Article
Recognition Rate Advancement and Data Error Improvement of
Pathology Cutting with H-DenseUNet for Hepatocellular
Carcinoma Image
Wen-Fan Chen
1,†
, Hsin-You Ou
2,†
, Cheng-Tang Pan
3
, Chien-Chang Liao
2
, Wen Huang
3
, Han-Yu Lin
3
,
Yu-Fan Cheng
2,
* and Chia-Po Wei
4,
*
Citation: Chen, W.-F.; Ou, H.-Y.; Pan,
C.-T.; Liao, C.-C.; Huang, W.; Lin,
H.-Y.; Cheng, Y.-F.; Wei, C.-P.
Recognition Rate Advancement and
Data Error Improvement of Pathology
Cutting with H-DenseUNet for
Hepatocellular Carcinoma Image.
Diagnostics 2021, 11, 1599. https://
doi.org/10.3390/diagnostics11091599
Academic Editors: Keun Ho Ryu and
Nipon Theera-Umpon
Received: 4 August 2021
Accepted: 29 August 2021
Published: 2 September 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
1
Institute of Medical Science and Technology, National Sun Yat-sen University, Kaohsiung 80424, Taiwan;
sallychen@imst.nsysu.edu.tw
2
Liver Transplantation Program and Departments of Diagnostic Radiology, Surgery Kaohsiung Chang Gung
Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung 833401, Taiwan;
ouhsinyou@gmail.com (H.-Y.O.); liao1009@gmail.com (C.-C.L.)
3
Department of Mechanical and Electro-Mechanical Engineering, National Sun Yat-sen University,
Kaohsiung 80424, Taiwan; pan@mem.nsysu.edu.tw (C.-T.P.); hwkakaku@mem.nsysu.edu.tw (W.H.);
hanyu@mem.nsysu.edu.tw (H.-Y.L.)
4
Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung 80424, Taiwan
* Correspondence: prof.chengyufan@gmail.com (Y.-F.C.); cpwei@mail.ee.nsysu.edu.tw (C.-P.W.);
Tel.: +886-773-17123-3027 (Y.-F.C.); +886-752-52000-4189 (C.-P.W.)
† These authors contribute equally.
Abstract:
Due to the fact that previous studies have rarely investigated the recognition rate discrep-
ancy and pathology data error when applied to different databases, the purpose of this study is to
investigate the improvement of recognition rate via deep learning-based liver lesion segmentation
with the incorporation of hospital data. The recognition model used in this study is H-DenseUNet,
which is applied to the segmentation of the liver and lesions, and a mixture of 2D/3D Hybrid-
DenseUNet is used to reduce the recognition time and system memory requirements. Differences in
recognition results were determined by comparing the training files of the standard LiTS competition
data set with the training set after mixing in an additional 30 patients. The average error value of
9.6% was obtained by comparing the data discrepancy between the actual pathology data and the
pathology data after the analysis of the identified images imported from Kaohsiung Chang Gung
Memorial Hospital. The average error rate of the recognition output after mixing the LiTS database
with hospital data for training was 1%. In the recognition part, the Dice coefficient was 0.52 after
training 50 epochs using the standard LiTS database, while the Dice coefficient was increased to
0.61 after
adding 30 hospital data to the training. After importing 3D Slice and ITK-Snap software, a
3D image of the lesion and liver segmentation can be developed. It is hoped that this method could
be used to stimulate more research in addition to the general public standard database in the future,
as well as to study the applicability of hospital data and improve the generality of the database.
Keywords:
data comparison; deep learning; H-DenseUNet; lesion segmentation; liver segmentation;
medical statistics; pathological
1. Introduction
According to statistics, chronic liver disease and liver cancer are among the leading
causes of death each year. Hepatocellular carcinoma (HCC) is mainly caused by primary
malignant tumors of the liver and is commonly seen in patients with chronic liver disease or
cirrhosis following hepatitis B and C infection and has fewer early symptoms. Traditionally,
radiologists often need to collect a lot of patient information and review each magnetic
resonance imaging (MRI) report separately, which not only generates a huge workload but
also may delay the optimal treatment time for liver cancer patients. In recent years, artificial
Diagnostics 2021, 11, 1599. https://doi.org/10.3390/diagnostics11091599 https://www.mdpi.com/journal/diagnostics
