1
|
Salehi MA, Harandi H, Mohammadi S, Shahrabi Farahani M, Shojaei S, Saleh RR. Diagnostic Performance of Artificial Intelligence in Detection of Hepatocellular Carcinoma: A Meta-analysis. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01058-1. [PMID: 38438694 DOI: 10.1007/s10278-024-01058-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Revised: 02/18/2024] [Accepted: 02/19/2024] [Indexed: 03/06/2024]
Abstract
Due to the increasing interest in the use of artificial intelligence (AI) algorithms in hepatocellular carcinoma detection, we performed a systematic review and meta-analysis to pool the data on diagnostic performance metrics of AI and to compare them with clinicians' performance. A search in PubMed and Scopus was performed in January 2024 to find studies that evaluated and/or validated an AI algorithm for the detection of HCC. We performed a meta-analysis to pool the data on the metrics of diagnostic performance. Subgroup analysis based on the modality of imaging and meta-regression based on multiple parameters were performed to find potential sources of heterogeneity. The risk of bias was assessed using Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) and Prediction Model Study Risk of Bias Assessment Tool (PROBAST) reporting guidelines. Out of 3177 studies screened, 44 eligible studies were included. The pooled sensitivity and specificity for internally validated AI algorithms were 84% (95% CI: 81,87) and 92% (95% CI: 90,94), respectively. Externally validated AI algorithms had a pooled sensitivity of 85% (95% CI: 78,89) and specificity of 84% (95% CI: 72,91). When clinicians were internally validated, their pooled sensitivity was 70% (95% CI: 60,78), while their pooled specificity was 85% (95% CI: 77,90). This study implies that AI can perform as a diagnostic supplement for clinicians and radiologists by screening images and highlighting regions of interest, thus improving workflow.
Collapse
Affiliation(s)
| | - Hamid Harandi
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
- Research Center for Antibiotic Stewardship and Antimicrobial Resistance, Imam Khomeini Hospital Complex, Tehran University of Medical Sciences, Tehran, Iran
| | - Soheil Mohammadi
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
| | | | - Shayan Shojaei
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - Ramy R Saleh
- Department of Oncology, McGill University, Montreal, QC, H3A 0G4, Canada
- Division of Medical Oncology, McGill University Health Centre, Montreal, QC, H4A 3J1, Canada
| |
Collapse
|
2
|
Takenaga T, Hanaoka S, Nomura Y, Nakao T, Shibata H, Miki S, Yoshikawa T, Hayashi N, Abe O. Development and evaluation of an integrated liver nodule diagnostic method by combining the liver segment division and lesion localization/classification models for enhanced focal liver lesion detection. Radiol Phys Technol 2024; 17:103-111. [PMID: 37917288 DOI: 10.1007/s12194-023-00753-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2023] [Revised: 10/02/2023] [Accepted: 10/10/2023] [Indexed: 11/04/2023]
Abstract
The purpose of the study was to develop a liver nodule diagnostic method that accurately localizes and classifies focal liver lesions and identifies the specific liver segments in which they reside by integrating a liver segment division algorithm using a four-dimensional (4D) fully convolutional residual network (FC-ResNet) with a localization and classification model. We retrospectively collected data and divided 106 gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid-enhanced magnetic resonance examinations into Case-sets 1, 2, and 3. A liver segment division algorithm was developed using a 4D FC-ResNet and trained with semi-automatically created silver-standard annotations; performance was evaluated using manually created gold-standard annotations by calculating the Dice scores for each liver segment. The performance of the liver nodule diagnostic method was assessed by comparing the results with those of the original radiology reports. The mean Dice score between the output of the liver segment division model and the gold standard was 0.643 for Case-set 2 (normal liver contours) and 0.534 for Case-set 1 (deformed liver contours). Among the 64 lesions in Case-set 3, the diagnostic method localized 37 lesions, classified 33 lesions, and identified the liver segments for 30 lesions. A total of 28 lesions were true positives, matching the original radiology reports. The liver nodule diagnostic method, which integrates a liver segment division algorithm with a lesion localization and classification model, exhibits great potential for localizing and classifying focal liver lesions and identifying the liver segments in which they reside. Further improvements and validation using larger sample sizes will enhance its performance and clinical applicability.
Collapse
Affiliation(s)
- Tomomi Takenaga
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan.
| | - Shouhei Hanaoka
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan
| | - Yukihiro Nomura
- Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan
- Center for Frontier Medical Engineering, Chiba University, 1-33 Yayoi-Cho, Inage-Ku, Chiba, Japan
| | - Takahiro Nakao
- Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan
| | - Hisaichi Shibata
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan
| | - Soichiro Miki
- Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan
| | - Takeharu Yoshikawa
- Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan
| | - Naoto Hayashi
- Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan
| | - Osamu Abe
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan
| |
Collapse
|
3
|
Automated volume measurement of abdominal adipose tissue from entire abdominal cavity in Dixon MR images using deep learning. Radiol Phys Technol 2023; 16:28-38. [PMID: 36344662 DOI: 10.1007/s12194-022-00687-x] [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: 08/08/2022] [Revised: 11/02/2022] [Accepted: 11/03/2022] [Indexed: 11/11/2022]
Abstract
The purpose of this study was to realize an automated volume measurement of abdominal adipose tissue from the entire abdominal cavity in Dixon magnetic resonance (MR) images using deep learning. Our algorithm involves a combination of extraction of the abdominal cavity and body trunk regions using deep learning and extraction of a fat region based on automatic thresholding. To evaluate the proposed method, we calculated the Dice coefficient (DC) between the extracted regions using deep learning and labeled images. We also compared the visceral adipose tissue (VAT) and subcutaneous adipose tissue volumes calculated by employing the proposed method with those calculated from computed tomography (CT) images scanned on the same day using the automatic calculation method previously developed by our group. We implemented our method as a plug-in in a web-based medical image processing platform. The DCs of the abdominal cavity and body trunk regions were 0.952 ± 0.014 and 0.995 ± 0.002, respectively. The VAT volume measured from MR images using the proposed method was almost equivalent to that measured from CT images. The time required for our plug-in to process the test set was 118.9 ± 28.0 s. Using our proposed method, the VAT volume measured from MR images can be an alternative to that measured from CT images.
Collapse
|
4
|
Wei J, Jiang H, Zhou Y, Tian J, Furtado FS, Catalano OA. Radiomics: A radiological evidence-based artificial intelligence technique to facilitate personalized precision medicine in hepatocellular carcinoma. Dig Liver Dis 2023:S1590-8658(22)00863-5. [PMID: 36641292 DOI: 10.1016/j.dld.2022.12.015] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Revised: 12/15/2022] [Accepted: 12/19/2022] [Indexed: 01/16/2023]
Abstract
The high postoperative recurrence rates in hepatocellular carcinoma (HCC) remain a major hurdle in its management. Appropriate staging and treatment selection may alleviate the extent of fatal recurrence. However, effective methods to preoperatively evaluate pathophysiologic and molecular characteristics of HCC are lacking. Imaging plays a central role in HCC diagnosis and stratification due to the non-invasive diagnostic criteria. Vast and crucial information is hidden within image data. Other than providing a morphological sketch for lesion diagnosis, imaging could provide new insights to describe the pathophysiological and genetic landscape of HCC. Radiomics aims to facilitate diagnosis and prognosis of HCC using artificial intelligence techniques to harness the immense information contained in medical images. Radiomics produces a set of archetypal and robust imaging features that are correlated to key pathological or molecular biomarkers to preoperatively risk-stratify HCC patients. Inferred with outcome data, comprehensive combination of radiomic, clinical and/or multi-omics data could also improve direct prediction of response to treatment and prognosis. The evolution of radiomics is changing our understanding of personalized precision medicine in HCC management. Herein, we review the key techniques and clinical applications in HCC radiomics and discuss current limitations and future opportunities to improve clinical decision making.
Collapse
Affiliation(s)
- Jingwei Wei
- Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, PR. China; Beijing Key Laboratory of Molecular Imaging, Beijing 100190, PR. China.
| | - Hanyu Jiang
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, Sichuan, 610041, PR. China
| | - Yu Zhou
- Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, PR. China; Beijing Key Laboratory of Molecular Imaging, Beijing 100190, PR. China; School of Life Science and Technology, Xidian University, Xi'an, PR. China
| | - Jie Tian
- Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, PR. China; Beijing Key Laboratory of Molecular Imaging, Beijing 100190, PR. China; Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine, Beihang University, Beijing, 100191, PR. China; Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, PR. China.
| | - Felipe S Furtado
- Department of Radiology, Massachusetts General Hospital, Boston, MA 02114, United States; Harvard Medical School, 25 Shattuck St, Boston, MA 02115, United States
| | - Onofrio A Catalano
- Department of Radiology, Massachusetts General Hospital, Boston, MA 02114, United States; Harvard Medical School, 25 Shattuck St, Boston, MA 02115, United States.
| |
Collapse
|
5
|
Cutolo C, Fusco R, Simonetti I, De Muzio F, Grassi F, Trovato P, Palumbo P, Bruno F, Maggialetti N, Borgheresi A, Bruno A, Chiti G, Bicci E, Brunese MC, Giovagnoni A, Miele V, Barile A, Izzo F, Granata V. Imaging Features of Main Hepatic Resections: The Radiologist Challenging. J Pers Med 2023; 13:jpm13010134. [PMID: 36675795 PMCID: PMC9862253 DOI: 10.3390/jpm13010134] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2022] [Revised: 12/31/2022] [Accepted: 01/06/2023] [Indexed: 01/12/2023] Open
Abstract
Liver resection is still the most effective treatment of primary liver malignancies, including hepatocellular carcinoma (HCC) and cholangiocarcinoma (CCA), and of metastatic disease, such as colorectal liver metastases. The type of liver resection (anatomic versus non anatomic resection) depends on different features, mainly on the type of malignancy (primary liver neoplasm versus metastatic lesion), size of tumor, its relation with blood and biliary vessels, and the volume of future liver remnant (FLT). Imaging plays a critical role in postoperative assessment, offering the possibility to recognize normal postoperative findings and potential complications. Ultrasonography (US) is the first-line diagnostic tool to use in post-surgical phase. However, computed tomography (CT), due to its comprehensive assessment, allows for a more accurate evaluation and more normal findings than the possible postoperative complications. Magnetic resonance imaging (MRI) with cholangiopancreatography (MRCP) and/or hepatospecific contrast agents remains the best tool for bile duct injuries diagnosis and for ischemic cholangitis evaluation. Consequently, radiologists should be familiar with the surgical approaches for a better comprehension of normal postoperative findings and of postoperative complications.
Collapse
Affiliation(s)
- Carmen Cutolo
- Department of Medicine, Surgery and Dentistry, University of Salerno, 84084 Salerno, Italy
| | - Roberta Fusco
- Medical Oncology Division, Igea SpA, 80013 Napoli, Italy
- Correspondence:
| | - Igino Simonetti
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy
| | - Federica De Muzio
- Department of Medicine and Health Sciences “V. Tiberio”, University of Molise, 86100 Campobasso, Italy
| | - Francesca Grassi
- Division of Radiology, Università degli Studi della Campania Luigi Vanvitelli, 80127 Naples, Italy
| | - Piero Trovato
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy
| | - Pierpaolo Palumbo
- Department of Diagnostic Imaging, Area of Cardiovascular and Interventional Imaging, Abruzzo Health Unit 1, 67100 L’Aquila, Italy
- Italian Society of Medical and Interventional Radiology (SIRM), SIRM Foundation, Via della Signora 2, 20122 Milan, Italy
| | - Federico Bruno
- Department of Diagnostic Imaging, Area of Cardiovascular and Interventional Imaging, Abruzzo Health Unit 1, 67100 L’Aquila, Italy
- Italian Society of Medical and Interventional Radiology (SIRM), SIRM Foundation, Via della Signora 2, 20122 Milan, Italy
| | - Nicola Maggialetti
- Department of Medical Science, Neuroscience and Sensory Organs (DSMBNOS), University of Bari “Aldo Moro”, 70124 Bari, Italy
| | - Alessandra Borgheresi
- Department of Radiology, University Hospital “Azienda Ospedaliera Universitaria delle Marche”, Via Conca 71, 60126 Ancona, Italy
- Department of Clinical, Special and Dental Sciences, University Politecnica delle Marche, Via Conca 71, 60126 Ancona, Italy
| | - Alessandra Bruno
- Department of Radiology, University Hospital “Azienda Ospedaliera Universitaria delle Marche”, Via Conca 71, 60126 Ancona, Italy
- Department of Clinical, Special and Dental Sciences, University Politecnica delle Marche, Via Conca 71, 60126 Ancona, Italy
| | - Giuditta Chiti
- Italian Society of Medical and Interventional Radiology (SIRM), SIRM Foundation, Via della Signora 2, 20122 Milan, Italy
- Department of Emergency Radiology, University Hospital Careggi, Largo Brambilla 3, 50134 Florence, Italy
| | - Eleonora Bicci
- Italian Society of Medical and Interventional Radiology (SIRM), SIRM Foundation, Via della Signora 2, 20122 Milan, Italy
- Department of Emergency Radiology, University Hospital Careggi, Largo Brambilla 3, 50134 Florence, Italy
| | - Maria Chiara Brunese
- Department of Medicine and Health Sciences “V. Tiberio”, University of Molise, 86100 Campobasso, Italy
| | - Andrea Giovagnoni
- Department of Radiology, University Hospital “Azienda Ospedaliera Universitaria delle Marche”, Via Conca 71, 60126 Ancona, Italy
- Department of Clinical, Special and Dental Sciences, University Politecnica delle Marche, Via Conca 71, 60126 Ancona, Italy
| | - Vittorio Miele
- Italian Society of Medical and Interventional Radiology (SIRM), SIRM Foundation, Via della Signora 2, 20122 Milan, Italy
- Department of Emergency Radiology, University Hospital Careggi, Largo Brambilla 3, 50134 Florence, Italy
| | - Antonio Barile
- Department of Applied Clinical Sciences and Biotechnology, University of L’Aquila, 67100 L’Aquila, Italy
| | - Francesco Izzo
- Division of Epatobiliary Surgical Oncology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy
| | - Vincenza Granata
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy
| |
Collapse
|
6
|
Imaging-based deep learning in liver diseases. Chin Med J (Engl) 2022; 135:1325-1327. [PMID: 35837673 PMCID: PMC9433077 DOI: 10.1097/cm9.0000000000002199] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/05/2023] Open
|