Search

Convolutional neural networks (CNNs) have shown great effectiveness in medical image segmentation. However, they may be limited in modeling large inter-subject variations in organ shapes and sizes and exploiting global long-range contextual information. This is because CNNs typically employ convolutions with fixed-sized local receptive fields and lack the mechanisms to utilize global information. To address these limitations, we developed Dynamic Multi-Resolution Convolution (DMRC) and Dynamic Multi-Scale Convolution (DMSC) modules. Both modules enhance the representation capabilities of single convolutions to capture varying scaled features and global contextual information. This is achieved in the DMRC module by employing a convolutional filter on images with different resolutions and subsequently utilizing dynamic mechanisms to model global inter-dependencies between features. In contrast, the DMSC module extracts features at different scales by employing convolutions with different kernel sizes and utilizing dynamic mechanisms to extract global contextual information. The utilization of convolutions with different kernel sizes in the DMSC module may increase computational complexity. To lessen this burden, we propose to use a lightweight design for convolution layers with a large kernel size. Thus, DMSC and DMRC modules are designed as lightweight drop-in replacements for single convolutions, and they can be easily integrated into general CNN architectures for end-to-end training. The segmentation network was proposed by incorporating our DMSC and DMRC modules into a standard U-Net architecture, termed Dynamic Multi-scale and Multi-resolution Convolution network (DMC-Net). The results demonstrate that our proposed DMSC and DMRC can enhance the representation capabilities of single convolutions and improve segmentation accuracy., Comment: 14 pages, 4 figures

Multiple instance learning (MIL) stands as a powerful approach in weakly supervised learning, regularly employed in histological whole slide image (WSI) classification for detecting tumorous lesions. However, existing mainstream MIL methods focus on modeling correlation between instances while overlooking the inherent diversity among instances. However, few MIL methods have aimed at diversity modeling, which empirically show inferior performance but with a high computational cost. To bridge this gap, we propose a novel MIL aggregation method based on diverse global representation (DGR-MIL), by modeling diversity among instances through a set of global vectors that serve as a summary of all instances. First, we turn the instance correlation into the similarity between instance embeddings and the predefined global vectors through a cross-attention mechanism. This stems from the fact that similar instance embeddings typically would result in a higher correlation with a certain global vector. Second, we propose two mechanisms to enforce the diversity among the global vectors to be more descriptive of the entire bag: (i) positive instance alignment and (ii) a novel, efficient, and theoretically guaranteed diversification learning paradigm. Specifically, the positive instance alignment module encourages the global vectors to align with the center of positive instances (e.g., instances containing tumors in WSI). To further diversify the global representations, we propose a novel diversification learning paradigm leveraging the determinantal point process. The proposed model outperforms the state-of-the-art MIL aggregation models by a substantial margin on the CAMELYON-16 and the TCGA-lung cancer datasets. The code is available at \url{https://github.com/ChongQingNoSubway/DGR-MIL}., Comment: Accepted to ECCV 2024

Since its introduction, UNet has been leading a variety of medical image segmentation tasks. Although numerous follow-up studies have also been dedicated to improving the performance of standard UNet, few have conducted in-depth analyses of the underlying interest pattern of UNet in medical image segmentation. In this paper, we explore the patterns learned in a UNet and observe two important factors that potentially affect its performance: (i) irrelative feature learned caused by asymmetric supervision; (ii) feature redundancy in the feature map. To this end, we propose to balance the supervision between encoder and decoder and reduce the redundant information in the UNet. Specifically, we use the feature map that contains the most semantic information (i.e., the last layer of the decoder) to provide additional supervision to other blocks to provide additional supervision and reduce feature redundancy by leveraging feature distillation. The proposed method can be easily integrated into existing UNet architecture in a plug-and-play fashion with negligible computational cost. The experimental results suggest that the proposed method consistently improves the performance of standard UNets on four medical image segmentation datasets. The code is available at \url{https://github.com/ChongQingNoSubway/SelfReg-UNet}, Comment: Accepted as a conference paper to 2024 MICCAI

Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully account for the sparsity and locality of patterns in time series data (e.g., diseases-related anomalous points in ECG). To address this challenge, we formally reformulate MTSC as a weakly supervised problem, introducing a novel multiple-instance learning (MIL) framework for better localization of patterns of interest and modeling time dependencies within time series. Our novel approach, TimeMIL, formulates the temporal correlation and ordering within a time-aware MIL pooling, leveraging a tokenized transformer with a specialized learnable wavelet positional token. The proposed method surpassed 26 recent state-of-the-art methods, underscoring the effectiveness of the weakly supervised TimeMIL in MTSC. The code will be available at https://github.com/xiwenc1/TimeMIL., Comment: Accepted by ICML2024

INTRODUCTION: Previous studies have applied normative modeling on a single neuroimaging modality to investigate Alzheimer Disease (AD) heterogeneity. We employed a deep learning-based multimodal normative framework to analyze individual-level variation across ATN (amyloid-tau-neurodegeneration) imaging biomarkers. METHODS: We selected cross-sectional discovery (n = 665) and replication cohorts (n = 430) with available T1-weighted MRI, amyloid and tau PET. Normative modeling estimated individual-level abnormal deviations in amyloid-positive individuals compared to amyloid-negative controls. Regional abnormality patterns were mapped at different clinical group levels to assess intra-group heterogeneity. An individual-level disease severity index (DSI) was calculated using both the spatial extent and magnitude of abnormal deviations across ATN. RESULTS: Greater intra-group heterogeneity in ATN abnormality patterns was observed in more severe clinical stages of AD. Higher DSI was associated with worse cognitive function and increased risk of disease progression. DISCUSSION: Subject-specific abnormality maps across ATN reveal the heterogeneous impact of AD on the brain., Comment: Under review in Alzheimer's & Dementia

In the past decades, deep neural networks, particularly convolutional neural networks, have achieved state-of-the-art performance in a variety of medical image segmentation tasks. Recently, the introduction of the vision transformer (ViT) has significantly altered the landscape of deep segmentation models. There has been a growing focus on ViTs, driven by their excellent performance and scalability. However, we argue that the current design of the vision transformer-based UNet (ViT-UNet) segmentation models may not effectively handle the heterogeneous appearance (e.g., varying shapes and sizes) of objects of interest in medical image segmentation tasks. To tackle this challenge, we present a structured approach to introduce spatially dynamic components to the ViT-UNet. This adaptation enables the model to effectively capture features of target objects with diverse appearances. This is achieved by three main components: \textbf{(i)} deformable patch embedding; \textbf{(ii)} spatially dynamic multi-head attention; \textbf{(iii)} deformable positional encoding. These components were integrated into a novel architecture, termed AgileFormer. AgileFormer is a spatially agile ViT-UNet designed for medical image segmentation. Experiments in three segmentation tasks using publicly available datasets demonstrated the effectiveness of the proposed method. The code is available at \href{https://github.com/sotiraslab/AgileFormer}{https://github.com/sotiraslab/AgileFormer}.

Hierarchical transformers have achieved significant success in medical image segmentation due to their large receptive field and capabilities of effectively leveraging global long-range contextual information. Convolutional neural networks (CNNs) can also deliver a large receptive field by using large kernels, enabling them to achieve competitive performance with fewer model parameters. However, CNNs incorporated with large convolutional kernels remain constrained in adaptively capturing multi-scale features from organs with large variations in shape and size due to the employment of fixed-sized kernels. Additionally, they are unable to utilize global contextual information efficiently. To address these limitations, we propose Dynamic Large Kernel (DLK) and Dynamic Feature Fusion (DFF) modules. The DLK module employs multiple large kernels with varying kernel sizes and dilation rates to capture multi-scale features. Subsequently, a dynamic selection mechanism is utilized to adaptively highlight the most important spatial features based on global information. Additionally, the DFF module is proposed to adaptively fuse multi-scale local feature maps based on their global information. We integrate DLK and DFF in a hierarchical transformer architecture to develop a novel architecture, termed D-Net. D-Net is able to effectively utilize a multi-scale large receptive field and adaptively harness global contextual information. Extensive experimental results demonstrate that D-Net outperforms other state-of-the-art models in the two volumetric segmentation tasks, including abdominal multi-organ segmentation and multi-modality brain tumor segmentation. Our code is available at https://github.com/sotiraslab/DLK., Comment: 18 pages, 8 figures, 9 tables

U-Net has been widely used for segmenting abdominal organs, achieving promising performance. However, when it is used for multi-organ segmentation, first, it may be limited in exploiting global long-range contextual information due to the implementation of standard convolutions. Second, the use of spatial-wise downsampling (e.g., max pooling or strided convolutions) in the encoding path may lead to the loss of deformable or discriminative details. Third, features upsampled from the higher level are concatenated with those that persevered via skip connections. However, repeated downsampling and upsampling operations lead to misalignments between them and their concatenation degrades segmentation performance. To address these limitations, we propose Dynamically Calibrated Convolution (DCC), Dynamically Calibrated Downsampling (DCD), and Dynamically Calibrated Upsampling (DCU) modules, respectively. The DCC module can utilize global inter-dependencies between spatial and channel features to calibrate these features adaptively. The DCD module enables networks to adaptively preserve deformable or discriminative features during downsampling. The DCU module can dynamically align and calibrate upsampled features to eliminate misalignments before concatenations. We integrated the proposed modules into a standard U-Net, resulting in a new architecture, termed Dynamic U-Net. This architectural design enables U-Net to dynamically adjust features for different organs. We evaluated Dynamic U-Net in two abdominal multi-organ segmentation benchmarks. Dynamic U-Net achieved statistically improved segmentation accuracy compared with standard U-Net. Our code is available at https://github.com/sotiraslab/DynamicUNet., Comment: 11 pages, 3 figures, 2 tables

Normative models in neuroimaging learn the brain patterns of healthy population distribution and estimate how disease subjects like Alzheimer's Disease (AD) deviate from the norm. Existing variational autoencoder (VAE)-based normative models using multimodal neuroimaging data aggregate information from multiple modalities by estimating product or averaging of unimodal latent posteriors. This can often lead to uninformative joint latent distributions which affects the estimation of subject-level deviations. In this work, we addressed the prior limitations by adopting the Mixture-of-Product-of-Experts (MoPoE) technique which allows better modelling of the joint latent posterior. Our model labelled subjects as outliers by calculating deviations from the multimodal latent space. Further, we identified which latent dimensions and brain regions were associated with abnormal deviations due to AD pathology., Comment: IEEE Internattional Symposium in Biomedical Imaging 2024

Multiple Instance Learning (MIL) has been widely used in weakly supervised whole slide image (WSI) classification. Typical MIL methods include a feature embedding part, which embeds the instances into features via a pre-trained feature extractor, and an MIL aggregator that combines instance embeddings into predictions. Most efforts have typically focused on improving these parts. This involves refining the feature embeddings through self-supervised pre-training as well as modeling the correlations between instances separately. In this paper, we proposed a sparsely coding MIL (SC-MIL) method that addresses those two aspects at the same time by leveraging sparse dictionary learning. The sparse dictionary learning captures the similarities of instances by expressing them as sparse linear combinations of atoms in an over-complete dictionary. In addition, imposing sparsity improves instance feature embeddings by suppressing irrelevant instances while retaining the most relevant ones. To make the conventional sparse coding algorithm compatible with deep learning, we unrolled it into a sparsely coded module leveraging deep unrolling. The proposed SC module can be incorporated into any existing MIL framework in a plug-and-play manner with an acceptable computational cost. The experimental results on multiple datasets demonstrated that the proposed SC module could substantially boost the performance of state-of-the-art MIL methods. The codes are available at \href{https://github.com/sotiraslab/SCMIL.git}{https://github.com/sotiraslab/SCMIL.git}.

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. 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. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space.The BraTS-METS 2023 challenge successfully curated well-annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied clinical environments and providing personalized volumetric reports to patients undergoing BM treatment.

Learning rich data representations from unlabeled data is a key challenge towards applying deep learning algorithms in downstream tasks. Several variants of variational autoencoders (VAEs) have been proposed to learn compact data representations by encoding high-dimensional data in a lower dimensional space. Two main classes of VAEs methods may be distinguished depending on the characteristics of the meta-priors that are enforced in the representation learning step. The first class of methods derives a continuous encoding by assuming a static prior distribution in the latent space. The second class of methods learns instead a discrete latent representation using vector quantization (VQ) along with a codebook. However, both classes of methods suffer from certain challenges, which may lead to suboptimal image reconstruction results. The first class suffers from posterior collapse, whereas the second class suffers from codebook collapse. To address these challenges, we introduce a new VAE variant, termed sparse coding-based VAE with learned ISTA (SC-VAE), which integrates sparse coding within variational autoencoder framework. The proposed method learns sparse data representations that consist of a linear combination of a small number of predetermined orthogonal atoms. The sparse coding problem is solved using a learnable version of the iterative shrinkage thresholding algorithm (ISTA). Experiments on two image datasets demonstrate that our model achieves improved image reconstruction results compared to state-of-the-art methods. Moreover, we demonstrate that the use of learned sparse code vectors allows us to perform downstream tasks like image generation and unsupervised image segmentation through clustering image patches., Comment: 21 pages, 23 figures, and 4 tables

Isocitrate dehydrogenase (IDH) mutation and 1p/19q codeletion status are important prognostic markers for glioma. Currently, they are determined using invasive procedures. Our goal was to develop artificial intelligence-based methods to non-invasively determine these molecular alterations from MRI. For this purpose, pre-operative MRI scans of 2648 patients with gliomas (grade II-IV) were collected from Washington University School of Medicine (WUSM; n = 835) and publicly available datasets viz. Brain Tumor Segmentation (BraTS; n = 378), LGG 1p/19q (n = 159), Ivy Glioblastoma Atlas Project (Ivy GAP; n = 41), The Cancer Genome Atlas (TCGA; n = 461), and the Erasmus Glioma Database (EGD; n = 774). A 2.5D hybrid convolutional neural network was proposed to simultaneously localize the tumor and classify its molecular status by leveraging imaging features from MR scans and prior knowledge features from clinical records and tumor location. The models were tested on one internal (TCGA) and two external (WUSM and EGD) test sets. For IDH, the best-performing model achieved areas under the receiver operating characteristic (AUROC) of 0.925, 0.874, 0.933 and areas under the precision-recall curves (AUPRC) of 0.899, 0.702, 0.853 on the internal, WUSM, and EGD test sets, respectively. For 1p/19q, the best model achieved AUROCs of 0.782, 0.754, 0.842, and AUPRCs of 0.588, 0.713, 0.782, on those three data-splits, respectively. The high accuracy of the model on unseen data showcases its generalization capabilities and suggests its potential to perform a 'virtual biopsy' for tailoring treatment planning and overall clinical management of gliomas.

Efforts to utilize growing volumes of clinical imaging data to generate tumor evaluations continue to require significant manual data wrangling owing to the data heterogeneity. Here, we propose an artificial intelligence-based solution for the aggregation and processing of multisequence neuro-oncology MRI data to extract quantitative tumor measurements. Our end-to-end framework i) classifies MRI sequences using an ensemble classifier, ii) preprocesses the data in a reproducible manner, iii) delineates tumor tissue subtypes using convolutional neural networks, and iv) extracts diverse radiomic features. Moreover, it is robust to missing sequences and adopts an expert-in-the-loop approach, where the segmentation results may be manually refined by radiologists. Following the implementation of the framework in Docker containers, it was applied to two retrospective glioma datasets collected from the Washington University School of Medicine (WUSM; n = 384) and the M.D. Anderson Cancer Center (MDA; n = 30) comprising preoperative MRI scans from patients with pathologically confirmed gliomas. The scan-type classifier yielded an accuracy of over 99%, correctly identifying sequences from 380/384 and 30/30 sessions from the WUSM and MDA datasets, respectively. Segmentation performance was quantified using the Dice Similarity Coefficient between the predicted and expert-refined tumor masks. Mean Dice scores were 0.882 ($\pm$0.244) and 0.977 ($\pm$0.04) for whole tumor segmentation for WUSM and MDA, respectively. This streamlined framework automatically curated, processed, and segmented raw MRI data of patients with varying grades of gliomas, enabling the curation of large-scale neuro-oncology datasets and demonstrating a high potential for integration as an assistive tool in clinical practice.

Registration of longitudinal brain MRI scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been progress in developing general-purpose medical image registration techniques, they have not yet attained the requisite precision and reliability for this task, highlighting its inherent complexity. Here we describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge, as the first public benchmark environment for deformable registration algorithms focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a diffuse brain glioma. The BraTS-Reg data comprise de-identified multi-institutional multi-parametric MRI (mpMRI) scans, curated for size and resolution according to a canonical anatomical template, and divided into training, validation, and testing sets. Clinical experts annotated ground truth (GT) landmark points of anatomical locations distinct across the temporal domain. Quantitative evaluation and ranking were based on the Median Euclidean Error (MEE), Robustness, and the determinant of the Jacobian of the displacement field. The top-ranked methodologies yielded similar performance across all evaluation metrics and shared several methodological commonalities, including pre-alignment, deep neural networks, inverse consistency analysis, and test-time instance optimization per-case basis as a post-processing step. The top-ranked method attained the MEE at or below that of the inter-rater variability for approximately 60% of the evaluated landmarks, underscoring the scope for further accuracy and robustness improvements, especially relative to human experts. The aim of BraTS-Reg is to continue to serve as an active resource for research, with the data and online evaluation tools accessible at https://bratsreg.github.io/.

Late-life depression (LLD) is characterized by considerable heterogeneity in clinical manifestation. Unraveling such heterogeneity would aid in elucidating etiological mechanisms and pave the road to precision and individualized medicine. We sought to delineate, cross-sectionally and longitudinally, disease-related heterogeneity in LLD linked to neuroanatomy, cognitive functioning, clinical symptomatology, and genetic profiles. Multimodal data from a multicentre sample (N=996) were analyzed. A semi-supervised clustering method (HYDRA) was applied to regional grey matter (GM) brain volumes to derive dimensional representations. Two dimensions were identified, which accounted for the LLD-related heterogeneity in voxel-wise GM maps, white matter (WM) fractional anisotropy (FA), neurocognitive functioning, clinical phenotype, and genetics. Dimension one (Dim1) demonstrated relatively preserved brain anatomy without WM disruptions relative to healthy controls. In contrast, dimension two (Dim2) showed widespread brain atrophy and WM integrity disruptions, along with cognitive impairment and higher depression severity. Moreover, one de novo independent genetic variant (rs13120336) was significantly associated with Dim 1 but not with Dim 2. Notably, the two dimensions demonstrated significant SNP-based heritability of 18-27% within the general population (N=12,518 in UKBB). Lastly, in a subset of individuals having longitudinal measurements, Dim2 demonstrated a more rapid longitudinal decrease in GM and brain age, and was more likely to progress to Alzheimers disease, compared to Dim1 (N=1,413 participants and 7,225 scans from ADNI, BLSA, and BIOCARD datasets).

Normative modelling is an emerging method for understanding the underlying heterogeneity within brain disorders like Alzheimer Disease (AD) by quantifying how each patient deviates from the expected normative pattern that has been learned from a healthy control distribution. Since AD is a multifactorial disease with more than one biological pathways, multimodal magnetic resonance imaging (MRI) neuroimaging data can provide complementary information about the disease heterogeneity. However, existing deep learning based normative models on multimodal MRI data use unimodal autoencoders with a single encoder and decoder that may fail to capture the relationship between brain measurements extracted from different MRI modalities. In this work, we propose multi-modal variational autoencoder (mmVAE) based normative modelling framework that can capture the joint distribution between different modalities to identify abnormal brain structural patterns in AD. Our multi-modal framework takes as input Freesurfer processed brain region volumes from T1-weighted (cortical and subcortical) and T2-weighed (hippocampal) scans of cognitively normal participants to learn the morphological characteristics of the healthy brain. The estimated normative model is then applied on Alzheimer Disease (AD) patients to quantify the deviation in brain volumes and identify the abnormal brain structural patterns due to the effect of the different AD stages. Our experimental results show that modeling joint distribution between the multiple MRI modalities generates deviation maps that are more sensitive to disease staging within AD, have a better correlation with patient cognition and result in higher number of brain regions with statistically significant deviations compared to a unimodal baseline model with all modalities concatenated as a single input., Comment: Medical Imaging Meets NeurIPS workshop in NeurIPS 2022

Neuroimaging biomarkers that distinguish between typical brain aging and Alzheimer's disease (AD) are valuable for determining how much each contributes to cognitive decline. Machine learning models can derive multi-variate brain change patterns related to the two processes, including the SPARE-AD (Spatial Patterns of Atrophy for Recognition of Alzheimer's Disease) and SPARE-BA (of Brain Aging) investigated herein. However, substantial overlap between brain regions affected in the two processes confounds measuring them independently. We present a methodology toward disentangling the two. T1-weighted MRI images of 4,054 participants (48-95 years) with AD, mild cognitive impairment (MCI), or cognitively normal (CN) diagnoses from the iSTAGING (Imaging-based coordinate SysTem for AGIng and NeurodeGenerative diseases) consortium were analyzed. First, a subset of AD patients and CN adults were selected based purely on clinical diagnoses to train SPARE-BA1 (regression of age using CN individuals) and SPARE-AD1 (classification of CN versus AD). Second, analogous groups were selected based on clinical and molecular markers to train SPARE-BA2 and SPARE-AD2: amyloid-positive (A+) AD continuum group (consisting of A+AD, A+MCI, and A+ and tau-positive CN individuals) and amyloid-negative (A-) CN group. Finally, the combined group of the AD continuum and A-/CN individuals was used to train SPARE-BA3, with the intention to estimate brain age regardless of AD-related brain changes. Disentangled SPARE models derived brain patterns that were more specific to the two types of the brain changes. Correlation between the SPARE-BA and SPARE-AD was significantly reduced. Correlation of disentangled SPARE-AD was non-inferior to the molecular measurements and to the number of APOE4 alleles, but was less to AD-related psychometric test scores, suggesting contribution of advanced brain aging to these scores., Comment: 4 figures, 3 tables

There is a growing amount of clinical, anatomical and functional evidence for the heterogeneous presentation of neuropsychiatric and neurodegenerative diseases such as schizophrenia and Alzheimers Disease (AD). Elucidating distinct subtypes of diseases allows a better understanding of neuropathogenesis and enables the possibility of developing targeted treatment programs. Recent semi-supervised clustering techniques have provided a data-driven way to understand disease heterogeneity. However, existing methods do not take into account that subtypes of the disease might present themselves at different spatial scales across the brain. Here, we introduce a novel method, MAGIC, to uncover disease heterogeneity by leveraging multi-scale clustering. We first extract multi-scale patterns of structural covariance (PSCs) followed by a semi-supervised clustering with double cyclic block-wise optimization across different scales of PSCs. We validate MAGIC using simulated heterogeneous neuroanatomical data and demonstrate its clinical potential by exploring the heterogeneity of AD using T1 MRI scans of 228 cognitively normal (CN) and 191 patients. Our results indicate two main subtypes of AD with distinct atrophy patterns that consist of both fine-scale atrophy in the hippocampus as well as large-scale atrophy in cortical regions. The evidence for the heterogeneity is further corroborated by the clinical evaluation of two subtypes, which indicates that there is a subpopulation of AD patients that tend to be younger and decline faster in cognitive performance relative to the other subpopulation, which tends to be older and maintains a relatively steady decline in cognitive abilities., Comment: 11 pages, 3 figures, accepted by MICCAI2020

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 biomarkers. 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., Comment: Presents final results of the TADPOLE competition. 60 pages, 7 tables, 14 figures