Search

Cardiovascular diseases, which include all heart and circulatory diseases, are among the major death-causing diseases in women. Cardiovascular diseases are not subject to screening programs, and early detection can reduce their mortal effect. Recent studies have shown a strong association between severe Breast Arterial Calcifications and cardiovascular diseases. The aim of this study is to use the screening programs for breast cancer to detect the high severity of BACs and therefore to obtain indirect information about coronary diseases. Previous attempts in the literature on the detection of BACs from digital mammograms still need improvements to be used as a standalone technique. In this study, a dataset of mammograms with BACs is divided into 4 grades of severity, and this study aims to improve their classification through a transfer learning approach to overcome the need for a large dataset of training. The performances achieved in this study by using pre-trained models to detect four Breast Arterial Calcifications severity grades reached an accuracy of 94% during testing. Therefore, it is possible to benefit from the advantage of Deep Learning models to define a rapid marker of BACs along Brest Cancer screening programs.

Socially assistive robots have the potential to help keep people with dementia cognitively active and entertained. This is important for their wellbeing. We explored staff perceptions of the acceptability of a new humanoid robot, Stevie, in an adult day care center for people with dementia. Stevie was deployed over 2 weeks in the day center to entertain 40 guests with dementia with three activities: (i) musical bingo, (ii) quizzes, and (iii) meet and greet. Nine staff members were asked what went well, whether the robot operated as expected, experiences of any technical issues, and the extent to which it hindered or aided their duties. Staff also rated guest engagement, guest enjoyment, and whether they were able to spend more time with guests. The sessions were successfully delivered. Staff reported that Stevie operated as expected, guest engagement with the robot was high, interactions with the robot were natural and the robot’s novelty helped engagement. Use of the robot gave staff more time to attend to guests’ needs. Suggested improvements included improvements to the robot’s voice and adding a pause function during activities. With greater autonomy and/or extended use of its telepresence functionality, use of Stevie could become cost effective in such settings.

The use of flexible and autonomous robotics systems is the solution for the automation task of the production and intra-logistics environments. This dynamic context requires the robot to be aware of its surroundings through the whole task, also after accomplishing the gripping action. We present an anomaly detection approach based on unsupervised learning and reconstruction fidelity of image data. We design our method to enhance the dynamic environment perception of robotics systems and apply it in a palletizing robot, in order to perceive and detect changes to its surrounding and process after the gripping step. Our proposed approach achieves the performance targeted by the considered industrial requirements.

Cloud computing, supported by advancements in virtualisation and distributed computing, became the default options for implementing the IT infrastructure of organisations. Medical data and in particular medical images have increasing storage space and remote access requirements. Cloud computing satisfies these requirements but unclear safeguards on data security can expose sensitive data to possible attacks. Furthermore, recent changes in legislation imposed additional security constraints in technology to ensure the privacy of individuals and the integrity of data when stored in the cloud. In contrast with this trend, current data security methods, based on encryption, create an additional overhead to the performance, and often they are not allowed in public cloud servers. Hence, this paper proposes a mechanism that combines data fragmentation to protect medical images on the public cloud servers, and a NoSQL database to secure an efficient organisation of such data. Results of this paper indicate that the latency of the proposed method is significantly lower if compared with AES, one of the most adopted data encryption mechanisms. Therefore, the proposed method is an optimal trade-off in environments with low latency requirements or limited resources.