Non-small cell lung cancer diagnosis aid with histopathological images using Explainable Deep Learning techniques

Background: Lung cancer has the highest mortality rate in the world, twice as high as the second highest. On the other hand, pathologists are overworked and this is detrimental to the time spent on each patient, diagnostic turnaround time, and their success rate. Objective: In this work, we design,...

Descripción completa

Detalles Bibliográficos
Autores: Civit Masot, Javier, Bañuls-Beaterio, Alejandro, Domínguez Morales, Manuel Jesús, Rivas Pérez, Manuel, Muñoz Saavedra, Luis, Rodríguez Corral, José María
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/140043
Acceso en línea:https://hdl.handle.net/11441/140043
https://doi.org/10.1016/j.cmpb.2022.107108
Access Level:acceso abierto
Palabra clave:Deep learning
Explainable deep learning
Convolutional neural networks
Lung cancer
Histopathology
Descripción
Sumario:Background: Lung cancer has the highest mortality rate in the world, twice as high as the second highest. On the other hand, pathologists are overworked and this is detrimental to the time spent on each patient, diagnostic turnaround time, and their success rate. Objective: In this work, we design, implement, and evaluate a diagnostic aid system for non-small cell lung cancer detection, using Deep Learning techniques. Methods: The classifier developed is based on Artificial Intelligence techniques, obtaining an automatic classification result between healthy, adenocarcinoma and squamous cell carcinoma, given an histopathological image from lung tissue. Moreover, a report module based on Explainable Deep Learning techniques is included and gives the pathologist information about the image’s areas used to classify the sample and the confidence of belonging to each class. Results: The results show a system accuracy between 97.11 and 99.69%, depending on the number of classes classified, and a value of the area under ROC curve between 99.77 and 99.94%. Conclusions: The classification results obtain a substantial improvement according to previous works. Thanks to the given report, the time spent by the pathologist and the diagnostic turnaround time can be reduced.