Abstract
Breast cancer is one of the most common malignanciesaffecting women worldwide. However, despite its incidence trends have increased, the mortality rate has significantly decreased. The primary concern in any cancer treatment is the oncological outcome but, in the case of breast cancer, the surgery aesthetic result has become an important quality indicator for breast cancer patients. In this sense, an adequate surgical planning and prediction tool would empower the patient regarding the treatment decision process, enabling a better communication between the surgeon and the patient and a better understanding of the impact of each surgical option. To develop such tool, it is necessary to create complete 3D model of the breast, integrating both inner and outer breast data. In this review, we thoroughly explore and review the major existing works that address, directly or not, the technical challenges involved in the development of a 3D software planning tool in the field of breast conserving surgery. © 2018 by Begell House, Inc.

Abstract
Lung cancer is one of the most common causes of death in the world. The early detection of lung nodules allows an appropriate follow-up, timely treatment and potentially can avoid greater damage in the patient health. The texture is one of the nodule characteristics that is correlated with the malignancy. We developed convolutional neural network architectures to classify automatically the texture of nodules into the non-solid, part-solid and solid classes. The different architectures were tested to determine if the context, the number of slices considered as input and the relation between slices influence on the texture classification performance. The architecture that obtained better performance took into account different scales, different rotations and the context of the nodule, obtaining an accuracy of 0.833 ± 0.041. © Springer Nature Switzerland AG 2019.

Abstract

Abstract
Performance assessment is critical in today's competitive environments, where companies need to establish trade-offs between key competitive dimensions. The complexity of these environments calls for new approaches to performance assessment. Thus, in this work, we propose a novel conceptual framework for performance assessment in manufacturing environments combining different production strategies. Focus is laid on MTO/ETO combined environments and a three-stage problem analysis is considered. Firstly, a hybrid SD-DES-ABS model approach addresses the needs of a system that handles different types of orders, processes and workforce allocation requirements; secondly, the model results for different demand scenarios are assessed using a one-way ANOVA analysis followed by a Tukey - Kramer's test, with pairwise comparisons for assessment of significant performance variations under different system operating policies. A full factorial Design of Experiments (DOE) analysis follows, for determining the relevant process parameters influencing the system performance. As an example of application of the proposed framework, we consider the case of an advanced manufacturing company, whose manufacturing environment encompasses combined MTO/ETO production strategies.

Abstract
The visually impaired must face several well-known difficulties on their daily life. The use of technology in assistive systems can greatly improve their lives by helping with navigation and orientation, for which several approaches and technologies have been proposed. Lately, it has been introduced powerful online image processing services, based on machine learning and deep learning, promising truly cognitive assessment capacities. Google and Microsoft are two of these main players. In this work we built a device to be used by the blind in order to test the usage of the Google and Microsoft services to assist the blind. The online services were tested by researchers in a laboratory environment and by blind users on a large meeting room, familiar to them. This work reports on our findings regarding the online services effectiveness, the user interface and system latency. © Springer International Publishing AG, part of Springer Nature 2018.

Abstract
Purpose: Consumption of game meat is growing when compared to other meats. It is susceptible to adulteration because of its cost and availability. Spectroscopy may lead to rapid methodologies for detecting adulteration. The purpose of this study is to detect the adulteration of wild fallow deer (Dama dama) meat with domestic goat (G) (Capra aegagrus hircus) meat, for samples stored for different periods of time using Fourier transform infrared (FTIR) spectroscopy coupled with chemometric. Design/methodology/approach: Meat was cut and mixed in different percentages, transformed into mini-burgers and stored at 3°C from 12 to 432 h and periodically examined for FTIR, pH and microbial analysis. Principal component analysis (PCA) and partial least squares discriminant analysis (PLS-DA) were applied to detect adulteration. Findings: The PCA model, applied to the spectral region from 1,138 to 1,180, 1,314 to 1,477, 1,535 to 1,556 and from 1,728 to 1,759 cm^-1, describes the adulteration using four principal components which explained 95 per cent of variance. For the levels of Adulteration A1 (pure meat), A2 (25 and 50 %w/wG) and A3 (75 and 100 %w/wG) for an external set of samples, the correlation coefficients for prediction were 0.979, 0.941 and 0.971, and the room mean square error were 8.58, 12.46 and 9.47 per cent, respectively. Originality/value: The PLS-DA model predicted the adulteration for an external set of samples with high accuracy. The proposed method has the advantage of allowing rapid results, despite the storage time of the adulterated meat. It was shown that FTIR combined with chemometrics can be used to establish a methodology for the identification of adulteration of game meat, not only for fresh meat but also for meat stored for different periods of time.