AUTOMATED DETERMINATION OF PEDIATRIC LOWER LIMB ALIGNMENT

    公开(公告)号:US20250017544A1

    公开(公告)日:2025-01-16

    申请号:US18773341

    申请日:2024-07-15

    Abstract: Systems and methods for performing a pediatric lower limb alignment assessment by: receiving a pediatric lower limb radiographic image; identifying a plurality of regions of interest in the radiographic image using a first artificial intelligence model such that each one of the plurality of regions of interest contains at least one of a plurality of anatomical features of interest; determining a plurality of landmark locations for each one of the plurality of identified regions of interest in the radiographic image using a second AI model; and calculating one or more parameter values representative of the pediatric lower limb alignment based on a geometric relationship between the plurality of landmark locations.

    Mucoadhesive polymeric drug delivery compositions and methods

    公开(公告)号:US12171833B2

    公开(公告)日:2024-12-24

    申请号:US17797627

    申请日:2021-02-06

    Abstract: This invention provides compositions for controlled localized depositing of one or more drugs within a subject. More particularly, described herein are compositions comprising a) a polyethylene glycol (PEG) composition having a first low molecular weight PEG (Mw between 200-500 Da) and a second low molecular weight PEG (Mw between 500-2000 Da) and b) a mucoadhesive in polymer. Alternatively, composition may comprise a) a polyethylene glycol (PEG) composition having a first low molecular weight PEG (Mw between 200-500 Da) and a second low molecular weight PEG (Mw between 500-2000 Da), b) a water insoluble polymer and c) a mucoadhesive polymer. Furthermore, the composition may further comprise one or more drugs. Also provided are methods of manufacturing and administering the compositions described herein, which are used as biodegradable, injectable mucoadhesive low-viscosity pastes.

    METHOD AND SYSTEM FOR GENERATING ONE OR MORE CONDITIONALLY DEPENDENT DATA ENTRIES

    公开(公告)号:US20240386249A1

    公开(公告)日:2024-11-21

    申请号:US18199865

    申请日:2023-05-19

    Abstract: Methods, systems, and techniques for generating one or more conditionally dependent data entries using a probabilistic generative model, and for training that model. The probabilistic generative model is trained using a plurality of data generation tasks respectively corresponding to a plurality of vectors each having a sequence of differently indexed data entries that are conditionally dependent on each other. Each of the data generation tasks involves generating at least one latent data entry selected from the sequence of data entries in response to being provided at least one index for each of the at least one latent data entry. Training can be performed by minimizing an expected value of a denoising loss over all training stages.

    Heat dissipation apparatus and methods for UV-LED photoreactors

    公开(公告)号:US12134572B2

    公开(公告)日:2024-11-05

    申请号:US18317660

    申请日:2023-05-15

    Abstract: A UV reactor irradiates a flow of fluid with UV radiation. The reactor comprises: a fluid conduit defined by a heat conducting conduit body comprising one or more heat conducting walls for permitting a flow of fluid therethrough; a UV-LED operatively connected to a PCB and oriented for directing radiation into the fluid conduit. The PCB comprises a heat conducting substrate having a first surface. The conduit body is in thermal contact with the first surface of the heat conducting substrate. Heat is dissipated from the UV-LED via the heat conducting substrate, the thermal contact between the first surface of the heat conducting substrate and the heat conducting conduit body, and from the one or more heat conducting walls of the heat conducting conduit body to the fluid flowing through the fluid conduit.

Patent Agency Ranking