Cerebral microbleeds (CMBs) are gaining increasing interest due to their importance in diagnosing cerebral small vessel diseases. However, manual inspection of CMBs is time-consuming and prone to human error. Existing automated or semi-automated solutions still have insufficient detection sensitivity and specificity. Furthermore, they frequently use more than one magnetic resonance imaging modality, but these are not always available. The majority of AI-based solutions use either numeric or image data, which may not provide sufficient information about the true nature of CMBs. This paper proposes a deep neural network with multi-type input data for automated CMB detection (CMB-HUNT) using only susceptibility-weighted imaging data (SWI). Combination of SWIs and radiomic-type numerical features allowed us to identify CMBs with high accuracy without the need for additional imaging modalities or complex predictive models. Two independent datasets were used: one with 304 patients (39 with CMBs) for training and internal system validation and one with 61 patients (21 with CMBs) for external validation. For the hold-out testing dataset, CMB-HUNT reached a sensitivity of 90.0%. As results of testing showed, CMB-HUNT outperforms existing methods in terms of the number of FPs per case, which is the lowest reported thus far (0.54 FPs/patient). The proposed system was successfully applied to the independent validation set, reaching a sensitivity of 91.5% with 1.9 false positives per patient and proving its generalization potential. The results were comparable to previous studies. Our research confirms the usefulness of deep learning solutions for CMB detection based only on one MRI modality.

Tumor-infiltrating lymphocytes (TILs), identified on HE-stained histopathological images in the cancer area, are indicators of the adaptive immune response against cancers and play a major role in personalized cancer immunotherapy. Recent works indicate that the spatial organization of TILs may be prognostic of disease-specific survival and recurrence. However, there are a limited number of methods that were proposed and tested in analyses of the spatial structure of TILs. In this work, we evaluated 14 different spatial measures, including the one developed for other omics data, on 10,532 TIL maps from 23 cancer types in terms of reproducibility, uniqueness, and impact on patient survival. For each spatial measure, 16 different scenarios for the definition of prognostic factor were tested. We found no difference in survival prediction when TIL maps were stored as binary images or continuous TIL probability scores. When spatial measures were discretized into a low and high category, a higher correlation with survival was observed. Three measures with the highest cancer prognosis capability were spatial autocorrelation, GLCM M1, and closeness centrality. Most of the tested measures could be further tuned to increase prediction performance.

Identification of Parkinson’s disease (PD) patients at risk for development of dementia is crucial for early intervention. However, diagnosing dementia in PD patients requires the use of a time-consuming and complex battery of psychological tests performed by an experienced psychologist. The study aims to prove the usefulness of convolutional neural networks for the identification of brain areas related to the progress of cognitive impairment by using standard magnetic resonance imaging (MRI) sequences. T1 & T2 sequences of 18 patients were used in the pilot study. Activation maps were generated, and the brain regions most involved in the classification process were identified, showing areas potentially significant in the diagnosis of cognitive impairment severity. The cerebellum was proven significant for distinguishing the above-mentioned classes in relative cerebellum volume (ANOVA p value = 0.0038 with large effect size $$\eta ^{2}$$η 2 = 0.5254) and folding (p value = 0.0031, $$\eta ^{2}$$η 2 = 0.5357), which is consistent with reports by other authors. Our analysis demonstrates that convolutional neural networks combined with a proper image preprocessing pipeline could be used for feature extraction in MRI sequences and can successfully support the identification of disease-specific abnormalities of the brain image.

Background/Objectives: The accurate localization of interfascial planes is critical for effective regional anesthesia, yet current techniques relying on ultrasound guidance can be challenging, especially in obese or pediatric patients. Previous cadaveric and clinical studies have suggested that injection pressure varies depending on needle placement relative to fascial and neural structures. This pilot study aimed to evaluate whether the continuous monitoring of injection pressure can reliably differentiate interfascial spaces from surrounding anatomical structures in a porcine tissue model. Methods: A custom-built pressure monitoring system was used to continuously measure saline injection pressure during regional block procedures performed on porcine thighs. Injections were guided by ultrasound and conducted using an infusion pump. Needle positions were classified as intramuscular, resting on fascia, or interfascial. Statistical comparisons of pressure levels, variability, and temporal trends were conducted using Wilcoxon signed-rank tests and regression analysis. Results: Mean intramuscular pressure was significantly higher than the mean interfascial pressure (p < 1 × 10⁻¹³). Interfascial injections demonstrated lower pressure variability (p = 2.1 × 10⁻⁴) and an increasing trend in pressure over time (p = 2.1 × 10⁻⁴), whereas intramuscular injections exhibited a decreasing pressure trend (p = 3.15 × 10⁻³). Conclusions: Continuous pressure monitoring effectively distinguishes interfascial from intramuscular and fascial penetration phases during regional anesthesia. The method demonstrates potential as a real-time, objective tool for enhancing needle guidance and improving the safety and accuracy of interfascial plane blocks. Further cadaveric and clinical studies are warranted to validate these findings.

Introduction: Reliable identification regarding interfascial spaces proves essential to achieve successful nerve block analgesia; however, ultrasound guided approaches are recognized as challenging, particularly in obese or pediatric patients. In prior cadaveric and clinical investigations, multiple approaches were evaluated to identify methods for measuring injection pressures as a function of needle position relative to fascia. Our previous study proposed simpler method of finding interfascial spaces with the needle tip. In this study, it was examined whether needle tip design influences injection pressures during regional anesthesia procedures, via an ex vivo pig specimen setup. Methods: A bespoke apparatus for tracking injection pressure was deployed to enable continuous measurement of intraluminal pressure generated while delivering saline throughout ultrasound guided peripheral nerve block needles conducted within pig thigh specimens. Delivery was performed using an infusion pump. Three types of needles of the same manufacturer (Pajunk) and same diameter (22G) but with different tips (Facet, Facet S and Sprotte) were used to measure injection pressures during penetration through tissues until interfascial plane hydrodissection was created. Statistical analyses were performed to compare pressure levels, variability, and temporal pressure trends. Results: Ninety ultrasound guided injections in porcine thigh tissue were analyzed, with thirty procedures per needle type. Injection pressure differed significantly between intramuscular, fascial puncture, and interfascial phases, showing a distinct puncture peak (p ≤ 3.44 × 10⁻¹⁴). Needle geometry significantly affected pressures across all phases (Kruskal–Wallis intramuscular p = 2.0 × 10⁻⁶, puncture p = 7.52 × 10⁻⁸, interfascial p = 9.2 × 10⁻⁵), with large pairwise effects (Hedges g up to 1.51). The classical tip produced the highest intramuscular and higher interfascial pressures, the sharp tip required the lowest puncture pressure, and the lateral tip yielded the lowest intramuscular and interfascial pressures. Conclusions: Needle tip geometry substantially influences pressure dynamics throughout the injection process, with the classical design associated with the highest fascia-penetration injection pressures and the sharp needle exhibiting the lowest, while the lateral design associated with lowest intramuscular-penetration and interfascial pressures.