Abstract:
The present invention relates to detecting objects in medical images. In order to provide an improved detection of objects in medical images, a medical image detection device (10) is provided that comprises an image data input (12) and a processing unit (14). The image data input is configured to receive image data of a biological sample. The processing unit comprises a detector (16) and a classifier (18). The detector is configured to detect objects of interest in the sample by a detection in the image data of at least one predetermined object feature. The detected objects being candidate objects, wherein the candidate objects comprise true positives and possible false positives. Further, the classifier is configured to classify the possible false positives as false positives or as true positives. The classifier is a trained classifier, trained specifically to recognize the false positives of the detector.
Abstract:
A device for identifying a region of interest to be dissected from a biological tissue sample is presented. The device comprises an image analyzing unit which iteratively grows the region of interest from an initial size to a final size as long as a target parameter which is based on the two detected densities D 1 and D 2 and which describes the region of interest, is above a predefined target value. Preferably, the target parameter is the density ratio D 1 /D 2 of the region of interest and the first type of detected cells are tumor cells whereas the second type of cells are non-tumor cells. Furthermore, optimization or cost functions can be applied which take into account the percentage of number of cells of the first cell type and the total number of cells of the first cell type in the respective region of interest.
Abstract:
A system (10) is for performing ECG measurements and comprises a probe (12) with an integrated one or more ECG electrodes (22) and an ultrasound sensing means (18), such as a transducer arrangement. The probe thus provides a mobile ECG electrode which can be sequentially moved between a set of different locations on the body for acquiring ECG measurements from different angles relative to the heart (i.e. different 'leads'). Positioning of the probe in each required location is guided by a position guidance function which uses ultrasound data acquired by the ultrasound sensing means to locate the probe (with reference to an ultrasound body atlas (28) or map), and uses a stored set of reference body locations to guide a user with guidance information as to how to move the probe to arrive at a next target electrode location. In examples, the user may be guided through a sequence of electrode locations, with ECG data acquired at each one, thereby sequentially building up a set of standard ECG lead measurements.
Abstract:
Currently, there is interest in applying machine learning techniques to analyse digital pathology images automatically. Machine learning techniques often rely on training with a ground-truth image input. The quality and amount of training data determines the quality of the detector, as expressed in the rate of true and false positives, and robustness against variations in the appearance of the input images. The present application proposes to obtain image data of the same sample before and after at least one re- staining step (firstly with a structure-revealing stain, and secondly with a bio marker revealing stain). Sections of the first and second image data having a good registration relationship are chosen, along with the probability of detecting a desired candidate object (such as nucleus) and the probability of the bio marker revealing stain being present annotation data suitable for training a machine learning algorithm on the first and/or the second image data is provided.
Abstract:
The present invention relates to an ultrasound imaging system (100) comprising: an ultrasound probe (10) that comprises a single element ultrasound transducer (16) for transmitting an receiving ultrasound signals; a movement sensor (18) for sensing a displacement-over-time signal x(t) of a displacement (x) of the ultrasound probe (10) relative to an examination object (24) during signal acquisition; an image acquisition hardware (26) that is configured to reconstruct an M- mode ultrasound image from the received ultrasound signals, said reconstructed M-mode ultrasound image being a two-dimensional image I(t,y) comprising multiple one-dimensional depth signals of substantially constant depth (y) in the examination object (24) illustrated over time (t), wherein the image acquisition hardware (26) is further configured to map said M-mode ultrasound image I(t,y) to a two-dimensional second image I(x,y) comprising the depth signals illustrated over the displacement (x) by using the displacement-over-time signal x(t) that is sensed with the movement sensor (18); and an image analysis unit (48) that is configured to analyse said second image and to detect at least one tissue layer boundary of the examination object (24) in said second image.
Abstract:
A computer implemented method for use in monitoring a first entity in a medical facility comprises: i) obtaining an image of the medical facility, ii) using a machine learning process to fit a first articulated model to the first entity in the image, wherein the first articulated model comprises keypoints corresponding to joints and affinity fields that indicate links between the keypoints. The method further comprises iii) determining a location or posture of the first entity in the medical facility from relative locations of fitted keypoints of the first articulated model in the image.
Abstract:
A device (20) and method for controlling a camera (10) are provided. The device comprises an input unit (21) configured to obtain video data from the camera; an image processing unit (22) configured to determine from the obtained video data if a particular person is present alone in a first area monitored by the camera; a control unit (23) configured to generate a control signal for controlling the camera to operate in a first monitoring mode or a second monitoring mode based on the determination by the image processing unit if the particular person is present alone in the first area monitored by the camera; and an output unit (24) configured to output the control signal to the camera.
Abstract:
The invention relates to a printing control device (10) to control printing of a cover layer on a tissue or cell sample to be examined, a system (1) for printing of a cover layer (1) on a tissue or cell sample to be examined, a method to control printing of a cover layer on a tissue or cell sample to be examined, a computer program element for controlling such device or system for performing such method and a computer readable medium having stored such computer program element. The printing control device (10) comprises an imaging unit (11) and a printing control unit (12). The imaging unit (11) is configured to provide image data of the sample, and to determine a local image parameter from the image data. The local image parameter relates to local tissue porosity and/or a local capillary force of the sample. The printing control unit (12) is configured to control a printing parameter for printing the cover layer on the sample based on the local image parameter.
Abstract:
The invention relates to an ultrasound data visualization apparatus for visualizing ultrasound data, in particular, during a cardiac ablation procedure. An M-mode ultrasound image of an object (23) being preferentially a heart of a person or a feature image of the object comprising features derived from the M-mode ultrasound image and a repetitive signal like an electrocardiography signal being indicative of a repetitive cycle in the image are provided. An image frames determination unit (13) determines image frames by temporally segmenting the provided image into image frames corresponding to different repetitive cycles based on the repetitive signal, wherein a display (24) displays the image frames temporally consecutively. Since the display shows these image frames temporally consecutively, a movie-like displaying of the ultrasound data is provided, which allows for a better observation of details and changes of the object, especially of changes in cardiac tissue during an ablation procedure.
Abstract:
An ultrasound transducer unit (12), e.g. probe, is configured with a friction guiding function. The transducer unit (12) comprises a vibration generating means (20) at a tissue contact area, and has means for sensing a sliding direction of the transducer unit across a tissue surface (42) at which the contact area is incident. The tissue surface may be an external skin surface or an internal tissue surface, e.g. in case of a catheter. A control means is operable to control the vibration of the vibration generator to adjust a level of friction at the tissue contact area. This is used by the control means to implement a friction guiding function for guiding a user in sliding the unit across the incident surface, e.g. toward a target location (44), based on controlling the friction level responsive to sensed sliding direction, for instance providing lower friction when sliding is in a target direction, while leaving other directions with relative higher frictional resistance.