Convolutional Neural Networks for the evaluation of cancer in Barrett’s esophagus: Explainable AI to lighten up the black-box
- 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 × 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.
Verfasserangaben: | Luis Antonio De Souza Jr.ORCiD, Robert MendelORCiD, Sophia Strasser, Alanna EbigboORCiD, Andreas Probst, Helmut Messmann, João Paulo PapaORCiD, Christoph PalmORCiDGND |
---|---|
URN: | urn:nbn:de:bvb:898-opus4-20126 |
DOI: | https://doi.org/10.1016/j.compbiomed.2021.104578 |
ISSN: | 0010-4825 |
Titel des übergeordneten Werkes (Englisch): | Computers in Biology and Medicine |
Verlag: | Elsevier |
Dokumentart: | Artikel aus einer Zeitschrift/Zeitung |
Sprache der Veröffentlichung: | Englisch |
Jahr der Veröffentlichung: | 2021 |
Veröffentlichende Institution: | Ostbayerische Technische Hochschule Regensburg |
Datum der Freischaltung: | 25.06.2021 |
Freies Schlagwort / Tag: | Adenocarcinoma; Barrett's esophagus; Computer-aided diagnosis; Explainable artificial intelligence; Machine learning |
GND-Schlagwort: | Deep Learning; Künstliche Intelligenz; Computerunterstützte Medizin |
Jahrgang: | 135 |
Aufsatznummer: | 104578 |
Erste Seite: | 1 |
Letzte Seite: | 14 |
Fakultäten / Institute / Einrichtungen: | Fakultät Informatik und Mathematik |
Regensburg Center of Health Sciences and Technology - RCHST | |
Fakultät Informatik und Mathematik / Regensburg Medical Image Computing (ReMIC) | |
Begutachtungsstatus: | peer-reviewed |
OpenAccess Publikationsweg: | Gold Open Access- Erstveröffentlichung in einem/als Open-Access-Medium |
Forschungsschwerpunkt: | Lebenswissenschaften und Ethik |
Lizenz (Deutsch): | Creative Commons - CC BY - Namensnennung 4.0 International |