Sotiras, Aristeidis

The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. The mean scores for the teams were calculated. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. The Dice score for the winning team was 0.65 ± 0.25. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space. The Dice scores and lesion detection rates of all algorithms diminished with decreasing tumor size, particularly for tumors smaller than 100 mm3. In conclusion, algorithms for BM segmentation require further refinement to balance high sensitivity in lesion detection with the minimization of false positives and negatives. The BraTS-METS 2023 challenge successfully curated well- annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied environments and providing the tools for future development of personalized volumetric reports to patients undergoing BM treatment.

AbstractBackgroundAlzheimer disease (AD) involves neurodegenerative disorders with progressive cognitive decline. Atypical presentations like Posterior Cortical Atrophy (PCA) and Logopenic Variant Primary Progressive Aphasia (lvPPA) exhibit distinct clinical profiles. PCA affects the posterior parietal and occipital lobes, causing visuospatial deficits, while lvPPA manifests as language impairment in the temporoparietal region. Understanding the biological underpinnings of these variants is crucial for deciphering AD’s heterogeneity.MethodParticipants diagnosed with AD dementia (n = 54, female = 25, Age: 75.23±6.52), PCA (n = 9, female = 8, Age: 62.78±7.21), and lvPPA (n = 6, female = 2, Age: 66.33±6.38) from the Knight Alzheimer Disease Research Center (Knight ADRC) underwent 18F‐AV‐1451 tau‐PET imaging. Tau deposition, along with nine biological properties, was mapped to the cortical surface (Figure 1A): gene expression, myelin, cortical thickness, sensorimotor association axis, evolutionary expansion, cerebral blood flow (CBF), cerebral blood volume (CBV), and cerebral metabolic rate of glucose (CMRglu) (Figure 1B). Correlation matrices and generalized linear models (GLMs) assessed relationships between tau accumulation and biological properties.ResultA correlation matrix (Figure 2A) shows significant positive associations (p<0.05) between evolutionary expansion patterns and tau accumulation in AD (r = 0.53), PCA (r = 0.29), and lvPPA (r = 0.56); and gene expression in PCA (r = 0.51). Conversely, strongest negative associations were observed in AD (r = ‐0.38, r = ‐0.15) and lvPPA (r = ‐0.18, r = ‐0.28) for CBF and myelin mapping, respectively, and in PCA (r = ‐0.25, ‐0.23) for cortical thickness and sensorimotor association axis. GLMs demonstrated significant relationships between cerebrovascular health and evolutionary expansion with tau measures across all groups. AD (r = ‐0.52) and PCA (r = ‐0.19) exhibited negative associations with gene expression and myelin mapping, respectively. Additionally, lvPPA (r = 0.39) displayed positive association with the sensorimotor association cortex.ConclusionResults elucidate distinct tau deposition patterns in AD, PCA, and lvPPA, providing insights into subtype‐specific pathophysiology. The correlation matrix and GLMs highlight the significance of evolutionary expansion and cerebrovascular health in tau accumulation. Associations underscore the complex interplay of gene expression, myelin mapping, and cortical thickness with tau pathology. Findings contribute to understanding heterogeneity within AD spectrum disorders, emphasizing the multifaceted nature of neurodegenerative processes. Further research promises refined diagnostic and therapeutic strategies tailored to distinct neurobiological profiles in AD, PCA, and lvPPA.

Accurate prediction of progression in subjects at risk of Alzheimer's disease is crucial for enrolling the right subjects in clinical trials. However, a prospective comparison of state-of-the-art algorithms for predicting disease onset and progression is currently lacking. We present the findings of "The Alzheimer's Disease Prediction Of Longitudinal Evolution" (TADPOLE) Challenge, which compared the performance of 92 algorithms from 33 international teams at predicting the future trajectory of 219 individuals at risk of Alzheimer's disease. Challenge participants were required to make a prediction, for each month of a 5-year future time period, of three key outcomes: clinical diagnosis, Alzheimer's Disease Assessment Scale Cognitive Subdomain (ADAS-Cog13), and total volume of the ventricles. The methods used by challenge participants included multivariate linear regression, machine learning methods such as support vector machines and deep neural networks, as well as disease progression models. No single submission was best at predicting all three outcomes. For clinical diagnosis and ventricle volume prediction, the best algorithms strongly outperform simple baselines in predictive ability. However, for ADAS-Cog13 no single submitted prediction method was significantly better than random guesswork. Two ensemble methods based on taking the mean and median over all predictions, obtained top scores on almost all tasks. Better than average performance at diagnosis prediction was generally associated with the additional inclusion of features from cerebrospinal fluid (CSF) samples and diffusion tensor imaging (DTI). On the other hand, better performance at ventricle volume prediction was associated with inclusion of summary statistics, such as the slope or maxima/minima of patient-specific biomarkers. On a limited, cross-sectional subset of the data emulating clinical trials, performance of the best algorithms at predicting clinical diagnosis decreased only slightly (2 percentage points) compared to the full longitudinal dataset. The submission system remains open via the website https://tadpole.grand-challenge.org, while TADPOLE SHARE (https://tadpole-share.github.io/) collates code for submissions. TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease. However, results call into question the usage of cognitive test scores for patient selection and as a primary endpoint in clinical trials.