Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparison
Abstract Early detection of liver malignancy based on medical image analysis plays a crucial role in patient prognosis and personalized treatment. This task, however, is challenging due to several factors, including medical data scarcity and limited training samples. This paper presents a study of t...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-11-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-46695-8 |
_version_ | 1797630275571679232 |
---|---|
author | Van Ha Tang Soan T. M. Duong Chanh D. Tr. Nguyen Thanh M. Huynh Vo T. Duc Chien Phan Huyen Le Trung Bui Steven Q. H. Truong |
author_facet | Van Ha Tang Soan T. M. Duong Chanh D. Tr. Nguyen Thanh M. Huynh Vo T. Duc Chien Phan Huyen Le Trung Bui Steven Q. H. Truong |
author_sort | Van Ha Tang |
collection | DOAJ |
description | Abstract Early detection of liver malignancy based on medical image analysis plays a crucial role in patient prognosis and personalized treatment. This task, however, is challenging due to several factors, including medical data scarcity and limited training samples. This paper presents a study of three important aspects of radiomics feature from multiphase computed tomography (CT) for classifying hepatocellular carcinoma (HCC) and other focal liver lesions: wavelet-transformed feature extraction, relevant feature selection, and radiomics features-based classification under the inadequate training samples. Our analysis shows that combining radiomics features extracted from the wavelet and original CT domains enhance the classification performance significantly, compared with using those extracted from the wavelet or original domain only. To facilitate the multi-domain and multiphase radiomics feature combination, we introduce a logistic sparsity-based model for feature selection with Bayesian optimization and find that the proposed model yields more discriminative and relevant features than several existing methods, including filter-based, wrapper-based, or other model-based techniques. In addition, we present analysis and performance comparison with several recent deep convolutional neural network (CNN)-based feature models proposed for hepatic lesion diagnosis. The results show that under the inadequate data scenario, the proposed wavelet radiomics feature model produces comparable, if not higher, performance metrics than the CNN-based feature models in terms of area under the curve. |
first_indexed | 2024-03-11T11:06:02Z |
format | Article |
id | doaj.art-ee5d1ee07edb49b6b61dcd286702fe22 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-11T11:06:02Z |
publishDate | 2023-11-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-ee5d1ee07edb49b6b61dcd286702fe222023-11-12T12:16:06ZengNature PortfolioScientific Reports2045-23222023-11-0113111410.1038/s41598-023-46695-8Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparisonVan Ha Tang0Soan T. M. Duong1Chanh D. Tr. Nguyen2Thanh M. Huynh3Vo T. Duc4Chien Phan5Huyen Le6Trung Bui7Steven Q. H. Truong8VinBrain JSC.VinBrain JSC.VinBrain JSC.VinBrain JSC.University Medical Center Ho Chi Minh CityUniversity Medical Center Ho Chi Minh CityUniversity Medical Center Ho Chi Minh CityAdobe ResearchVinBrain JSC.Abstract Early detection of liver malignancy based on medical image analysis plays a crucial role in patient prognosis and personalized treatment. This task, however, is challenging due to several factors, including medical data scarcity and limited training samples. This paper presents a study of three important aspects of radiomics feature from multiphase computed tomography (CT) for classifying hepatocellular carcinoma (HCC) and other focal liver lesions: wavelet-transformed feature extraction, relevant feature selection, and radiomics features-based classification under the inadequate training samples. Our analysis shows that combining radiomics features extracted from the wavelet and original CT domains enhance the classification performance significantly, compared with using those extracted from the wavelet or original domain only. To facilitate the multi-domain and multiphase radiomics feature combination, we introduce a logistic sparsity-based model for feature selection with Bayesian optimization and find that the proposed model yields more discriminative and relevant features than several existing methods, including filter-based, wrapper-based, or other model-based techniques. In addition, we present analysis and performance comparison with several recent deep convolutional neural network (CNN)-based feature models proposed for hepatic lesion diagnosis. The results show that under the inadequate data scenario, the proposed wavelet radiomics feature model produces comparable, if not higher, performance metrics than the CNN-based feature models in terms of area under the curve.https://doi.org/10.1038/s41598-023-46695-8 |
spellingShingle | Van Ha Tang Soan T. M. Duong Chanh D. Tr. Nguyen Thanh M. Huynh Vo T. Duc Chien Phan Huyen Le Trung Bui Steven Q. H. Truong Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparison Scientific Reports |
title | Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparison |
title_full | Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparison |
title_fullStr | Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparison |
title_full_unstemmed | Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparison |
title_short | Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparison |
title_sort | wavelet radiomics features from multiphase ct images for screening hepatocellular carcinoma analysis and comparison |
url | https://doi.org/10.1038/s41598-023-46695-8 |
work_keys_str_mv | AT vanhatang waveletradiomicsfeaturesfrommultiphasectimagesforscreeninghepatocellularcarcinomaanalysisandcomparison AT soantmduong waveletradiomicsfeaturesfrommultiphasectimagesforscreeninghepatocellularcarcinomaanalysisandcomparison AT chanhdtrnguyen waveletradiomicsfeaturesfrommultiphasectimagesforscreeninghepatocellularcarcinomaanalysisandcomparison AT thanhmhuynh waveletradiomicsfeaturesfrommultiphasectimagesforscreeninghepatocellularcarcinomaanalysisandcomparison AT votduc waveletradiomicsfeaturesfrommultiphasectimagesforscreeninghepatocellularcarcinomaanalysisandcomparison AT chienphan waveletradiomicsfeaturesfrommultiphasectimagesforscreeninghepatocellularcarcinomaanalysisandcomparison AT huyenle waveletradiomicsfeaturesfrommultiphasectimagesforscreeninghepatocellularcarcinomaanalysisandcomparison AT trungbui waveletradiomicsfeaturesfrommultiphasectimagesforscreeninghepatocellularcarcinomaanalysisandcomparison AT stevenqhtruong waveletradiomicsfeaturesfrommultiphasectimagesforscreeninghepatocellularcarcinomaanalysisandcomparison |