OBJECTIVES:Hearing impairment is strongly linked to cognitive decline, with individuals having mild-to-severe hearing loss estimated as having a twofold to fivefold increased risk of all-cause dementia. Given the lack of a cure for dementia, addressing conditions associated with increased dementia risk, like hearing loss, is essential. "Brain age," estimated from magnetic resonance imaging (MRI) scans, has emerged as a promising objective marker of brain health, aging, and dementia risk. This study aimed to evaluate brain age and the brain age gap (BAG) in patients with severe-to-profound hearing loss using MRI and explore correlations between these measures and clinical factors such as age, hearing loss onset, duration of auditory deprivation, and etiology. DESIGN:Prospective monocentric observational study conducted from January 2021 to September 2024 at a tertiary referral center. Sixty-nine patients aged over 18 with severe-to-profound hearing loss eligible for cochlear implantation were included based on national guidelines. All underwent a three-dimensional T1-weighted brain MRI before implantation to estimate brain MRI age and BAG in patients with severe-to-profound hearing loss. RESULTS:The cohort included 30 women and 39 men with a mean age of 64.07 ± 14.4 years. The mean estimated brain age was 69.57 ± 6.89 years, resulting in a mean BAG of 5.86 ± 8.94 years, indicating accelerated brain aging. Causes of hearing loss included congenital factors (17 patients), presbycusis (16), otosclerosis (8), trauma (8), chronic otitis (8), Ménière disease (7), sudden sensorineural hearing loss (4), and ototoxicity (2). Estimated brain age and BAG showed statistically significant differences based on patient etiology ( p = 0.04 and p = 0.03, respectively). Significant positive correlations were found between estimated brain age and chronological age ( ρ = 0.87; p < 0.001), hearing loss onset age ( ρ = 0.31; p = 0.01), and age at auditory rehabilitation ( ρ = 0.50; p < 0.001). BAG was negatively correlated with chronological age ( ρ = -0.94; p < 0.001), hearing loss onset age ( ρ = -0.35; p < 0.01), and age at rehabilitation ( ρ = -0.53; p < 0.001). CONCLUSIONS:Patients with severe-to-profound hearing loss had a higher estimated brain age and increased BAG, providing evidence of altered brain aging patterns in adults with hearing loss, which have been associated with increased dementia risk in prior studies. Early-onset hearing loss, prolonged auditory deprivation, and delayed rehabilitation were linked to increased BAG, emphasizing the need for timely intervention to mitigate potential vulnerability associated with altered brain aging patterns.

Neurodegenerative diseases like Alzheimer's are difficult to diagnose due to brain complexity and imaging variability. However, volumetric analysis tools, using reference curves, help detect abnormal brain atrophy and support diagnosis and monitoring. This study evaluates the robustness of three segmentation algorithms, AssemblyNet, FastSurfer and FreeSurfer, in constructing brain volume reference curves and detecting hippocampal atrophy. Using data from 3,730 cognitively normal subjects, we built reference curves and assessed robustness to magnetic field strength (1.5T vs. 3T) using four error metrics (sMAPE, sMSPE, wMAPE, sMdAPE) with bootstrap validation. We evaluated classification performance using hippocampal atrophy rates and HAVAs scores (Hippocampal-Amygdalo-Ventricular Atrophy scores). AssemblyNet shows the lowest errors across all robustness metrics. In contrast, FastSurfer and FreeSurfer exhibit greater deviations, indicating higher sensitivity to field strength variability. AssemblyNet provides consistent hippocampal atrophy rates across all reference models, despite slightly lower sensitivity, while FastSurfer and FreeSurfer display greater variability. Specificity ranges from 0.87 to 0.91 for AssemblyNet, compared to 0.76-0.93 for FastSurfer and 0.86-0.93 for FreeSurfer. Using the HAVAs score, all methods detect high atrophy rates in Alzheimer's patients. FastSurfer achieves the highest sensitivity (0.98), while AssemblyNet reaches the best specificity (0.95) and the highest balanced accuracy (0.91). This study underscores the importance of algorithm choice for reliable brain volumetric analysis in heterogeneous imaging environments. Among the methods tested, AssemblyNet stands out as both sensitive to Alzheimer's-related atrophy and robust to acquisition variability, making it a strong candidate when analyzing hippocampal volumes in large, multi-site datasets.

Background:Defining optimal adjuvant therapeutic strategies for older adult patients with breast cancer remains a challenge, given that this population is often overlooked and underserved in clinical research and decision-making tools. objectives:This study aimed to develop a prognostic and treatment guidance tool tailored to older adult patients using artificial intelligence (AI) and a combination of clinical and biological features. Methods:A retrospective analysis was conducted on data from women aged 70+ years with HER2-negative early-stage breast cancer treated at the French Léon Bérard Cancer Center between 1997 and 2016. Manifold learning and machine learning algorithms were applied to uncover complex data relationships and develop predictive models. Predictors included age, BMI, comorbidities, hemoglobin levels, lymphocyte counts, hormone receptor status, Scarff-Bloom-Richardson grade, tumor size, and lymph node involvement. The dimension reduction technique PaCMAP was used to map patient profiles into a 3D space, allowing comparison with similar cases to estimate prognoses and potential treatment benefits. Results:Out of 1229 initial patients, 793 were included after data refinement. The selected predictors demonstrated high predictive efficacy for 5-year mortality, with mean area under the curve scores of 0.81 for Random Forest Classification and 0.76 for Support Vector Classifier. The tool categorized patients into prognostic clusters and enabled the estimation of treatment outcomes, such as chemotherapy benefits. Unlike traditional models that focus on isolated factors, this AI-based approach integrates multiple clinical and biological features to generate a comprehensive biomedical profile. Conclusions:This study introduces a novel AI-driven prognostic tool for older adult patients with breast cancer, enhancing treatment guidance by leveraging advanced machine learning techniques. The model provides a more nuanced understanding of disease dynamics and therapeutic strategies, emphasizing the importance of personalized oncology care.

PURPOSE. Central vision loss in macular diseases severely affects visual perception and cognition, particularly scene recognition. A key question is whether observed impairments result solely from reduced input or reflect functional changes in spatial frequency processing. This study investigated how macular diseases affects this processing at both behavioral and brain levels. METHODS. We compared patients with macular diseases with age-matched controls using an artificial scotoma simulating each patient's central vision loss. Participants performed a scene categorization task with images filtered in high spatial frequencies (HSFs; fine details) or low spatial frequencies (LSFs; global shape). Patients fixated using their preferred retinal locus (PRL), whereas controls fixated on the location corresponding to the patient's fovea, within the artificial scotoma. Behavioral performance and functional magnetic resonance imaging (fMRI) responses were analyzed. RESULTS. Patients performed worse than the healthy controls for both HSF and LSF scenes, with a more pronounced deficit for HSFs. These deficits were associated with reduced activation in occipital cortex and in the parahippocampal place area (PPA), particularly for HSF scenes. In contrast, LSF processing was relatively preserved and accompanied by increased recruitment of higher-level cognitive and oculomotor areas in patients. CONCLUSIONS. These findings demonstrate that macular diseases leads to altered spatial frequency processing within residual vision itself, particularly affecting fine-detail analysis. This perceptual degradation is accompanied by functional brain reorganization supporting partial compensation. The results highlight the importance of considering both degraded input and adaptive mechanisms when designing rehabilitation strategies based on residual peripheral vision.

In medicine, abnormalities in quantitative metrics such as the volume reduction of one brain region of an individual versus a control group are often provided as deviations from so-called normal values. These normative reference values are traditionally calculated based on the quantitative values from a control group, which can be adjusted for relevant clinical co-variables, such as age or sex. However, these average normative values do not take into account the globality of the available quantitative information. For example, quantitative analysis of T1-weighted magnetic resonance images based on anatomical structure segmentation frequently includes over 100 cerebral structures in the quantitative reports, and these tend to be analyzed separately. In this study, we propose a global approach to personalized normative values for each brain structure using an unsupervised Artificial Intelligence technique known as generative manifold learning. We test the potential benefit of these personalized normative values in comparison with the more traditional average normative values on a population of patients with drug-resistant epilepsy operated for focal cortical dysplasia, as well as on a supplementary healthy group and on patients with Alzheimer’s disease.

BackgroundThe intricate three-dimensional anatomy of the inner ear presents significant challenges in diagnostic procedures and critical surgical interventions. Recent advancements in deep learning (DL), particularly convolutional neural networks (CNN), have shown promise for segmenting specific structures in medical imaging. This study aimed to train and externally validate an open-source U-net DL general model for automated segmentation of the inner ear from computed tomography (CT) scans, using quantitative and qualitative assessments.MethodsIn this multicenter study, we retrospectively collected a dataset of 271 CT scans to train an open-source U-net CNN model. An external set of 70 CT scans was used to evaluate the performance of the trained model. The model's efficacy was quantitatively assessed using the Dice similarity coefficient (DSC) and qualitatively assessed using a 4-level Likert score. For comparative analysis, manual segmentation served as the reference standard, with assessments made on both training and validation datasets, as well as stratified analysis of normal and pathological subgroups.ResultsThe optimized model yielded a mean DSC of 0.83 and achieved a Likert score of 1 in 42% of the cases, in conjunction with a significantly reduced processing time. Nevertheless, 27% of the patients received an indeterminate Likert score of 4. Overall, the mean DSCs were notably higher in the validation dataset than in the training dataset.ConclusionThis study supports the external validation of an open-source U-net model for the automated segmentation of the inner ear from CT scans.Relevance statementThis study optimized and assessed an open-source general deep learning model for automated segmentation of the inner ear using temporal CT scans, offering perspectives for application in clinical routine. The model weights, study datasets, and baseline model are worldwide accessible.Key PointsA general open-source deep learning model was trained for CT automated inner ear segmentation.The Dice similarity coefficient was 0.83 and a Likert score of 1 was attributed to 42% of automated segmentations.The influence of scanning protocols on the model performances remains to be assessed.

Introduction: Cochlear implants have advanced the management of severe to profound deafness. However, there is a strong disparity in hearing performance after implantation from one patient to another. Moreover, there are several advanced kinds of imaging assessment before cochlear implantation. Microstructural white fiber degeneration can be studied with Diffusion weighted MRI (DWI) or tractography of the central auditory pathways. Functional MRI (fMRI) allows us to evaluate brain function, and CT or MRI segmentation to better detect inner ear anomalies. Objective: This literature review aims to evaluate how helpful pre-implantation anatomic imaging can be to predict hearing rehabilitation outcomes in deaf patients. These techniques include DWI and fMRI of the central auditory pathways, and automated labyrinth segmentation by CT scan, cone beam CT and MRI. Design: This systematic review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Studies were selected by searching in PubMed and by checking the reference lists of relevant articles. Inclusion criteria were adults over 18, with unilateral or bilateral hearing loss, who had DWI acquisition or fMRI or CT/ Cone Beam CT/ MRI image segmentation. Results: After reviewing 172 articles, we finally included 51. Studies on DWI showed changes in the central auditory pathways affecting the white matter, extending to the primary and non-primary auditory cortices, even in sudden and mild hearing impairment. Hearing loss patients show a reorganization of brain activity in various areas, such as the auditory and visual cortices, as well as regions involved in language and emotions, according to fMRI studies. Deep Learning's automatic segmentation produces the best CT segmentation in just a few seconds. MRI segmentation is mainly used to evaluate fluid space of the inner ear and determine the presence of an endolymphatic hydrops. Conclusion: Before cochlear implantation, a DWI with tractography can evaluate the central auditory pathways up to the primary and non-primary auditory cortices. This data is then used to generate predictions on the auditory rehabilitation of patients. A CT segmentation with systematic 3D reconstruction allow a better evaluation of cochlear malformations and predictable difficulties during surgery. (c) 2023 Elsevier Masson SAS. All rights reserved.

We aimed to examine the white matter changes associated with lexical production difficulties, beginning in midlife with increased naming latencies. To delay lexical production decline, middle-aged adults may rely on domain-general and language-specific compensatory mechanisms proposed by the LARA model (Lexical Access and Retrieval in Aging). However, the white matter changes supporting these mechanisms remains largely unknown. Using data from the CAMCAN cohort, we employed an unsupervised and data-driven methodology to examine the relationships between diffusion-weighted imaging and lexical production. Our findings indicate that midlife is marked by alterations in brain structure within distributed dorsal, ventral, and anterior cortico-subcortical networks, marking the onset of lexical production decline around ages 53-54. Middle-aged adults may initially adopt a "semantic strategy" to compensate for lexical production challenges, but this strategy seems compromised later (ages 55-60) as semantic control declines. These insights underscore the interplay between domain-general and language-specific processes in the trajectory of lexical production performance in healthy aging and hint at potential biomarkers for language-related neurodegenerative pathologies.

A 14-year-old girl initially presented to a pediatric gastroenterology office with a 1-month history of right upper quadrant abdominal pain, which radiated to the right shoulder and back. Her pain was worse after heavy meals and with deep breaths. She reported anorexia, fatigue, dyspnea while playing soccer, and a 5-pound weight loss. She denied any fevers, cough, or changes in her bowel habits.

Les démences fronto-temporales (DFT) sont des maladies rares et hétérogènes cliniquement, qui sont liées soit à un dépôt de protéines Tau dans le cerveau, soit à un dépôt de protéines TDP43. A l'heure actuelle, seuls les tests de dépistage génétique permettent d'obtenir inconstamment des arguments en faveur d'un type de protéine cérébrale causale. Nous testons ici l'intérêt d'une intelligence artificielle (IA) non supervisée pour différencier les deux sous-types d'atteinte biologique, à partir d'IRM en pondération T1. Nous avons rétrospectivement entrainé notre IA avec 111 patients venant de la base de données publique 4RTNI (61 femmes, âge moyen : 68,4 ans) pour les tauopathies, et 144 patients venant de la base de données NIFD pour les maladies à protéines TDP43.Le volume du cerveau a été parcellisé en 132 régions à l'aide de réseaux de neurones du logiciel AssemblyNet(1). Des jumeaux numériques des patients DFT ont ensuite été généré puis les anomalies détectées grâce à ces jumeaux ont été projeté dans un espace réduit (2,3,4). Nous avons finalement appliqué l'algorithme préalablement entrainé sur 52 patients (23 femmes, âge moyen : 65.15 ans) issu d'une cohorte externe Australienne, ayant bénéficiés de biopsies post mortem permettant de détecter la présence de protéines Tau ou TDP. L'entrainement préalable de l'algorithme non supervisé permet de détecter deux grands clusters de DFT, l'un plus lié à la base de données 4RTNI, l'autre à la base NIFD. L'utilisation d'un classifier sur les données de validation externe permet de catégoriser les patients avec une précision de 82% sur la base externe. L'utilisation de jumeaux numériques basé sur de l'IRM permet de distinguer le type de protéinopathie impliqué dans les DFT avec une bonne précision diagnostic faisant envisager de pouvoir cibler les protéines adéquates lors des essais thérapeutiques.

Background and purpose: Approximately 65% of moderate-to-severe traumatic brain injury (m-sTBI) patients present with poor long-term behavioural outcomes, which can significantly impair activities of daily living. Numerous diffusion-weighted MRI studies have linked these poor outcomes to decreased white matter integrity of several commissural tracts, association fibres and projection fibres in the brain. However, most studies have focused on group-based analyses, which are unable to deal with the substantial between-patient heterogeneity in m-sTBI. As a result, there is increasing interest and need in conducting individualised neuroimaging analyses. Materials and methods: Here, we generated a detailed subject-specific characterisation of microstructural orga-nisation of white matter tracts in 5 chronic patients with m-sTBI (29 - 49y, 2 females), presented as a proof-of -concept. We developed an imaging analysis framework using fixel-based analysis and TractLearn to determine whether the values of fibre density of white matter tracts at the individual patient level deviate from the healthy control group (n = 12, 8F, Mage = 35.7y, age range 25 - 64y). Results: Our individualised analysis revealed unique white matter profiles, confirming the heterogenous nature of m-sTBI and the need of individualised profiles to properly characterise the extent of injury. Future studies incorporating clinical data, as well as utilising larger reference samples and examining the test-retest reliability of the fixel-wise metrics are warranted. Conclusions: Individualised profiles may assist clinicians in tracking recovery and planning personalised training programs for chronic m-sTBI patients, which is necessary to achieve optimal behavioural outcomes and improved quality of life.

The prediction of the therapeutic intensity level (TIL) for severe traumatic brain injury (TBI) patients at the early phase of intensive care unit (ICU) remains challenging. Computed tomography images are still manually quantified and then underexploited. In this study, we develop an artificial intelligence-based tool to segment brain lesions on admission CT-scan and predict TIL within the first week in the ICU. A cohort of 29 head injured patients (87 CT-scans; Dataset1) was used to localize (using a structural atlas), segment (manually or automatically with or without transfer learning) 4 or 7 types of lesions and use these metrics to train classifiers, evaluated with AUC on a nested cross-validation, to predict requirements for TIL sum of 11 points or more during the 8 first days in ICU. The validation of the performances of both segmentation and classification tasks was done with Dice and accuracy scores on a sub-dataset of Dataset1 (internal validation) and an external dataset of 12 TBI patients (12 CT-scans; Dataset2). Automatic 4-class segmentation (without transfer learning) was not able to correctly predict the apparition of a day of extreme TIL (AUC = 60 ± 23%). In contrast, manual quantification of volumes of 7 lesions and their spatial location provided a significantly better prediction power (AUC = 89 ± 17%). Transfer learning significantly improved the automatic 4-class segmentation (DICE scores 0.63 vs 0.34) and trained more efficiently a 7-class convolutional neural network (DICE = 0.64). Both validations showed that segmentations based on transfer learning were able to predict extreme TIL with better or equivalent accuracy (83%) as those made with manual segmentations. Our automatic characterization (volume, type and spatial location) of initial brain lesions observed on CT-scan, publicly available on a dedicated computing platform, could predict requirements for high TIL during the first 8 days after severe TBI. Transfer learning strategies may improve the accuracy of CNN-based segmentation models. Trial registrations Radiomic-TBI cohort; NCT04058379, first posted: 15 august 2019; Radioxy-TC cohort; Health Data Hub index F20220207212747, first posted: 7 February 2022.

The majority of intracranial expansive lesions are tumors. However, a wide range of lesions can mimic neoplastic pathology. Differentiating pseudotumoral lesions from brain tumors is crucial to patient management. This article describes the most common intracranial pseudotumors, with a focus on the imaging features that serve as clues to detect pseudotumors.

Purpose: The purpose of this study was to compare the degree of perilymphatic enhancement between 4 hour post-contrast constant flip angle three-dimensional fluid attenuated inversion recovery (3D-FLAIR) images obtained with short repetition time (TR) and those obtained with long TR.Materials and methods: This single-center, prospective study included patients who underwent MRI of the inner ear with heavily T2-weighted sequence, 3D-FLAIR sequence with a "short" TR of 10,000 ms (s3D-FLAIR) and with a "long" TR of 16,000 ms (l3D-FLAIR). Signal intensity ratio (SIR) and contrast-to-noise ratio (CNR) obtained with s3D-FLAIR and l3D-FLAIR were quantitatively assessed using region of interest (ROI) method and compared. The morphology of the endolymphatic space on both sequences was also evaluated.Results: From March 2020 to July 2020, 20 consecutive patients were enrolled (9 women and 11 men; mean age, 52.1 +/- 14.5 [SD] years; age range: 29-75 years). On l3D-FLAIR images, mean SIR (21.1 +/- 8.8 [SD]; range: 7.6-46.1) was significantly greater than that on s3D-FLAIR images (15.7 +/- 6.7 [SD]; range: 5.9-33.4) (P < 0.01). On l3D-FLAIR images, mean CNR (17 +/- 8.5 [SD]; range: 2-40) was significantly greater than that on s3D-FLAIR images (12 +/- 6.3 [SD]; range: 3.2-29.8) (P < 0.01). Kappa value for inter-rater agreement for endolymphatic hydrops, vestibular atelectasis and perilymphatic fistula were 0.93 (95% CI: 0.74-1), 1 (95% CI: 0.85-1) and 1 (95% CI: 0.85-1) respectively.Conclusion: This study demonstrates that the sensitivity of 3D-FLAIR sequences to low concentration gadolinium in the perilymphatic space is improved by elongation of the TR, with SIR and CNR increased by +34.4% and +41.3% respectively.(c) 2021 Societe francaise de radiologie. Published by Elsevier Masson SAS. All rights reserved.