This study explores diffusion-based generative modeling using a Denoising Diffusion Probabilistic Model (DDPM) framework to conditionally synthesize chest X-rays from echocardiographic measurements and demographic features. We evaluate whether synthetic images produced by the model can enhance the performance of a diagnostic convolutional neural network in detecting structural heart disease across varying combinations of real and synthetic data.
This work presents the development and evaluation of coordn8, a web-based application that streamlines fax processing in outpatient clinics using a “human-in-the-loop” machine learning framework. We demonstrate the effectiveness of the platform at reducing fax processing time and producing accurate machine learning inferences across the tasks of patient identification, document classification, spam classification, and duplicate document detection.
Glioblastoma (GBM), the deadliest primary brain tumor, exhibits high therapeutic resistance and recurrence due to its genomic and cellular diversity. This study utilizes single-cell genomic analyses to correlate somatic mutations with transcriptomic profiles within tumor tissues. We established a concise three-stage pipeline: variant calling, machine learning (ML) classification, and biological pathway analysis.
In this vision paper, we argue that many data center networking techniques, e.g., routing, topology augmentation, energy savings, with diverse goals share design and architectural similarities. We present a framework for developing general intermediate representations of network topologies using deep learning that is amenable to solving a large class of data center problems.
Distracted driving is known to be the leading cause of motor vehicle accidents. In this work, we present a unified data collection and analysis framework, DarNet, capable of detecting and classifying distracted driving behavior using a multimodal CNN+RNN framework.
