1
|
Fotouhi M, Samadi Khoshe Mehr F, Delazar S, Shahidi R, Setayeshpour B, Toosi MN, Arian A. Assessment of LI-RADS efficacy in classification of hepatocellular carcinoma and benign liver nodules using DCE-MRI features and machine learning. Eur J Radiol Open 2023; 11:100535. [PMID: 37964787 PMCID: PMC10641154 DOI: 10.1016/j.ejro.2023.100535] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2023] [Revised: 10/12/2023] [Accepted: 10/23/2023] [Indexed: 11/16/2023] Open
Abstract
Purpose The current study aimed to evaluate the efficiency of dynamic contrast-enhanced (DCE) MRI visual features in classifying benign liver nodules and hepatocellular carcinoma (HCC) using a machine learning model. Methods 115 LI-RADS3, 137 LI-RADS4, and 140 LI-RADS5 nodules were included (392 nodules from 245 patients), which were evaluated by follow-up imaging for LR-3 and pathology results for LR-4 and LR-5 nodules. Data was collected retrospectively from 3 T and 1.5 T MRI scanners. All the lesions were categorized into 124 benign and 268 HCC lesions. Visual features included tumor size, arterial-phase hyper-enhancement (APHE), washout, lesion segment, mass/mass-like, and capsule presence. Gini-importance method extracted the most important features to prevent over-fitting. Final dataset was split into training(70%), validation(10%), and test dataset(20%). The SVM model was used to train the classifying algorithm. For model validation, 5-fold cross-validation was utilized, and the test data set was used to assess the final accuracy. The area under the curve and receiver operating characteristic curves were used to assess the performance of the classifier model. Results For test dataset, the accuracy, sensitivity, and specificity values for classifying benign and HCC lesions were 82%,84%, and 81%, respectively. APHE, washout, tumor size, and mass/mass-like features significantly differentiated benign and HCC lesions with p-value < .001. Conclusions The developed classification model employing DCE-MRI features showed significant performance of visual features in classifying benign and HCC lesions. Our study also highlighted the significance of mass and mass-like features in addition to LI-RADS categorization. For future work, this study suggests developing a deep-learning algorithm for automatic lesion segmentation and feature assessment to reduce lesion categorization errors.
Collapse
Affiliation(s)
- Maryam Fotouhi
- Advanced Diagnostic and Interventional Radiology (ADIR), Radiology department, Imam Khomeini Hospital Complex, Tehran University of Medical Science, Iran
| | - Fardin Samadi Khoshe Mehr
- Research Centre for Molecular and Cellular Imaging (RCMCI), Advanced Medical Technologies and Equipment Institute (AMTEI), Tehran University of Medical Sciences, Tehran, Iran
| | - Sina Delazar
- Advanced Diagnostic and Interventional Radiology (ADIR), Radiology department, Imam Khomeini Hospital Complex, Tehran University of Medical Science, Iran
| | - Ramin Shahidi
- School of Medicine, Bushehr University of Medical Sciences, Bushehr, Iran
| | | | - Mohssen Nassiri Toosi
- Imam Khomeini Hospital Complex, Liver Transplantation Research Centre, Tehran University of Medical Sciences, Tehran, Iran
| | - Arvin Arian
- Advanced Diagnostic and Interventional Radiology (ADIR), Radiology department, Imam Khomeini Hospital Complex, Tehran University of Medical Science, Iran
| |
Collapse
|
2
|
Fujima N, Nakagawa J, Kameda H, Ikebe Y, Harada T, Shimizu Y, Tsushima N, Kano S, Homma A, Kwon J, Yoneyama M, Kudo K. Improvement of image quality in diffusion-weighted imaging with model-based deep learning reconstruction for evaluations of the head and neck. MAGMA (NEW YORK, N.Y.) 2023:10.1007/s10334-023-01129-4. [PMID: 37989922 DOI: 10.1007/s10334-023-01129-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/15/2023] [Revised: 10/18/2023] [Accepted: 10/23/2023] [Indexed: 11/23/2023]
Abstract
OBJECTIVES To investigate the utility of deep learning (DL)-based image reconstruction using a model-based approach in head and neck diffusion-weighted imaging (DWI). MATERIALS AND METHODS We retrospectively analyzed the cases of 41 patients who underwent head/neck DWI. The DWI in 25 patients demonstrated an untreated lesion. We performed qualitative and quantitative assessments in the DWI analyses with both deep learning (DL)- and conventional parallel imaging (PI)-based reconstructions. For the qualitative assessment, we visually evaluated the overall image quality, soft tissue conspicuity, degree of artifact(s), and lesion conspicuity based on a five-point system. In the quantitative assessment, we measured the signal-to-noise ratio (SNR) of the bilateral parotid glands, submandibular gland, the posterior muscle, and the lesion. We then calculated the contrast-to-noise ratio (CNR) between the lesion and the adjacent muscle. RESULTS Significant differences were observed in the qualitative analysis between the DWI with PI-based and DL-based reconstructions for all of the evaluation items (p < 0.001). In the quantitative analysis, significant differences in the SNR and CNR between the DWI with PI-based and DL-based reconstructions were observed for all of the evaluation items (p = 0.002 ~ p < 0.001). DISCUSSION DL-based image reconstruction with the model-based technique effectively provided sufficient image quality in head/neck DWI.
Collapse
Affiliation(s)
- Noriyuki Fujima
- Department of Diagnostic and Interventional Radiology, Hokkaido University Hospital, N14 W5, Kita-Ku, Sapporo, 060-8638, Japan.
| | - Junichi Nakagawa
- Department of Diagnostic and Interventional Radiology, Hokkaido University Hospital, N14 W5, Kita-Ku, Sapporo, 060-8638, Japan
| | - Hiroyuki Kameda
- Faculty of Dental Medicine Department of Radiology, Hokkaido University, N13 W7, Kita-Ku, Sapporo, Hokkaido, 060-8586, Japan
| | - Yohei Ikebe
- Department of Diagnostic Imaging, Graduate School of Medicine, Hokkaido University, N15 W7, Kita-Ku, Sapporo, Hokkaido, 060-8638, Japan
- Center for Cause of Death Investigation, Faculty of Medicine, Hokkaido University, N15 W7, Kita-Ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Taisuke Harada
- Center for Cause of Death Investigation, Faculty of Medicine, Hokkaido University, N15 W7, Kita-Ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Yukie Shimizu
- Department of Diagnostic and Interventional Radiology, Hokkaido University Hospital, N14 W5, Kita-Ku, Sapporo, 060-8638, Japan
| | - Nayuta Tsushima
- Department of Otolaryngology-Head and Neck Surgery, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, N15 W7, Kita Ku, Sapporo, 060-8638, Japan
| | - Satoshi Kano
- Department of Otolaryngology-Head and Neck Surgery, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, N15 W7, Kita Ku, Sapporo, 060-8638, Japan
| | - Akihiro Homma
- Department of Otolaryngology-Head and Neck Surgery, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, N15 W7, Kita Ku, Sapporo, 060-8638, Japan
| | - Jihun Kwon
- Philips Japan, 3-37 Kohnan 2-Chome, Minato-Ku, Tokyo, 108-8507, Japan
| | - Masami Yoneyama
- Philips Japan, 3-37 Kohnan 2-Chome, Minato-Ku, Tokyo, 108-8507, Japan
| | - Kohsuke Kudo
- Department of Diagnostic Imaging, Graduate School of Medicine, Hokkaido University, N15 W7, Kita-Ku, Sapporo, Hokkaido, 060-8638, Japan
- Medical AI Research and Development Center, Hokkaido University Hospital, N14 W5, Kita-Ku, Sapporo, Hokkaido, 060-8638, Japan
- Global Center for Biomedical Science and Engineering, Faculty of Medicine, Hokkaido University, N14 W5, Kita-Ku, Sapporo, Hokkaido, 060-8638, Japan
| |
Collapse
|
3
|
Liu X, Elbanan MG, Luna A, Haider MA, Smith AD, Sabottke CF, Spieler BM, Turkbey B, Fuentes D, Moawad A, Kamel S, Horvat N, Elsayes KM. Radiomics in Abdominopelvic Solid-Organ Oncologic Imaging: Current Status. AJR Am J Roentgenol 2022; 219:985-995. [PMID: 35766531 PMCID: PMC10616929 DOI: 10.2214/ajr.22.27695] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
Radiomics is the process of extraction of high-throughput quantitative imaging features from medical images. These features represent noninvasive quantitative biomarkers that go beyond the traditional imaging features visible to the human eye. This article first reviews the steps of the radiomics pipeline, including image acquisition, ROI selection and image segmentation, image preprocessing, feature extraction, feature selection, and model development and application. Current evidence for the application of radiomics in abdominopelvic solid-organ cancers is then reviewed. Applications including diagnosis, subtype determination, treatment response assessment, and outcome prediction are explored within the context of hepatobiliary and pancreatic cancer, renal cell carcinoma, prostate cancer, gynecologic cancer, and adrenal masses. This literature review focuses on the strongest available evidence, including systematic reviews, meta-analyses, and large multicenter studies. Limitations of the available literature are highlighted, including marked heterogeneity in radiomics methodology, frequent use of small sample sizes with high risk of overfitting, and lack of prospective design, external validation, and standardized radiomics workflow. Thus, although studies have laid a foundation that supports continued investigation into radiomics models, stronger evidence is needed before clinical adoption.
Collapse
Affiliation(s)
- Xiaoyang Liu
- Joint Department of Medical Imaging, Division of Abdominal Imaging, University Health Network, University of Toronto, ON, Canada
| | - Mohamed G Elbanan
- Department of Radiology, Yale New Haven Health, Bridgeport Hospital, Bridgeport, CT
| | | | - Masoom A Haider
- Lunenfeld-Tanenbaum Research Institute, Sinai Health System, Toronto, ON, Canada
- Joint Department of Medical Imaging, University Health Network, Sinai Health System and University of Toronto, Toronto, ON, Canada
| | - Andrew D Smith
- Department of Radiology, University of Alabama at Birmingham, Birmingham, AL
| | - Carl F Sabottke
- Department of Medical Imaging, University of Arizona College of Medicine, Tucson, AZ
| | - Bradley M Spieler
- Department of Radiology, University Medical Center, Louisiana State University Health Sciences Center, New Orleans, LA
| | - Baris Turkbey
- Molecular Imaging Program, National Cancer Institute, NIH, Bethesda, MD
| | - David Fuentes
- Department of Imaging Physics, University of Texas MD Anderson Cancer Center, Houston, TX
| | - Ahmed Moawad
- Department of Diagnostic and Interventional Radiology, Mercy Catholic Medical Center, Darby, PA
| | - Serageldin Kamel
- Department of Lymphoma, University of Texas MD Anderson Cancer Center, Houston, TX
| | - Natally Horvat
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY
| | - Khaled M Elsayes
- Department of Abdominal Imaging, University of Texas MD Anderson Cancer Center, 1400 Pressler St, Houston, TX 77030
| |
Collapse
|
4
|
Martinino A, Aloulou M, Chatterjee S, Scarano Pereira JP, Singhal S, Patel T, Kirchgesner TPE, Agnes S, Annunziata S, Treglia G, Giovinazzo F. Artificial Intelligence in the Diagnosis of Hepatocellular Carcinoma: A Systematic Review. J Clin Med 2022; 11:6368. [PMID: 36362596 PMCID: PMC9655417 DOI: 10.3390/jcm11216368] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2022] [Revised: 10/21/2022] [Accepted: 10/26/2022] [Indexed: 09/21/2023] Open
Abstract
Hepatocellular carcinoma ranks fifth amongst the most common malignancies and is the third most common cause of cancer-related death globally. Artificial Intelligence is a rapidly growing field of interest. Following the PRISMA reporting guidelines, we conducted a systematic review to retrieve articles reporting the application of AI in HCC detection and characterization. A total of 27 articles were included and analyzed with our composite score for the evaluation of the quality of the publications. The contingency table reported a statistically significant constant improvement over the years of the total quality score (p = 0.004). Different AI methods have been adopted in the included articles correlated with 19 articles studying CT (41.30%), 20 studying US (43.47%), and 7 studying MRI (15.21%). No article has discussed the use of artificial intelligence in PET and X-ray technology. Our systematic approach has shown that previous works in HCC detection and characterization have assessed the comparability of conventional interpretation with machine learning using US, CT, and MRI. The distribution of the imaging techniques in our analysis reflects the usefulness and evolution of medical imaging for the diagnosis of HCC. Moreover, our results highlight an imminent need for data sharing in collaborative data repositories to minimize unnecessary repetition and wastage of resources.
Collapse
Affiliation(s)
| | | | - Surobhi Chatterjee
- Department of Internal Medicine, King George’s Medical University, Lucknow 226003, Uttar Pradesh, India
| | | | - Saurabh Singhal
- Department of HPB Surgery and Liver Transplantation, BLK-MAX Superspeciality Hospital, New Delhi 110005, Delhi, India
| | - Tapan Patel
- Department of Surgery, Baroda Medical College and SSG Hospital, Vadodara 390001, Gujarat, India
| | - Thomas Paul-Emile Kirchgesner
- Département of Radiology and Medical Imaging, Cliniques Universitaires Saint-Luc, Institut de Recherche Expérimentale et Clinique, Université Catholique de Louvain, 1348 Brussels, Belgium
| | - Salvatore Agnes
- General Surgery and Liver Transplantation Unit, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy
| | - Salvatore Annunziata
- Unit of Nuclear Medicine, Department of Radiology, Radiotherapy and Hematology, Fondazione Policlinico Universitario A. Gemelli IRCCS, 00168 Rome, Italy
| | - Giorgio Treglia
- Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale, 6500 Bellinzona, Switzerland
- Faculty of Biomedical Sciences, Università della Svizzera Italiana, 6900 Lugano, Switzerland
- Faculty of Biology and Medicine, University of Lausanne, 1015 Lausanne, Switzerland
| | - Francesco Giovinazzo
- General Surgery and Liver Transplantation Unit, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy
| |
Collapse
|
5
|
Focal Liver Lesion MRI Feature Identification Using Efficientnet and MONAI: A Feasibility Study. Cells 2022; 11:cells11091558. [PMID: 35563862 PMCID: PMC9104155 DOI: 10.3390/cells11091558] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2022] [Revised: 05/01/2022] [Accepted: 05/03/2022] [Indexed: 11/30/2022] Open
Abstract
Liver tumors constitute a major part of the global disease burden, often making regular imaging follow-up necessary. Recently, deep learning (DL) has increasingly been applied in this research area. How these methods could facilitate report writing is still a question, which our study aims to address by assessing multiple DL methods using the Medical Open Network for Artificial Intelligence (MONAI) framework, which may provide clinicians with preliminary information about a given liver lesion. For this purpose, we collected 2274 three-dimensional images of lesions, which we cropped from gadoxetate disodium enhanced T1w, native T1w, and T2w magnetic resonance imaging (MRI) scans. After we performed training and validation using 202 and 65 lesions, we selected the best performing model to predict features of lesions from our in-house test dataset containing 112 lesions. The model (EfficientNetB0) predicted 10 features in the test set with an average area under the receiver operating characteristic curve (standard deviation), sensitivity, specificity, negative predictive value, positive predictive value of 0.84 (0.1), 0.78 (0.14), 0.86 (0.08), 0.89 (0.08) and 0.71 (0.17), respectively. These results suggest that AI methods may assist less experienced residents or radiologists in liver MRI reporting of focal liver lesions.
Collapse
|