Background and Objectives: Prematurity of birth occurs before the 37th week of gestation and affects up to 10% of births worldwide. It is correlated with critical outcomes; therefore, constant monitoring in neonatal intensive care units or home environments is required. The aim of this work was to develop solutions for remote neonatal intensive supervision systems, which should assist medical diagnosis of premature infants and raise alarm at cardiac abnormalities, such as bradycardia. Additionally, the COVID-19 pandemic has put a worldwide stress upon the medical staff and the management of healthcare units. Materials and Methods: A traditional medical diagnosing scheme was set up, implemented with the aid of powerful mathematical operators. The algorithm was tailored to the infants’ personal ECG characteristics and was tested on real ECG data from the publicly available PhysioNet database “Preterm Infant Cardio-Respiratory Signals Database”. Different processing problems were solved: noise filtering, baseline drift removal, event detection and compression of medical data using the à trous wavelet transform. Results: In all 10 available clinical cases, the bradycardia events annotated by the physicians were correctly detected using the RR intervals. Compressing the ECG signals for remote transmission, we obtained compression ratios (CR) varying from 1.72 to 7.42, with the median CR value around 3. Conclusions: We noticed that a significant amount of noise can be added to a signal while monitoring using standard clinical sensors. We tried to offer solutions for these technical problems. Recent studies have shown that persons infected with the COVID-19 disease are frequently reported to develop cardiovascular symptoms and cardiac arrhythmias. An automatic surveillance system (both for neonates and adults) has a practical medical application. The proposed algorithm is personalized, no fixed reference value being applied, and the algorithm follows the neonate’s cardiac rhythm changes. The performance depends on the characteristics of the input ECG. The signal-to-noise ratio of the processed ECG was improved, with a value of up to 10 dB.
Magnetic resonance angiography is a medical procedure used to offer an image of the blood vessels and organs of the body. Given the worldwide spread of cardiovascular diseases, more and more resources are invested in treating them. One of the most modern treatments involves the acquisition of images of the heart. Sometimes the contrast of these images is not satisfactory. Injecting invasive enhancement substances to obtain a better view of the cardiac route is not advisable. However, software algorithms can solve the problem. This study proposes and tests a local adaptive contrast-adjustment algorithm using the dual-tree complex wavelet transform. The method has been tested with medical data from a public database to allow comparisons to other methods. The selected algorithm further improved the contrast of images. The performances are given for evaluation, both visually (to help doctors make accurate diagnoses) and in parametric form (to show engineers which parts of the algorithm might need improvement). Compared to other contrast enhancement methods, the proposed wavelet algorithm shows good results and greater stability. Thus, we aim to avoid future pointless complications due to unnecessary contrast substances.
(1) Background: The prevention of critical situations is a key ability in medicine. Hip ultrasound for neonates is a standard procedure to prevent later critical outcomes, such as hip dysplasia. Additionally, the SARS-CoV-2 pandemic has put worldwide stress upon healthcare units, resulting often in a lack of sufficient medical personnel. This work aims to develop solutions to ease and speed up the process of coming to a correct diagnosis. (2) Methods: Traditional medical procedures are envisaged, but they are enhanced to reduce diagnosing errors due to the movements of the neonates. Echographic noise filtering and contrast correction methods are implemented the Hyperanalytic Wavelet Transform, combined with an adaptive Soft Thresholding Filter. The algorithm is tailored to infants’ structure and is tested on real ultrasounds provided by the “Victor Babes” University of Medicine and Pharmacy. Denoising and contrast correction problems are targeted. (3) Results: In available clinical cases, the noise affecting the image was reduced and the contrast was enhanced. (4) Discussion: We noticed that a significant amount of noise can be added to the image, as the patients are neonates and can hardly avoid movements. (5) Conclusions: The algorithm is personalized with no fixed reference value. Any device easing the clinical procedures of physicians has a practical medical application.
Pneumonia detection in chest X-rays is commonly treated as a binary classification task, although the radiographic burden of disease varies substantially across patients. This study investigates whether the expert bounding-box annotations available in the RSNA 2018 Pneumonia Detection dataset can be reused to derive an interpretable severity grading framework based on lesion extent. For each pneumonia-positive image, total disease burden was computed as the cumulative area of all annotated opacity boxes, and a balanced three-tier split was generated, defining Severity 1 (low/mild), Severity 2 (moderate), and Severity 3 (severe). The resulting severity groups contained 1999, 2006, and 2007 images, respectively. To validate the usefulness of this annotation-driven severity formulation, we trained Vision Transformer models in both a classical binary setting and a severity-specialized setup. The classical binary baseline reached a maximum validation accuracy of 95.05%, while the specialized models achieved 94.98% for Severity 1, 97.88% for Severity 2, and 99.08% for Severity 3. These results indicate that radiographic burden derived from bounding-box extent supports highly separable severity-aware subproblems, particularly for severe pneumonia, while lower-burden categories remain more difficult. The proposed framework offers a transparent and reproducible way to transform RSNA 2018 lesion annotations into ordinal severity labels. Beyond its original use as a detection and localization benchmark, the dataset can therefore also support severity-aware classification, radiographic burden analysis, and future explainable AI studies in chest X-ray interpretation.
Chest X-ray pneumonia assessment is commonly formulated as a binary classification problem that does not explicitly represent radiographic burden. In this work, we reinterpret the RSNA 2018 Pneumonia Detection Challenge dataset by using expert bounding-box annotations to derive three burden-oriented groups: low/mild (Severity 1), moderate (Severity 2), and severe (Severity 3). We evaluate a classical binary baseline, a unified four-class classifier, and three severity-specific binary specialist branches. The selected binary Vision Transformer achieved maximum validation accuracy, while the unified four-class model reached . To complement exact-match accuracy, we report three task-specific ordinal measures: Severity Consistency Score (SCS), probability-aware Severity Consistency Score (pSCS), and Adjacent-Class Accuracy (ACA). These reached 91.80%, 89.18%, and 96.10%, respectively, indicating that many non-exact predictions remained close to the reference burden category. The specialist branches achieved maximum validation accuracies of , , and for Severity 1, Severity 2, and Severity 3, respectively. At the joint-system level, maximum-probability fusion of the three specialist outputs achieved a Severity Binary Accuracy (SBA) of on the common evaluation cohort. Overall, the results show that RSNA bounding-box extent can support a reproducible, annotation-derived radiographic burden analysis, while ordinal-aware measures provide complementary information to strict four-class accuracy.