Abstract
Inherited retinal diseases (IRDs) are rare and genetically diverse disorders that cause progressive vision loss and affect 1 in 3000 individuals worldwide. Their rarity and genetic variability pose a challenge for deep learning models due to the limited amount of data. Generative models offer a promising solution by creating synthetic data to improve training datasets. This study carried out a systematic literature review to investigate the use of generative models to augment data in IRDs and assess their impact on the performance of classifiers for these diseases. Following PRISMA 2020 guidelines, searches in four databases identified 32 relevant studies, 2 focused on IRD and the rest on other retinal diseases. The results indicate that generative models effectively augment small datasets. Among the techniques identified, Deep Convolutional Adversarial Generative Networks (DCGAN) and the Style-Based Generator Architecture of Generative Adversarial Networks 2 (StyleGAN2) were the most widely used. These architectures generated highly realistic and diverse synthetic data, often indistinguishable from real data, even for experts. The results highlight the need for more research into data generation in IRD to develop robust diagnostic tools and improve genetic studies by creating more comprehensive genetic repositories.

Abstract
In modern industrial environments, ensuring the quality of manufactured components is critical, particularly when dealing with reflective surfaces that hinder conventional inspection techniques. Although deep learning-based methods offer robust solutions for visual defect detection, their performance often hinges on the availability of substantial annotated datasets. In industrial scenarios, labeling such datasets is costly and time-consuming. This study investigates applying sample selection techniques to reduce annotation efforts for porosity detection on machined aluminium parts. Several selection strategies were evaluated using a real-world dataset composed of high-resolution images, including uncertainty, diversity, random-based criteria, and hybrid combinations. The best-performing strategy, which combined entropy-based uncertainty, spatial diversity, and random-based, achieved an F1-score of 86.70% and a recall of 82.99% after ten iterations using only 2,400 annotated images, corresponding to 66.67% of the active learning pool. Although the fully supervised model achieved an F1-score of 88.84% and a recall of 86.30%, the proposed approach proved a competitive alternative. These results demonstrate that selective data annotation can significantly reduce labeling effort while maintaining reliable performance in defect detection, even under the challenging conditions posed by reflective industrial parts.

Abstract
Precision Agriculture (PA) has emerged as an approach to optimize production, comprise different technology and principles focusing on how to improve agricultural production. Currently, one of the main foundations of PA is the use of artificial intelligence, through deep learning (DL) algorithms. By processing large volumes of complex data, DL enhances decision-making and boosts farming efficiency. However, these methods are hungry for annotated data, which contrasts with the scarce availability of annotated agricultural data and the costs of annotation. Self-supervised learning (SSL) has emerged as a solution to tackle the lack of annotated agricultural data. This study presents a review of the application of SSL methods to computer vision tasks in the agricultural context. The aim is to create a starting point for professionals and scientists who intend to apply these methods using agricultural data. The results of 33 studies found in the literature are discussed, highlighting their pros and cons. In most of the studies, SSL outperformed its supervised counterpart, using datasets from 4000 to 60,000 samples. Potential directions for improving future research are suggested.

Abstract
The medical imaging field contends with limited data for training deep learning (DL) models. Our study evaluated traditional data augmentation (DA) and Generative Adversarial Networks (GANs) in enhancing DL models for identifying stomach precancerous lesions. Classic DA consistently outperformed GAN-based methods with ResNet50 (0.94 vs 0.93 accuracy) and ViT (0.85 vs 0.84 accuracy) models achieving higher accuracy and other performance metrics with DA compared to GANs. Despite this, GAN augmentation showed significant improvements when compared to train with the original dataset, highlighting its role in diversifying datasets and aiding generalization across different medical imaging datasets. Combining both augmentation techniques can enhance model robustness and generalisation capabilities in DL applications for medical diagnostics, leveraging DA's consistency and GANs' diversity.

Abstract
Inherited retinal diseases (IRDs) are genetic disorders affecting photoreceptors and the retinal pigment epithelium, leading to progressive vision loss. Retinitis pigmentosa (RP), the most common IRD, manifests as night blindness, peripheral vision loss, and eventually central vision decline. RP is genetically diverse and can be categorized into non-syndromic and syndromic. Advanced imaging technologies such as fundus autofluorescence (FAF) and spectral-domain optical coherence tomography (SD-OCT) facilitate diagnosing and managing these conditions. The integration of artificial intelligence in analyzing retinal images has shown promise in identifying genes associated with RP. This study used a dataset from Portuguese public hospitals, comprising 2798 FAF images labeled for syndromic and non-syndromic RP across 66 genes. Three pre-trained models, Inception-v3, ResNet-50, and VGG-19, were used to classify these images, obtaining an accuracy of over 80% in the training data and 54%, 56%, and 54% in the test data for all models. Data preprocessing included class balancing and boosting to address variability in gene representation. Model performance was evaluated using some main metrics. The findings demonstrate the effectiveness of deep learning in automatically classifying retinal images for different RP-associated genes, marking a significant advancement in the diagnostic capabilities of artificial intelligence and advanced imaging techniques in IRD.

Abstract
Histopathological analysis is an essential exam for detecting various types of cancer. The process is traditionally time-consuming and laborious. Taking advantage of deep learning models, assisting the pathologist in the diagnosis process is possible. In this work, a study was carried out based on the DenseNet neural network. It consisted of changing its architecture through combinations of Transformer and MBConv blocks to investigate its impact on classifying histopathological images of penile cancer. Due to the limited number of samples in this dataset, pre-training is performed on another larger lung and colon cancer histopathological image dataset. Various combinations of these architectural components were systematically evaluated to compare their performance. The results indicate significant improvements in feature representation, demonstrating the effectiveness of these combined elements resulting in an F1-Score of up to 95.78%. Its diagnostic performance confirms the importance of deep learning techniques in men's health.