Multimodal image assisted diagnosis system and construction method thereof

Abstract

The invention discloses a multimodal image assisted diagnosis system and a construction method thereof. The multimodal image assisted diagnosis system comprises a hospital server, an embedded development platform and a neural computing stick, wherein the neural computing stick is connected with the embedded development platform; the embedded development platform is connected with the hospital server; the hospital server, the embedded development platform and the neural computing stick are all in the same local area network environment; the hospital server stores patient information and corresponding multimodal image data; and a pre-trained deep learning model is deployed in the neural computing stick, thereby being capable of reducing the burdens on patients and doctors at the same time, and improving the working efficiency.

Description

technical field [0001] The invention relates to the technical field of medical diagnosis, and more specifically relates to a multimodal image-aided diagnosis system and a construction method thereof. Background technique [0002] In the clinical medical diagnosis process, the patient's image data often requires experts to manually select the target area and segment the ROI area, which is a very time-consuming and labor-intensive task. In addition, the current hospital has a variety of inspection tools and methods, and can obtain a variety of image data of patients, such as CT, MR, PET, SPECT, etc. However, these multi-modal images are often not collected by the same department and collected in the same department. In a single diagnostic device, patients often need to print the diagnostic results of multiple images and present them to the diagnostician for final decision-making, which increases the burden on patients and doctors and reduces work efficiency. [0003] Therefor...

AI Technical Summary

Problems solved by technology

[0002] In the process of clinical medical diagnosis, the patient's image data often requires experts to manually select the target area and segment the ROI area, which is a very time-consuming and labor-intensive task.

Moreover, the current hospital has a variety of inspection tools and methods, and can obtain a variety of image data of patients, such as CT, MR, PET, SPECT, etc. However, these multi-modal images are often not collected by the same department and collected in the same department. In a single diagnostic device, patients often need to print the diagnostic results of multiple images and present them to the diagnostician for final decision-making, which increases the burden on patients and doctors and reduces work efficiency

Images