MRI Embeddings Complement Clinical Predictors for Cognitive Decline Modeling in Alzheimer's Disease Cohorts

The article introduces Convolutional Nearest Neighbors (ConvNN), a framework that unifies Convolutional Neural Networks (CNNs) and Transformers by viewing convolution and self-attention as neighbor selection and aggregation methods. ConvNN allows for a systematic exploration of the spectrum between these two architectures, serving as a drop-in replacement for convolutional and attention layers. The framework's effectiveness is validated through classification tasks on CIFAR-10 and CIFAR-100 datasets.

Bladder cancer is a prevalent malignancy with a high recurrence rate of up to 78%, necessitating precise post-operative monitoring. Multi-sequence contrast-enhanced MRI is commonly utilized for recurrence detection, but interpreting these scans is challenging due to post-surgical changes. This study introduces a curated multi-sequence, multi-modal MRI dataset designed for bladder cancer recurrence prediction and proposes H-CNN-ViT, a new model aimed at enhancing prediction accuracy in this critical area.

The Abstraction and Reasoning Corpus (ARC) aims to advance research in abstract reasoning, a key component of human intelligence. Traditional methods approach ARC as a language problem, often utilizing large language models or recurrent reasoning models. This study proposes a vision-centric approach, treating ARC as an image-to-image translation task. By using a 'canvas' for input representation, standard vision architectures like Vision Transformers (ViT) can be applied, allowing the model to generalize to new tasks through test-time training.

A new method for predicting biomarker trajectories in Alzheimer's disease has been developed, addressing the uncertainty in clinical predictions. This conformal prediction technique allows for reliable forecasts from randomly-timed clinical visits, ensuring that the prediction bands cover the actual biomarker trajectories with a specified probability. The approach was tested using neuroimaging data from established clinical studies, demonstrating its effectiveness in enhancing the safety of clinical applications.

Automatic Music Transcription (AMT) is a process that converts audio recordings into symbolic musical representations. Traditional training of deep neural networks (DNNs) for AMT requires well-aligned training pairs with precise annotations, which can be costly. Weakly aligned methods using segment-level annotations have emerged, but they often depend on Dynamic Time Warping (DTW) or soft alignment loss functions, leading to errors and high computational costs. The new CountEM framework addresses these issues by using note event histograms for supervision, allowing for more efficient computati…