Deep Learning in High-Resolution Anoscopy: Assessing the Impact of Staining and Therapeutic Manipulation on Automated Detection of Anal Cancer Precursors.

INTRODUCTION: High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell carcinoma (ASCC) precursors. Preliminary studies on the application of artificial intelligence (AI) models to this modality have revealed promising results. However, the impact of staining techniques and anal manipulation on the effectiveness of these algorithms has not been evaluated. We aimed to develop a deep learning system for automatic differentiation of high-grade squamous intraepithelial lesion vs low-grade squamous intraepithelial lesion in HRA images in different subsets of patients (nonstained, acetic acid, lugol, and after manipulation). METHODS: A convolutional neural network was developed to detect and differentiate high-grade and low-grade anal squamous intraepithelial lesions based on 27,770 images from 103 HRA examinations performed in 88 patients. Subanalyses were performed to evaluate the algorithm's performance in subsets of images without staining, acetic acid, lugol, and after manipulation of the anal canal. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve were calculated. RESULTS: The convolutional neural network achieved an overall accuracy of 98.3%. The algorithm had a sensitivity and specificity of 97.4% and 99.2%, respectively. The accuracy of the algorithm for differentiating high-grade squamous intraepithelial lesion vs low-grade squamous intraepithelial lesion varied between 91.5% (postmanipulation) and 100% (lugol) for the categories at subanalysis. The area under the curve ranged between 0.95 and 1.00. DISCUSSION: The introduction of AI to HRA may provide an accurate detection and differentiation of ASCC precursors. Our algorithm showed excellent performance at different staining settings. This is extremely important because real-time AI models during HRA examinations can help guide local treatment or detect relapsing disease.

From positron emission tomography to cell analysis of the 18-kDa Translocator Protein in mild traumatic brain injury.

Traumatic brain injury (TBI) leads to a deleterious neuroinflammation, originating from microglial activation. Monitoring microglial activation is an indispensable step to develop therapeutic strategies for TBI. In this study, we evaluated the use of the 18-kDa translocator protein (TSPO) in positron emission tomography (PET) and cellular analysis to monitor microglial activation in a mild TBI mouse model. TBI was induced on male Swiss mice. PET imaging analysis with [18F]FEPPA, a TSPO radiotracer, was performed at 1, 3 and 7 days post-TBI and flow cytometry analysis on brain at 1 and 3 days post-TBI. PET analysis showed no difference in TSPO expression between non-operated, sham-operated and TBI mice. Flow cytometry analysis demonstrated an increase in TSPO expression in ipsilateral brain 3 days post-TBI, especially in microglia, macrophages, lymphocytes and neutrophils. Moreover, microglia represent only 58.3% of TSPO+ cells in the brain. Our results raise the question of the use of TSPO radiotracer to monitor microglial activation after TBI. More broadly, flow cytometry results point the lack of specificity of TSPO for microglia and imply that microglia contribute to the overall increase in TSPO in the brain after TBI, but is not its only contributor.

Traumatic Brain Injury: An Age-Dependent View of Post-Traumatic Neuroinflammation and Its Treatment.

Traumatic brain injury (TBI) is a leading cause of death and disability all over the world. TBI leads to (1) an inflammatory response, (2) white matter injuries and (3) neurodegenerative pathologies in the long term. In humans, TBI occurs most often in children and adolescents or in the elderly, and it is well known that immune responses and the neuroregenerative capacities of the brain, among other factors, vary over a lifetime. Thus, age-at-injury can influence the consequences of TBI. Furthermore, age-at-injury also influences the pharmacological effects of drugs. However, the post-TBI inflammatory, neuronal and functional consequences have been mostly studied in experimental young adult animal models. The specificity and the mechanisms underlying the consequences of TBI and pharmacological responses are poorly understood in extreme ages. In this review, we detail the variations of these age-dependent inflammatory responses and consequences after TBI, from an experimental point of view. We investigate the evolution of microglial, astrocyte and other immune cells responses, and the consequences in terms of neuronal death and functional deficits in neonates, juvenile, adolescent and aged male animals, following a single TBI. We also describe the pharmacological responses to anti-inflammatory or neuroprotective agents, highlighting the need for an age-specific approach to the development of therapies of TBI.