Search

Abstract While multiple factors impact disease, artificial intelligence (AI) studies in medicine often use small, non-diverse patient cohorts due to data sharing and privacy issues. Federated learning (FL) has emerged as a solution, enabling training across hospitals without direct data sharing. Here, we present FL-PedBrain, an FL platform for pediatric posterior fossa brain tumors, and evaluate its performance on a diverse, realistic, multi-center cohort. Pediatric brain tumors were targeted due to the scarcity of such datasets, even in tertiary care hospitals. Our platform orchestrates federated training for joint tumor classification and segmentation across 19 international sites. FL-PedBrain exhibits less than a 1.5% decrease in classification and a 3% reduction in segmentation performance compared to centralized data training. FL boosts segmentation performance by 20 to 30% on three external, out-of-network sites. Finally, we explore the sources of data heterogeneity and examine FL robustness in real-world scenarios with data imbalances.

Abstract Background Gallbladder cancer (GBC) is an aggressive malignancy that is usually diagnosed at a late stage. Prior data showed increasing incidence of GBC in the US. However, little is known about race/ethnic‐specific incidence and mortality trends of GBC per stage at diagnosis. Therefore, we aimed to conduct a time‐trend analysis of GBC incidence and mortality rates categorized by race/ethnicity and stage‐at‐diagnosis. Methods Age‐adjusted GBC incidence and mortality rates were calculated using SEER*Stat software from the United States Cancer Statistics database (covers ~98% of US population between 2001 and 2020) and NCHS (covers ~100% of the US population between 2000 and 2020) databases, respectively. Race/Ethnic groups were Non‐Hispanic‐White (NHW), Non‐Hispanic‐Black (NHB), Hispanic, Non‐Hispanic‐Asian/Pacific‐Islander (NHAPI), and Non‐Hispanic‐American‐Indian/Alaska‐Native (NHAIAN). Stage‐at‐diagnoses were all stages, early, regional, and distant stages. Joinpoint regression was used to generate time‐trends [annual percentage change (APC) and average APC (AAPC)] with parametric estimations and a two‐sided t‐test (p‐value cut‐off 0.05). Results 76,873 patients were diagnosed with GBC with decreasing incidence rates in all races/ethnicities except NHB who experienced an increasing trend between 2001 and 2014 (APC = 2.08, p

Abstract Background The type of suture used in periodontal surgery can affect post-surgical complications. This study aimed to compare simple with cross-mattress sutures for nondisplaced flaps of the maxillary molar region. Methods This randomized controlled trial included 32 candidates of nondisplaced flap surgery of the maxillary molar region referred to the private office of a periodontist in Bandar Abbas, Iran from January 21 to May 4, 2020. First, the patients’ age, sex, and plaque index were recorded. Then, they were randomized into two equal groups. In the first group, the interdental suturing was done using simple sutures with 4–0 vicryl threads, and in the second group, interdental suturing was performed using cross-mattress sutures with the same threads. The primary outcome was suture time, including the duration of the first suture and the total duration of all sutures. The secondary outcomes were bleeding on probing and the requirement of supplementary sutures immediately after the surgery, as well as the gingival index (at suture removal and one month after surgery). Results The two groups were comparable regarding age, sex, and plaque index. The first suture duration was significantly longer in the simple group compared to the cross-mattress group (P

Background Infants with congenital heart disease (CHD) are at risk for white matter injury (WMI) before neonatal heart surgery. Better knowledge of the causes of preoperative WMI may provide insights into interventions that improve neurodevelopmental outcomes in these patients. Methods and Results A prospective single‐center study of preoperative WMI in neonates with CHD recorded data on primary cardiac diagnosis, maternal‐fetal environment (MFE), delivery type, subject anthropometrics, and preoperative care. Total maturation score and WMI were assessed, and stepwise logistic regression modeling selected risk factors for WMI. Among subjects with severe CHD (n=183) who received a preoperative brain magnetic resonance imaging, WMI occurred in 40 (21.9%) patients. WMI prevalence (21.4%–22.1%) and mean volumes (119.7–160.4 mm3) were similar across CHD diagnoses. Stepwise logistic regression selected impaired MFE (odds ratio [OR], 2.85 [95% CI, 1.29–6.30]), male sex (OR, 2.27 [95% CI, 1.03–5.36]), and older age at surgery/magnetic resonance imaging (OR, 1.20 per day [95% CI, 1.03–1.41]) as risk factors for preoperative WMI and higher total maturation score values (OR, 0.65 per unit increase [95% CI, 0.43–0.95]) as protective. A quarter (24.6%; n=45) of subjects had ≥1 components of impaired MFE (gestational diabetes [n=12; 6.6%], gestational hypertension [n=11; 6.0%], preeclampsia [n=2; 1.1%], tobacco use [n=9; 4.9%], hypothyroidism [n=6; 3.3%], and other [n=16; 8.7%]). In a subset of 138 subjects, an exploratory analysis of additional MFE‐related factors disclosed other potential risk factors for WMI. Conclusions This study is the first to identify impaired MFE as an important risk factor for preoperative WMI. Vulnerability to preoperative WMI was shared across CHD diagnoses.

Introduction: Despite advancements in molecular and histopathologic characterization of pediatric low-grade gliomas (pLGGs), there remains significant phenotypic heterogeneity among tumors with similar categorizations. We hypothesized that an unsupervised machine learning approach based on radiomic features may reveal distinct pLGG imaging subtypes. Methods: Multi-parametric MR images (T1 pre- and post-contrast, T2, and T2 FLAIR) from 157 patients with pLGGs were collected and 881 quantitative radiomic features were extracted from tumorous region. Clustering was performed using K-means after applying principal component analysis (PCA) for feature dimensionality reduction. Molecular and demographic data was obtained from the PedCBioportal and compared between imaging subtypes. Results: K-means identified three distinct imaging-based subtypes. Subtypes differed in mutational frequencies of BRAF (p < 0.05) as well as the gene expression of BRAF (p

The simplest approach to convey the results of scientific analysis, which can include complex comparisons, is typically through the use of visual items, including figures and plots. These statistical plots play a critical role in scientific studies, making data more accessible, engaging, and informative. A growing number of visual representations have been utilized recently to graphically display the results of oncologic imaging, including radiomic and radiogenomic studies. Here, we review the applications, distinct properties, benefits, and drawbacks of various statistical plots. Furthermore, we provide neuroradiologists with a comprehensive understanding of how to use these plots to effectively communicate analytical results based on imaging data. [ABSTRACT FROM AUTHOR]

Patients with hypoplastic left heart syndrome who have been palliated with the Fontan procedure are at risk for adverse neurodevelopmental outcomes, lower quality of life, and reduced employability. We describe the methods (including quality assurance and quality control protocols) and challenges of a multi-center observational ancillary study, SVRIII (Single Ventricle Reconstruction Trial) Brain Connectome. Our original goal was to obtain advanced neuroimaging (Diffusion Tensor Imaging and Resting-BOLD) in 140 SVR III participants and 100 healthy controls for brain connectome analyses. Linear regression and mediation statistical methods will be used to analyze associations of brain connectome measures with neurocognitive measures and clinical risk factors. Initial recruitment challenges occurred that were related to difficulties with: (1) coordinating brain MRI for participants already undergoing extensive testing in the parent study, and (2) recruiting healthy control subjects. The COVID-19 pandemic negatively affected enrollment late in the study. Enrollment challenges were addressed by: (1) adding additional study sites, (2) increasing the frequency of meetings with site coordinators, and (3) developing additional healthy control recruitment strategies, including using research registries and advertising the study to community-based groups. Technical challenges that emerged early in the study were related to the acquisition, harmonization, and transfer of neuroimages. These hurdles were successfully overcome with protocol modifications and frequent site visits that involved human and synthetic phantoms.

Background: Gallbladder cancer (GBC) is an aggressive malignancy that is usually diagnosed at a late stage. Prior data showed increasing incidence of GBC in the US. However, little is known about race/ethnic‐specific incidence and mortality trends of GBC per stage at diagnosis. Therefore, we aimed to conduct a time‐trend analysis of GBC incidence and mortality rates categorized by race/ethnicity and stage‐at‐diagnosis. Methods: Age‐adjusted GBC incidence and mortality rates were calculated using SEER*Stat software from the United States Cancer Statistics database (covers ~98% of US population between 2001 and 2020) and NCHS (covers ~100% of the US population between 2000 and 2020) databases, respectively. Race/Ethnic groups were Non‐Hispanic‐White (NHW), Non‐Hispanic‐Black (NHB), Hispanic, Non‐Hispanic‐Asian/Pacific‐Islander (NHAPI), and Non‐Hispanic‐American‐Indian/Alaska‐Native (NHAIAN). Stage‐at‐diagnoses were all stages, early, regional, and distant stages. Joinpoint regression was used to generate time‐trends [annual percentage change (APC) and average APC (AAPC)] with parametric estimations and a two‐sided t‐test (p‐value cut‐off 0.05). Results: 76,873 patients were diagnosed with GBC with decreasing incidence rates in all races/ethnicities except NHB who experienced an increasing trend between 2001 and 2014 (APC = 2.08, p < 0.01) and plateauing afterward (APC = −1.21, p = 0.31); (AAPC = 1.03, p = 0.03). Among early‐stage tumors (9927 patients), incidence rates were decreasing only in Hispanic (AAPC = −4.24, p = 0.006) while stable in other races/ethnicities (NHW: AAPC = −2.61, p = 0.39; NHB: AAPC = −1.73, p = 0.36). For regional‐stage tumors (29,690 patients), GBC incidence rates were decreasing only in NHW (AAPC = −1.61, p < 0.001) while stable in other races/ethnicities (NHB: AAPC = 0.73, p = 0.34; Hispanic: AAPC = −1.58, p = 0.24; NHAPI: AAPC = −1.22, p = 0.07). For distant‐stage tumors (31,735 patients), incidence rates were increasing in NHB (AAPC = 2.72, p < 0.001), decreasing in Hispanic (AAPC = −0.64, p = 0.04), and stable in NHW (AAPC = 0.07, p = 0.84) and NHAPI (AAPC = 0.79, p = 0.13). There were 43,411 deaths attributed to GBC with decreasing mortality rates in all races/ethnicities except NHB who experienced a stable trend (AAPC = 0.25, p = 0.25). Conclusion: Nationwide data over the last two decades show that NHB patients experienced increasing GBC incidence between 2001 and 2014 followed by stabilization of the rates. This increase was driven by late‐stage tumors and occurred in the first decade. NHB also experienced non‐improving GBC mortality, compared to other race and ethnic groups who had decreasing mortality. This can be due to lack of timely‐access to healthcare leading to delayed diagnosis and worse outcomes. Future studies are warranted to investigate contributions to the revealed racial and ethnic disparities, especially in NHB, to improve early detection. [ABSTRACT FROM AUTHOR]

Although vast, the medical literature is deficient in reports of gastroesophageal junction (GEJ) involvement of mantle cell lymphoma (MCL). We present the unique case of a 76-year-old male who presented with worsening dysphagia, weight loss, and heartburn and who was found to have blastic variant of MCL in the GEJ. He had undergone extensive workup in the past for an ulcerative, gastric/GEJ lesion, found on four separate esophagogastroduodenoscopies (EGDs) and two esophageal ultrasounds, whose biopsies were repeatedly negative for malignancy. On admission, physical examination and labs were unremarkable, but computed tomography showed an irregular mass involving the GEJ. EGD on admission showed a large friable, ulcerated lesion with heaped-up margins involving the GEJ whose biopsies showed histological and immunohistochemical (IHC) findings consistent with blastic MCL. A bone marrow biopsy showed minimal involvement (90%, all consistent with blastic MCL, a rare and aggressive subtype of MCL. He was started on guideline-based chemoimmunotherapy as he was not a candidate for stem cell transplantation. Repeat imaging 1 year later showed improvement of the mass, with negative endoscopic biopsies for lymphoma. This case provides additional distinct features to the various clinical presentations associated with this rare proliferative disorder, thereby enhancing the medical literature on MCL.

The shortly upcoming 5th edition of the World Health Organization Classification of Tumors of the Central Nervous System is bringing extensive changes in the terminology of diffuse high-grade gliomas (DHGGs). Previously “glioblastoma,” as a descriptive entity, could have been applied to classify some tumors from the family of pediatric or adult DHGGs. However, now the term “glioblastoma” has been divested and is no longer applied to tumors in the family of pediatric types of DHGGs. As an entity, glioblastoma remains, however, in the family of adult types of diffuse gliomas under the insignia of “glioblastoma, IDH-wildtype.” Of note, glioblastomas still can be detected in children when glioblastoma, IDH-wildtype is found in this population, despite being much more common in adults. Despite the separation from the family of pediatric types of DHGGs, what was previously labeled as “pediatric glioblastomas” still remains with novel labels and as new entities. As a result of advances in molecular biology, most of the previously called “pediatric glioblastomas” are now classified in one of the four family members of pediatric types of DHGGs. In this review, the term glioblastoma is still apocryphally employed mainly due to its historical relevance and the paucity of recent literature dealing with the recently described new entities. Therefore, “glioblastoma” is used here as an umbrella term in the attempt to encompass multiple entities such as astrocytoma, IDH-mutant (grade 4); glioblastoma, IDH-wildtype; diffuse hemispheric glioma, H3 G34-mutant; diffuse pediatric-type high-grade glioma, H3-wildtype and IDH-wildtype; and high grade infant-type hemispheric glioma. Glioblastomas are highly aggressive neoplasms. They may arise anywhere in the developing central nervous system, including the spinal cord. Signs and symptoms are non-specific, typically of short duration, and usually derived from increased intracranial pressure or seizure. Localized symptoms may also occur. The standard of care of “pediatric glioblastomas” is not well-established, typically composed of surgery with maximal safe tumor resection. Subsequent chemoradiation is recommended if the patient is older than 3 years. If younger than 3 years, surgery is followed by chemotherapy. In general, “pediatric glioblastomas” also have a poor prognosis despite surgery and adjuvant therapy. Magnetic resonance imaging (MRI) is the imaging modality of choice for the evaluation of glioblastomas. In addition to the typical conventional MRI features, i.e., highly heterogeneous invasive masses with indistinct borders, mass effect on surrounding structures, and a variable degree of enhancement, the lesions may show restricted diffusion in the solid components, hemorrhage, and increased perfusion, reflecting increased vascularity and angiogenesis. In addition, magnetic resonance spectroscopy has proven helpful in pre- and postsurgical evaluation. Lastly, we will refer to new MRI techniques, which have already been applied in evaluating adult glioblastomas, with promising results, yet not widely utilized in children.

RNA sequencing (RNAseq) is a recent technology that profiles gene expression by measuring the relative frequency of the RNAseq reads. RNAseq read counts data is increasingly used in oncologic care and while radiology features (radiomics) have also been gaining utility in radiology practice such as disease diagnosis, monitoring, and treatment planning. However, contemporary literature lacks appropriate RNA-radiomics (henceforth, radiogenomics) joint modeling where RNAseq distribution is adaptive and also preserves the nature of RNAseq read counts data for glioma grading and prediction. The Negative Binomial (NB) distribution may be useful to model RNAseq read counts data that addresses potential shortcomings. In this study, we propose a novel radiogenomics-NB model for glioma grading and prediction. Our radiogenomics-NB model is developed based on differentially expressed RNAseq and selected radiomics/volumetric features which characterize tumor volume and sub-regions. The NB distribution is fitted to RNAseq counts data, and a log-linear regression model is assumed to link between the estimated NB mean and radiomics. Three radiogenomics-NB molecular mutation models (e.g., IDH mutation, 1p/19q codeletion, and ATRX mutation) are investigated. Additionally, we explore gender-specific effects on the radiogenomics-NB models. Finally, we compare the performance of the proposed three mutation prediction radiogenomics-NB models with different well-known methods in the literature: Negative Binomial Linear Discriminant Analysis (NBLDA), differentially expressed RNAseq with Random Forest (RF-genomics), radiomics and differentially expressed RNAseq with Random Forest (RF-radiogenomics), and Voom-based count transformation combined with the nearest shrinkage classifier (VoomNSC). Our analysis shows that the proposed radiogenomics-NB model significantly outperforms (ANOVA test, p < 0.05) for prediction of IDH and ATRX mutations and offers similar performance for prediction of 1p/19q codeletion, when compared to the competing models in the literature, respectively.