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 3. Отображено 3.
01-08-2023 дата публикации

Ejecting fraction automatic evaluation method and device for echocardiography feature map filtering

Номер: CN116524001A
Автор: XU MINGJIE, JIANG YITAO, ZHANG YUNXU, SHI SIYUAN, CUI CHEN
Принадлежит:

The invention discloses an automatic ejection fraction evaluation method and device for echocardiogram feature map filtering, and the method comprises the steps: intercepting echocardiogram video data of any time length of a standard section, and enabling the image quality of the echocardiogram video data to reach the standard; using a neural network segmentation model obtained by pre-training to identify data of tangent surfaces of a left ventricle long-axis four-lumen heart and a left ventricle long-axis two-lumen heart in the echocardiogram data; filtering the feature map on a time axis by using data of tangent surfaces of a left ventricle long-axis four-lumen heart and a left ventricle long-axis two-lumen heart, taking the filtered feature map as input of a segmentation prediction head and a key point prediction head, and calculating a myocardial segmentation map and a left ventricle basal segment key point; obtaining a left ventricular myocardial inner contour and a left ventricular ...

Подробнее
Номер записи: 1
14-07-2023 дата публикации

Feature map filtering prediction method and device based on echocardiography

Номер: CN116421224A
Автор: ZHANG YUNXU, CHEN JIAYI, JIANG YITAO, SHI SIYUAN, CUI CHEN
Принадлежит:

The invention discloses a feature map filtering prediction method and device based on echocardiography, and the method comprises the steps: training a neural network model in a single-frame image training set, and obtaining a feature extraction trunk and a neural network prediction head of the neural network model; sequentially inputting the single-frame image training set of the test sample into a feature extraction trunk according to a time sequence, and extracting an image feature map set corresponding to the single-frame image training set; carrying out filtering processing on the single image feature maps in the feature map set based on a time neighborhood; and inputting the filtered single image feature map into a neural network prediction head to obtain a prediction result of the video sample, the prediction result of the video sample corresponding to the time axis of the single image feature map. According to the method, the image feature map extracted by the neural network model ...

Подробнее
Номер записи: 2
16-06-2023 дата публикации

Feature point extraction method and device, computer equipment and storage medium

Номер: CN116263985A
Автор: ZHANG YUNXU, CHEN JUNQIANG, CUI CHEN, SHI SIYUAN, ZOU YINQING
Принадлежит:

The invention relates to a feature point extraction method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a tooth three-dimensional mesh model comprising a plurality of mesh vertexes of a target object, and calculating the height value of each mesh vertex in the tooth three-dimensional mesh model; according to a preset watershed algorithm and the height value of each grid vertex included in the tooth three-dimensional grid model, screening the grid vertex corresponding to the local minimum value from each grid vertex to obtain a local minimum value set; and performing hierarchical clustering on the local minimum value set, and determining the feature points of the tooth three-dimensional grid model according to the hierarchical clustering result, so that automatic extraction of the tooth feature points can be realized without precise segmentation of the tooth model, the extraction precision is relatively high, the extraction efficiency ...

Подробнее
Номер записи: 3