USPTO Machine-Learning Framework Patent for Cancer Analysis

The USPTO has granted a patent (US12584176B2) to Tempus AI, Inc. for an integrated machine-learning framework designed to estimate homologous recombination deficiency in cancer patients. This framework aims to improve cancer treatment predictions and outcomes by analyzing various genetic and tumor purity factors.

USPTO Patent Grant for Data Generation Device and Learning Method

The USPTO has granted a patent (US12582959B2) to FUJIFILM Corporation for a data generation device and learning method. This patent covers a system designed to create datasets for training neural networks used in product manufacturing processes.

USPTO Patent US12583122B2: Automated cavity filter tuning using machine learning

The USPTO has granted patent US12583122B2 to Tektronix, Inc. for an automated cavity filter tuning system utilizing machine learning. The patent describes a method for optimizing tuning screws on devices under test using robotic control and AI-driven parameter prediction.

Robot Program Teaching System and Method Patent Grant

The USPTO has granted patent US12583104B2 for a system and method for teaching a robot program, assigned to SCALABLE ROBOTICS INC. The patent covers machine learning algorithms for determining robot instructions based on user input and augmented/virtual reality interfaces.

USPTO Grants Patent for Robot Arm Control Device

The USPTO has granted a new patent (US12583103B2) to the Agency for Defense Development for a robot arm control device and a method for training a hierarchical reinforcement learning model. The patent, granted on March 24, 2026, details a system that uses target images and virtual canvas representations to determine joint angle changes for robot arm operation.

USPTO Patent Grant for Thermal Ablation Planning and Neural Network Training

The USPTO has granted patent US12582479B2 to Siemens Healthineers AG for a method and system for planning minimally invasive thermal ablation using neural network training. The patent covers a computer-implemented method that utilizes acquired object images and neural ordinary differential equations to output an ablation plan for guiding clinicians.

USPTO Patent US12582386B2: Aberration Corrections for Ultrasound Therapy

The USPTO has granted patent US12582386B2 to Insightec Ltd. for a differential prediction method for aberration corrections in ultrasound therapy. The patent utilizes a machine-learning model to optimize focal zones during therapeutic or diagnostic procedures.

USPTO Patent Grant: Synthetic Electron Density Images from MRI

The USPTO has granted patent US12582373B2 to Spectronic AB for a method of generating synthetic electron density images (sCT) from magnetic resonance (MR) images using a machine-learning model. This technology aims to improve the accuracy and efficiency of medical image processing.

USPTO Patent Grant: Pulmonary Hypertension Assessment System

The USPTO has granted a patent (US12582342B2) to Analytics for Life Inc. for a system using phase space tomography and machine learning to assess pulmonary hypertension. The patent details methods and systems for analyzing cardiac system dynamics and using computed images as input for a neural network classifier to detect the disease.

USPTO Patent Grant: Distributed Data Analytics Systems

The USPTO has granted a patent to Xailient for systems and methods related to distributed data analytics and device-specific artificial neural network (ANN) models. The patent covers the generation and distribution of ANN models across user devices, utilizing collected datasets for updates.