Among the many medical imaging modalities, CT and MRI scans are utilized most often for imaging bone and soft tissue respectively. As such, physicians often require both images to fully diagnose patients and determine treatment plans.
Stanford researchers in the Xing Lab have developed GPT-RadPlan, a large language model (LLM) and vision-language model (VLM) based radiation therapy treatment planning automation tool that reduces treatment planning time and lowers costs.
Researchers at Stanford have developed a methodology for deep learning-based image reconstruction by incorporating the physics or geometry priors of the imaging system with deep neural networks.
Stanford scientists have invented an implicit an Neural Representation learning methodology with Prior embedding (NeRP) to reconstruct a computational medical image from sparsely sampled measurements using only a prior image of the subject.
As of 2020, radiation therapy has saved over 3.38 million cancer patients in the US. Radiation therapy treatment planning often involves a time-consuming and labor-intensive process where physicians must manually optimize the prescribed radiation dose.
Researchers at Stanford have developed, for the first time, a component analysis algorithm that does not require any assumption on the data structure or data generation process to find out the important components or trends in data.
Stanford researchers have used deep learning to create a radiotherapy treatment plan verification algorithm. Patient specific dose verification is traditionally done by checking the dose in a patient-mimicking phantom or by using an independent dose calculation algorithm.
Stanford researchers at the Liao and Xing Labs have developed and tested a machine learning algorithm for augmented detection of bladder cancer. Machine learning has the potential to enhance medical decision making in cancer detection and image analysis.
Stanford researchers at the Xing Lab have developed a novel technique to enable retrospective tuning of soft tissue contrast in MRI (i.e. adjusting the contrast after the image acquisition) using a deep learning-based strategy.
Researchers at Stanford University have developed a quick, robust, machine learning based method for linear accelerator (LINAC) commissioning and beam data modeling.
Stanford researchers at the Xing Lab have developed a dosimetric features driven- machine learning model for dose volume histograms (DVHs) and dose prediction for volumetric modulated arc therapy (VMAT) planning.
Stanford researchers at the Xing Lab have developed a novel method using deep neural networks called "Q2MRI" to simultaneously acquire qualitative MR image and quantitative MRI parametric maps without changing the clinical imaging protocol or elongating MRI scan tim
Stanford researchers have developed a novel and efficient method for generating real-time 3D volumetric computed tomography (CT) images with 2D single or few-view projections, instead of several hundreds of projections as required in existing CT imaging system.