TY - GEN
T1 - Deep Learning Based Classiftcation of Normal and Hepatic Fibrosis Mouse Model Using Digital Pathology Images
AU - Kousar, Ayesha
AU - Damani, Shivam
AU - Anvekar, Priyanka
AU - Rajotia, Arush
AU - Gopalakrishnan, Keerthy
AU - Baraskar, Bhavana
AU - Modi, Vaishnavi K.
AU - Aedma, Keirthana
AU - Agarwal, Joshika
AU - Voruganti, Hima Varsha
AU - Singh, Mansunderbir
AU - Kostallari, Enis
AU - Arunachalam, Shivaram P.
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported by the GIH Division for the GIH Artificial Intelligence Laboratory (GAIL), Department of Medicine, Mayo Clinic, Rochester, MN USA.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Hepatic fibrosis, or the excessive accumulation of extracellular matrix proteins, such as collagen, is the hallmark of the most prevalent type of chronic liver disease. Advanced liver fibrosis has adverse consequences such as cirrhosis, liver failure, and portal hypertension, which frequently call for liver transplantation. Current research on liver fibrosis is heavily focused on understanding the molecular mechanisms underlying this disorder and provides an up-to-date overview of deep learning models used in experimental liver fibrosis research. We evaluated the original and augmented mice liver dataset using a convolutional neural network, VGG16, and a stratified k-fold cross validation model. The results obtained from VGG16 models were taken into consideration due to their suitable object recognition and classification algorithm. Our study suggested that the deep learning VGG16 model can classify healthy and fibrotic liver cells with an accuracy of 95% despite training and validation loss. This study creates a foundation for future research that will employ deep learning models as a non-invasive tool to gauge the severity of the disease and identify the best treatment course to hinder the advancement of fibrosis.
AB - Hepatic fibrosis, or the excessive accumulation of extracellular matrix proteins, such as collagen, is the hallmark of the most prevalent type of chronic liver disease. Advanced liver fibrosis has adverse consequences such as cirrhosis, liver failure, and portal hypertension, which frequently call for liver transplantation. Current research on liver fibrosis is heavily focused on understanding the molecular mechanisms underlying this disorder and provides an up-to-date overview of deep learning models used in experimental liver fibrosis research. We evaluated the original and augmented mice liver dataset using a convolutional neural network, VGG16, and a stratified k-fold cross validation model. The results obtained from VGG16 models were taken into consideration due to their suitable object recognition and classification algorithm. Our study suggested that the deep learning VGG16 model can classify healthy and fibrotic liver cells with an accuracy of 95% despite training and validation loss. This study creates a foundation for future research that will employ deep learning models as a non-invasive tool to gauge the severity of the disease and identify the best treatment course to hinder the advancement of fibrosis.
UR - http://www.scopus.com/inward/record.url?scp=85146687682&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85146687682&partnerID=8YFLogxK
U2 - 10.1109/BIBM55620.2022.9995460
DO - 10.1109/BIBM55620.2022.9995460
M3 - Conference contribution
AN - SCOPUS:85146687682
T3 - Proceedings - 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022
SP - 2308
EP - 2313
BT - Proceedings - 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022
A2 - Adjeroh, Donald
A2 - Long, Qi
A2 - Shi, Xinghua
A2 - Guo, Fei
A2 - Hu, Xiaohua
A2 - Aluru, Srinivas
A2 - Narasimhan, Giri
A2 - Wang, Jianxin
A2 - Kang, Mingon
A2 - Mondal, Ananda M.
A2 - Liu, Jin
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022
Y2 - 6 December 2022 through 8 December 2022
ER -