Kyle Jon Lafata

Conference Int J Radiat Oncol Biol Phys · June 1, 2026 PURPOSE: As survival improves for patients with brain metastases (BM), distinguishing local recurrence (LR) from radionecrosis (RN) is a growing neuro-oncologic challenge. We aimed to develop an explainable deep learning model to noninvasively distinguish ... Full text Link to item Cite

Large Intestine 3D Shape Refinement Using Conditional Latent Point Diffusion Models

Conference Lecture Notes in Computer Science · January 1, 2026 Accurate 3D modeling of human organs is critical for constructing digital phantoms in virtual imaging trials. However, organs such as the large intestine remain particularly challenging due to their complex geometry and shape variability. We propose CLAP, ... Full text Cite

Radiogenomic explainable AI with neural ordinary differential equation for identifying post-SRS brain metastasis radionecrosis.

Conference Med Phys · April 2025 BACKGROUND: Stereotactic radiosurgery (SRS) is widely used for managing brain metastases (BMs), but an adverse effect, radionecrosis, complicates post-SRS management. Differentiating radionecrosis from tumor recurrence non-invasively remains a major clinic ... Full text Link to item Cite

Radiomics on spatial-temporal manifolds via Fokker-Planck dynamics.

Conference Med Phys · May 2024 BACKGROUND: Delta radiomics is a high-throughput computational technique used to describe quantitative changes in serial, time-series imaging by considering the relative change in radiomic features of images extracted at two distinct time points. Recent wo ... Full text Link to item Cite

Virtual NLST: Towards Replicating National Lung Screening Trial

Conference Progress in Biomedical Optics and Imaging Proceedings of SPIE · January 1, 2024 Virtual Imaging Trials, known as VITs, provide a computational substitute for clinical trials. These traditional trials tend to be sluggish, costly, and frequently deficient in definitive evidence, all the while subjecting participants to ionizing radiatio ... Full text Cite

Inference Serving System for Stable Diffusion as a Service

Conference Proceeding 2024 IEEE Cloud Summit Cloud Summit 2024 · January 1, 2024 We present a model-less, privacy-preserving, low-latency inference framework to satisfy user-defined System-Level Objectives (SLO) for Stable Diffusion as a Service (SDaaS). Developers of Stable Diffusion (SD) models register their trained models on our pr ... Full text Cite

Neural Architecture Search for Blood Glucose Prediction in Type-1 Diabetics

Conference 2024 IEEE 20th International Conference on Body Sensor Networks Bsn 2024 Proceedings · January 1, 2024 For subjects affected with type-1 diabetes mellitus, accurately predicting future blood glucose values helps regulate insulin delivery. This paper introduces a dual Q-network-based neural architecture search approach to develop and train per-sonalized BG p ... Full text Cite

Preserving Accuracy While Stealing Watermarked Deep Neural Networks

Conference Proceedings 2024 International Conference on Machine Learning and Applications Icmla 2024 · January 1, 2024 The deployment of Deep Neural Networks (DNNs) as cloud services has accelerated significantly over the years. Training an application-specific DNN for cloud deployment requires substantial computational resources and costs associated with hyper-parameter t ... Full text Cite

Decoding the Encoder

Conference Conference Proceedings IEEE SOUTHEASTCON · January 1, 2023 Autoencoders are used in a variety of safety-critical applications. Uncertainty quantification is a key component to bolster the trustworthiness of such models. With the growing complexity of the autoencoder design and the dataset they are trained on, ther ... Full text Cite

Automatic quality control in computed tomography volumes segmentation using a small set of XCAT as reference images

Conference Progress in Biomedical Optics and Imaging Proceedings of SPIE · January 1, 2023 Deep learning methods have performed superiorly to segment organs of interest from Computed Tomography images than traditional methods. However, the trained models do not generalize well at the inference phase, and manual validation and correction are not ... Full text Cite

Privacy-preserving Job Scheduler for GPU Sharing

Conference Proceedings 23rd IEEE ACM International Symposium on Cluster Cloud and Internet Computing Workshops Ccgridw 2023 · January 1, 2023 Machine learning (ML) training jobs are resource intensive. High infrastructure costs of computing clusters encourage multi-tenancy in GPU resources. This invites a scheduling problem in assigning multiple ML training jobs on a single GPU while minimizing ... Full text Cite

Job Recommendation Service for GPU Sharing in Kubernetes

Conference Proceedings 2023 IEEE Cloud Summit Cloud Summit 2023 · January 1, 2023 Cloud infrastructures encourage the multi-tenancy of hardware resources. User-defined Machine Learning (ML) training jobs are offloaded to the cloud for efficient training. State-of-the-art resource schedulers do not preserve user privacy by accessing sens ... Full text Cite

Blood Glucose Prediction for Type-1 Diabetics using Deep Reinforcement Learning

Conference Proceedings 2023 IEEE International Conference on Digital Health Icdh 2023 · January 1, 2023 An accurate prediction of blood glucose levels for individuals affected with type-1 diabetes mellitus helps to regulate blood glucose through specific insulin delivery. In our work, we propose the design of a densely-connected encoder-decoder network in co ... Full text Cite

A radiomics-boosted deep-learning model for COVID-19 and non-COVID-19 pneumonia classification using chest x-ray images.

Conference Med Phys · May 2022 PURPOSE: To develop a deep learning model design that integrates radiomics analysis for enhanced performance of COVID-19 and non-COVID-19 pneumonia detection using chest x-ray images. METHODS: As a novel radiomics approach, a 2D sliding kernel was implemen ... Full text Link to item Cite

Spectral micro-CT and nanoradiomic analysis for classification of tumors based on lymphocytic burden in cancer therapy studies

Conference Progress in Biomedical Optics and Imaging Proceedings of SPIE · January 1, 2022 The purpose of this study was to investigate if radiomic analysis based on spectral micro-CT with nanoparticle contrast-enhancement can differentiate tumors based on tumor-infiltrating lymphocyte (TIL) burden. High mutational load transplant soft tissue sa ... Full text Cite

Computer-Assisted Diagnosis of Hepatic Portal Hypertension: A Novel, Attention-Guided Deep Learning Framework Based On CT Imaging and Laboratory Data Integration

Conference MEDICAL PHYSICS · June 2021 Link to item Cite

Multi-Domain Statistical Modeling of Treatment Tolerance in Patients with Gastric and Esophageal Adenocarcinoma

Conference MEDICAL PHYSICS · June 2021 Link to item Cite

Measuring Distribution of An I-125 Labeled Elastin-Like Polypeptide (ELP) Nanoparticle Within Mice Tumors for Consideration as a Novel Technique of Delivering Brachytherapy

Conference MEDICAL PHYSICS · June 2021 Link to item Cite

Biologically Guided Deep Learning for Post-Radiation PET Image Outcome Prediction: A Feasibility Study of Oropharyngeal Cancer Application

Conference MEDICAL PHYSICS · June 2021 Link to item Cite

Cortical Tubulointerstitial Mononuclear Inflammation in Renal Biopsies is a Quantitative Biomarker of Clinical Outcomes in NEPTUNE Glomerular Diseases

Conference MODERN PATHOLOGY · March 2021 Link to item Cite