An Intelligent Radiomic Approach for Lung Cancer Screening
Torres, Guillermo (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Baeza, Sonia (Universitat Autònoma de Barcelona. Departament de Medicina)
Sánchez Ramos, Carles (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Guasch, Ignasi (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol)
Rosell, Antoni (Universitat Autònoma de Barcelona. Departament de Medicina)
Gil, Debora (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)

Date:	2022
Abstract:	The efficiency of lung cancer screening for reducing mortality is hindered by the high rate of false positives. Artificial intelligence applied to radiomics could help to early discard benign cases from the analysis of CT scans. The available amount of data and the fact that benign cases are a minority, constitutes a main challenge for the successful use of state of the art methods (like deep learning), which can be biased, over-fitted and lack of clinical reproducibility. We present an hybrid approach combining the potential of radiomic features to characterize nodules in CT scans and the generalization of the feed forward networks. In order to obtain maximal reproducibility with minimal training data, we propose an embedding of nodules based on the statistical significance of radiomic features for malignancy detection. This representation space of lesions is the input to a feed forward network, which architecture and hyperparameters are optimized using own-defined metrics of the diagnostic power of the whole system. Results of the best model on an independent set of patients achieve 100% of sensitivity and 83% of specificity (AUC = 0. 94) for malignancy detection.
Grants:	Agència de Gestió d'Ajuts Universitaris i de Recerca 2017-SGR-1624 Agencia Estatal de Investigación RTI2018-095209-B-C21
Note:	Funding: This project is supported by the Ministerio de Ciencia e Innovación (MCI), Agencia Estatal de Investigación (AEI) and Fondo Europeo de Desarrollo Regional (FEDER), RTI2018-095209-B-C21 (MCI/AEI/FEDER, UE), Generalitat de Catalunya, 2017-SGR-1624 and CERCA-Programme. Debora Gil is supported by Serra Hunter Fellow.
Note:	This project is supported by the Ministerio de Ciencia e Innovaci?n (MCI), Agencia Estatal de Investigaci?n (AEI) and Fondo Europeo de Desarrollo Regional (FEDER), RTI2018-095209-B-C21 (MCI/AEI/FEDER, UE), Generalitat de Catalunya, 2017-SGR-1624 and CERCA-Programme. Debora Gil is supported by Serra Hunter Fellow. Barcelona Respiratory Network (BRN), Acad?mia de Ci?ncies M?diques de Catalunya i Balears, i Fundaci? Ramon Pla i Armengol.
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Language:	Anglès
Document:	Article ; recerca ; Versió publicada
Subject:	Lung cancer ; Early diagnosis ; Screening ; Neural networks ; Image embedding ; Architecture optimization
Published in:	Applied sciences (Basel), Vol. 12 Núm. 3 (2-1 2022) , p. 1568, ISSN 2076-3417

DOI: 10.3390/app12031568

14 p, 925.5 KB

The record appears in these collections:
Research literature > UAB research groups literature > Research Centres and Groups (research output) > Health sciences and biosciences > Institut d'Investigació en Ciencies de la Salut Germans Trias i Pujol (IGTP)
Articles > Research articles
Articles > Published articles