| Developers: | Samsung Electronics, Samsung Medison |
| Date of the premiere of the system: | November, 2018 |
| Branches: | Pharmaceutics, medicine, health care |
2018: Announcement of AI programs for KT-and MRT-scanners
At the end of November, 2018 Samsung was provided by several program for diagnostic medical imaging on the basis of artificial intelligence. The company already uses the announced tools in some, MRT-, KT- and the ultrasonography scanners.
The ultrasonic S-Detect system for researches of a breast represents the software on the basis of AI which analyzes damages of mammary glands according to the ultrasonography images, helps to standardize reports and to classify suspicious deviations using BIRADS ATLAS (reporting system and data analysis of visualization researches of a mammary gland).
According to recently published research of professor Tommaso Bartolotta from the University of Palermo in Italy, S-Detect significantly improves the accuracy of the general diagnostics of damages of a mammary gland: at doctors with experience up to four years the accuracy of establishment of the diagnosis increased from 0.83 to 0.87 (AUC). S-Detect can become the useful instrument of diagnostics for doctors who are not experts in diseases of mammary glands, however should reveal and diagnose them.
Using the AI function Bone Suppression, Samsung could show more accurately the drawing of lungs on roentgenograms in the sections which are usually shaded by edges. Besides, the South Korean company provided SimGrid – a system for optimization of replacement of the eliminating grids that allows to increase image quality by reduction by dispersion artifacts. Also the system of auto detection of nodal educations in easy (ALND) which represents a solution CAD on the basis of AI technology will be provided.
According to the research published in Journal of Thoracic Imaging, ALND increased the accuracy of identification of nodal malignant new growths of lungs of 3 cm in size or less on roentgenograms of a thorax by 7% (i.e. up to 92%) in comparison with normal methods of diagnostics.[1]
Notes
| The site content is translated by machine translation software powered by PROMT. The machine-translated articles are not always perfect and may contain errors in vocabulary, syntax or grammar. Read original article If you find inaccuracies or errors in the results of machine translation, please write to editor@tadviser.ru. We will make every effort to correct them as soon as possible. |