Automated surgical margin assessment in breast conserving surgery using SFDI with ensembles of self-confident deep convolutional networks

Abstract: With an adequate tissue dataset, supervised classification of tissue optical properties can be achieved in SFDI images of breast cancer lumpectomies with deep convolutional networks. Nevertheless, the use of a black-box classifier in current ex vivo setups provides output diagnostic images that are inevitably bound to show misclassified areas due to inter- and intra-patient variability that could potentially be misinterpreted in a real clinical setting. This work proposes the use of a novel architecture, the self-introspective classifier, where part of the model is dedicated to estimating its own expected classification error. The model can be used to generate metrics of self-confidence for a given classification problem, which can then be employed to show how much the network is familiar with the new incoming data. A heterogenous ensemble of four deep convolutional models with self-confidence, each sensitive to a different spatial scale of features, is tested on a cohort of 70 specimens, achieving a global leave-one-out cross-validation accuracy of up to 81%, while being able to explain where in the output classification image the system is most confident.

Otras comunicaciones del congreso o articulos relacionados con autores/as de la Universidad de Cantabria

 Autoría: Pardo A., Gutiérrez-Gutiérrez J.A., Streeter S.S., Maloney B.W., López-Higuera J.M., Pogue B.W., Conde O.M.,

 Congreso: Clinical Biophotonics Conference (2020 : Francia)

Editorial: SPIE Society of Photo-Optical Instrumentation Engineers

 Fecha de publicación: 01/04/2020

Tipo de publicación: Comunicación a Congreso

DOI: 10.1117/12.2554965

ISSN: 0277-786X,1996-756X

Url de la publicación: https://doi.org/10.1117/12.2554965