Ensemble of Convolutional Neural Networks Improves Automated Segmentation of Acute Ischemic Lesions Using Multiparametric Diffusion-Weighted MRI

BACKGROUND AND PURPOSE

Accurate automated infarct segmentation is needed for acute ischemic stroke studies relying on infarct volumes as an imaging phenotype or biomarker that require large numbers of subjects. This study investigated whether an ensemble of convolutional neural networks trained on multiparametric DWI maps outperforms single networks trained on solo DWI parametric maps.

MATERIALS AND METHODS

Convolutional neural networks were trained on combinations of DWI, ADC, and low b-value-weighted images from 116 subjects. The performances of the networks (measured by the Dice score, sensitivity, and precision) were compared with one another and with ensembles of 5 networks. To assess the generalizability of the approach, we applied the best-performing model to an independent Evaluation Cohort of 151 subjects. Agreement between manual and automated segmentations for identifying patients with large lesion volumes was calculated across multiple thresholds (21, 31, 51, and 70 cm³).

RESULTS

An ensemble of convolutional neural networks trained on DWI, ADC, and low b-value-weighted images produced the most accurate acute infarct segmentation over individual networks (P < .001). Automated volumes correlated with manually measured volumes (Spearman ρ = 0.91, P < .001) for the independent cohort. For the task of identifying patients with large lesion volumes, agreement between manual outlines and automated outlines was high (Cohen κ, 0.86-0.90; P < .001).

CONCLUSIONS

Acute infarcts are more accurately segmented using ensembles of convolutional neural networks trained with multiparametric maps than by using a single model trained with a solo map. Automated lesion segmentation has high agreement with manual techniques for identifying patients with large lesion volumes.

The accuracy of multiparametric magnetic resonance imaging (mpMRI) using PI-RADS v2 in disease upgrading on re-biopsy among patients with low-risk prostate cancer (PCa) on active surveillance (AS): A Brazilian perspective

5084

Background: The current selection criteria to AS is critical and it becomes even more relevant in Latin America, given the higher proportion of high risk cancers. The objective of this study is to analyze the accuracy of mpMRI using PI-RADS v2 in predicting the risk of upgrading on re-biopsy (UR) in men with low-risk PCa on AS. Methods: In this Institutional Review Board approved prospective study, patients with low-grade PCa selected for AS at our institution underwent mpMRI at least 6 weeks after the baseline 12-core random prostate biopsy (BSB), from March 2014 to March 2016. One blinded abdominal radiologist evaluated the exams regarding presence of dominant lesion and assigned the PI-RADS v2 score. MRI-target transrectal ultrasound-guided re-biopsies were performed in all patients within 6-12 months after the BSB. Standardized 12-core biopsy was performed and additional cores were taken from suspicious areas on mpMRI. Results: One hundred and nine patients were included, 93 (85.3%) patients had a dominant lesion on MRI. mpMRI were classified as PI-RADS 1, 2 or 3 in 67 (61.5%) patients, and as PI-RADS 4 or 5 in 42 (38.5%) patients. UR occurred in 42 (38.5%) patients. Out of these, 39 (92.8%) had radical prostatectomy, 6 (15.4%) T2a, 24 (61.5%) T2b, and 9 (23.1%) T3a. The diagnostic performance of mpMRI for PCa upgrading after re-biopsy was summarized in table 1. Patients assigned as PI-RADS 4 or 5 presented a significantly higher risk for UR compared with patients with PI-RADS 1, 2 or 3 (73.8% vs 16.4%, p < 0.001). Logistic regression analyses demonstrated that PI-RADS 4 or 5 remained a significant predictor of UR (OR: 37.366, p < 0.0001). Conclusions: We demonstrated in our population that mpMRI using PI-RADS v2 is a significant predictor for upgrading on re-biopsy in patients on AS and could be used to guide TRUS biopsy, increasing the accuracy of current clinical criteria for AS. [Table: see text]

[The effects of bromazepam on contingent negative variation and reaction time in a visuomotor task]

INTRODUCTION

Bromazepam is the second most commonly used benzodiazepine in Brazil. Psychophysiological research on this substance is still in its early stages.

AIM

To determine the neurotoxicity of bromazepam by examining reaction times (RT) and contingent negative variations (CNV).

SUBJECTS AND METHODS

Using a videogame produced in our laboratory for psychophysiological research purposes (Car Acquisition), 14 healthy volunteers (9 males) aged between 23 and 42 drove a vehicle along a road full of curves (i.e. distractors) while they had to respond to imperative stimuli (i.e. orders to press the button on the joystick) that were preceded by warnings (S1-S2-RM paradigm with distractor). We compared RT, amplitudes and latencies of the CNV at each of the three electrodes on the median line (Fz, Cz and Pz) one hour after random, double-blind and crossed administration of placebo (P), 3 mg of bromazepam (B3) or 6 mg of bromazepam (B6) on different days.

STATISTICS

one-way ANOVA and Post Hoc Scheffé.

RESULTS

No significant differences were observed in the RT. At Pz, the CNV amplitudes displayed significant differences for P, B3 and B6 (p = 0.006), and also for B3 and B6 (p = 0.018), with B6 > B3 = P. At Fz, a non-significant tendency (p = 0.074) suggested a difference between the latencies, shorter in B6 than in B3 (p = 0.098), both equivalent to placebo. The mean amplitudes ranged between 2.4 and 5.9 microV.

CONCLUSIONS

Behavioural and neurophysiological neurotoxicity was insignificant one hour after administration of a single 3 or 6 mg dose of bromazepam in healthy young adults. Low mean amplitudes were compatible with the interference from distractors and did not result in floor effect.

Is gastric ulceration different in normal and malnourished rats?

Protein malnutrition can adversely affect all tissues. The aim of the present study was to test the hypothesis that protein deprivation influences gastric ulcer formation, as well as metabolism and organ growth, in rats. In the present study, there was a significant reduction in the body and organ weight of rats fed a low-protein diet (P<0.001). Malnourished rats were less susceptible to ulceration of the gastric mucosa in ethanol and indomethacin models of acute gastric ulcers when compared with rats fed a normoproteic diet (17 % protein). Mucus production and prostaglandin E2 formation increased in malnourished rats, possibly explaining the lower number of acute ulcers in these animals. Pylorus ligature altered gastric juice composition (increased pH and gastric volume, and decreased total acid concentration) in the animal group fed a low-protein diet compared with the group fed a diet containing 17 % protein (P<0.05). The gastric mucosa was more damaged in malnourished rats than in normal rats evaluated for 14 d after acetic acid injection (P<0.001). Malnourished rats exhibited resistance to acute gastric lesions, owing to an increase in prostaglandin GE2 release and mucus secretion, which protected their gastric mucosa. This phenomenon was not seen in subchronic gastric ulceration.

In vivo incorporation of the intrinsic photolabel 4-thiouridine into Escherichia coli RNAs

The in vivo incorporation of the photoactivable uridine analogue 4-thiouridine into the RNAs of an Escherichia coli K12 pyrD strain has been optimised. s4Urd uptake in RNAs appears to be strikingly dependent upon the age of the preculture, i.e. the number of generations the cells have undergone immediately before dilution in the thiolation medium. Conditions have been set up where efficient RNA thiolation occurs in cells growing exponentially at 50 to 70% the rate of the control. The substitution level s4U/U is maximal after growth for 9 to 10 generations in the thiolation medium and reaches 17 +/- 3% in tRNA and bulk RNA. Most of ribosomal derived ribonucleoproteins, 65 +/- 5%, sediment as 70S ribosomes (s4U/U = 7 +/- 2%) on a high Mg2+ sucrose gradient. The thiolated RNAs were characterized by their migration on a thiol-specific affinity electrophoretic gel.

Substitution of uridine in vivo by the intrinsic photoactivable probe 4-thiouridine in Escherichia coli RNA. Its use for E. coli ribosome structural analysis

In vivo incorporation of the uridine-photoactivable analogue, 4-thiouridine, into the ribosomal RNA of an Escherichia coli pyrD strain has been demonstrated. It is highly dependent on the exogenous uridine and 4-thiouridine concentrations as well as on temperature. We have defined conditions allowing the substitution of 13 +/- 2% of the uridine residues in bulk RNA by 4-thiouridine. On a high-Mg2+ sucrose gradient, 33 +/- 3% of ribonucleic particles sediment as 70S ribosomes, the remaining being in the form of non-associated 50S and 30S particles containing immature rRNA. The thiolated 70S ribosomes tolerate a 4-5% substitution level (40 thiouridine molecules/particle). Surprisingly, 3-4% of ribosomal proteins, about two protein molecules/particle, were spontaneously covalently bound to 4-thiouridine-substituted rRNA. Specific 366-nm photoactivation increased this proportion to 10-12%, i.e. up to six or seven ribosomal protein molecules/particle. The photochemical cross-linking proceeds with apparent first-order kinetics with a quantum yield close to 5 X 10(-3). Although extensive photodynamic breakage of rRNA occurs under aerobic conditions, both the kinetics and yield of ribosomal protein cross-linking were independent of oxygenation conditions. The thiolated (4.5%) 70S ribosomes allowed the poly(U)-directed poly(Phe)synthesis at 48% the control rate. Photoactivation decreased this activity to 28% and 10% when performed under nitrogen and in aerated conditions, respectively.