Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 2. Отображено 2.
25-04-2023 дата публикации

CT (Computed Tomography) metal artifact removal method based on convergent diffusion model

Номер: CN116012478A
Автор: LUO GONGNING, MA XINGHUA, WANG KUANQUAN, WANG WEI
Принадлежит:

The invention relates to a CT metal artifact removal method, in particular to a CT metal artifact removal method based on a convergence type diffusion model. In order to solve the problem that the MAR method in the existing metal artifact removal cannot effectively cope with a zero training sample MAR scene, the metal artifact removal is carried out by using a convergent diffusion model, and the method comprises the following steps of: firstly, superposing Gaussian noise reaching a moment T on a CT image accompanied with metal artifact noise, namely a forward diffusion process corresponding to an image to be denoised; then estimating m and xi at the current moment t through a neural network by taking Gaussian noise accompanied with image information bias as input, and carrying out denoising reasoning from the moment t to the moment t-1 to obtain biased Gaussian distribution y 't-1; and repeating T times from the time T to the time 0 to obtain the CT image after metal artifact de-noising ...

Подробнее
Номер записи: 1
23-05-2023 дата публикации

Image segmentation system based on deep learning and grayscale information

Номер: CN116152285A
Автор: WANG KUANQUAN, LIU YASHU, LUO GONGNING, WANG WEI
Принадлежит:

The invention relates to an image segmentation system based on deep learning and gray scale information, in particular to a segmentation system based on deep learning and gray scale information for a small sample nuclear magnetic resonance data image, and aims to solve the problems that nuclear magnetic resonance image segmentation depends on a large amount of image data, generalization performance is poor, and image segmentation efficiency is high. The invention relates to a nuclear magnetic resonance image segmentation method, which solves the problems of low segmentation accuracy in a nuclear magnetic resonance image with non-uniform gray level distribution, or incomplete segmentation and discontinuous segmentation targets, and comprises a coding module, a space attention module, a gray level correction module, a segmentation module and a loss module, and is characterized in that the coding module is connected with the space attention module, the gray level correction module and the ...

Подробнее
Номер записи: 2