A method, device and system for calculating a microcirculation indicator are provided. A method includes: injecting a vasodilator and subjecting a blood vessel to be measured to coronary angiography; selecting at least one angiographic image of a first body position when the blood vessel to be measured is in a resting state and an angiographic image of a second body position when the blood vessel to be measured is in a dilated state; obtaining a three-dimensional coronary artery vascular model by three-dimensional modeling; injecting a contrast agent, and obtaining time T.sub.1 taken for the contrast agent flowing from an inlet to an outlet of the segment of blood vessel and time T.sub.2 taken for the contrast agent flowing from an inlet to an outlet of the segment of blood vessel; obtaining the microcirculation indicator.

A diagnostic assistance method for a disease based on an endoscopic image of a digestive organ with use of a convolutional neural network (CNN). A diagnostic assistance method for a disease based on an endoscopic image of a digestive organ with a CNN trains the CNN using a first endoscopic image of the digestive organ and at least one final diagnosis result on positivity or negativity to the disease in the digestive organ, a past disease, a severity level, and information corresponding to a site where an image is captured, the final diagnosis result corresponding to the first endoscopic image, and the trained CNN outputs at least one of a probability of the positivity and/or the negativity to the disease, a probability of the past disease, a severity level of the disease, an invasion depth of the disease, and a probability corresponding to the site where the image is captured.

A computer-implemented method for comparing follow-up medical findings includes receiving image data showing a body part of a patient at a first time and retrieving, from a database, reference data associated to the image data. The reference data includes reference biometric data and one or more reference medical findings. Thereby the reference biometric data and the one or more reference medical findings have been extracted from reference image data depicting the body part of the patient at a second time, different than the first time. The method further includes processing the received image data to extract, from the image data, biometric data corresponding to the reference biometric data and one or more medical findings; performing a registration of the extracted biometric data with the reference biometric data; and comparing the extracted medical findings with the reference medical findings using the registration.

A computer-implemented method for identifying pathological changes in follow-up medical images is provided. In an embodiment, the method includes: providing reference image data showing a body part of a patient at a first time; providing follow-up image data showing a body part of a patient at a subsequent second time; generating one or more deformation fields for the reference image data and the follow-up image data describing anatomical deformations in the body part between the reference image data and the follow-up image data using at least one image registration; aligning the reference image data and the follow up image data using the one or more deformation fields to generate co-aligned image data; analyzing the co-aligned image data to identify pathological changes in the body part from the reference image data to the follow image data using a machine learned network trained to recognize pathological relevant changes in co-aligned image data.

Implementations relate to diagnosis of crop yield predictions and/or crop yields at the field- and pixel-level. In various implementations, a first temporal sequence of high-elevation digital images may be obtained that captures a geographic area over a given time interval through a crop cycle of a first type of crop. Ground truth operational data generated through the given time interval and that influences a final crop yield of the first geographic area after the crop cycle may also be obtained. Based on these data, a ground truth-based crop yield prediction may be generated for the first geographic area at the crop cycle's end. Recommended operational change(s) may be identified based on distinct hypothetical crop yield prediction(s) for the first geographic area. Each distinct hypothetical crop yield prediction may be generated based on hypothetical operational data that includes altered data point(s) of the ground truth operational data.

In a related-art technology, training images in accordance with the number of classifications need to be prepared to perform training process. For this reason, in a case where a model is caused to output how much effect of a drug is expressed, a training image needs to be prepared for each expression degree, and it is troublesome to create the model. Provided is an apparatus including an image obtaining unit configured to obtain an evaluation target image depicting a subject of an evaluation target, a probability obtaining unit configured to obtain a recognition probability regarding the evaluation target image by using a model that outputs, in accordance with input of an image, a recognition probability at which a subject of the image is recognized as the subject before effect of a drug is expressed or the subject after the effect of the drug is expressed, and a calculation unit configured to calculate an expression degree of the effect of the drug based on the recognition probability of the evaluation target image.

The exemplified methods and systems facilitate the training of a noise-robust deep learning network that is sufficiently robust in the recognition of objects in images having extremely noisy elements such that the noise-robust network can match, or exceed, the performance of human counterparts. The extremely noisy elements may correspond to extremely noisy viewing conditions, e.g., that often manifests themselves in the real-world as poor weather or environment conditions, sub-optimal lighting conditions, sub-optimal image acquisition or capture, etc. The noise-robust deep learning network is trained both (i) with noisy training images with low signal-to-combined-signal-and-noise ratio (SSNR) and (ii) either with noiseless, or generally noiseless, training images or a second set of noisy training images having a SSNR value greater than that of the low-SSNR noisy training images.

A method, apparatus and storage medium for analyzing insect feeding behaviors are disclosed. The method comprises detecting insects in a video recording feeding activities of the insects by deep learning using a neural network to obtain a detection result, obtaining insect trajectories according to the detection result, and obtaining an analysis result according to the insect trajectories. According to the present disclosure, the detection and analysis are performed on a pre-recorded video by deep learning using a neural network, and then the insect trajectories and an analysis result are obtained according to the detection result, thus manual observation, recording and analysis are not needed, the efficiency is high. Besides, subjective assumptions are eliminated for higher accuracy. The present disclosure, as a method, apparatus and storage medium for analyzing insect feeding behaviors, can be widely used in the field of insect behavior analysis.

A medical scan viewing system is conFIG.d to: receive a first medical scan and a second medical scan from a medical picture archive system, the first medical scan associated with a unique patient ID and a first scan date and the second medical scan associated with the unique patient ID and a second scan date; identify locations of anatomical landmarks in the first medical scan; identifying corresponding locations of the anatomical landmarks in the second medical scan; co-register the first medical scan with the second medical scan based on the locations of the anatomical landmarks in the first medical scan with the corresponding locations of the anatomical landmarks in the second medical scan; and present for display, via an interactive user interface, the first medical scan with the second medical scan, wherein the first medical scan and the second medical scan are synchronously presented, based on the co-registering.

Disclosed is a method of measuring a physiological parameter in a contactless manner. The method includes acquiring a plurality of image frames for a subject, acquiring a first color channel value, a second color channel value, and a third color channel value for at least one image frame included in the plurality of image frames. The method further includes calculating a first difference and a second difference on the basis of the first color channel value, the second color channel value, and the third color channel value for at least one image frame included in the plurality of image frames. The first difference represents a difference between the first color channel value and the second color channel value for the same image frame, and the second difference represents a difference between the first color channel value and the third color channel value for the same image frame.