Robust, credible, and interpretable AI-based histopathological prostate cancer grading.

Background: Prostate cancer (PCa) is among the most common cancers in men and its diagnosis requires the histopathological evaluation of biopsies by human experts. While several recent artificial intelligence-based (AI) approaches have reached human expert-level PCa grading, they often display significantly reduced performance on external datasets. This reduced performance can be caused by variations in sample preparation, for instance the staining protocol, section thickness, or scanner used. Another limiting factor of contemporary AI-based PCa grading is the prediction of ISUP grades, which leads to the perpetuation of human annotation errors. Methods: We developed the p rostate c ancer a ggressiveness index (PCAI), an AI-based PCa detection and grading framework that is trained on objective patient outcome, rather than subjective ISUP grades. We designed PCAI as a clinical application, containing algorithmic modules that offer robustness to data variation, medical interpretability, and a measure of prediction confidence. To train and evaluate PCAI, we generated a multicentric, retrospective, observational trial consisting of six cohorts with 25,591 patients, 83,864 images, and 5 years of median follow-up from 5 different centers and 3 countries. This includes a high-variance dataset of 8,157 patients and 28,236 images with variations in sample thickness, staining protocol, and scanner, allowing for the systematic evaluation and optimization of model robustness to data variation. The performance of PCAI was assessed on three external test cohorts from two countries, comprising 2,255 patients and 9,437 images. Findings: Using our high-variance datasets, we show how differences in sample processing, particularly slide thickness and staining time, significantly reduce the performance of AI-based PCa grading by up to 6.2 percentage points in the concordance index (C-index). We show how a select set of algorithmic improvements, including domain adversarial training, conferred robustness to data variation, interpretability, and a measure of credibility to PCAI. These changes lead to significant prediction improvement across two biopsy cohorts and one TMA cohort, systematically exceeding expert ISUP grading in C-index and AUROC by up to 22 percentage points. Interpretation: Data variation poses serious risks for AI-based histopathological PCa grading, even when models are trained on large datasets. Algorithmic improvements for model robustness, interpretability, credibility, and training on high-variance data as well as outcome-based severity prediction gives rise to robust models with above ISUP-level PCa grading performance.

Deep learning-based BMI inference from structural brain MRI reflects brain alterations following lifestyle intervention.

Obesity is associated with negative effects on the brain. We exploit Artificial Intelligence (AI) tools to explore whether differences in clinical measurements following lifestyle interventions in overweight population could be reflected in brain morphology. In the DIRECT-PLUS clinical trial, participants with criterion for metabolic syndrome underwent an 18-month lifestyle intervention. Structural brain MRIs were acquired before and after the intervention. We utilized an ensemble learning framework to predict Body-Mass Index (BMI) scores, which correspond to adiposity-related clinical measurements from brain MRIs. We revealed that patient-specific reduction in BMI predictions was associated with actual weight loss and was significantly higher in active diet groups compared to a control group. Moreover, explainable AI (XAI) maps highlighted brain regions contributing to BMI predictions that were distinct from regions associated with age prediction. Our DIRECT-PLUS analysis results imply that predicted BMI and its reduction are unique neural biomarkers for obesity-related brain modifications and weight loss.

A Real-Time Eye Tracking System for the Detection of Eye Blinks.

INTRODUCTION: This paper proposes an eye blink detection system that automatically detects eye blinks, which can be an indicator of fatigue or cognitive load, among others. As a key feature, the real-time capability of the system is being required to use it, for example, as a monitoring system for people in potentially critical situations (e.g., drivers or operators of heavy machinery). METHODS: The system uses the Viola-Jones algorithm for face detection and the median flow tracker to track the face in video sequences. Eye detection is implemented using face proportions, and template matching is used for blink detection. RESULTS: The resulting system processes 40-47 frames per second on default consumer hardware and achieves an accuracy of 80.33% and a precision of 85.22% in the evaluation. DISCUSSION: The proposed system shows promising results under ideal viewing conditions but has difficulty maintaining high precision during head movements. The proposed system could be integrated with various health-related assistance systems to monitor the individual's well-being in real time, as long as their head is observed from the front if possible.

Predicting brain-age from multimodal imaging data captures cognitive impairment.

The disparity between the chronological age of an individual and their brain-age measured based on biological information has the potential to offer clinically relevant biomarkers of neurological syndromes that emerge late in the lifespan. While prior brain-age prediction studies have relied exclusively on either structural or functional brain data, here we investigate how multimodal brain-imaging data improves age prediction. Using cortical anatomy and whole-brain functional connectivity on a large adult lifespan sample (N=2354, age 19-82), we found that multimodal data improves brain-based age prediction, resulting in a mean absolute prediction error of 4.29 years. Furthermore, we found that the discrepancy between predicted age and chronological age captures cognitive impairment. Importantly, the brain-age measure was robust to confounding effects: head motion did not drive brain-based age prediction and our models generalized reasonably to an independent dataset acquired at a different site (N=475). Generalization performance was increased by training models on a larger and more heterogeneous dataset. The robustness of multimodal brain-age prediction to confounds, generalizability across sites, and sensitivity to clinically-relevant impairments, suggests promising future application to the early prediction of neurocognitive disorders.

Higher body mass index in older adults is associated with lower gray matter volume: implications for memory performance.

Midlife obesity has been associated with increased dementia risk, yet reports on brain structure and function are mixed. We therefore assessed the effects of body mass index (BMI) on gray matter volume (GMV) and cognition in a well-characterized sample of community-dwelled older adults. GMV was measured using 3T-neuroimaging in 617 participants (258 women, 60-80 years, BMI 17-41 kg/m(2)). In addition, cognitive performance and various confounders including hypertension, diabetes, and apolipoprotein E genotype were assessed. A higher BMI correlated significantly with lower GMV in multiple brain regions, including (pre)frontal, temporal, insular and occipital cortex, thalamus, putamen, amygdala, and cerebellum, even after adjusting for confounders. In addition, lower GMV in prefrontal and thalamic areas partially mediated negative effects of (1) higher BMI and (2) higher age on memory performance. We here showed that a higher BMI in older adults is associated with widespread gray matter alterations, irrespective of obesity-related comorbidities and other confounders. Our results further indicate that a higher BMI induces structural alterations that translate into subtle impairments in memory performance in aging.

Cerebral autoregulation and brain networks in occlusive processes of the internal carotid artery.

Patients with unilateral occlusive processes of the internal carotid artery (ICA) show subtle cognitive deficits. Decline in cerebral autoregulation and in functional and structural integrity of brain networks have previously been reported in the affected hemisphere (AH). However, the association between cerebral autoregulation, brain networks, and cognition remains to be elucidated. Fourteen neurologically asymptomatic patients (65±11 years) with either ICA occlusion or high-grade ICA stenosis and 11 age-matched healthy controls (HC) (67±6 years) received neuropsychologic testing, transcranial Doppler sonography to assess cerebral autoregulation using vasomotor reactivity (VMR), and magnetic resonance imaging to probe white matter microstructure and resting-state functional connectivity (RSFC). Patients performed worse on memory and executive tasks when compared with controls. Vasomotor reactivity, white matter microstructure, and RSFC were lower in the AH of the patients when compared with the unaffected hemisphere and with controls. Lower VMR of the AH was associated with several ipsilateral clusters of lower white matter microstructure and lower bilateral RSFC in patients. No correlations were found between VMR and cognitive scores. In sum, impaired cerebral autoregulation was associated with reduced structural and functional connectivity in cerebral networks, indicating possible mechanisms by which severe unilateral occlusive processes of the ICA lead to cognitive decline.

COMT Val158Met Polymorphism Modulates Cognitive Effects of Dietary Intervention.

A common single nucleotide polymorphism (SNP) in the gene encoding catechol-O-methyltransferase (COMT), Val158Met, is thought to influence cognitive performance due to differences in prefrontal dopaminergic neurotransmission. Previous studies lend support for the hypothesis that the "at risk" genotype comprising two Val-alleles (low dopamine) might benefit more from plasticity-enhancing interventions than carriers of one or two Met-alleles. This study aimed to determine whether the response to dietary interventions, known to modulate cognition, is dependent on COMT genotype. Blood samples of 35 healthy elderly subjects (61.3 years ±8 SD; 19 women, 16 men, BMI: 28.2 kg/m(2) ±4 SD) were genotyped for COMT Val158Met by standard procedures (Val/Val = 6; Val/Met = 20; Met/Met = 9). Subjects had previously completed a randomized controlled trial investigating the effects of caloric restriction (CR) or enhancement of unsaturated fatty acids (UFA) on immediate and delayed verbal recognition memory. Homozygous Val/Val-carriers had significantly lower memory scores than Met-carriers at baseline (p < 0.001). Significant interactions of genotype and dietary intervention with regard to cognition were found: CR- and UFA enhancement-induced memory improvements of Val/Val-carriers were considerably greater than those of Met-carriers (ANOVA p's < 0.02). The current study shows for the first time that cognitive effects of dietary interventions are dependent on COMT Val158Met genotype. Our findings lend further support to the hypothesis that an "at risk" genotype might benefit more from plasticity-enhancing interventions than the "not at risk" genotype. This might help to develop individualized therapies in future research based on genetic background.