Con esta herramienta te facilitamos un acceso a todas las ofertas y demandas de tecnología europeas y a búsquedas de socios para participar en propuestas europeas de I+D publicadas en la red Enterprise Europe Network, pudiendo filtrar los resultados para facilitar las búsquedas más acordes con tus necesidades.

¿Quieres recibir estos listados de oportunidades de colaboración en tu correo de forma periódica y personalizada? Date de alta en nuestro Boletín

Para optimizar los resultados de la búsqueda, se recomienda utilizar términos en inglés.

Nuevo método de segmentación de órganos para tomografía por resonancia magnética (TRM)

Resumen

Tipo:
Oferta Tecnológica
Referencia:
TODE20171012001
Publicado:
23/11/2017
Caducidad:
23/11/2018
Resumen:
Un científico alemán ha desarrollado un método totalmente automático de segmentación de órganos para tomografía por resonancia magnética (MRT) que se utiliza en estudios epidemiológicos y en la práctica clínica. Este método segmenta órganos o áreas de órganos a partir de conjuntos de datos volumétricos de TRM multicanal. Para ello utiliza los resultados de la segmentación de datos de la prueba generados a mano y grabados por varias personas. Después de grabar un conjunto de datos de TRM, se utiliza un método de presegmentación. La información en la escala de grises se emplea con las regiones características para crear datos de probabilidad para el órgano. Se buscan socios con el fin de establecer acuerdos de licencia o cooperación en materia de investigación.



Details

Tittle:
Novel method for organ segmentation for magnetic resonance tomography (MRT)
Summary:
A German scientist developed a fully automated method for magnetic resonance tomography (MRT) for 3D segmentation of organs as used in epidemiological studies and clinical practice.
A cooperation in the frame of License or research cooperation agreement is offered.


Description:
The segmentation of organs or organ-regions into volumetric data is of great interest in epidemiological studies and in the clinical practice. Especially, the segmentation of the kidney parenchyma (kidney cortex and -mark) is very difficult due to the fluctuations of the magnetic resonance (MR) intensities in the kidney tissue.

In most of the known methods it is necessary to select the MRT data partly by hand. This manual segmentation needs a lot of time and makes such studies very expensive. To decrease the costs for epidemiological studies in the clinical practice and to avoid faulty segmentations, fully automated methods for 3D segmenting organs out of volumetric data are needed.

A German scientist developed a method to segment organs or organ areas out of multi-channeled volumetric MRT datasets.
To do so, the first invention uses segmentation outcomes from trial data which were generated by hand and recorded by several people. After recording a MRT dataset, a first pre-segmentation method is used. In this case, the grayscale information from the MRT data is used along with characteristic regions to create probability data for the organ.

A further development of this technique delivers the possibility to use the image slices from the training data to determine at least three classes of characteristic shape. For every class a support vector machine is trained. By using an exclusion method they are able to detect the characteristic organ form. Based on this segmented area a patient specific probability data set is generated, on which a further segmentation technique is used. By combining both methods, a reliable fully automated segmentation is possible, with one or more emphases. Furthermore, this application is less susceptible to variability in the MRT data. It is also possible to process one channel volumetric data.

The offered method is in a concept stage and needs further development. It is offered for licensing to companies interested in exploiting the method for their business in e. g. medical software development, imaging processes, biostatistics or epidemiology. Additionally, the scientist is interested in a further common development on the basis of a research cooperation agreement in order to transfer this method into a daily clinical practice.
Advantages and Innovations:
Compared with the state of the art the offered method:

- Is globally the only method for segmentation of kidney cortex and mark out of native MRT data.

- Delivers a reliable and fully automated segmentation and organ volumetric.

- Leads to time and cost saving because no manual intervention is needed.
Stage of Development:
Concept stage
IPs:
Patent(s) applied for but not yet granted

Partner sought

Type and Role of Partner Sought:
Type:
- Industry

Specific area of activity of the partner:
- Industry: Medical Technology, Imaging techniques

Task to be performed:
- Industry: Interest in development cooperation and commercialization of the invention

Client

Type and Size of Client:
University
Already Engaged in Trans-National Cooperation:
Si
Languages Spoken:
English
German

Keywords

Technology Keywords:
01004001 Applications for Health
06001001 Bioestadística, epidemiología
01003006 Computer Software
01003012 Imaging, Image Processing, Pattern Recognition