One of the most challenging tasks for bladder cancer diagnosis is to histologically differentiate two early stages, non-invasive Ta and superficially invasive T1, the latter of which is associated ...with a significantly higher risk of disease progression. Indeed, in a considerable number of cases, Ta and T1 tumors look very similar under microscope, making the distinction very difficult even for experienced pathologists. Thus, there is an urgent need for a favoring system based on machine learning (ML) to distinguish between the two stages of bladder cancer.
A total of 1177 images of bladder tumor tissues stained by hematoxylin and eosin were collected by pathologists at University of Rochester Medical Center, which included 460 non-invasive (stage Ta) and 717 invasive (stage T1) tumors. Automatic pipelines were developed to extract features for three invasive patterns characteristic to the T1 stage bladder cancer (i.e., desmoplastic reaction, retraction artifact, and abundant pinker cytoplasm), using imaging processing software ImageJ and CellProfiler. Features extracted from the images were analyzed by a suite of machine learning approaches.
We extracted nearly 700 features from the Ta and T1 tumor images. Unsupervised clustering analysis failed to distinguish hematoxylin and eosin images of Ta vs. T1 tumors. With a reduced set of features, we successfully distinguished 1177 Ta or T1 images with an accuracy of 91-96% by six supervised learning methods. By contrast, convolutional neural network (CNN) models that automatically extract features from images produced an accuracy of 84%, indicating that feature extraction driven by domain knowledge outperforms CNN-based automatic feature extraction. Further analysis revealed that desmoplastic reaction was more important than the other two patterns, and the number and size of nuclei of tumor cells were the most predictive features.
We provide a ML-empowered, feature-centered, and interpretable diagnostic system to facilitate the accurate staging of Ta and T1 diseases, which has a potential to apply to other types of cancer.
Background. Residual renal function (RRF) impacts outcome of peritoneal dialysis (PD) patients. Some PD fluids contain glucose degradation products (GDPs) which have been shown to affect cell systems ...and tissues. They may also act as precursors of advanced glycosylation endproducts (AGEs) both locally and systemically, potentially inflicting damage to the kidney as the major organ for AGE elimination. We conducted a clinical study in PD patients to see if the content of GDP in the PD fluid has any influence on the decline of the residual renal function. Methods. In a multicentre approach, 80 patients (GFF ≥ 3 mL/min/1.732 or creatinine clearance ≥3 mL/min/1.73 m2) were randomized to treatment with a PD fluid containing low levels of GDP or standard PD fluid for 18 months. RRF was assessed every 4–6 weeks. Fluid balance, mesothelial cell mass marker CA125, peritoneal membrane characteristics, C-reactive protein (CRP), total protein, albumin, electrolytes and phosphate were measured repeatedly. Results. Data from 69 patients revealed a significant difference in monthly RRF change: −1.5% (95% CI = −3.07% to +0.03%) with low GDP (43 patients) vs −4.3% (95% CI = −6.8% to −2.06%) with standard fluids (26 patients) (P = 0.0437), independent of angiotensin-converting enzyme (ACE) inhibitor or angiotensin receptor blocker medication. Twenty-four-hour urine volume declined more slowly with low-GDP fluid compared to standard fluids (12 vs 38 mL/month, P = 0.0241), and monthly change of phosphate level was smaller (+0.013 vs +0.061 mg/dL, P = 0.0381). Conclusions. Our prospective study demonstrates for the first time a significant benefit concerning preservation of RRF and urine volume of using a PD fluid with low GDP levels. These findings suggest that GDPs might affect patient outcome related to RRF.
We highlight the case of a 12 year old male who presented after sustaining a gunshot injury to the scrotum resulting in testicular, prostatic, and urethral transection in addition to pelvic fracture, ...extra peritoneal bladder injury, and transmural injury to recto sigmoid and ileum. The patient underwent a left orchiectomy, primary repair of the bladder and urethra, placement of universal plate on superior pubic rami, and segmental rectosigmoid and ileum resection. These findings illustrate the collaborative efforts of trauma surgery and urology to treat complex lower genitourinary (GU) injuries and how the direct prioritization of surgical efforts provides acceptable outcomes.
To identify the first time point of an MRI-verified response to certolizumab pegol (CZP) therapy in patients with rheumatoid arthritis (RA).
Forty-one patients with active RA despite ...disease-modifying antirheumatic drug therapy were randomised 2:1 to CZP (CZP loading dose 400 mg every 2 weeks at weeks 0-4; CZP 200 mg every 2 weeks at weeks 6-16) or placebo→CZP (placebo at weeks 0-2; CZP loading dose at weeks 2-6; CZP 200 mg every 2 weeks at weeks 8-16). Contrast-enhanced MRI of one hand and wrist was acquired at baseline (week 0) and weeks 1, 2, 4, 8 and 16. All six time points were read simultaneously, blinded to time, using the Outcome Measures in Rheumatology Clinical Trials RA MRI scoring system. Primary outcome was change in synovitis score in the CZP group; secondary outcomes were change in bone oedema (osteitis) and erosion scores and clinical outcome measures.
Forty patients were treated (27 CZP, 13 placebo→CZP), and 36 (24 CZP, 12 placebo→CZP) completed week 16. In the CZP group, there were significant reductions from baseline synovitis (Hodges-Lehmann estimate of median change, -1.5, p=0.049) and osteitis scores (-2.5, p=0.031) at week 16. Numerical, but statistically insignificant, MRI inflammation reductions were observed at weeks 1-2 in the CZP group. No significant change was seen in bone erosion score. Improvements across all clinical outcomes were seen in the CZP group.
CZP reduced MRI synovitis and osteitis scores at week 16, despite small sample size and the technical challenge of reading six time points simultaneously. This study provides essential information on optimal MRI timing for subsequent trials.
ClinicalTrials.gov, NCT01235598.
The topological landscape of gene interaction networks provides a rich source of information for inferring functional patterns of genes or proteins. However, it is still a challenging task to ...aggregate heterogeneous biological information such as gene expression and gene interactions to achieve more accurate inference for prediction and discovery of new gene interactions. In particular, how to generate a unified vector representation to integrate diverse input data is a key challenge addressed here.
We propose a scalable and robust deep learning framework to learn embedded representations to unify known gene interactions and gene expression for gene interaction predictions. These low- dimensional embeddings derive deeper insights into the structure of rapidly accumulating and diverse gene interaction networks and greatly simplify downstream modeling. We compare the predictive power of our deep embeddings to the strong baselines. The results suggest that our deep embeddings achieve significantly more accurate predictions. Moreover, a set of novel gene interaction predictions are validated by up-to-date literature-based database entries.
The proposed model demonstrates the importance of integrating heterogeneous information about genes for gene network inference. GNE is freely available under the GNU General Public License and can be downloaded from GitHub ( https://github.com/kckishan/GNE ).
Biomedical interaction networks have incredible potential to be useful in the prediction of biologically meaningful interactions, identification of network biomarkers of disease, and the discovery of ...putative drug targets. Recently, graph neural networks have been proposed to effectively learn representations for biomedical entities and achieved state-of-the-art results in biomedical interaction prediction. These methods only consider information from immediate neighbors but cannot learn a general mixing of features from neighbors at various distances. In this paper, we present a higher-order graph convolutional network (HOGCN)to aggregate information from the higher-order neighborhood for biomedical interaction prediction. Specifically, HOGCN collects feature representations of neighbors at various distances and learns their linear mixing to obtain informative representations of biomedical entities. Experiments on four interaction networks, including protein-protein, drug-drug, drug-target, and gene-disease interactions, show that HOGCN achieves more accurate and calibrated predictions. HOGCN performs well on noisy, sparse interaction networks when feature representations of neighbors at various distances are considered. Moreover, a set of novel interaction predictions are validated by literature-based case studies.
Background. This double-blind, placebo-controlled study was conducted to assess the efficacy of the nonabsorbed oral antibiotic rifaximin to prevent shigellosis in volunteers challenged with Shigella ...flexneri. Methods. Volunteers were randomized to receive either prophylactic rifaximin (200 mg 3 times daily for 3 days; n = 15) or placebo (n = 10) on days 0, 1, and 2. On day 1, volunteers were challenged with ∼1500 colony-forming units of S. flexneri 2a strain 2457T given orally in sodium bicarbonate buffer. Results. The incidence of diarrhea was 0 with rifaximin, compared with 60% with placebo (P = .001). The median time to onset of diarrhea was 78.5 h with placebo (P < .001). The incidence of dysentery was 0 for rifaximin and 10% for placebo (P = .4). The incidence of colonization with Shigella was 0 with rifaximin, compared with 50% with placebo (P < .005). A significant serum or mucosal immune response after challenge by at least 1 indicator (immunoglobulin A titer, immunoglobulin G titer, and immunoglobulin A antibody—secreting cell count) was 0 with rifaximin and 80% with placebo (P < .001). Conclusions. Rifaximin was effective and well tolerated, compared with placebo, in preventing shigellosis in this double-blind study of volunteers challenged with S. flexneri 2a.
Homeostasis in continually renewing tissues is maintained by a tightly regulated balance between cell proliferation, cell differentiation, and cell death. Until recently, proliferation was thought to ...be the primary point of control in the regulation of normal tissue kinetic homeostasis and as such has been the major focus of both understanding the etiology of disease and developing therapeutic strategies. Now, physiologic cell death, known as apoptosis (â-pôp-tō'sîs, â-pōp-tō'sîs Thomas CL (ed.): Taber's Cyclopedic Medical Dictionary. F.A. Davis, Co., Philadelphia, 1989) has gained scientific recognition as an active regulatory mechanism, complementary, but functionally opposite, to proliferation with important roles in shaping and maintaining tissue size and prevention of disease. In this review we will describe the concept of apoptosis and discuss possible molecular mechanisms of its regulation that may have implications for skin biology.
Experts have a remarkable capability of locating, perceptually organizing, identifying, and categorizing objects in images specific to their domains of expertise. In this article, we present a ...hierarchical probabilistic framework to discover the stereotypical and idiosyncratic viewing behaviors exhibited with expertise-specific groups. Through these patterned eye movement behaviors we are able to elicit the domain-specific knowledge and perceptual skills from the subjects whose eye movements are recorded during diagnostic reasoning processes on medical images. Analyzing experts’ eye movement patterns provides us insight into cognitive strategies exploited to solve complex perceptual reasoning tasks. An experiment was conducted to collect both eye movement and verbal narrative data from three groups of subjects with different levels or no medical training (eleven board-certified dermatologists, four dermatologists in training and thirteen undergraduates) while they were examining and describing 50 photographic dermatological images. We use a hidden Markov model to describe each subject’s eye movement sequence combined with hierarchical stochastic processes to capture and differentiate the discovered eye movement patterns shared by multiple subjects within and among the three groups. Independent experts’ annotations of diagnostic conceptual units of thought in the transcribed verbal narratives are time-aligned with discovered eye movement patterns to help interpret the patterns’ meanings. By mapping eye movement patterns to thought units, we uncover the relationships between visual and linguistic elements of their reasoning and perceptual processes, and show the manner in which these subjects varied their behaviors while parsing the images. We also show that inferred eye movement patterns characterize groups of similar temporal and spatial properties, and specify a subset of distinctive eye movement patterns which are commonly exhibited across multiple images. Based on the combinations of the occurrences of these eye movement patterns, we are able to categorize the images from the perspective of experts’ viewing strategies in a novel way. In each category, images share similar lesion distributions and configurations. Our results show that modeling with multi-modal data, representative of physicians’ diagnostic viewing behaviors and thought processes, is feasible and informative to gain insights into physicians’ cognitive strategies, as well as medical image understanding.