Koninklijke Philips Corporation N.V.

Xiaomin Li

Yinhui Deng

Ying Wu

Vijay Thakur Shamdasani

Xiaolin Gu

Jingping Xu

Kai Huang

Individual computer diagnostic support (CDS) systems are coupled to a 'global' CDS system, each of the CDS systems using the same learning system or the same learning system technique. Training and testing cases from each of the individual CDS systems are provided to the global CDS system, and the global CDS system uses these training cases to produce learning system parameters based on the training cases. Having more training cases than any of the individual CDS systems, the parameters provided by the global CDS system offer a higher quality diagnostic output than any of the individual CDS systems. The learning system parameters at the global CDS system may be provided to each of the individual CDS systems, to update the parameters of the individual CDS systems' learning system. The global CDS may also refine and/or adjust the structure of the embodied learning systems.

Hierarchical self-learning system for computerized clinical diagnostic support

An ultrasonic diagnostic imaging system and method acquire a sequence of image data as a bolus of contrast agent washes into and out of the liver. The image data of contrast intensity is used to compute time-intensity curves of contrast flow for points in an ultrasound image. Time-dependent data is calculated from the data of the time-intensity curves which, in a described implementation, comprise first and second derivatives of the time-intensity curves. A color map is formed of the time-dependent data or the polarities of the data and displayed in a parametric image as a color overlay of a contrast image of the liver.

Time-based parametric contrast enhanced ultrasound imaging system and method

The present invention provides a method and a system for medical imaging and information display. According to an aspect of the present invention, there is proposed a method of medical imaging and information display, comprising: acquiring imaging data of each point of a plurality of points in an imaging plane or imaging volume of a subject in each mode of a plurality of different imaging modes of a medical imaging apparatus; deriving, for said each point, a value by applying the imaging data of the point in said each mode and the imaging data of at least one other point of said plurality of points adjacent to the point in said each mode to a predetermined model, wherein the predetermined model is selected in accordance with a clinical medical application related to the subject; constructing an image based on all the derived values; and displaying the constructed image to a user. Accordingly, the novel method of medical imaging and information display may reduce the burden of doctors, and provide them with an image with a higher definition compared to the conventional ROI method.

Method and system for medical imaging and information display

The present invention provides a method and a system for processing ultrasonic data. The method comprises: obtaining () a B-mode ultrasonic image; setting () a first ROI on the ultrasonic image according to a first input received from a user; measuring () elasticity-related data for the first ROI by using a shear wave ultrasonic imaging technique; generating () a second ROI on the ultrasonic image on the basis of the first ROI; and extracting image features for the second ROI from the ultrasonic image.

Method and system for processing ultrasonic imaging data

An ultrasonic diagnostic imaging system produces contrast enhanced images which are processed differently during different stages of contrast agent wash-in. During an initial stage of contrast wash-in, imaging is done using pixels processed by maximum intensity detection, to better reflect the rapid change in contrast intensity. During a later stage of contrast wash-in, time averaged processing is used to diminish the effects of noise and motion on the pixel values. During an intermediate period of peak enhancement, a combination of both pixel values processed by both techniques is used. In another aspect, a wash-in period can be characterized by an appearance stage, a growth stage and a peak stage, in which contrast pixel data is adaptively processed in different ways during these periods.

Micro vascular ultrasonic contrast imaging by adaptive temporal processing

The present invention proposes an apparatus and method for characterizing a tissue in a first region of a subject. The apparatus comprises a receiving unit () for receiving ultrasound data of the tissue in the first region and ultrasound data of a predetermined target reference tissue of said subject; a deriving unit () for deriving a subject-specific model of the target reference tissue on the basis of the ultrasound data of the target reference tissue; and a characterizing unit () for determining a match between tissue in the first region and the target reference tissue on the basis of the subject-specific model and ultrasound data of the tissue in the first region. Unlike conventional tissue characterization based on a large cohort of patient data, the proposed subject-specific model is personalized for the specific subject without any generalization, resulting in higher sensitivity and/or accuracy. Preferably, the subject-specific model of the target reference tissue is derived on the basis of both the ultrasound data of the target reference tissue and the ultrasound data of a background reference tissue of a different type than the target reference tissue.

Apparatus and method for characterizing a tissue of a subject

The present invention provides a method and a system for medical imaging and information display. According to an aspect of the present invention, there is proposed a method () of medical imaging and information display, comprising: acquiring () imaging data of each point of a plurality of points in an imaging plane or imaging volume of a subject in each mode of a plurality of different imaging modes of a medical imaging apparatus; deriving (), for said each point, a value by applying the imaging data of the point in said each mode and the imaging data of at least one other point of said plurality of points adjacent to the point in said each mode to a predetermined model, wherein the predetermined model is selected in accordance with a clinical medical application related to the subject; constructing () an image based on all the derived values; and displaying () the constructed image to a user. Accordingly, the novel method of medical imaging and information display may reduce the burden of doctors, and provide them with an image with a higher definition compared to the conventional ROI method.

The present invention proposes an ultrasound imaging system and a method of calculating a perfusion parameter ratio. The proposed approach comprises: acquiring a time intensity curve of a contrast agent for each region unit of a plurality of region units of an imaging region of a subject, each region unit comprising one or more points of the imaging region; selecting, among the plurality of region units, a first, second and third sets of region units respectively corresponding to normal tissue, vessel and background noise, based on the time-intensity curves; calculating a perfusion parameter for each of one or more region units of the first set of region units and a perfusion parameter for a region of interest in the imaging region based on the calculated time-intensity curves; calculating a reference perfusion parameter based on the perfusion parameters of the one or more region units; and calculating a ratio value for the region of interest as a ratio of the perfusion parameter of the region of interest and the reference perfusion parameter. Since the reference perfusion parameter is calculated based on the one or more region units which are automatically selected, the approach requires no manual manipulation and the calculated perfusion parameter ratios are independent of operator experience.

Ultrasound imaging system and method

The present invention provides an ultrasound imaging system and an ultrasound imaging method for improving the imaging quality of the desired imaging plane in the volume of interest of a subject. According to the present invention, it is possible to directly scan the desired imaging plane by exploiting the capability of a 2D matrix ultrasound transducer and/or the flexibility of the position/orientation of the ultrasound probe. In some cases, the setting parameters of the transducer elements can be adjusted so that the ultrasound signal transmitted from the transducer elements is able to derive ultrasound echo data of the desired imaging plane without moving the probe. In other cases where the desired imaging plane cannot be directly scanned without changing the position/orientation of the ultrasound probe, the position/orientation of the ultrasound probe can be adjusted by means of user interaction, namely by outputting the instruction for guiding the user to move the probe so as to enable direct scanning of the desired imaging plane. In this way, the image of the desired imaging plane is not reconstructed by interpolation of the ultrasound echo data of the plurality of scanning planes (which are determined by the setting parameters of the transducer elements), but instead it is reconstructed from the ultrasound echo data of the desired imaging plane itself. In other words, the desired imaging plane is directly scanned. Thus, the image quality of the desired imaging plane is improved and may help doctors conduct a more accurate diagnosis.

Growing community of inventors

Shanghai, China

Xiaomin Li