1
|
Han S, Kim JM, Park J, Kim SW, Park S, Cho J, Park SJ, Chung HJ, Ham SM, Park SJ, Kim JH. Clinical feasibility of deep learning based synthetic contrast enhanced abdominal CT in patients undergoing non enhanced CT scans. Sci Rep 2024; 14:17635. [PMID: 39085456 PMCID: PMC11291756 DOI: 10.1038/s41598-024-68705-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2024] [Accepted: 07/25/2024] [Indexed: 08/02/2024] Open
Abstract
Our objective was to develop and evaluate the clinical feasibility of deep-learning-based synthetic contrast-enhanced computed tomography (DL-SynCCT) in patients designated for nonenhanced CT (NECT). We proposed a weakly supervised learning with the utilization of virtual non-contrast CT (VNC) for the development of DL-SynCCT. Training and internal validations were performed with 2202 pairs of retrospectively collected contrast-enhanced CT (CECT) images with the corresponding VNC images acquired from dual-energy CT. Clinical validation was performed using an external validation set including 398 patients designated for true nonenhanced CT (NECT), from multiple vendors at three institutes. Detection of lesions was performed by three radiologists with only NECT in the first session and an additionally provided DL-SynCCT in the second session. The mean peak signal-to-noise ratio (PSNR) and structural similarity index map (SSIM) of the DL-SynCCT compared to CECT were 43.25 ± 0.41 and 0.92 ± 0.01, respectively. With DL-SynCCT, the pooled sensitivity for lesion detection (72.0% to 76.4%, P < 0.001) and level of diagnostic confidence (3.0 to 3.6, P < 0.001) significantly increased. In conclusion, DL-SynCCT generated by weakly supervised learning showed significant benefit in terms of sensitivity in detecting abnormal findings when added to NECT in patients designated for nonenhanced CT scans.
Collapse
Affiliation(s)
- Seungchul Han
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03087, Republic of Korea
- Department of Radiology, Samsung Medical Center, 81 Irwon-Ro Gangnam-gu, Seoul, 03087, Republic of Korea
| | - Jong-Min Kim
- Research and Science Division, MEDICALIP Co., Ltd., Seoul, Korea
| | - Junghoan Park
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03087, Republic of Korea
| | - Se Woo Kim
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03087, Republic of Korea
| | - Sungeun Park
- Department of Radiology, Konkuk University Medical Center, 4-12 Hwayang Gwangjin-gu, Seoul, 03087, Republic of Korea
| | - Jungheum Cho
- Department of Radiology, Seoul National University Bundang Hospital, Seongnam, 13620, Republic of Korea
| | - Sae-Jin Park
- Department of Radiology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - Han-Jae Chung
- Research and Science Division, MEDICALIP Co., Ltd., Seoul, Korea
| | - Seung-Min Ham
- Research and Science Division, MEDICALIP Co., Ltd., Seoul, Korea
| | - Sang Joon Park
- Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03087, Republic of Korea
- Research and Science Division, MEDICALIP Co., Ltd., Seoul, Korea
| | - Jung Hoon Kim
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea.
- Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03087, Republic of Korea.
- Institute of Radiation Medicine, Seoul National University Medical Research Center, 103 Daehak-ro, Jongno-gu, Seoul, 03087, Republic of Korea.
| |
Collapse
|
2
|
Ahn S, Noh H, Nam S, Jang Y, Chun Y, Park H, Choi S, Choi H, Kim J. Comparison of diagnostic performance and confidence between contrast-enhanced computed tomography scan and non-contrast-enhanced computed tomography plus abdomen ultrasound for hepatic metastasis in patients with breast cancer. J Med Ultrasound 2022; 30:116-124. [PMID: 35832367 PMCID: PMC9272726 DOI: 10.4103/jmu.jmu_58_21] [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: 03/17/2021] [Revised: 06/15/2021] [Accepted: 08/25/2021] [Indexed: 11/07/2022] Open
Abstract
Background: The purpose of this study was to compare the performance between noncontrast-enhanced computed tomography (NECT) plus abdominal ultrasound (US) (NECT + US) with contrast-enhanced computed tomography (CECT) for the detection of hepatic metastasis in breast cancer patient with postsurgical follow-up. Methods: A total of 1470 patients without already diagnosed hepatic metastasis were included. All patients underwent US and multiphase CECT including the NECT. Independent reviewers analyzed images obtained in four settings, namely, abdominal US, NECT, NECT + US, and CECT and recorded liver metastases using a 5-grade scale of diagnostic confidence. Sensitivity, specificity (diagnostic performance), and area under the receiver operating characteristic curve (AUC, diagnostic confidence) were calculated. Interoperator agreement was calculated using the kappa test. Results: Reference standards revealed no metastases in 1108/1470 patients, and metastasis was detected in 362/1470 patients. Abdominal US (P < 0.01) and NECT (P = 0.01) significantly differed from CECT, but NECT + US did not significantly differ from CECT in terms of sensitivity (P = 0.09), specificity (P = 0.5), and AUC (P = 0.43). After an additional review of abdominal US, readers changed the diagnostic confidence scores of 106 metastatic lesions diagnosed using NECT. Interobserver agreements were good or very good in all four settings. Additional review of abdominal US with NECT allowed a change in the therapeutic plan of 108 patients. Conclusion: Abdominal US + NECT showed better diagnostic performance for the detection of hepatic metastases than did NECT alone; its diagnostic performance and confidence were similar to those of CECT.
Collapse
|
3
|
Zhou Y, Zhu Y, Li J. Advantages of CT nano-contrast agent in tumor diagnosis: A retrospective study. Medicine (Baltimore) 2021; 100:e27044. [PMID: 34664829 PMCID: PMC8448064 DOI: 10.1097/md.0000000000027044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/26/2020] [Accepted: 08/11/2021] [Indexed: 12/02/2022] Open
Abstract
The purpose of this retrospective study was to explore the advantages of computed tomography (CT) nano-contrast agent in tumor diagnosis.A total of 100 patients with malignant tumor who were diagnosed in Shaanxi Province Public Hospital between January 2018 and January 2019 were included in this retrospective study. They were randomly divided into observation and control groups with 50 patients in each group. The patients in the observation group used new type of nano-contrast agent for examination, and the patients in the control group used traditional iohexol contrast agent for examination. The detection rate, misdiagnosis rate, and incidence of adverse reactions were observed. In addition, single photon emission computed tomography or CT scan was performed on patients to observe the radioactive concentration.The detection rate was 100% in the observation group and 84% in the control group, and the difference between the 2 groups was statistically significant (χ2 = 8.763, P = .001). The incidence of adverse reactions was 2% in the observation group and 30% in the control group, and the difference between the 2 groups was significantly different (χ2 = 12.683, P = .000). The radioactive concentration in the observation group was markedly higher than that in the control group (t = 19.692, P = .001).The use of CT nano-contrast agent in tumor diagnosis had higher detection rate of tumor and radioactive concentration, and it had lower misdiagnosis rate and adverse reaction rate than traditional iohexol contrast agent.
Collapse
Affiliation(s)
- Yong Zhou
- Medical Imaging Center – CT Room, The 3rd Affiliated Teaching Hospital of Xinjiang Medical University (Affiliated Cancer Hospital), Urumqi, Xinjiang, China
| | - Yufen Zhu
- Department of Radiology, Bethune International Peace Hospital of PLA, Shijiazhuang, Hebei Province, China
| | - Jian Li
- Deparpment of Radiology, Shaanxi Province Public Hospital, Xi’an, Shaanxi Province, China
| |
Collapse
|
4
|
Nam SY, Ahn SJ, Jang YR, Chun YS, Park HK, Choi SJ, Choi HY, Kim JH. Diagnostic accuracy of non-contrast abdominopelvic computed tomography scans in follow-up of breast cancer patients. Br J Radiol 2020; 94:20201087. [PMID: 33306919 DOI: 10.1259/bjr.20201087] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022] Open
Abstract
OBJECTIVES To evaluate the effectiveness of follow-up with non-enhanced CT (NECT) in patients with breast cancer. METHODS The present retrospective study included 1396 patients with breast cancer. Group A included patients with no metastasis to evaluate the diagnostic performance of NECT in detecting newly developed metastasis. Group B included patients with known hepatic metastasis to evaluate the accuracy of NECT for the assessment of hepatic metastasis. RESULTS Group A included 895 patients (mean age 52.8 years). Among them, 145 patients had 160 metastases. The per-patient sensitivities for diagnosing newly developed metastasis were 68.3 and 53.8% according to the two reviewers, while the per-lesion sensitivities were 89.4 and 85.0%. Sensitivities for bone metastasis were 98.9 and 95.9%, while sensitivities for hepatic metastasis were 73.7 and 68.4%. In group B, the accuracy of hepatic metastasis response evaluation according to the RECIST criteria was 70.8% for reviewer 1 and 63.8% for reviewer 2. CONCLUSIONS NECT showed inadequate diagnostic performance in detecting newly developed metastasis and in evaluating the response of hepatic metastasis. However, NECT can be utilized as a follow-up modality in patients with decreased renal function or hypersensitivity to iodinated contrast media. ADVANCES IN KNOWLEDGE The risk of side effects of contrast media should be considered as important when NECT can be utilized as a follow-up modality in decreased renal function patients.
Collapse
Affiliation(s)
- Sang Yu Nam
- Department of Radiology, Gil Medical Center of Gachon University, Incheon, South Korea
| | - Su Joa Ahn
- Department of Radiology, Gil Medical Center of Gachon University, Incheon, South Korea
| | - Young Rock Jang
- Department of Internal Medicine, Gil Medical Center of Gachon University, Incheon, South Korea
| | - Yong Soon Chun
- Department of Surgery Breast Cancer Center, Gil Medical Center of Gachon University, Incheon, South Korea
| | - Heung Kyu Park
- Department of Surgery Breast Cancer Center, Gil Medical Center of Gachon University, Incheon, South Korea
| | - Seung Joon Choi
- Department of Radiology, Gil Medical Center of Gachon University, Incheon, South Korea
| | - Hye Young Choi
- Department of Radiology, Gil Medical Center of Gachon University, Incheon, South Korea
| | - Jeong Ho Kim
- Department of Radiology, Gil Medical Center of Gachon University, Incheon, South Korea
| |
Collapse
|
5
|
Bogowicz M, Vuong D, Huellner MW, Pavic M, Andratschke N, Gabrys HS, Guckenberger M, Tanadini-Lang S. CT radiomics and PET radiomics: ready for clinical implementation? THE QUARTERLY JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING : OFFICIAL PUBLICATION OF THE ITALIAN ASSOCIATION OF NUCLEAR MEDICINE (AIMN) [AND] THE INTERNATIONAL ASSOCIATION OF RADIOPHARMACOLOGY (IAR), [AND] SECTION OF THE SOCIETY OF RADIOPHARMACEUTICAL CHEMISTRY AND BIOLOGY 2019; 63:355-370. [PMID: 31527578 DOI: 10.23736/s1824-4785.19.03192-3] [Citation(s) in RCA: 47] [Impact Index Per Article: 9.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
INTRODUCTION Today, rapid technical and clinical developments result in an increasing number of treatment options for oncological diseases. Thus, decision support systems are needed to offer the right treatment to the right patient. Imaging biomarkers hold great promise in patient-individual treatment guidance. Routinely performed for diagnosis and staging, imaging datasets are expected to hold more information than used in the clinical practice. Radiomics describes the extraction of a large number of meaningful quantitative features from medical images, such as computed tomography (CT) and positron emission tomography (PET). Due to the non-invasive nature and ability to capture 3D image-based heterogeneity, radiomic features are potential surrogate markers of the cancer phenotype. Several radiomic studies are published per day, owing to encouraging results of many radiomics-based patient outcome models. Despite this comparably large number of studies, radiomics is mainly studied in proof of principle concept. Hence, a translation of radiomics from a hot topic research field into an essential clinical decision-making tool is lacking, but of high clinical interest. EVIDENCE ACQUISITION Herein, we present a literature review addressing the clinical evidence of CT and PET radiomics. An extensive literature review was conducted in PubMed, including papers on robustness and clinical applications. EVIDENCE SYNTHESIS We summarize image-modality related influences on the robustness of radiomic features and provide an overview of clinical evidence reported in the literature. Today, more evidence has been provided for CT imaging, however, PET imaging offers the promise of direct imaging of biological processes and functions. We provide a summary of future research directions, which needs to be addressed in order to successfully introduce radiomics into clinical medicine. In comparison to CT, more focus should be directed towards harmonization of PET acquisition and reconstruction protocols, which is important for transferable modelling. CONCLUSIONS Both CT and PET radiomics are promising pre-treatment and intra-treatment biomarkers for outcome prediction. Most studies are performed in retrospective setting, however their validation in prospective data collections is ongoing.
Collapse
Affiliation(s)
- Marta Bogowicz
- Department of Radiation Oncology, University Hospital Zurich and University of Zurich, Zurich, Switzerland -
| | - Diem Vuong
- Department of Radiation Oncology, University Hospital Zurich and University of Zurich, Zurich, Switzerland
| | - Martin W Huellner
- Department of Nuclear Medicine, University Hospital Zurich and University of Zurich, Zurich, Switzerland
| | - Matea Pavic
- Department of Radiation Oncology, University Hospital Zurich and University of Zurich, Zurich, Switzerland
| | - Nicolaus Andratschke
- Department of Radiation Oncology, University Hospital Zurich and University of Zurich, Zurich, Switzerland
| | - Hubert S Gabrys
- Department of Radiation Oncology, University Hospital Zurich and University of Zurich, Zurich, Switzerland
| | - Matthias Guckenberger
- Department of Radiation Oncology, University Hospital Zurich and University of Zurich, Zurich, Switzerland
| | - Stephanie Tanadini-Lang
- Department of Radiation Oncology, University Hospital Zurich and University of Zurich, Zurich, Switzerland
| |
Collapse
|
6
|
Layer G. [When are contrast agents really needed? : Cross-sectional imaging with computed tomography and magnetic resonance imaging]. Radiologe 2019; 59:541-549. [PMID: 31197399 DOI: 10.1007/s00117-019-0543-4] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
CLINICAL ISSUE The intravenous administration of contrast agents increases the contrast between diverse tissues and vessels against their surroundings in both computed tomography (CT) and magnetic resonance imaging (MRI) scans and has been generously used for years. There are only a few scientific publications that have systematically evaluated the impact of this contrast-enhancing technique over noncontrast enhancing techniques. RADIOLOGICAL STANDARD According to these publications and our clinical experiences, there are far more indications to use non-contrast-enhancing techniques as they are used in clinical practice. The most important requirement to renounce the use of a contrast agent is sufficient clinical information and differentiated justified indication. The present review shows useful non-contrast-enhanced examination techniques for neuroradiology, musculoskeletal system, lymphatic system, and thorax, including the hearth, abdomen and breasts. CLINICAL RECOMMENDATIONS Good indications for non-contrast imaging are generally follow-ups. In cerebral related questions, like in traumatic or atraumatic emergencies, transient ischemic attacks, minor stroke diagnostic, dementia and in follow-ups of multiple sclerosis, there is usually no need for contrast agent. Examinations of the musculoskeletal systems and follow-up examinations of the lymphatic system can generally be done without a contrast agent. There is no major loss of value in CT and MRI scans of the thorax by examining without contrast. The value of using a contrast agent in the abdomen is far less than expected. Up to now use of a contrast agent is essential in evaluating questions related to vessels or angiomatous tissue and in breast MRI.
Collapse
Affiliation(s)
- G Layer
- Zentralinstitut für Diagnostische und Interventionelle Radiologie, Klinikum Ludwigshafen gGmbH, 67063, Ludwigshafen, Deutschland.
| |
Collapse
|