Autor(es): de Souza, Luis A. ; Mendel, Robert ; Strasser, Sophia ; Ebigbo, Alanna ; Probst, Andreas ; Messmann, Helmut ; Papa, João P. [UNESP] ; Palm, Christoph
Data: 2022
Identificador Persistente: http://hdl.handle.net/11449/233177
Origem: Oasisbr
Assunto(s): Adenocarcinoma; Barrett's esophagus; Computer-aided diagnosis; Explainable artificial intelligence; Machine learning
Made available in DSpace on 2022-05-01T05:29:29Z (GMT). No. of bitstreams: 0 Previous issue date: 2021-08-01
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their level of accountability and transparency must be provided in such evaluations. The reliability related to machine learning predictions must be explained and interpreted, especially if diagnosis support is addressed. For this task, the black-box nature of deep learning techniques must be lightened up to transfer its promising results into clinical practice. Hence, we aim to investigate the use of explainable artificial intelligence techniques to quantitatively highlight discriminative regions during the classification of early-cancerous tissues in Barrett's esophagus-diagnosed patients. Four Convolutional Neural Network models (AlexNet, SqueezeNet, ResNet50, and VGG16) were analyzed using five different interpretation techniques (saliency, guided backpropagation, integrated gradients, input × gradients, and DeepLIFT) to compare their agreement with experts' previous annotations of cancerous tissue. We could show that saliency attributes match best with the manual experts' delineations. Moreover, there is moderate to high correlation between the sensitivity of a model and the human-and-computer agreement. The results also lightened that the higher the model's sensitivity, the stronger the correlation of human and computational segmentation agreement. We observed a relevant relation between computational learning and experts' insights, demonstrating how human knowledge may influence the correct computational learning.
Department of Computing São Carlos Federal University - UFSCar
Regensburg Medical Image Computing (ReMIC) Ostbayerische Technische Hochschule Regensburg (OTH Regensburg)
Medizinische Klinik III Universitätsklinikum Augsburg
Department of Computing São Paulo State University UNESP
Regensburg Center of Health Sciences and Technology (RCHST)
Department of Computing São Paulo State University UNESP
FAPESP: 2013/07375–0
FAPESP: 2014/12236–1
FAPESP: 2016/19403–6
FAPESP: 2017/04847–9
FAPESP: 2019/08605–5
CNPq: 306166/2014–3
CNPq: 307066/2017–7
