Using deep convolutional neural networks for multi-classification of thyroid tumor by histopathology: a large-scale pilot study
Lists
Only you see this
Abstract
The DCNN models, especially VGG-19, achieved satisfactory accuracies on the task of differentiating thyroid tumors by histopathology. Analysis of the misdiagnosed cases revealed that normal tissue and adenoma were the most challenging histological types for the DCNN to differentiate, while all the malignant classifications achieved excellent diagnostic efficiencies. The results indicate that DCNN models may have potential for facilitating histopathologic thyroid disease diagnosis.
BibTeX
@article{wang2019using,
author = {Yunjun Wang and Qing Guan and I Weng Lao and Li Wang and Yi‐Long Wu and Duanshu Li and Qinghai Ji and Yu Wang and Yongxue Zhu and Hongtao Lu and Jun Xiang},
title = {{Using deep convolutional neural networks for multi-classification of thyroid tumor by histopathology: a large-scale pilot study}},
journal = {Annals},
year = {2019},
doi = {10.21037/atm.2019.08.54},
}Loading related content...