Advanced search
Start date
Betweenand

LivIA - a tool for diagnostic aid for hepatic lesions

Grant number: 19/05723-7
Support Opportunities:Research Grants - Innovative Research in Small Business - PIPE
Duration: February 01, 2020 - April 30, 2022
Field of knowledge:Health Sciences - Medicine - Medical Radiology
Convênio/Acordo: FINEP - PIPE/PAPPE Grant
Principal Investigator:Luis Gustavo Rocha Vianna
Grantee:Luis Gustavo Rocha Vianna
Host Company:Machiron Desenvolvimento de Sistemas Ltda
CNAE: Desenvolvimento de programas de computador sob encomenda
Desenvolvimento e licenciamento de programas de computador customizáveis
Tratamento de dados, provedores de serviços de aplicação e serviços de hospedagem na internet
City: São Paulo
Associated researchers:Marco Antonio Gutierrez ; Ricardo Di Lazzaro Filho ; Suzane Kioko Ono
Associated research grant:17/15770-7 - Development of Artificial Intelligence algorithm for diagnostic aid for hepatic lesions, AP.PIPE
Associated scholarship(s):21/04762-9 - LivIA: a tool for diagnostic Aid for hepatic lesions, BP.TT
21/04199-2 - LivIA: a tool for diagnostic Aid for hepatic lesions, BP.TT
20/07411-0 - LivIA: a tool for diagnostic aid for hepatic lesions, BP.TT
+ associated scholarships 20/05312-4 - LivIA: a tool for diagnostic aid for hepatic lesions, BP.TT
20/01079-3 - LivIA: a tool for diagnostic aid for hepatic lesions, BP.TT
20/00037-5 - LivIA: a tool for diagnostic aid for hepatic lesions, BP.PIPE - associated scholarships

Abstract

There is a market motivation and a trend towards the development of new technologies to improve diagnostic medicine, especially using Artificial Intelligence (AI). In this way, MaChiron was created with the aim of promoting computational solutions in several areas of health following the needs of the market of hospitals, medical insurance and laboratories in Brazil. The initiative of this project appeared in the Hepatology Department of the Hospital das Clínicas of the Faculty of Medicine of the University of São Paulo (HC-FMUSP), due to the growing demand for follow-up of patients at risk for hepatocellular carcinoma (HCC) together with the of a significant number of computed tomographies(CTs) for the early detection of this pathology. In this context, the LivIA tool will be developed to speed up the examination process, indicating which patients have suspected cancer nodules, so that these tests are evaluated as a priority in the workflow of the hospital radiology service. During Phase 1 of the PIPE program, MaChiron developed a platform to host the database required for algorithm training. To populate the database from the CT examinations provided by the Institute of Radiology (InRad-HC / USP), two radiologists are creating reports and masks following the standards used in competitions promoted by the academic area. In parallel, we are developing the algorithm for automatic segmentation of the liver and its lesions using public data. In this phase of feasibility study of the product, we obtained positive results. We have now been able to identify the liver in exams from HC already registered on the platform. The algorithm of lesion segmentation is in the validation phase. In the academic area, we are working on two articles: a review of liver segmentation methods using HC database and a description of the database development. With entrepreneurship training, we structure our business model and adapt our platform to meet the needs of our customers. During the second phase of PIPE, our objectives include increasing the number of exams in the database, developing the lesion classifier, generating a pre-report indicating the main features of the exams and associating a CHC risk value for each exam. For the whole process, we will have a follow-up of medical radiologists to evaluate the results. The Hospital das Clínicas offered to help us create an approval environment for the algorithm to be validated and inserted in the hospital flow. LivIA is a tool that brings a number of benefits to both public and private health care providers and patients. Among the advantages, it is worth noting the complete reports in less time, prioritization of patients according to the degree of risk, cost savings with hospitalized patients, standardization of reports and assistance for second medical opinion. (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
ROCHA, BRUNO ARAGAO; FERREIRA, LORENA CARNEIRO; ROCHA VIANNA, LUIS GUSTAVO; GOMES FERREIRA, LUMA GALLACIO; MARTINS CICONELLE, ANA CLAUDIA; DA SILVA NORONHA, ALEX; MARTINS CORTEZ FILHO, JOAO; LIMA NOGUEIRA, LUCAS SALUME; ROCHA SAMPAIO LEITE, JEAN MICHEL; DA SILVA FILHO, MAURICIO RICARDO MOREIRA; et al. Contrast phase recognition in liver computer tomography using deep learning. SCIENTIFIC REPORTS, v. 12, n. 1, p. 12-pg., . (20/01079-3, 20/00037-5, 21/04199-2, 19/05723-7, 20/07411-0)

Please report errors in scientific publications list using this form.
X

Report errors in this page


Error details: