The Prostate Imaging Reporting and Data System (PI-RADS) classification is based on a scale of values from 1 to 5. The value is assigned according to the probability that a finding is a malignant tumor (prostate carcinoma) and is calculated by evaluating the signal behavior in morphological, diffusion, and post-contrastographic sequences. A PI-RADS score of 3 is recognized as the equivocal likelihood of clinically significant prostate cancer, making its diagnosis very challenging. While PI-RADS values of 4 and 5 make biopsy necessary, it is very hard to establish whether to perform a biopsy or not in patients with a PI-RADS score 3. In recent years, machine learning algorithms have been proposed for a wide range of applications in medical fields, thanks to their ability to extract hidden information and to learn from a set of data without previous specific programming. In this paper, we evaluate machine learning approaches in detecting prostate cancer in patients with PI-RADS score 3 lesions via considering clinical-radiological characteristics. A total of 109 patients were included in this study. We collected data on body mass index (BMI), location of suspicious PI-RADS 3 lesions, serum prostate-specific antigen (PSA) level, prostate volume, PSA density, and histopathology results. The implemented classifiers exploit a patient’s clinical and radiological information to generate a probability of malignancy that could help the physicians in diagnostic decisions, including the need for a biopsy.

Glioblastoma Multiforme (GBM) is considered one of the most aggressive malignant tumors, characterized by a tremendously low survival rate. Despite alkylating chemotherapy being typically adopted to fight this tumor, it is known that O(6)-methylguanine-DNA methyltransferase (MGMT) enzyme repair abilities can antagonize the cytotoxic effects of alkylating agents, strongly limiting tumor cell destruction. However, it has been observed that MGMT promoter regions may be subject to methylation, a biological process preventing MGMT enzymes from removing the alkyl agents. As a consequence, the presence of the methylation process in GBM patients can be considered a predictive biomarker of response to therapy and a prognosis factor. Unfortunately, identifying signs of methylation is a non-trivial matter, often requiring expensive, time-consuming, and invasive procedures. In this work, we propose to face MGMT promoter methylation identification analyzing Magnetic Resonance Imaging (MRI) data using a Deep Learning (DL) based approach. In particular, we propose a Convolutional Neural Network (CNN) operating on suspicious regions on the FLAIR series, pre-selected through an unsupervised Knowledge-Based filter leveraging both FLAIR and T1-weighted series. The experiments, run on two different publicly available datasets, show that the proposed approach can obtain results comparable to (and in some cases better than) the considered competitor approach while consisting of less than $0.29\%$ of its parameters. Finally, we perform an eXplainable AI (XAI) analysis to take a little step further toward the clinical usability of a DL-based approach for MGMT promoter detection in brain MRI.

Background: The axillary lymph node status (ALNS) is one of the most important prognostic factors in breast cancer (BC) patients, and it is currently evaluated by invasive procedures. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), highlights the physiological and morphological characteristics of primary tumor tissue. Deep learning approaches (DL), such as convolutional neural networks (CNNs), are able to autonomously learn the set of features directly from images for a specific task. Materials and Methods: A total of 155 malignant BC lesions evaluated via DCE-MRI were included in the study. For each patient’s clinical data, the tumor histological and MRI characteristics and axillary lymph node status (ALNS) were assessed. LNS was considered to be the final label and dichotomized (LN+ (27 patients) vs. LN− (128 patients)). Based on the concept that peritumoral tissue contains valuable information about tumor aggressiveness, in this work, we analyze the contributions of six different tumor bounding options to predict the LNS using a CNN. These bounding boxes include a single fixed-size box (SFB), a single variable-size box (SVB), a single isotropic-size box (SIB), a single lesion variable-size box (SLVB), a single lesion isotropic-size box (SLIB), and a two-dimensional slice (2DS) option. According to the characteristics of the volumes considered as inputs, three different CNNs were investigated: the SFB-NET (for the SFB), the VB-NET (for the SVB, SIB, SLVB, and SLIB), and the 2DS-NET (for the 2DS). All the experiments were run in 10-fold cross-validation. The performance of each CNN was evaluated in terms of accuracy, sensitivity, specificity, the area under the ROC curve (AUC), and Cohen’s kappa coefficient (K). Results: The best accuracy and AUC are obtained by the 2DS-NET (78.63% and 77.86%, respectively). The 2DS-NET also showed the highest specificity, whilst the highest sensibility was attained by the VB-NET based on the SVB and SIB as bounding options. Conclusion: We have demonstrated that a selective inclusion of the DCE-MRI’s peritumoral tissue increases accuracy in the lymph node status prediction in BC patients using CNNs as a DL approach.

Bullying and cyberbullying are harmful social phenomena that involve the intentional, repeated use of power to intimidate or harm others. The ramifications of these actions are felt not just at the individual level but also pervasively throughout society, necessitating immediate attention and practical solutions. The BullyBuster project pioneers a multi-disciplinary approach, integrating artificial intelligence (AI) techniques with psychological models to comprehensively understand and combat these issues. In particular, employing AI in the project allows the automatic identification of potentially harmful content by analyzing linguistic patterns and behaviors in various data sources, including photos and videos. This timely detection enables alerts to relevant authorities or moderators, allowing for rapid interventions and potential harm mitigation. This paper, a culmination of previous research and advancements, details the potential for significantly enhancing cyberbullying detection and prevention by focusing on the system’s design and the novel application of AI classifiers within an integrated framework. Our primary aim is to evaluate the feasibility and applicability of such a framework in a real-world application context. The proposed approach is shown to tackle the pervasive issue of cyberbullying effectively.

In the field of veterinary medicine, the detection of parasite eggs in the fecal samples of livestock animals represents one of the most challenging tasks, since their spread and diffusion may lead to severe clinical disease. Nowadays, the scanning procedure is typically performed by physicians with professional microscopes and requires a significant amount of time, domain knowledge, and resources. The Kubic FLOTAC Microscope (KFM) is a compact, low-cost, portable digital microscope that can autonomously analyze fecal specimens for parasites and hosts in both field and laboratory settings. It has been shown to acquire images that are comparable to those obtained with traditional optical microscopes, and it can complete the scanning and imaging process in just a few minutes, freeing up the operator's time for other tasks. To promote research in this area, the first AI-KFM challenge was organized, which focused on the detection of gastrointestinal nematodes (GINs) in cattle using RGB images. The challenge aimed to provide a standardized experimental protocol with a large number of samples collected in a well-known environment and a set of scores for the approaches submitted by the competitors. This paper describes the process of generating and structuring the challenge dataset and the approaches submitted by the competitors, as well as the lessons learned throughout this journey.