Convolutional Neural Networks for the evaluation of cancer in Barrett's esophagus: Explainable AI to lighten up the black-box

Autor(es)

de Souza Jr, Luis A. ; Mendel, Robert ^[1] ; Strasser, Sophia ^[1] ; Ebigbo, Alanna ^[2] ; Probst, Andreas ^[2] ; Messmann, Helmut ^[2] ; Papa, Joao P. ^[3] ; Palm, Christoph ^{[1, 4]}

Afiliação do(s) autor(es)

^[1] de Souza Jr, Jr., Luis A., Ostbayer TH Regensburg OTH Regensburg, Regensburg Med Image Comp ReM, Regensburg - Germany

^[2] Univ Klinikum Augsburg, Med Klin 3, Augsburg - Germany

^[3] Sao Paulo State Univ, Dept Comp, UNESP, Sao Paulo - Brazil

^[4] OTH Regensburg, Regensburg Ctr Hlth Sci & Technol RCHST, Regensburg - Germany

• Tipo de documento: Artigo Científico
• Fonte: COMPUTERS IN BIOLOGY AND MEDICINE; v. 135, AUG 2021.
• Citações Web of Science: 0

Resumo

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 earlycancerous 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 x 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. (AU)

• Processo FAPESP: 17/04847-9 - Auxílio ao Diagnóstico Automático do Esôfago de Barrett Utilizando Aprendizado de Máquina
• Beneficiário: Luis Antonio de Souza Júnior
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 16/19403-6 - Modelos de aprendizado baseados em energia e suas aplicações
• Beneficiário: João Paulo Papa
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 14/12236-1 - AnImaLS: Anotação de Imagem em Larga Escala: o que máquinas e especialistas podem aprender interagindo?
• Beneficiário: Alexandre Xavier Falcão
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
• Beneficiário: Francisco Louzada Neto
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 19/08605-5 - Diagnóstico do esôfago de Barrett auxiliado por computador utilizando técnicas de aprendizado de máquina
• Beneficiário: Luis Antonio de Souza Júnior
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado