Abstract
Industry 4.0 is changing the manufacturing paradigms across industries. However, many repetitive processes still rely heavily on human workers, as in the case of the automotive industry, where the final quality inspection of assembled vehicles is still performed using a paper-based conformity list. We instead propose a hybrid solution where a deep learning-based hierarchical autonomous detection system identifies the non-conforming parts and informs the operator via a wearable device, trained exclusively with simulated data. This scalable and cost-effective system achieved a 65.7% accuracy score, which, considering the experimental nature of this work, further confirms the potential of this approach.

Abstract
With the increasing adoption of teledermatology, there is a need to improve the automatic organization of medical records, being dermatological image modality a key filter in this process. Although there has been considerable effort in the classification of medical imaging modalities, this has not been in the field of dermatology. Moreover, as various devices are used in teledermatological consultations, image acquisition conditions may differ. In this work, two models (VGG-16 and MobileNetV2) were used to classify dermatological images from the Portuguese National Health System according to their modality. Afterwards, four incremental learning strategies were applied to these models, namely naive, elastic weight consolidation, averaged gradient episodic memory, and experience replay, enabling their adaptation to new conditions while preserving previously acquired knowledge. The evaluation considered catastrophic forgetting, accuracy, and computational cost. The MobileNetV2 trained with the experience replay strategy, with 500 images in memory, achieved a global accuracy of 86.04% with only 0.0344 of forgetting, which is 6.98% less than the second-best strategy. Regarding efficiency, this strategy took 56 s per epoch longer than the baseline and required, on average, 4554 megabytes of RAM during training. Promising results were achieved, proving the effectiveness of the proposed approach.

Abstract
Considerable amounts of data are required for a deep learning model to generalize to unseen cases successfully. Furthermore, such data is often manually labeled, making its annotation process costly and time-consuming. We propose using unlabeled real-world data in conjunction with automatically labeled synthetic data, obtained from simulators, to surpass the increasing need for annotated data. By obtaining real counterparts of simulated samples using CycleGAN and subsequently performing fine-tuning with such samples, we manage to improve a vehicle part's detection system performance by 2.5%, compared to the baseline exclusively trained on simulated images. We explore adding a semantic consistency loss to CycleGAN by re-utilizing previous work's trained networks to regularize the conversion process. Moreover, the addition of a post-processing step, which we denominate global NMS, highlights our approach's effectiveness by better utilizing our detection model's predictions and ultimately improving the system's performance by 14.7%.

Abstract
The high incidence of cervical cancer in women has prompted the research of automatic screening methods. This work focuses on two of the steps present in such systems, more precisely, the identification of cervical lesions and their respective classification. The development of automatic methods for these tasks is associated with some shortcomings, such as acquiring sufficient and representative clinical data. These limitations are addressed through a hybrid pipeline based on a deep learning model (RetinaNet) for the detection of abnormal regions, combined with random forest and SVM classifiers for their categorization, and complemented by the use of domain knowledge in its design. Additionally, the nuclei in each detected region are segmented, providing a set of nuclei-specific features whose impact on the classification result is also studied. Each module is individually assessed in addition to the complete system, with the latter achieving a precision, recall and F1 score of 0.04, 0.20 and 0.07, respectively. Despite the low precision, the system demonstrates potential as an analysis support tool with the capability of increasing the overall sensitivity of the human examination process.

Abstract
Lung cancer is still the leading cause of cancer death in the world. For this reason, novel approaches for early and more accurate diagnosis are needed. Computer-aided decision (CAD) can be an interesting option for a noninvasive tumour characterisation based on thoracic computed tomography (CT) image analysis. Until now, radiomics have been focused on tumour features analysis, and have not considered the information on other lung structures that can have relevant features for tumour genotype classification, especially for epidermal growth factor receptor (EGFR), which is the mutation with the most successful targeted therapies. With this perspective paper, we aim to explore a comprehensive analysis of the need to combine the information from tumours with other lung structures for the next generation of CADs, which could create a high impact on targeted therapies and personalised medicine. The forthcoming artificial intelligence (AI)-based approaches for lung cancer assessment should be able to make a holistic analysis, capturing information from pathological processes involved in cancer development. The powerful and interpretable AI models allow us to identify novel biomarkers of cancer development, contributing to new insights about the pathological processes, and making a more accurate diagnosis to help in the treatment plan selection.

Abstract
Lower limb amputation is a condition affecting millions of people worldwide. Patients are often prescribed with lower limb prostheses to aid their mobility, but these prostheses require frequent adjustments through an iterative and manual process, which heavily depends on patient feedback and on the prosthetist's experience. New computer-aided design and manufacturing technologies have been emerging as a way to improve the fitting process by creating virtual socket models. Statistical Shape modelling was used to create 3D models of transtibial (TT) and transfemoral (TF) sockets. Their generalization errors were, respectively, 6.8 +/- 1.8 mm and 10.5 +/- 1.6 mm, while specificity errors were 9.7 +/- 0.6 mm and 9.8 +/- 0.2 mm. In both models, a visual analysis showed that biomechanically meaningful features were captured: the largest variations found for both types were in the length of the residual limb and in the perimeter variation along the limb. The results obtained proved that statistical shape modelling methods can be applied to TF and TT sockets, with several potential applications in the orthoprosthetic field: generation of new plausible shapes and on-demand socket design adjustments.