Search

Abstract Objectives To use convolutional neural networks (CNNs) for the differentiation between benign and malignant renal tumors using contrast-enhanced CT images of a multi-institutional, multi-vendor, and multicenter CT dataset. Methods A total of 264 histologically confirmed renal tumors were included, from US and Swedish centers. Images were augmented and divided randomly 70%:30% for algorithm training and testing. Three CNNs (InceptionV3, Inception-ResNetV2, VGG-16) were pretrained with transfer learning and fine-tuned with our dataset to distinguish between malignant and benign tumors. The ensemble consensus decision of the three networks was also recorded. Performance of each network was assessed with receiver operating characteristics (ROC) curves and their area under the curve (AUC-ROC). Saliency maps were created to demonstrate the attention of the highest performing CNN. Results Inception-ResNetV2 achieved the highest AUC of 0.918 (95% CI 0.873–0.963), whereas VGG-16 achieved an AUC of 0.813 (95% CI 0.752–0.874). InceptionV3 and ensemble achieved the same performance with an AUC of 0.894 (95% CI 0.844–0.943). Saliency maps indicated that Inception-ResNetV2 decisions are based on the characteristics of the tumor while in most tumors considering the characteristics of the interface between the tumor and the surrounding renal parenchyma. Conclusion Deep learning based on a diverse multicenter international dataset can enable accurate differentiation between benign and malignant renal tumors. Critical relevance statement Convolutional neural networks trained on a diverse CT dataset can accurately differentiate between benign and malignant renal tumors. Key points • Differentiation between benign and malignant tumors based on CT is extremely challenging. • Inception-ResNetV2 trained on a diverse dataset achieved excellent differentiation between tumor types. • Deep learning can be used to distinguish between benign and malignant renal tumors. Graphical Abstract

Abstract Differentiating benign renal oncocytic tumors and malignant renal cell carcinoma (RCC) on imaging and histopathology is a critical problem that presents an everyday clinical challenge. This manuscript aims to demonstrate a novel methodology integrating metabolomics with radiomics features (RF) to differentiate between benign oncocytic neoplasia and malignant renal tumors. For this purpose, thirty-three renal tumors (14 renal oncocytic tumors and 19 RCC) were prospectively collected and histopathologically characterised. Matrix-assisted laser desorption/ionisation mass spectrometry imaging (MALDI-MSI) was used to extract metabolomics data, while RF were extracted from CT scans of the same tumors. Statistical integration was used to generate multilevel network communities of -omics features. Metabolites and RF critical for the differentiation between the two groups (delta centrality > 0.1) were used for pathway enrichment analysis and machine learning classifier (XGboost) development. Receiver operating characteristics (ROC) curves and areas under the curve (AUC) were used to assess classifier performance. Radiometabolomics analysis demonstrated differential network node configuration between benign and malignant renal tumors. Fourteen nodes (6 RF and 8 metabolites) were crucial in distinguishing between the two groups. The combined radiometabolomics model achieved an AUC of 86.4%, whereas metabolomics-only and radiomics-only classifiers achieved AUC of 72.7% and 68.2%, respectively. Analysis of significant metabolite nodes identified three distinct tumour clusters (malignant, benign, and mixed) and differentially enriched metabolic pathways. In conclusion, radiometabolomics integration has been presented as an approach to evaluate disease entities. In our case study, the method identified RF and metabolites important in differentiating between benign oncocytic neoplasia and malignant renal tumors, highlighting pathways differentially expressed between the two groups. Key metabolites and RF identified by radiometabolomics can be used to improve the identification and differentiation between renal neoplasms.

Abstract Background Identifying people with diabetes who are likely to experience a foot ulcer is an important part of preventative care. Many cohort studies report predictive models for foot ulcerations and for people with diabetes, but reports of long‐term outcomes are scarce. Aim We aimed to develop a predictive model for foot ulceration in diabetes using a range of potential risk factors with a follow‐up of 10 years after recruitment. A new foot ulceration was the outcome of interest and death was the secondary outcome of interest. Design A 10‐year follow‐up cohort study. Methods 1193 people with a diagnosis of diabetes who took part in a study in 2006–2007 were invited to participate in a 10‐year follow‐up. We developed a prognostic model for the incidence of incident foot ulcerations using a survival analysis, Cox proportional hazards model. We also utilised survival analysis Kaplan–Meier curves, and relevant tests, to assess the association between the predictor variables for foot ulceration and death. Results At 10‐year follow‐up, 41% of the original study population had died and more than 18% had developed a foot ulcer. The predictive factors for foot ulceration were an inability to feel a 10 g monofilament or vibration from a tuning fork, previous foot ulceration and duration of diabetes. Conclusions The prognostic model shows an increased risk of ulceration for those with previous history of foot ulcerations, insensitivity to a 10 g monofilament, a tuning fork and duration of diabetes. The incidence of foot ulceration at 10‐year follow‐up was 18%; however, the risk of death for this community‐based population was far greater than the risk of foot ulceration.

Contrary to popular lore, optimal visual acuity is typically better than 20/20. Could correcting acuity beyond 20/20 offer any benefit? An affirmative answer could present new confounds in studies of aging, development, psychiatric illness, neurodegenerative disorders, or any other population where refractive error might be more likely. An affirmative answer would also offer a novel explanation of inter-observer variability in visual performance. To address the question, we had individuals perform two well-studied visual tasks, once with 20/20 vision and once with optical correction, so that observers could see one line better on an eye chart. In the contour integration task, observers sought to identify the screen quadrant location of a sparsely defined (integrated) shape embedded in varying quantities of randomly oriented "noise" elements. In the collinear facilitation task, observers sought to detect a low-contrast element flanked by collinear or orthogonal high-contrast elements. In each case, displays were scaled in size to modulate element visibility and spatial frequency (4–12 cycles/deg). We found that improving acuity beyond 20/20 improved contour integration for the high spatial frequency displays. Although improving visual acuity did not affect collinear facilitation, it did improve detection of the central low-contrast target, especially at high spatial frequencies. These results, which were large in magnitude, suggest that optically correcting beyond 20/20 improves the detection and integration of contour elements, especially those that are smaller and of higher spatial frequency. Refractive blur within the normal range may confound special population studies, explain inter-observer differences, and meaningfully impact performance in low-visibility environments. [ABSTRACT FROM AUTHOR]

Summary Bayesian mixture modelling is widely used for density estimation and clustering. The Dirichlet process mixture model (DPMM) is the most popular Bayesian non‐parametric mixture modelling approach. In this manuscript, we study the choice of prior for the variance or precision matrix when Gaussian kernels are adopted. Typically, in the relevant literature, the assessment of mixture models is done by considering observations in a space of only a handful of dimensions. Instead, we are concerned with more realistic problems of higher dimensionality, in a space of up to 20 dimensions. We observe that the choice of prior is increasingly important as the dimensionality of the problem increases. After identifying certain undesirable properties of standard priors in problems of higher dimensionality, we review and implement possible alternative priors. The most promising priors are identified, as well as other factors that affect the convergence of MCMC samplers. Our results show that the choice of prior is critical for deriving reliable posterior inferences. This manuscript offers a thorough overview and comparative investigation into possible priors, with detailed guidelines for their implementation. Although our work focuses on the use of the DPMM in clustering, it is also applicable to density estimation. [ABSTRACT FROM AUTHOR]

Objective: Rare coexistence of disease or pathology Background: Hereditary breast cancer arising in BRCA1-deficient patients is commonly diagnosed as invasive carcinoma of no special type (NST) with medullary features, while invasive lobular carcinoma (ILC) appears to be significantly under-represented in BRCA1 mutation carriers. We report a case of pleomorphic ILC arising in a 28-year-old woman harboring a germline BRCA1 c.3756_3759delGTCT p.(Ser1253Argfs*10) pathogenic variant. Case Report: A nulliparous 28-year-old woman with a family history of BRCA1 mutation presented to the symptomatic breast clinic with a several-week history of a left 80-mm breast lump. Core biopsy established a diagnosis of a poorly differentiated triple-negative breast cancer (TNBC) of pleomorphic lobular phenotype. Her clinical diagnosis was cT3, N0, M0, cStageIIB. The MDT recommended CT staging, MRI breast imaging and neoadjuvant chemotherapy (NACT). PET CT imaging showed no evidence of distant metastatic disease. The patient had a good radiological response to NACT with a FEC-T carboplatin regimen. Post-NACT imaging showed a residual cystic mass and the patient underwent a mastectomy and sentinel lymph node biopsy with plans for a delayed latissimus dorsi reconstruction following her adjuvant radiotherapy treatment. A complete pathological response was subsequently demonstrated without any evidence of metastatic disease. Conclusions: This case is the first report of pleomorphic ILC with a triple-negative receptor status and a complete pathological response in a BRCA1 mutation carrier. Our study expands the heterogeneous spectrum of TNBC and contributes to a better understanding of the molecular genetic landscape that characterizes invasive pleomorphic lobular neoplasia. [ABSTRACT FROM AUTHOR]