» Articles » PMID: 36671641

Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses

Overview
Date 2023 Jan 21
PMID 36671641
Authors
Affiliations
Soon will be listed here.
Abstract

Ultrasound (US) is often used to diagnose liver masses. Ensemble learning has recently been commonly used for image classification, but its detailed methods are not fully optimized. The purpose of this study is to investigate the usefulness and comparison of some ensemble learning and ensemble pruning techniques using multiple convolutional neural network (CNN) trained models for image classification of liver masses in US images. Dataset of the US images were classified into four categories: benign liver tumor (BLT) 6320 images, liver cyst (LCY) 2320 images, metastatic liver cancer (MLC) 9720 images, primary liver cancer (PLC) 7840 images. In this study, 250 test images were randomly selected for each class, for a total of 1000 images, and the remaining images were used as the training. 16 different CNNs were used for training and testing ultrasound images. The ensemble learning used soft voting (SV), weighted average voting (WAV), weighted hard voting (WHV) and stacking (ST). All four types of ensemble learning (SV, ST, WAV, and WHV) showed higher values of accuracy than the single CNN. All four types also showed significantly higher deep learning (DL) performance than ResNeXt101 alone. For image classification of liver masses using US images, ensemble learning improved the performance of DL over a single CNN.

Citing Articles

Liver fibrosis stage classification in stacked microvascular images based on deep learning.

Miura D, Suenaga H, Hiwatashi R, Mabu S BMC Med Imaging. 2025; 25(1):8.

PMID: 39773130 PMC: 11706143. DOI: 10.1186/s12880-024-01531-x.


Sonoelastography for Testicular Tumor Identification: A Systematic Review and Meta-Analysis of Diagnostic Test Accuracy.

Lai D, Cheng E, Mao Y, Zheng Y, Yao K, Ni M Cancers (Basel). 2023; 15(15).

PMID: 37568585 PMC: 10417060. DOI: 10.3390/cancers15153770.

References
1.
Kondo S, Takagi K, Nishida M, Iwai T, Kudo Y, Ogawa K . Computer-Aided Diagnosis of Focal Liver Lesions Using Contrast-Enhanced Ultrasonography With Perflubutane Microbubbles. IEEE Trans Med Imaging. 2017; 36(7):1427-1437. DOI: 10.1109/TMI.2017.2659734. View

2.
Heisler M, Karst S, Lo J, Mammo Z, Yu T, Warner S . Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography. Transl Vis Sci Technol. 2020; 9(2):20. PMC: 7396168. DOI: 10.1167/tvst.9.2.20. View

3.
Cassinotto C, Aube C, Dohan A . Diagnosis of hepatocellular carcinoma: An update on international guidelines. Diagn Interv Imaging. 2017; 98(5):379-391. DOI: 10.1016/j.diii.2017.01.014. View

4.
Hwang Y, Lee J, Young Kim G, Jiang Y, Kim S . Classification of focal liver lesions on ultrasound images by extracting hybrid textural features and using an artificial neural network. Biomed Mater Eng. 2015; 26 Suppl 1:S1599-611. DOI: 10.3233/BME-151459. View

5.
Streba C, Ionescu M, Gheonea D, Sandulescu L, Ciurea T, Saftoiu A . Contrast-enhanced ultrasonography parameters in neural network diagnosis of liver tumors. World J Gastroenterol. 2012; 18(32):4427-34. PMC: 3436061. DOI: 10.3748/wjg.v18.i32.4427. View