1
|
Li J, Li H, Xiao F, Liu R, Chen Y, Xue M, Yu J, Liang P. Comparison of machine learning models and CEUS LI-RADS in differentiation of hepatic carcinoma and liver metastases in patients at risk of both hepatitis and extrahepatic malignancy. Cancer Imaging 2023; 23:63. [PMID: 37337302 DOI: 10.1186/s40644-023-00573-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2022] [Accepted: 05/19/2023] [Indexed: 06/21/2023] Open
Abstract
BACKGROUND CEUS LI-RADS (Contrast Enhanced Ultrasound Liver Imaging Reporting and Data System) has good diagnostic efficacy for differentiating hepatic carcinoma (HCC) from solid malignant tumors. However, it can be problematic in patients with both chronic hepatitis B and extrahepatic primary malignancy. We explored the diagnostic performance of LI-RADS criteria and CEUS-based machine learning (ML) models in such patients. METHODS Consecutive patients with hepatitis and HCC or liver metastasis (LM) who were included in a multicenter liver cancer database between July 2017 and January 2022 were enrolled in this study. LI-RADS and enhancement features were assessed in a training cohort, and ML models were constructed using gradient boosting, random forest, and generalized linear models. The diagnostic performance of the ML models was compared with LI-RADS in a validation cohort of patients with both chronic hepatitis and extrahepatic malignancy. RESULTS The mild washout time was adjusted to 54 s from 60 s, increasing accuracy from 76.8 to 79.4%. Through feature screening, washout type II, rim enhancement and unclear border were identified as the top three predictor variables. Using LI-RADS to differentiate HCC from LM, the sensitivity, specificity, and AUC were 68.2%, 88.6%, and 0.784, respectively. In comparison, the random forest and generalized linear model both showed significantly higher sensitivity and accuracy than LI-RADS (0.83 vs. 0.784; all P < 0.001). CONCLUSIONS Compared with LI-RADS, the random forest and generalized linear model had higher accuracy for differentiating HCC from LM in patients with chronic hepatitis B and extrahepatic malignancy.
Collapse
Affiliation(s)
- Jianming Li
- Department of Interventional Ultrasound, Fifth Medical Center of Chinese PLA General Hospital, 100 West Fourth Ring Middle Road, Feng Tai District, Beijing, 100853, China
| | - Huarong Li
- Department of Ultrasound, Aero-space Center Hospital, Beijing, China
| | - Fan Xiao
- Department of Interventional Ultrasound, Fifth Medical Center of Chinese PLA General Hospital, 100 West Fourth Ring Middle Road, Feng Tai District, Beijing, 100853, China
| | - Ruiqi Liu
- Department of Ultrasound, Affiliated Hospital of Jilin Medical University, Changchun, China
| | - Yixu Chen
- Department of Ultrasound, Chengdu Fifth People's Hospital, Chengdu, China
| | - Menglong Xue
- Department of Ultrasound, Guangxi Guigang People's Hospital, Guigang, China
| | - Jie Yu
- Department of Interventional Ultrasound, Fifth Medical Center of Chinese PLA General Hospital, 100 West Fourth Ring Middle Road, Feng Tai District, Beijing, 100853, China.
| | - Ping Liang
- Department of Interventional Ultrasound, Fifth Medical Center of Chinese PLA General Hospital, 100 West Fourth Ring Middle Road, Feng Tai District, Beijing, 100853, China.
| |
Collapse
|
2
|
Yamada A, Kamagata K, Hirata K, Ito R, Nakaura T, Ueda D, Fujita S, Fushimi Y, Fujima N, Matsui Y, Tatsugami F, Nozaki T, Fujioka T, Yanagawa M, Tsuboyama T, Kawamura M, Naganawa S. Clinical applications of artificial intelligence in liver imaging. LA RADIOLOGIA MEDICA 2023:10.1007/s11547-023-01638-1. [PMID: 37165151 DOI: 10.1007/s11547-023-01638-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Subscribe] [Scholar Register] [Received: 03/30/2023] [Accepted: 04/21/2023] [Indexed: 05/12/2023]
Abstract
This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.
Collapse
Affiliation(s)
- Akira Yamada
- Department of Radiology, Shinshu University School of Medicine, Matsumoto, Nagano, Japan.
| | - Koji Kamagata
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-Ku, Tokyo, Japan
| | - Kenji Hirata
- Department of Nuclear Medicine, Hokkaido University Hospital, Sapporo, Japan
| | - Rintaro Ito
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan
| | - Takeshi Nakaura
- Department of Diagnostic Radiology, Kumamoto University Graduate School of Medicine, Chuo-Ku, Kumamoto, Japan
| | - Daiju Ueda
- Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Abeno-Ku, Osaka, Japan
| | - Shohei Fujita
- Department of Radiology, University of Tokyo, Tokyo, Japan
| | - Yasutaka Fushimi
- Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Sakyoku, Kyoto, Japan
| | - Noriyuki Fujima
- Department of Diagnostic and Interventional Radiology, Hokkaido University Hospital, Sapporo, Japan
| | - Yusuke Matsui
- Department of Radiology, Faculty of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Kita-Ku, Okayama, Japan
| | - Fuminari Tatsugami
- Department of Diagnostic Radiology, Hiroshima University, Minami-Ku, Hiroshima City, Hiroshima, Japan
| | - Taiki Nozaki
- Department of Radiology, St. Luke's International Hospital, Tokyo, Japan
| | - Tomoyuki Fujioka
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Tokyo, Japan
| | - Masahiro Yanagawa
- Department of Radiology, Osaka University Graduate School of Medicine, Suita-City, Osaka, Japan
| | - Takahiro Tsuboyama
- Department of Radiology, Osaka University Graduate School of Medicine, Suita-City, Osaka, Japan
| | - Mariko Kawamura
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan
| | - Shinji Naganawa
- Department of Radiology, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan
| |
Collapse
|
3
|
Shen X, Wu J, Su J, Yao Z, Huang W, Zhang L, Jiang Y, Yu W, Li Z. Revisiting artificial intelligence diagnosis of hepatocellular carcinoma with DIKWH framework. Front Genet 2023; 14:1004481. [PMID: 37007970 PMCID: PMC10064216 DOI: 10.3389/fgene.2023.1004481] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2022] [Accepted: 02/14/2023] [Indexed: 03/09/2023] Open
Abstract
Hepatocellular carcinoma (HCC) is the most common type of liver cancer with a high morbidity and fatality rate. Traditional diagnostic methods for HCC are primarily based on clinical presentation, imaging features, and histopathology. With the rapid development of artificial intelligence (AI), which is increasingly used in the diagnosis, treatment, and prognosis prediction of HCC, an automated approach to HCC status classification is promising. AI integrates labeled clinical data, trains on new data of the same type, and performs interpretation tasks. Several studies have shown that AI techniques can help clinicians and radiologists be more efficient and reduce the misdiagnosis rate. However, the coverage of AI technologies leads to difficulty in which the type of AI technology is preferred to choose for a given problem and situation. Solving this concern, it can significantly reduce the time required to determine the required healthcare approach and provide more precise and personalized solutions for different problems. In our review of research work, we summarize existing research works, compare and classify the main results of these according to the specified data, information, knowledge, wisdom (DIKW) framework.
Collapse
Affiliation(s)
- Xiaomin Shen
- State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, National Clinical Research Center for Infectious Diseases, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, Zhejiang Provincial Key Laboratory for Drug Clinical Research and Evaluation, The First Affiliated Hospital, Zhejiang University, Hangzhou, China
| | - Jinxin Wu
- School of Computer Science, The University of Sydney, Sydney, NSW, Australia
| | - Junwei Su
- State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, National Clinical Research Center for Infectious Diseases, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, Zhejiang Provincial Key Laboratory for Drug Clinical Research and Evaluation, The First Affiliated Hospital, Zhejiang University, Hangzhou, China
| | - Zhenyu Yao
- School of Computer Science, King's College London, London, United Kingdom
| | - Wei Huang
- Department of Gastroenterology II, The First Affiliated Hospital, Zhejiang University, Hangzhou, China
| | - Li Zhang
- State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, National Clinical Research Center for Infectious Diseases, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, Zhejiang Provincial Key Laboratory for Drug Clinical Research and Evaluation, The First Affiliated Hospital, Zhejiang University, Hangzhou, China
| | - Yiheng Jiang
- Clinical Medicine, Nanjing Medical University, Nanjing, China
| | - Wei Yu
- State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, National Clinical Research Center for Infectious Diseases, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, Zhejiang Provincial Key Laboratory for Drug Clinical Research and Evaluation, The First Affiliated Hospital, Zhejiang University, Hangzhou, China
| | - Zhao Li
- School of Computer Science, Zhejiang University, Hangzhou, China
| |
Collapse
|
4
|
Nagami N, Arimura H, Nojiri J, Yunhao C, Ninomiya K, Ogata M, Oishi M, Ohira K, Kitamura S, Irie H. Dual segmentation models for poorly and well-differentiated hepatocellular carcinoma using two-step transfer deep learning on dynamic contrast-enhanced CT images. Phys Eng Sci Med 2023; 46:83-97. [PMID: 36469246 DOI: 10.1007/s13246-022-01202-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2022] [Accepted: 11/17/2022] [Indexed: 12/12/2022]
Abstract
The aim of this study was to develop dual segmentation models for poorly and well-differentiated hepatocellular carcinoma (HCC), using two-step transfer learning (TSTL) based on dynamic contrast-enhanced (DCE) computed tomography (CT) images. From 2013 to 2019, DCE-CT images of 128 patients with 80 poorly differentiated and 48 well-differentiated HCCs were selected at our hospital. In the first transfer learning (TL) step, a pre-trained segmentation model with 192 CT images of lung cancer patients was retrained as a poorly differentiated HCC model. In the second TL step, a well-differentiated HCC model was built from a poorly differentiated HCC model. The average three-dimensional Dice's similarity coefficient (3D-DSC) and 95th-percentile of the Hausdorff distance (95% HD) were mainly employed to evaluate the segmentation accuracy, based on a nested fourfold cross-validation test. The DSC denotes the degree of regional similarity between the HCC reference regions and the regions estimated using the proposed models. The 95% HD is defined as the 95th-percentile of the maximum measures of how far two subsets of a metric space are from each other. The average 3D-DSC and 95% HD were 0.849 ± 0.078 and 1.98 ± 0.71 mm, respectively, for poorly differentiated HCC regions, and 0.811 ± 0.089 and 2.01 ± 0.84 mm, respectively, for well-differentiated HCC regions. The average 3D-DSC for both regions was 1.2 times superior to that calculated without the TSTL. The proposed model using TSTL from the lung cancer dataset showed the potential to segment poorly and well-differentiated HCC regions on DCE-CT images.
Collapse
Affiliation(s)
- Noriyuki Nagami
- Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-Ku, Fukuoka City, Fukuoka, 812-8582, Japan
- Department of Radiology, Saga University Hospital, 5-1-1, Nabeshima, Saga City, Saga, 849-8501, Japan
| | - Hidetaka Arimura
- Division of Medical Quantum Science, Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-Ku, Fukuoka City, Fukuoka, 812-8582, Japan.
| | - Junichi Nojiri
- Medical Corporation Kouhoukai, Takagi Hospital, 141-11, Sakemi, Okawa City, Fukuoka, 831-0016, Japan
- Department of Radiology, Faculty of Medicine, Saga University, 5-1-1, Nabeshima, Saga City , Saga, 849-8501, Japan
| | - Cui Yunhao
- Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-Ku, Fukuoka City, Fukuoka, 812-8582, Japan
| | - Kenta Ninomiya
- Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-Ku, Fukuoka City, Fukuoka, 812-8582, Japan
| | - Manabu Ogata
- Department of Radiology, Saga University Hospital, 5-1-1, Nabeshima, Saga City, Saga, 849-8501, Japan
| | - Mitsutoshi Oishi
- Department of Radiology, Faculty of Medicine, Saga University, 5-1-1, Nabeshima, Saga City , Saga, 849-8501, Japan
| | - Keiichi Ohira
- Department of Radiology, Faculty of Medicine, Saga University, 5-1-1, Nabeshima, Saga City , Saga, 849-8501, Japan
| | - Shigetoshi Kitamura
- Department of Radiology, Saga University Hospital, 5-1-1, Nabeshima, Saga City, Saga, 849-8501, Japan
| | - Hiroyuki Irie
- Department of Radiology, Faculty of Medicine, Saga University, 5-1-1, Nabeshima, Saga City , Saga, 849-8501, Japan
| |
Collapse
|
5
|
Mine Y, Iwamoto Y, Okazaki S, Nakamura K, Takeda S, Peng TY, Mitsuhata C, Kakimoto N, Kozai K, Murayama T. Detecting the presence of supernumerary teeth during the early mixed dentition stage using deep learning algorithms: A pilot study. Int J Paediatr Dent 2022; 32:678-685. [PMID: 34904304 DOI: 10.1111/ipd.12946] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/14/2021] [Revised: 11/05/2021] [Accepted: 11/28/2021] [Indexed: 11/28/2022]
Abstract
BACKGROUND Supernumerary teeth are a common anomaly and are frequently observed in paediatric patients. To prevent or minimize complications, early diagnosis and treatment is ideal in children with supernumerary teeth. AIM This study aimed to apply convolutional neural network (CNN)-based deep learning to detect the presence of supernumerary teeth in children during the early mixed dentition stage. DESIGN Three CNN models, AlexNet, VGG16-TL, and InceptionV3-TL, were employed in this study. A total of 220 panoramic radiographs (from children aged 6 years 0 months to 9 years 6 months) including supernumerary teeth (cases, n = 120) or no anomalies (controls, n = 100) were retrospectively analyzed. The CNN performances were assessed according to accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and area under the ROC curves for a cross-validation test dataset. RESULTS The VGG16-TL model had the highest performance according to accuracy, sensitivity, specificity, and area under the ROC curve, but the other models had similar performance. CONCLUSION CNN-based deep learning is a promising approach for detecting the presence of supernumerary teeth during the early mixed dentition stage.
Collapse
Affiliation(s)
- Yuichi Mine
- Department of Medical System Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Yuko Iwamoto
- Department of Pediatric Dentistry, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Shota Okazaki
- Department of Medical System Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Kentaro Nakamura
- Department of Medical System Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Saori Takeda
- Department of Medical System Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Tzu-Yu Peng
- Research Center of Digital Oral Science and Technology, College of Oral Medicine, Taipei Medical University, Taipei, Taiwan.,School of Dentistry, College of Oral Medicine, Taipei Medical University, Taipei, Taiwan.,Department of Anatomy and Functional Restorations, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Chieko Mitsuhata
- Department of Pediatric Dentistry, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Naoya Kakimoto
- Department of Oral and Maxillofacial Radiology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Katsuyuki Kozai
- Department of Pediatric Dentistry, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Takeshi Murayama
- Department of Medical System Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| |
Collapse
|
6
|
Kusunoki M, Nakayama T, Nishie A, Yamashita Y, Kikuchi K, Eto M, Oda Y, Ishigami K. A deep learning-based approach for the diagnosis of adrenal adenoma: a new trial using CT. Br J Radiol 2022; 95:20211066. [PMID: 35522787 PMCID: PMC10996310 DOI: 10.1259/bjr.20211066] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2021] [Revised: 04/03/2022] [Accepted: 04/20/2022] [Indexed: 12/22/2022] Open
Abstract
OBJECTIVE To develop and validate deep convolutional neural network (DCNN) models for the diagnosis of adrenal adenoma (AA) using CT. METHODS This retrospective study enrolled 112 patients who underwent abdominal CT (non-contrast, early, and delayed phases) with 107 adrenal lesions (83 AAs and 24 non-AAs) confirmed pathologically and with 8 lesions confirmed by follow-up as metastatic carcinomas. Three patients had adrenal lesions on both sides. We constructed six DCNN models from six types of input images for comparison: non-contrast images only (Model A), delayed phase images only (Model B), three phasic images merged into a 3-channel (Model C), relative washout rate (RWR) image maps only (Model D), non-contrast and RWR maps merged into a 2-channel (Model E), and delayed phase and RWR maps merged into a 2-channel (Model F). These input images were prepared manually with cropping and registration of CT images. Each DCNN model with six convolutional layers was trained with data augmentation and hyperparameter tuning. The optimal threshold values for binary classification were determined from the receiver-operating characteristic curve analyses. We adopted the nested cross-validation method, in which the outer fivefold cross-validation was used to assess the diagnostic performance of the models and the inner fivefold cross-validation was used to tune hyperparameters of the models. RESULTS The areas under the curve with 95% confidence intervals of Models A-F were 0.94 [0.90, 0.98], 0.80 [0.69, 0.89], 0.97 [0.94, 1.00], 0.92 [0.85, 0.97], 0.99 [0.97, 1.00] and 0.94 [0.86, 0.99], respectively. Model E showed high area under the curve greater than 0.95. CONCLUSION DCNN models may be a useful tool for the diagnosis of AA using CT. ADVANCES IN KNOWLEDGE The current study demonstrates a deep learning-based approach could differentiate adrenal adenoma from non-adenoma using multiphasic CT.
Collapse
Affiliation(s)
- Masaoki Kusunoki
- Department of Clinical Radiology, Kyushu
University, Fukuoka,
Japan
| | - Tomohiro Nakayama
- Department of Radiology, Saiseikai Fukuoka General
Hospital, Fukuoka,
Japan
| | - Akihiro Nishie
- Department of Clinical Radiology, Kyushu
University, Fukuoka,
Japan
| | - Yasuo Yamashita
- Department of Clinical Radiology, Kyushu
University, Fukuoka,
Japan
- Department of Medical Technology, Kyushu
University, Fukuoka,
Japan
| | - Kazufumi Kikuchi
- Department of Clinical Radiology, Kyushu
University, Fukuoka,
Japan
| | - Masatoshi Eto
- Department of Urology, Kyushu University,
Fukuoka, Japan
| | - Yoshinao Oda
- Department of Anatomic Pathology, Kyushu
University, Fukuoka,
Japan
| | - Kousei Ishigami
- Department of Clinical Radiology, Kyushu
University, Fukuoka,
Japan
| |
Collapse
|
7
|
Kim HE, Cosa-Linan A, Santhanam N, Jannesari M, Maros ME, Ganslandt T. Transfer learning for medical image classification: a literature review. BMC Med Imaging 2022; 22:69. [PMID: 35418051 PMCID: PMC9007400 DOI: 10.1186/s12880-022-00793-7] [Citation(s) in RCA: 89] [Impact Index Per Article: 44.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2021] [Accepted: 03/30/2022] [Indexed: 02/07/2023] Open
Abstract
BACKGROUND Transfer learning (TL) with convolutional neural networks aims to improve performances on a new task by leveraging the knowledge of similar tasks learned in advance. It has made a major contribution to medical image analysis as it overcomes the data scarcity problem as well as it saves time and hardware resources. However, transfer learning has been arbitrarily configured in the majority of studies. This review paper attempts to provide guidance for selecting a model and TL approaches for the medical image classification task. METHODS 425 peer-reviewed articles were retrieved from two databases, PubMed and Web of Science, published in English, up until December 31, 2020. Articles were assessed by two independent reviewers, with the aid of a third reviewer in the case of discrepancies. We followed the PRISMA guidelines for the paper selection and 121 studies were regarded as eligible for the scope of this review. We investigated articles focused on selecting backbone models and TL approaches including feature extractor, feature extractor hybrid, fine-tuning and fine-tuning from scratch. RESULTS The majority of studies (n = 57) empirically evaluated multiple models followed by deep models (n = 33) and shallow (n = 24) models. Inception, one of the deep models, was the most employed in literature (n = 26). With respect to the TL, the majority of studies (n = 46) empirically benchmarked multiple approaches to identify the optimal configuration. The rest of the studies applied only a single approach for which feature extractor (n = 38) and fine-tuning from scratch (n = 27) were the two most favored approaches. Only a few studies applied feature extractor hybrid (n = 7) and fine-tuning (n = 3) with pretrained models. CONCLUSION The investigated studies demonstrated the efficacy of transfer learning despite the data scarcity. We encourage data scientists and practitioners to use deep models (e.g. ResNet or Inception) as feature extractors, which can save computational costs and time without degrading the predictive power.
Collapse
Affiliation(s)
- Hee E Kim
- Department of Biomedical Informatics at the Center for Preventive Medicine and Digital Health (CPD-BW), Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167, Mannheim, Germany.
| | - Alejandro Cosa-Linan
- Department of Biomedical Informatics at the Center for Preventive Medicine and Digital Health (CPD-BW), Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167, Mannheim, Germany
| | - Nandhini Santhanam
- Department of Biomedical Informatics at the Center for Preventive Medicine and Digital Health (CPD-BW), Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167, Mannheim, Germany
| | - Mahboubeh Jannesari
- Department of Biomedical Informatics at the Center for Preventive Medicine and Digital Health (CPD-BW), Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167, Mannheim, Germany
| | - Mate E Maros
- Department of Biomedical Informatics at the Center for Preventive Medicine and Digital Health (CPD-BW), Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167, Mannheim, Germany
| | - Thomas Ganslandt
- Department of Biomedical Informatics at the Center for Preventive Medicine and Digital Health (CPD-BW), Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167, Mannheim, Germany
- Chair of Medical Informatics, Friedrich-Alexander-Universität Erlangen-Nürnberg, Wetterkreuz 15, 91058, Erlangen, Germany
| |
Collapse
|
8
|
Balsano C, Alisi A, Brunetto MR, Invernizzi P, Burra P, Piscaglia F. The application of artificial intelligence in hepatology: A systematic review. Dig Liver Dis 2022; 54:299-308. [PMID: 34266794 DOI: 10.1016/j.dld.2021.06.011] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/02/2021] [Revised: 06/04/2021] [Accepted: 06/07/2021] [Indexed: 02/06/2023]
Abstract
The integration of human and artificial intelligence (AI) in medicine has only recently begun but it has already become obvious that intelligent systems can dramatically improve the management of liver diseases. Big data made it possible to envisage transformative developments of the use of AI for diagnosing, predicting prognosis and treating liver diseases, but there is still a lot of work to do. If we want to achieve the 21st century digital revolution, there is an urgent need for specific national and international rules, and to adhere to bioethical parameters when collecting data. Avoiding misleading results is essential for the effective use of AI. A crucial question is whether it is possible to sustain, technically and morally, the process of integration between man and machine. We present a systematic review on the applications of AI to hepatology, highlighting the current challenges and crucial issues related to the use of such technologies.
Collapse
Affiliation(s)
- Clara Balsano
- Dept. of Life, Health and Environmental Sciences MESVA, University of L'Aquila, Piazza S. Salvatore Tommasi 1, 67100, Coppito, L'Aquila. Italy; Francesco Balsano Foundation, Via Giovanni Battista Martini 6, 00198, Rome, Italy.
| | - Anna Alisi
- Research Unit of Molecular Genetics of Complex Phenotypes, Bambino Gesù Children's Hospital, IRCCS, Rome, Italy
| | - Maurizia R Brunetto
- Hepatology Unit and Laboratory of Molecular Genetics and Pathology of Hepatitis Viruses, University Hospital of Pisa, Pisa, Italy
| | - Pietro Invernizzi
- Division of Gastroenterology and Center of Autoimmune Liver Diseases, Department of Medicine and Surgery, San Gerardo Hospital, University of Milano, Bicocca, Italy
| | - Patrizia Burra
- Multivisceral Transplant Unit, Department of Surgery, Oncology, Gastroenterology, Padua University Hospital, Padua, Italy
| | - Fabio Piscaglia
- Division of Internal Medicine, IRCCS Azienda Ospedaliero Universitaria di Bologna, Bologna, Italy
| | | |
Collapse
|
9
|
Castaldo A, De Lucia DR, Pontillo G, Gatti M, Cocozza S, Ugga L, Cuocolo R. State of the Art in Artificial Intelligence and Radiomics in Hepatocellular Carcinoma. Diagnostics (Basel) 2021; 11:1194. [PMID: 34209197 PMCID: PMC8307071 DOI: 10.3390/diagnostics11071194] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2021] [Revised: 06/24/2021] [Accepted: 06/24/2021] [Indexed: 12/12/2022] Open
Abstract
The most common liver malignancy is hepatocellular carcinoma (HCC), which is also associated with high mortality. Often HCC develops in a chronic liver disease setting, and early diagnosis as well as accurate screening of high-risk patients is crucial for appropriate and effective management of these patients. While imaging characteristics of HCC are well-defined in the diagnostic phase, challenging cases still occur, and current prognostic and predictive models are limited in their accuracy. Radiomics and machine learning (ML) offer new tools to address these issues and may lead to scientific breakthroughs with the potential to impact clinical practice and improve patient outcomes. In this review, we will present an overview of these technologies in the setting of HCC imaging across different modalities and a range of applications. These include lesion segmentation, diagnosis, prognostic modeling and prediction of treatment response. Finally, limitations preventing clinical application of radiomics and ML at the present time are discussed, together with necessary future developments to bring the field forward and outside of a purely academic endeavor.
Collapse
Affiliation(s)
- Anna Castaldo
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, 80131 Naples, Italy; (A.C.); (D.R.D.L.); (G.P.); (S.C.); (L.U.)
| | - Davide Raffaele De Lucia
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, 80131 Naples, Italy; (A.C.); (D.R.D.L.); (G.P.); (S.C.); (L.U.)
| | - Giuseppe Pontillo
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, 80131 Naples, Italy; (A.C.); (D.R.D.L.); (G.P.); (S.C.); (L.U.)
| | - Marco Gatti
- Radiology Unit, Department of Surgical Sciences, University of Turin, 10124 Turin, Italy;
| | - Sirio Cocozza
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, 80131 Naples, Italy; (A.C.); (D.R.D.L.); (G.P.); (S.C.); (L.U.)
| | - Lorenzo Ugga
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, 80131 Naples, Italy; (A.C.); (D.R.D.L.); (G.P.); (S.C.); (L.U.)
| | - Renato Cuocolo
- Department of Clinical Medicine and Surgery, University of Naples “Federico II”, 80131 Naples, Italy
| |
Collapse
|
10
|
Yamada A. Deep learning promotes B-mode ultrasound screening for focal liver lesions. EBioMedicine 2020; 56:102814. [PMID: 32512516 PMCID: PMC7276510 DOI: 10.1016/j.ebiom.2020.102814] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2020] [Accepted: 05/12/2020] [Indexed: 12/24/2022] Open
Affiliation(s)
- Akira Yamada
- Shinshu University School of Medicine, Radiology, 3-1-1 Asahi Matsumoto, Nagano 390-8621, Japan.
| |
Collapse
|