The introduction of machine learning in digital pathology has deeply impacted the field, especially with the advent of whole slide image (WSI) analysis. In this review, we tried to elucidate the role of machine learning algorithms in diagnostic precision, efficiency, and the reproducibility of the results. First, we discuss some of the most used tools, including QuPath, HistoQC, and HistomicsTK, and provide an updated overview of machine learning approaches and their application in pathology. Later, we report how these tools may simplify the automation of WSI analyses, also reducing manual workload and inter-observer variability. A novel aspect of this review is its focus on open-source tools, presented in a way that may help the adoption process for pathologists. Furthermore, we highlight the major benefits of these technologies, with the aim of making this review a practical guide for clinicians seeking to implement machine learning-based solutions in their specific workflows. Moreover, this review also emphasizes some crucial limitations related to data quality and the interpretability of the models, giving insight into future directions for research. Overall, this work tries to bridge the gap between the more recent technological progress in computer science and traditional clinical practice, supporting a broader, yet smooth, adoption of machine learning approaches in digital pathology.

With the advent of whole-slide imaging (WSI), a technology that can digitally scan whole slides in high resolution, pathology is undergoing a digital revolution. Detecting microsatellite instability (MSI) in colorectal cancer is crucial for proper treatment, as it identifies patients responsible for immunotherapy. Even though universal testing for MSI is recommended, particularly in patients affected by colorectal cancer (CRC), many patients remain untested, and they reside mainly in low-income countries. A critical need exists for accessible, low-cost tools to perform MSI pre-screening. Here, the potential predictive role of the most relevant artificial intelligence-driven models in predicting microsatellite instability directly from histology alone is discussed, focusing on CRC. The role of deep learning (DL) models in identifying the MSI status is here analyzed in the most relevant studies reporting the development of algorithms trained to this end. The most important performance and the most relevant deficiencies are discussed for every AI method. The models proposed for algorithm sharing among multiple research and clinical centers, including federal learning (FL) and swarm learning (SL), are reported. According to all the studies reported here, AI models are valuable tools for predicting MSI status on WSI alone in CRC. The use of digitized H&E-stained sections and a trained algorithm allow the extraction of relevant molecular information, such as MSI status, in a short time and at a low cost. The possible advantages related to introducing DL methods in routine surgical pathology are underlined here, and the acceleration of the digital transformation of pathology departments and services is recommended.

In several countries, thrombotic events after vaccination with ChAdOx1 nCoV-19 have led to heterologous messenger RNA (mRNA) boosting. We tested the antibody response to SARS-CoV-2 spike protein four weeks after heterologous priming with the ChAdOx1 (ChAd) vector vaccine followed by boosting with BNT162b2(ChAd/BNT), comparing data of homologous regimen (BNT/BNT, ChAd/ChAd) subjects positive for SARS-CoV-2 after the first dose of BNT162b2 (BNT1dose/CoV2) and convalescent COVID-19. Methods: healthy subjects naïve for SARS-CoV-2 infection were assessed for serum IgG anti-S-RBD response 21 days after priming (T1), 4 (T_FULL) and 15 (T_15W) weeks after booster dose. Results: The median IgG anti-S-RBD levels at T_FULL of Chad/BNT group were significantly higher than the BNT/BNT group and ChAd/ChAd. Those of BNT/BNT group were significantly higher than ChAd/ChAd. IgG anti-S-RBD of BNT1dose/CoV2 group were similar to BNT/BNT, ChAd/BNT and ChAd/Chad group. The levels among COVID-19 convalescents were significantly lower than ChAd/BNT, BNT/BNT, ChAd/Chad and BNT1dose/CoV2. The proportion of subjects reaching an anti-S-RBD titer >75 AU/mL, correlated with high neutralizing titer, was 94% in ChAd/BNT and BNT/BNT, 60% in BNT1dose/CoV2, 25% in ChAd/ChAd and 4.2% in convalescents. At T_15W the titer of ChAd/BNT was still significantly higher than other vaccine schedules, while the anti-S-RBD decline was reduced for ChAd/ChAd and similar for other combinations. Conclusion: Our data highlight the magnitude of IgG anti-S-RBD response in ChAd/BNT dosing, supporting the current national guidelines for heterologous boosting

Severe acute respiratory syndrome-related coronavirus 2 (SARS-CoV-2), the etiological agent of COVID-19, has caused over 460 million cases of infection and over 6 million deaths worldwide. The pandemic has called for science, technology, and innovation to provide solutions and, due to an incredible scientific and financial global effort, several prophylactic and therapeutic apparatuses such as monoclonal antibodies and vaccines were developed in less than one year to address this emergency. After SARS-CoV-2 infection, serum neutralizing antibodies are produced by B cells and studies on virus-neutralizing antibodies’ kinetics are pivotal. The process of protective immunity and the duration of this kind of protection against COVID-19 remain to be clarified. We tested 136 sera from 3 groups of individuals, some of them providing multiple sequential sera (1—healthy, no previous CoV2-infected, vaccinated; 2—healthy, previous CoV2 infected, vaccinated; 3—healed, previous CoV2-infected, not vaccinated) to assess the kinetics of antibodies (Abs) neutralizing activity. We found that SARS-CoV-2 infection elicits moderate neutralizing antibody activity in most individuals; neither age nor gender appear to have any influence on Abs responses. The BNT162b2 vaccine, when administered in two doses, induces high antibodies titre endowed with potent neutralizing activity against bare SARS-CoV-2 in in vitro neutralizing assay. The residual neutralization capability and the kinetic of waning immunity were also evaluated over 9 months after the second dose in a reference group of subjects. Neutralization titre showed a decline in all subjects and the median level of S-protein IgG, over 270 days after the second vaccination dose, was below 10 AU/mL in 53% of serum tested.

ER-low breast cancer (1–9% ER expression) represents a biologically and clinically distinct entity at the interface between ER-positive and ER-negative disease. Although traditionally managed as hormone receptor-positive, mounting evidence indicates that ER-low tumors share molecular signatures, aggressive behavior, and chemotherapeutic responsiveness with triple-negative breast cancer. Accurate ER assessment is hindered by methodological variability and interpretative challenges, leading to potential misclassification and suboptimal treatment choices. While the benefit of endocrine therapy remains uncertain, ER-low tumors consistently show sensitivity to chemotherapy and promising responses to neoadjuvant chemo-immunotherapy, paralleling outcomes observed in triple-negative breast cancer cohorts. Emerging artificial intelligence tools, including digital pathology and multimodal deep learning, may enhance ER quantification, reduce observer variability, and enable more precise patient stratification. This review synthesizes current pathological and clinical insights into ER-low breast cancer and highlights evolving therapeutic strategies, with a forward-looking perspective on AI-driven approaches to optimize personalized treatment for this challenging subtype.

Background: The aim was to outline a methodology to monitor the impact of vaccinations in different countries comparing in two different time within countries and between countries the frequency of new cases and Covid-19 related deaths and the percentage of vaccinations conducted. Design and methods: The 25 countries with the largest increase in SARS-CoV-2 cases on 8 August 2021 were evaluated. In each nation was calculated the proportion of Covid-19 deaths divided per new cases x 100 and the proportion of new cases per 1.000 inhabitant on 10 January 2021 (before vaccinations’ distribution) and 8 August 2021 (when large percentage of the population had been vaccinated in many countries). Results: The study shows that in the countries with the highest number of cases as of 8 August 2021, the proportion of vaccinations carried out in the population correlates negatively with both the proportion between Covid-19 dead people x100 infected people and with the rate of new cases. However, the proportion of vaccinations does not correlate with the differences in the two same indicators considered in the weeks observed, thus additional factors seem to play an important role. Conclusions: This work indicates that mass vaccination is associated with a lower spread of the pandemic and, to greater extent, with a lowering of mortality in infected people.