Resumen
Datos solicitados: Radiografías de tórax y/o TAC pulmonar de pacientes con diagnóstico de COVID-19
Objetivo del proyecto: Desarrollo de algoritmos de Inteligencia Artificial para mejorar el diagnóstico
Requester
Name: Akhmad Renata
Institution: Almaty, Kazakhstan, LLP Crystal Spring (in collaboration with Institution of Oncology and Radiology, Almaty, Kazakhstan)
Web: MedHub
Description of project:
Our team has developed a service for detection lung diseases on the chest x-ray images by neural networks analysis (freely available for simple users and for doctors on imedhub.org). This service was developed before the pandemic, and we have realized that it can detect symptoms of pneumonia and infiltration in COVID-19 patients. This preliminary work was done on a small set of images, and we need to obtain more data to improve our algorithm. We’re also working on the service that will analyze CT studies.
Terms of collaboration:
The requester is open to collaboration with the data provider, including co-authorship of any eventual paper. They are also open to collaborate with hospitals willing to use the service they already provide.
Detailed description of data:
Any of these datasets would help:
– Lung x-ray images with DX or CR modalities, ideally associated to their COVID-19 diagnosis. The requester needs more than 1000 images, but they don’t need to get them all from a single collaborator.
– CT scans, also associated to their COVID-19 diagnosis. Again, more than 1000 samples are needed in total, but not all need to come from a single collaborator.
All data can be anonymized before sending to the requester. If any personal information appears in the images themselves, Crowdfight can provide assistance to remove that information automatically.
Information about personal information:
All data can be anonymized before sending to the requester. Each image will be transformed into mathematical structures by the neural network, and only these structures need to be stored (so the images can be deleted from the requesters’ database after some time). If any personal information appears in the images themselves, Crowdfight can provide assistance to remove that information automatically.
Status of ethical approval:
The requester will work with anonymized datasets, and does not need ethical approval from their institution. They will work with the data provider to obtain any necessary ethical approvals to collect the data.
Nota: En caso necesario, Crowdfight COVID-19 puede proporcionar ayuda para el procesamiento, preparación o envío de los datos. Esto incluye asesoramiento técnico, apoyo de expertos en bases de datos, o voluntarios que realicen tareas manuales (organización de datos, etc.).