto.pt/~jsc/projects/OMR/

BCCT (Advanced Objective Method for the Evaluation of the Aesthetical Result of Breast Interventions) project (PTDC/EIA/64914/2006), funded by the Portuguese Foundation for Science and Technology (FCT), with a budget of 95K EUR for 2007/10. In BCCT we investigate the development of a totally objective methodology for the evaluation of the overall aesthetic outcome of breast cancer treatments. The results of this project, in the form of a software system, BCCT.core (see http://medicalresearch.inescporto.pt/breastresearch/), is being used by many international groups in prospective studies: Nottingham Breast Institute, UK; Leiden University Medical Centre, The Netherlands; Cancer Care Center, Sydney, Australia; University of Heidelberg, Breast Center, Heidelberg, Germany; Medical University, Vienna, Austria; etc. This work has also been mentioned in an Editorial of the Breast Journal.

Project VISNET II - Networked Audio Visual Media Technologies is a network of excellence approved by the European Commission in the evaluation procedure for proposals submitted in the first call for the Information Society Technologies (IST) programme of the European Commission’s Sixth Framework Programme in the area of "Networked audiovisual systems and home platforms".