The present invention relates to a method for cancer cell separation, and more specifically, relates to a method for cancer cell separation using micro-vibration.

The disclosure provides a method of generating an artificial immunohistochemistry (IHC) image of cells. The method includes receiving a hematoxylin and eosin (H&E) stained whole slide image (WSI) generated by a brightfield microscopy imaging modality of at least a portion of cells included in a specimen, applying, to the H&E brightfield image, at least one trained model, the trained model being trained to generate the artificial IHC image based on the H&E brightfield image, receiving the artificial IHC image from the trained model.

The disclosure provides a method of generating an artificial immunohistochemistry (IHC) image of cells. The method includes receiving a hematoxylin and eosin (H&E) stained whole slide image (WSI) generated by a brightfield microscopy imaging modality of at least a portion of cells included in a specimen, applying, to the H&E brightfield image, at least one trained model, the trained model being trained to generate the artificial IHC image based on the H&E brightfield image, receiving the artificial IHC image from the trained model.

The present disclosure provides methods for path planning, and methods, devices, and systems for determining operation guidance information. The methods include obtaining an X-ray image of a target object, and marking a location of a lesion on the X-ray image of the target object; obtaining an ultrasonic image of the target object, and obtaining a fused image by fusing the ultrasonic image of the target object with the marked X-ray image; and obtaining a planned path by performing a path planning based on a location of the lesion in the fused image. According to the methods provided herein, the problem that a single medical image providing relatively little information and without effective reference for surgery can now be solved. The surgical instrument can be implanted based on the planned path, thereby improving the success rate of surgery and reducing surgical complications.

A processor encodes a target image to derive at least one first feature amount indicating an image feature for an abnormality of a region of interest included in the target image. In addition, the processor encodes the target image to derive at least one second feature amount indicating an image feature for an image in a case in which the region of interest included in the target image is a normal region.

A surgical image capture and display system includes a handheld image capture and pointing device and a display assembly. An image is captured by an image sensor of the handheld device and displayed on the display assembly. The image sensor detects light emitted by one or more beacons of the display assembly. The system determines, based on the light emitted by the one or more beacons, a position or orientation of the handheld device relative to the display assembly. The system updates display of a graphical user interface comprising the image on the display assembly in accordance with the determined position or orientation of the handheld device.

A surgical image capture and display system includes a handheld image capture and pointing device and a display assembly. An image is captured by an image sensor of the handheld device and displayed on the display assembly. The image sensor detects light emitted by one or more beacons of the display assembly. The system determines, based on the light emitted by the one or more beacons, a position or orientation of the handheld device relative to the display assembly. The system updates display of a graphical user interface comprising the image on the display assembly in accordance with the determined position or orientation of the handheld device.

Machine training and application of machine-trained classifier are used for image-based tumor phenotyping in a medical system. To create a training database with known phenotype information, synthetic medical images are created. A computational tumor model creates various examples of tumors in tissue. Using the computational tumor model allows one to create examples not available from actual patients, increasing the number and variance of examples used for machine-learning to predict tumor phenotype. A model of an imaging system generates synthetic images from the examples. The machine-trained classifier is applied to images from actual patients to predict tumor phenotype for that patient based on the knowledge learned from the synthetic images.

A method comprising, responsive to a selecting event, rendering an interactive display screen of a saved first state of a display layout of a medical information compilation, the interactive display screen comprising first information in a first display area and second information in a second display area, the saved first state comprising a plurality of display attributes of the first information and the second information, wherein the first information and the second information each include one of (i) a medical image, (ii) medical notes, or (iii) a medical record is described.

A medical system includes an imager configured to pick up an image and output an image signal, a signal processing device configured to generate an observation image from the image signal, a display configured to display the observation image, and a relay device, and the signal processing device derives a processing sequence that minimizes a time duration from when the imager picks up an image until the display displays the observation image, based on a first specification of the image signal at the imager, a second specification of the signal processing device, a third specification of the observation image at the display, and a communication protocol of the relay device, provides instruction of a fourth specification to the imager based on the processing sequence, and provides instruction of a fifth specification to the display based on the processing sequence.