Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma
BackgroundThe typical enhancement patterns of hepatocellular carcinoma (HCC) on contrast-enhanced ultrasound (CEUS) are hyper-enhanced in the arterial phase and washed out during the portal venous and late phases. However, atypical variations make a differential diagnosis both challenging and crucia...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-03-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2021.544979/full |
| _version_ | 1831547751578468352 |
|---|---|
| author | Wei Li Xiao-Zhou Lv Xin Zheng Si-Min Ruan Hang-Tong Hu Li-Da Chen Yang Huang Xin Li Chu-Qing Zhang Xiao-Yan Xie Ming Kuang Ming Kuang Ming-De Lu Ming-De Lu Bo-Wen Zhuang Wei Wang |
| author_facet | Wei Li Xiao-Zhou Lv Xin Zheng Si-Min Ruan Hang-Tong Hu Li-Da Chen Yang Huang Xin Li Chu-Qing Zhang Xiao-Yan Xie Ming Kuang Ming Kuang Ming-De Lu Ming-De Lu Bo-Wen Zhuang Wei Wang |
| author_sort | Wei Li |
| collection | DOAJ |
| description | BackgroundThe typical enhancement patterns of hepatocellular carcinoma (HCC) on contrast-enhanced ultrasound (CEUS) are hyper-enhanced in the arterial phase and washed out during the portal venous and late phases. However, atypical variations make a differential diagnosis both challenging and crucial. We aimed to investigate whether machine learning-based ultrasonic signatures derived from CEUS images could improve the diagnostic performance in differentiating focal nodular hyperplasia (FNH) and atypical hepatocellular carcinoma (aHCC).Patients and MethodsA total of 226 focal liver lesions, including 107 aHCC and 119 FNH lesions, examined by CEUS were reviewed retrospectively. For machine learning-based ultrasomics, 3,132 features were extracted from the images of the baseline, arterial, and portal phases. An ultrasomics signature was generated by a machine learning model. The predictive model was constructed using the support vector machine method trained with the following groups: ultrasomics features, radiologist’s score, and combination of ultrasomics features and radiologist’s score. The diagnostic performance was explored using the area under the receiver operating characteristic curve (AUC).ResultsA total of 14 ultrasomics features were chosen to build an ultrasomics model, and they presented good performance in differentiating FNH and aHCC with an AUC of 0.86 (95% confidence interval [CI]: 0.80, 0.89), a sensitivity of 76.6% (95% CI: 67.5%, 84.3%), and a specificity of 80.5% (95% CI: 70.6%, 85.9%). The model trained with a combination of ultrasomics features and the radiologist’s score achieved a significantly higher AUC (0.93, 95% CI: 0.89, 0.96) than that trained with the radiologist’s score (AUC: 0.84, 95% CI: 0.79, 0.89, P < 0.001). For the sub-group of HCC with normal AFP value, the model trained with a combination of ultrasomics features, and the radiologist’s score remain achieved the highest AUC of 0.92 (95% CI: 0.87, 0.96) compared to that with the ultrasomics features (AUC: 0.86, 95% CI: 0.74, 0.89, P < 0.001) and radiologist’s score (AUC: 0.86, 95% CI: 0.79, 0.91, P < 0.001).ConclusionsMachine learning-based ultrasomics performs as well as the staff radiologist in predicting the differential diagnosis of FNH and aHCC. Incorporating an ultrasomics signature into the radiologist’s score improves the diagnostic performance in differentiating FNH and aHCC. |
| first_indexed | 2024-12-17T02:07:15Z |
| format | Article |
| id | doaj.art-1eb0af4ee44f444294359d2cd5ccc735 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-17T02:07:15Z |
| publishDate | 2021-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-1eb0af4ee44f444294359d2cd5ccc7352022-12-21T22:07:39ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-03-011110.3389/fonc.2021.544979544979Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular CarcinomaWei Li0Xiao-Zhou Lv1Xin Zheng2Si-Min Ruan3Hang-Tong Hu4Li-Da Chen5Yang Huang6Xin Li7Chu-Qing Zhang8Xiao-Yan Xie9Ming Kuang10Ming Kuang11Ming-De Lu12Ming-De Lu13Bo-Wen Zhuang14Wei Wang15Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Traditional Chinese Medicine, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaResearch Center, GE Healthcare, Shanghai, ChinaZhongshan School of Medicine, Sun Yat-sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Hepatobiliary Surgery, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Hepatobiliary Surgery, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, ChinaBackgroundThe typical enhancement patterns of hepatocellular carcinoma (HCC) on contrast-enhanced ultrasound (CEUS) are hyper-enhanced in the arterial phase and washed out during the portal venous and late phases. However, atypical variations make a differential diagnosis both challenging and crucial. We aimed to investigate whether machine learning-based ultrasonic signatures derived from CEUS images could improve the diagnostic performance in differentiating focal nodular hyperplasia (FNH) and atypical hepatocellular carcinoma (aHCC).Patients and MethodsA total of 226 focal liver lesions, including 107 aHCC and 119 FNH lesions, examined by CEUS were reviewed retrospectively. For machine learning-based ultrasomics, 3,132 features were extracted from the images of the baseline, arterial, and portal phases. An ultrasomics signature was generated by a machine learning model. The predictive model was constructed using the support vector machine method trained with the following groups: ultrasomics features, radiologist’s score, and combination of ultrasomics features and radiologist’s score. The diagnostic performance was explored using the area under the receiver operating characteristic curve (AUC).ResultsA total of 14 ultrasomics features were chosen to build an ultrasomics model, and they presented good performance in differentiating FNH and aHCC with an AUC of 0.86 (95% confidence interval [CI]: 0.80, 0.89), a sensitivity of 76.6% (95% CI: 67.5%, 84.3%), and a specificity of 80.5% (95% CI: 70.6%, 85.9%). The model trained with a combination of ultrasomics features and the radiologist’s score achieved a significantly higher AUC (0.93, 95% CI: 0.89, 0.96) than that trained with the radiologist’s score (AUC: 0.84, 95% CI: 0.79, 0.89, P < 0.001). For the sub-group of HCC with normal AFP value, the model trained with a combination of ultrasomics features, and the radiologist’s score remain achieved the highest AUC of 0.92 (95% CI: 0.87, 0.96) compared to that with the ultrasomics features (AUC: 0.86, 95% CI: 0.74, 0.89, P < 0.001) and radiologist’s score (AUC: 0.86, 95% CI: 0.79, 0.91, P < 0.001).ConclusionsMachine learning-based ultrasomics performs as well as the staff radiologist in predicting the differential diagnosis of FNH and aHCC. Incorporating an ultrasomics signature into the radiologist’s score improves the diagnostic performance in differentiating FNH and aHCC.https://www.frontiersin.org/articles/10.3389/fonc.2021.544979/fullultrasonographymachine learningfocal nodular hyperplasiahepatocellular carcinomaultrasomics |
| spellingShingle | Wei Li Xiao-Zhou Lv Xin Zheng Si-Min Ruan Hang-Tong Hu Li-Da Chen Yang Huang Xin Li Chu-Qing Zhang Xiao-Yan Xie Ming Kuang Ming Kuang Ming-De Lu Ming-De Lu Bo-Wen Zhuang Wei Wang Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma Frontiers in Oncology ultrasonography machine learning focal nodular hyperplasia hepatocellular carcinoma ultrasomics |
| title | Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma |
| title_full | Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma |
| title_fullStr | Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma |
| title_full_unstemmed | Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma |
| title_short | Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma |
| title_sort | machine learning based ultrasomics improves the diagnostic performance in differentiating focal nodular hyperplasia and atypical hepatocellular carcinoma |
| topic | ultrasonography machine learning focal nodular hyperplasia hepatocellular carcinoma ultrasomics |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2021.544979/full |
| work_keys_str_mv | AT weili machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT xiaozhoulv machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT xinzheng machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT siminruan machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT hangtonghu machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT lidachen machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT yanghuang machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT xinli machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT chuqingzhang machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT xiaoyanxie machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT mingkuang machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT mingkuang machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT mingdelu machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT mingdelu machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT bowenzhuang machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma AT weiwang machinelearningbasedultrasomicsimprovesthediagnosticperformanceindifferentiatingfocalnodularhyperplasiaandatypicalhepatocellularcarcinoma |