Early diagnosis and rapid treatment of respiratory abnormalities such as many lung diseases including pneumonia, TB, cancer, and other pulmonary problems depend on accurate and fast classification of chest X-ray images. Delayed diagnosis and insufficient treatment lead to the subjective, labour-intensive, error-prone features of current manual diagnosis systems. To tackle this pressing healthcare issue, this work investigates many deep convolutional neural network (CNN) architectures including VGG16, VGG19, ResNet50, InceptionV3, Xception, DenseNet121, NASNetMobile, and NASNet Large. LungVisionNet (LVNet) is an innovative hybrid model proposed here that combines MobileNetV2 with multilayer perceptron (MLP) layers in a unique way. LungVisionNet outperformed previous models in accuracy 96.91%, recall 97.59%, precision, specificity, F1-score 97.01%, and area under the curve (AUC) measurements according to thorough examination on two publicly available datasets including various chest abnormalities and normal cases exhibited. Comprehensive evaluation with an independent, real-world clinical dataset from King Hussein Cancer Centre (KHCC), which achieved 95.3% accuracy, 95.3% precision, 78.8% recall, 99.1% specificity, and 86.4% F1-score, confirmed the model’s robustness, generalizability, and clinical usefulness. We also created a simple mobile application that lets doctors quickly classify and evaluate chest X-ray images in hospitals, so enhancing clinical integration and practical application and supporting fast decision-making and better patient outcomes.

Background: An inferior vena cava thrombus (IVCT) occurs in approximately 4–10% of Wilms tumor (WT) cases. The presence of an IVCT complicates surgical management and potentially affects patient outcomes. We reviewed all patients with a WT with and without an IVCT treated at our center, comparing their characteristics and outcome. Patients and Methods: We retrospectively reviewed pediatric patients with a WT treated between November 2014 and July 2023. Patients were categorized according to the presence or absence of an IVCT. Data on demographics, clinical presentation, imaging findings, treatment modalities, and outcomes were collected. Group comparisons for categorical data were carried out using Chi-square tests, Event-free survival (EFS) and overall survival (OS) were estimated using Kaplan–Meier curves, and differences between groups were assessed with the log-rank test. Results: Among 110 children with a unilateral WT, 17 (15.4%) had an IVCT at presentation. Their median age at diagnosis was 4.2 years. Females predominated (65%) and 11 (65%) had distant metastasis. Thrombus levels were infra-hepatic (52.9%), retro-hepatic (23.6%), supra-hepatic (5.9%), and intra-cardiac (17.6%). Thrombus resolution following neo-adjuvant chemotherapy was achieved in 41.2% of patients, most frequently in infra-hepatic thrombi. Local control followed neo-adjuvant chemotherapy that included doxorubicin. Favorable histology was observed in 70% of patients with an IVCT. Compared with patients without an IVCT, children with an IVCT tend to present at an older age, have hematuria, a larger tumor, positive lymph node (LN) involvement, and metastatic disease (p value, 0.019, 0.008, 0.01, 0.014, and 0.002, respectively). On univariable analysis, older age, the presence of metastatic disease, IVCT, LN involvement, and diffuse anaplasia were associated with inferior EFS and OS. Five-year EFS and OS were significantly lower in patients with IVCT compared to those without (51% ± 12.5% vs. 74.5% ± 4.6%, p = 0.021 and 53.8% ± 15.4% vs. 82% ± 4.9%, p = 0.012, respectively). Conclusions: We observed a higher proportion of IVCT than previously reported. Consistent with prior studies, an IVCT was associated with more aggressive disease features. Although survival was worse in patients with an IVCT, the mere presence of a thrombus as an independent prognostic factor requires evaluation in larger patient cohorts.

Background: Tumor volume in Wilms tumor (WT) guides risk stratification under the International Society of Pediatric Oncology (SIOP) protocol. While the radiological ellipsoid formula is the current protocol-specified reference method, modalities such as planimetry, intraoperative specimen weight, and pathological volume are often used interchangeably in practice without systematic evaluation. Methods: We reviewed 60 pediatric WT patients. Three measurements were compared against the SIOP-standard radiological ellipsoid volume: radiological planimetry, intraoperative specimen weight, and pathological tumor volume. Pearson and Spearman correlations and Bland–Altman analysis were performed. Results: Radiological planimetry showed near-perfect correlation with the SIOP ellipsoid (Pearson r = 0.993, p < 0.001; mean bias +21.1 cm³, 95% limits of agreement −82.8 to +124.9 cm³, percentage bias +6.1%). Intraoperative specimen weight (r = 0.730) and pathological tumor volume (r = 0.594) showed moderate-to-good correlations but wide limits of agreement and systematic biases of +46.6% and −34.1%, respectively. At the critical 500 cm³ treatment threshold, ellipsoid and planimetry showed 100% concordance. However, using pathology volume would have produced discordant (lower) risk categorization for 47% of ellipsoid-defined high-risk patients, a discordance whose clinical treatment implications were not directly assessed in this study. Conversely, relying on intraoperative weight would have upstaged 9.1% of patients to a higher risk category, which could correspond to a more intensive treatment category, including doxorubicin, under the SIOP protocol; whether this would translate into unnecessary treatment in practice was not directly assessed in this study. Conclusions: Radiological planimetry is a highly reliable surrogate for the SIOP ellipsoid formula across all stages and histologies. Intraoperative weight and pathological volume exhibit significant systematic biases and should not be used to revise radiological risk groups. These findings support continued anchoring of SIOP risk stratification to preoperative radiological volumetry, consistent with the currently validated protocol threshold, to avoid unintended deviations in treatment intensity.