利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

5 条记录 (耗时 0.013 秒)

    INHALATION METRIC FOR CHEST X-RAY IMAGES
    2.
    发明公开
    INHALATION METRIC FOR CHEST X-RAY IMAGES 审中-公开

    公开(公告)号：US20240046452A1

    公开(公告)日：2024-02-08

    申请号：US17641122

    申请日：2020-09-01

    申请人： KONINKLIJKE PHILIPS N.V.

    发明人： JENS VON BERG ,  DANIEL BYSTROV ,  SVEN KROENKE ,  STEWART YOUNG

    IPC分类号： G06T7/00 ,  A61B6/00

    CPC分类号： G06T7/0012 ,  A61B6/5217 ,  A61B6/50 ,  G06T2207/10116 ,  G06T2207/30008 ,  G06T2207/20081 ,  G06T2207/30168

    摘要： In order to enhance enhanced X-ray image inhalation quality monitoring, a metric is proposed hat reproducibly provides an index of ribs visible to be used in the assessment of the inhalation state. In an example, a detected diaphragm in a chest X-ray image may be projected into an atlas that contains labels for all intercostal spaces, namely spaces between rib centerlines. A spatial representation of both the clavicle and the ribs is provided in the atlas, a cumulative histogram is built for all points, i.e. pixels, of the diaphragm, for every point a rib label counter of the rib in the rib label map at that point is incremented as well as all ribs above it, the rib label counter is normalized by a division by the number of points, the median (or a different quantile) may be taken of this distribution serving as an inhalation index. An objective metric of inhalation state is thus achieved.

    METHOD FOR ASSESSING A POSITION OF A PATIENT TO AN AUTOMATIC EXPOSURE CONTROL CHAMBER
    3.
    发明申请
    METHOD FOR ASSESSING A POSITION OF A PATIENT TO AN AUTOMATIC EXPOSURE CONTROL CHAMBER 有权

    公开(公告)号：US20220386983A1

    公开(公告)日：2022-12-08

    申请号：US17770175

    申请日：2020-10-16

    申请人： KONINKLIJKE PHILIPS N.V.

    发明人： TIM PHILIPP HARDER ,  THOMAS BUELOW ,  STEWART YOUNG ,  JENS VON BERG ,  SVEN KROENKE ,  DANIEL BYSTROV ,  ANDRÉ GOOSSEN

    IPC分类号： A61B6/00 ,  G06T7/70 ,  G06T7/11

    摘要： Method for assessing a position of a patient with respect to an automatic exposure control chamber, AEC chamber (11, 12), for a medical exam, wherein a patient is positioned between an X-ray source and the AEC chamber (11, 12); comprising the steps:—acquiring (S10) an X-ray image (32) of at least part of the patient, wherein the AEC chamber is configured for detecting a radiation dose of the X-ray source;—determining (S20), by the control unit, a position of the AEC chamber (11, 12) with respect to the patient from the acquired X-ray image (32);—determining (S30), by the control unit, an exam protocol performed on the patient dependent on the medical exam to be performed on the patient and determining, by the control unit, an ideal position of the AEC chamber (11, 12) with respect to the patient dependent on the exam protocol, wherein the ideal position relates to a position of the patient relative to the AEC chamber (11, 12), in which the detected radiation dose is reliable for the medical exam; and—determining (S40), by the control unit, a position deviation of the position of the AEC chamber from the ideal position of the AEC chambers; characterized in that determining, by the control unit, the position deviation comprises the steps:—segmenting at least an anatomical structure (21, 22) of the patient in the X-ray image (32) thereby determining at least one segmented anatomical structure (21, 22); and—determining the position deviation dependent on the at least one segmented anatomical structure (21, 22);—determining an overlap of the at least one segmented anatomical structure (21, 22) with the AEC chamber (11, 12); and—determining the position deviation dependent on the determined overlap.

    CONSTRAINED TRAINING OF ARTIFICIAL NEURAL NETWORKS USING LABELLED MEDICAL DATA OF MIXED QUALITY
    5.
    发明申请
    CONSTRAINED TRAINING OF ARTIFICIAL NEURAL NETWORKS USING LABELLED MEDICAL DATA OF MIXED QUALITY 有权

    公开(公告)号：US20220392198A1

    公开(公告)日：2022-12-08

    申请号：US17776083

    申请日：2020-11-09

    申请人： KONINKLIJKE PHILIPS N.V.

    发明人： SVEN KROENKE ,  JENS VON BERG ,  DANIEL BYSTROV ,  BERND LUNDT ,  NATALY WIEBERNEIT ,  STEWART YOUNG

    IPC分类号： G06V10/774 ,  G16H30/40 ,  G06T7/00 ,  G06V10/82 ,  G06V10/776

    摘要： The invention relates to a method (100) for supervised training of an artificial neural network for medical image analysis. The method comprises acquiring (SI) first and second sets of training samples, wherein the training samples comprise feature vectors and associated predetermined labels, the feature vectors being indicative of medical images and the labels pertaining to anatomy detection, to semantic segmentation of medical images, to classification of medical images, to computer-aided diagnosis, to detection and/or localization of biomarkers or to quality assessment of medical images. The accuracy of predetermined labels may be better for the second set of training samples than for the first set of training samples. The neural network is trained (S3) by reducing a cost function, which comprises a first and a second part. The first part of the cost function depends on the first set of training samples, and the second part of the cost function depends on a first subset of training samples, the first subset being a subset of the second set of training samples. In addition, the second part of the cost function depends on an upper bound for the average prediction performance of the neural network for the first subset of training samples and the second part of the cost function is configured for preventing that the average prediction performance for the first subset of training samples exceeds the upper bound.