Machine Extractable Knowledge from the Shape of Anatomical Structures

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Medical Imaging and Theranostics".

Deadline for manuscript submissions: closed (31 December 2023) | Viewed by 27695

Special Issue Editors

1. Professor of Neuroimaging, Department of Neuroscience, The University of Sheffield, Sheffield S10 2TN, UK
2. ARUK Senior Research Fellow, Department of Psychiatry, University of Cambridge, Cambridge CB2 1TN, UK
Interests: neuroimaging (PET/MR/MEG/EEG); cognitive neuroscience; artificial intelligence; computational modelling; formal methods
Special Issues, Collections and Topics in MDPI journals
1. International Research Organization for Advanced Science and Technology (IROAST), Kumamoto University, Kumamoto, Japan
2. Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore
3. Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore 599494, Singapore
4. Department of Biomedical Informatics and Medical Engineering, Asia University, Taichung 41354, Taiwan
5. School of Business (Information Systems), Faculty of Business, Education, Law & Arts, University of Southern Queensland, Toowoomba, QLD, Australia
Interests: biomedical signal processing; bioimaging; data mining; visualization; biophysics for better health care design; drug delivery and therapy
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

All anatomical structures in the human body, such as organs, bones, and muscles, are three-dimensional objects with a defined shape, and some diseases may alter that shape. As humans, we can detect shapes and indeed shape change because evolution has equipped us with spatial vision. Within the diagnosis process, we underutilize our spatial vision when we look at two-dimensional medical images. The argument for humans working with two dimensional images is centered on standardization and data reduction. For example, oncologists train to recognize cancer texture in medical images. They use this ability to measure tumor cross-sections on specific MRI slices. This operation condenses all the data from the MRI measurement corpus into a single standardized number which is easy to handle by human experts. Unfortunately, information is lost during that operation. Most current computer-aided diagnosis procedures mimic this approach by considering only texture features from a specific image. This approach has two conceptional shortcomings. The first of these shortcomings results from the fact that computing machines are capable of handling and processing large data volumes, because they are not limited by the human perception system. Hence, computers can interpret the shape of relevant objects, such as tumors, and shape change caused by specific diseases, based on three-dimensional image data. The second shortcoming arises from the selection process which determines the specific image of interest. In many cases, that process relies on human decision making, where a clinical expert selects one cross-sectional image from a 3D measurement corpus. Inevitably, executing this choice introduces inter- and intra-observer variability. Furthermore, involving human expertise early on in the analysis goes against the goal of reducing the workload through computer-aided diagnosis. For this Special Issue, we are interested in studies that push the boundaries of science and technology by offering computer-aided diagnosis based on machine extractable knowledge from the shape of anatomical structures.

Dr. Oliver Faust
Prof. Dr. Li Su
Prof. Dr. U Rajendra Acharya
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Medical image processing
  • Computer aided diagnosis
  • Artificial intelligence
  • 3D imaging
  • Hybrid decision support
  • Magnetic resonance imaging
  • Computed tomography
  • Positron emission tomography
  • Ultrasound

Related Special Issue

Published Papers (11 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review, Other

11 pages, 1979 KiB  
Article
Ethnic Differences in Western and Asian Sacroiliac Joint Anatomy for Surgical Planning of Minimally Invasive Sacroiliac Joint Fusion
Diagnostics 2023, 13(5), 883; https://doi.org/10.3390/diagnostics13050883 - 25 Feb 2023
Viewed by 971
Abstract
Pain originating in the sacroiliac joint (SIJ) is a contributor to chronic lower back pain. Studies on minimally invasive SIJ fusion for chronic pain have been performed in Western populations. Given the shorter stature of Asian populations compared with Western populations, questions can [...] Read more.
Pain originating in the sacroiliac joint (SIJ) is a contributor to chronic lower back pain. Studies on minimally invasive SIJ fusion for chronic pain have been performed in Western populations. Given the shorter stature of Asian populations compared with Western populations, questions can be raised regarding the suitability of the procedure in Asian patients. This study investigated the differences in 12 measurements of sacral and SIJ anatomy between two ethnic populations by analyzing computed tomography scans of 86 patients with SIJ pain. Univariate linear regression was performed to evaluate the correlations of body height with sacral and SIJ measurements. Multivariate regression analysis was used to evaluate systematic differences across populations. Most sacral and SIJ measurements were moderately correlated with body height. The anterior–posterior thickness of the sacral ala at the level of the S1 body was significantly smaller in the Asian patients compared with the Western patients. Most measurements were above standard surgical thresholds for safe transiliac placement of devices (1026 of 1032, 99.4%); all the measurements below these surgical thresholds were found in the anterior–posterior distance of the sacral ala at the S2 foramen level. Overall, safe placement of implants was allowed in 84 of 86 (97.7%) patients. Sacral and SIJ anatomy relevant to transiliac device placement is variable and correlates moderately with body height, and the cross-ethnic variations are not significant. Our findings raise a few concerns regarding sacral and SIJ anatomy variation that would prevent safe placement of fusion implants in Asian patients. However, considering the observed S2-related anatomic variation that could affect placement strategy, sacral and SIJ anatomy should still be preoperatively evaluated. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

11 pages, 2332 KiB  
Article
Role of Diffusion-Weighted Magnetic Resonance Imaging for Characterization of Mediastinal Lymphadenopathy
Diagnostics 2023, 13(4), 706; https://doi.org/10.3390/diagnostics13040706 - 13 Feb 2023
Viewed by 1156
Abstract
Background: To assess the diagnostic performance of diffusion-weighted (DW) magnetic resonance imaging (MRI) in the characterization of mediastinal lymph nodes and compare them with morphological parameters. Methods: A total of 43 untreated patients with mediastinal lymphadenopathy underwent DW and T2 weighted MRI followed [...] Read more.
Background: To assess the diagnostic performance of diffusion-weighted (DW) magnetic resonance imaging (MRI) in the characterization of mediastinal lymph nodes and compare them with morphological parameters. Methods: A total of 43 untreated patients with mediastinal lymphadenopathy underwent DW and T2 weighted MRI followed by pathological examination in the period from January 2015 to June 2016. The presence of diffusion restriction, apparent diffusion coefficient (ADC) value, short axis dimensions (SAD), and T2 heterogeneous signal intensity of the lymph nodes were evaluated using receiver operating characteristic curve (ROC) and forward step-wise multivariate logistic regression analysis. Results: The ADC of malignant lymphadenopathy was significantly lower (0.873 ± 0.109 × 10−3 mm2/s) than that of benign lymphadenopathy (1.663 ± 0.311 × 10−3 mm2/s) (p = 0.001). When an ADC of 1.0955 × 10−3 mm2/s was used as a threshold value for differentiating malignant from benign nodes, the best results were obtained with a sensitivity of 94%, a specificity of 96%, and an area under the curve (AUC) of 0.996. A model combining the other three MRI criteria showed less sensitivity (88.9%) and specificity (92%) compared to the ADC-only model. Conclusion: The ADC was the strongest independent predictor of malignancy. The addition of other parameters failed to show any increase in sensitivity and specificity. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

15 pages, 1724 KiB  
Article
Clinical Modelling of RVHF Using Pre-Operative Variables: A Direct and Inverse Feature Extraction Technique
Diagnostics 2022, 12(12), 3061; https://doi.org/10.3390/diagnostics12123061 - 06 Dec 2022
Cited by 4 | Viewed by 1307
Abstract
Right ventricular heart failure (RVHF) mostly occurs due to the failure of the left-side of the heart. RVHF is a serious disease that leads to swelling of the abdomen, ankles, liver, kidneys, and gastrointestinal (GI) tract. A total of 506 heart-failure subjects from [...] Read more.
Right ventricular heart failure (RVHF) mostly occurs due to the failure of the left-side of the heart. RVHF is a serious disease that leads to swelling of the abdomen, ankles, liver, kidneys, and gastrointestinal (GI) tract. A total of 506 heart-failure subjects from the Faculty of Medicine, Cardiovascular Surgery Department, Ege University, Turkey, who suffered from a severe heart failure and are currently receiving support from a ventricular assistance device, were involved in the current study. Therefore, the current study explored the application of both the direct and inverse modelling approaches, based on the correlation analysis feature extraction performance of various pre-operative variables of the subjects, for the prediction of RVHF. The study equally employs both single and hybrid paradigms for the prediction of RVHF using different pre-operative variables. The visualized and quantitative performance of the direct and inverse modelling approach indicates the robust prediction performance of the hybrid paradigms over the single techniques in both the calibration and validation steps. Whereby, the quantitative performance of the hybrid techniques, based on the Nash–Sutcliffe coefficient (NC) metric, depicts its superiority over the single paradigms by up to 58.7%/75.5% and 80.3%/51% for the calibration/validation phases in the direct and inverse modelling approaches, respectively. Moreover, to the best knowledge of the authors, this is the first study to report the implementation of direct and inverse modelling on clinical data. The findings of the current study indicates the possibility of applying these novel hybridised paradigms for the prediction of RVHF using pre-operative variables. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

13 pages, 625 KiB  
Article
Modifications in Electrocardiographic and Vectordardiographic Morphological Parameters in Elderly Males as Result of Cardiovascular Diseases and Diabetes Mellitus
Diagnostics 2022, 12(12), 2911; https://doi.org/10.3390/diagnostics12122911 - 23 Nov 2022
Viewed by 999
Abstract
Purpose. Morphological electrocardiographic and vectorcardiographic features have been used in the detection of cardiovascular diseases and prediction of the risk of cardiac death for a long time. The objective of the current study was to investigate the morphological electrocardiographic modifications in the presence [...] Read more.
Purpose. Morphological electrocardiographic and vectorcardiographic features have been used in the detection of cardiovascular diseases and prediction of the risk of cardiac death for a long time. The objective of the current study was to investigate the morphological electrocardiographic modifications in the presence of cardiovascular diseases and diabetes mellitus in an elderly male population, most of them with multiple comorbidities. Methods. A database of ECG recordings from the Italian Longitudinal Study on Aging (ILSA-CNR), created to evaluate physiological and pathological modifications related to aging, was considered. The study examined a group of 1109 males with full clinical documentation aged 65–84 years. A healthy control group (219 individuals) was compared to the groups of diabetes mellitus (130), angina pectoris (99), hypertension (607), myocardial infarction (160), arrhythmia (386), congestive heart failure (73), and peripheral artery disease (95). Twenty-one electrocardiographic features were explored, and the effects of cardiovascular diseases and diabetes on these parameters were analyzed. The three-years mortality index was derived and analyzed. Results and Conclusions. Myocardial infarction and arrhythmia were the diagnostic groups that showed a significant deviation of 11 electrocardiographic parameters compared to the healthy group, followed by hypertension and congestive heart failure (10), angina pectoris (9), and diabetes mellitus and peripheral artery disease (8). In particular, a set of three parameters (QRS and T roundness and principal component analysis of T wave) increased significantly, whereas four parameters (T amplitude, T maximal vector, T vector ratio, and T wave area dispersion) decreased significantly in all cardiovascular diseases and diabetes mellitus with respect to healthy group. The QRS parameters show a more specific discrimination with a single disease or a group of diseases, whereas the T-wave features seems to be influenced by all the pathological conditions. The present investigation of disease-related electrocardiographic parameters changes can be used in assessing the risk analysis of cardiac death, and gender medicine. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

9 pages, 1057 KiB  
Article
Changing the Patient’s Position: Pitfalls and Benefits for Radiation Dose and Image Quality of Computed Tomography in Polytrauma
Diagnostics 2022, 12(11), 2661; https://doi.org/10.3390/diagnostics12112661 - 02 Nov 2022
Viewed by 1869
Abstract
For computed tomography (CT), representing the diagnostic standard for trauma patients, image quality is essential. The positioning of the patient’s arms next to the abdomen causes artifacts and is also considered to increase radiation exposure. The aim of this study was to evaluate [...] Read more.
For computed tomography (CT), representing the diagnostic standard for trauma patients, image quality is essential. The positioning of the patient’s arms next to the abdomen causes artifacts and is also considered to increase radiation exposure. The aim of this study was to evaluate the effect of various positionings during different CT examination steps on the extent of artifacts as well as radiation dose using iterative reconstruction (IR). 354 trauma-CTs were analyzed retrospectively. All datasets were reconstructed using IR and three different examination protocols were applied. Arm elevation led to a significant improvement of the image quality across all examination protocols (p < 0.001). Variation in arm positioning during image acquisition did not lead to a reduction of radiation dose (p = 0.123). Only elevation during scout acquisition resulted in the reduction of radiation exposure (p < 0.001). To receive high-quality CT images, patients should be placed with elevated arms for the trunk scan, as artifacts remain even with the IR. Arm repositioning during the examination itself had no effect on the applied radiation dose because its modulation refers to the initial scout obtained. In order to achieve a dose effect by different positioning, a two-scout protocol (dual scout) should be used. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

28 pages, 7360 KiB  
Article
Physics Informed Neural Networks (PINN) for Low Snr Magnetic Resonance Electrical Properties Tomography (MREPT)
Diagnostics 2022, 12(11), 2627; https://doi.org/10.3390/diagnostics12112627 - 29 Oct 2022
Cited by 6 | Viewed by 2498
Abstract
Electrical properties (EPs) of tissues facilitate early detection of cancerous tissues. Magnetic resonance electrical properties tomography (MREPT) is a technique to non-invasively probe the EPs of tissues from MRI measurements. Most MREPT methods rely on numerical differentiation (ND) to solve partial differential Equations [...] Read more.
Electrical properties (EPs) of tissues facilitate early detection of cancerous tissues. Magnetic resonance electrical properties tomography (MREPT) is a technique to non-invasively probe the EPs of tissues from MRI measurements. Most MREPT methods rely on numerical differentiation (ND) to solve partial differential Equations (PDEs) to reconstruct the EPs. However, they are not practical for clinical data because ND is noise sensitive and the MRI measurements for MREPT are noisy in nature. Recently, Physics informed neural networks (PINNs) have been introduced to solve PDEs by substituting ND with automatic differentiation (AD). To the best of our knowledge, it has not been applied to MREPT due to the challenges in using PINN on MREPT as (i) a PINN requires part of ground-truth EPs as collocation points to optimize the network’s AD, (ii) the noisy input data disrupts the optimization of PINNs despite the noise-filtering nature of NNs and additional denoising processes. In this work, we propose a PINN-MREPT model based on a canonical analytic MREPT model. A reference padding layer with known EPs was added to surround the region of interest for providing additive collocation points. Moreover, an optimizable diffusion coefficient was embedded in the analytic MREPT model used in the PINN-MREPT. The noise robustness of the proposed PINN-MREPT for single-sample reconstruction was tested by using numerical phantoms of human brain with extra tumor-like tissues at different noise levels. The results of numerical experiments show that PINN-MREPT outperforms two typical numerical MREPT methods in terms of reconstruction accuracy, sensitivity to the extra tissues, and the correlations of line profiles in the regions of interest. The advantage of the PINN-MREPT is shown by the results of an experiment on phantom measurement, too. Moreover, it is found that the diffusion term plays an important role to achieve a noise-robust PINN-MREPT. This is an important step moving forward to a clinical application of MREPT. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

14 pages, 504 KiB  
Article
NDCN-Brain: An Extensible Dynamic Functional Brain Network Model
Diagnostics 2022, 12(5), 1298; https://doi.org/10.3390/diagnostics12051298 - 23 May 2022
Cited by 1 | Viewed by 1410
Abstract
As an extension of the static network, the dynamic functional brain network can show continuous changes in the brain’s connections. Then, limited by the length of the fMRI signal, it is difficult to show every instantaneous moment in the construction of a dynamic [...] Read more.
As an extension of the static network, the dynamic functional brain network can show continuous changes in the brain’s connections. Then, limited by the length of the fMRI signal, it is difficult to show every instantaneous moment in the construction of a dynamic network and there is a lack of effective prediction of the dynamic changes of the network after the signal ends. In this paper, an extensible dynamic brain function network model is proposed. The model utilizes the ability of extracting and predicting the instantaneous state of the dynamic network of neural dynamics on complex networks (NDCN) and constructs a dynamic network model structure that can provide more than the original signal range. Experimental results show that every snapshot in the network obtained by the proposed method has a usable network structure and that it also has a good classification result in the diagnosis of cognitive impairment diseases. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

Review

Jump to: Research, Other

20 pages, 2408 KiB  
Review
Progress of Multiparameter Magnetic Resonance Imaging in Bladder Cancer: A Comprehensive Literature Review
Diagnostics 2024, 14(4), 442; https://doi.org/10.3390/diagnostics14040442 - 17 Feb 2024
Viewed by 380
Abstract
Magnetic resonance imaging (MRI) has been proven to be an indispensable imaging method in bladder cancer, and it can accurately identify muscular invasion of bladder cancer. Multiparameter MRI is a promising tool widely used for preoperative staging evaluation of bladder cancer. Vesical Imaging-Reporting [...] Read more.
Magnetic resonance imaging (MRI) has been proven to be an indispensable imaging method in bladder cancer, and it can accurately identify muscular invasion of bladder cancer. Multiparameter MRI is a promising tool widely used for preoperative staging evaluation of bladder cancer. Vesical Imaging-Reporting and Data System (VI-RADS) scoring has proven to be a reliable tool for local staging of bladder cancer with high accuracy in preoperative staging, but VI-RADS still faces challenges and needs further improvement. Artificial intelligence (AI) holds great promise in improving the accuracy of diagnosis and predicting the prognosis of bladder cancer. Automated machine learning techniques based on radiomics features derived from MRI have been utilized in bladder cancer diagnosis and have demonstrated promising potential for practical implementation. Future work should focus on conducting more prospective, multicenter studies to validate the additional value of quantitative studies and optimize prediction models by combining other biomarkers, such as urine and serum biomarkers. This review assesses the value of multiparameter MRI in the accurate evaluation of muscular invasion of bladder cancer, as well as the current status and progress of its application in the evaluation of efficacy and prognosis. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

15 pages, 658 KiB  
Review
Radiation Exposure and Lifetime Attributable Risk of Cancer Incidence and Mortality from Low- and Standard-Dose CT Chest: Implications for COVID-19 Pneumonia Subjects
Diagnostics 2022, 12(12), 3043; https://doi.org/10.3390/diagnostics12123043 - 05 Dec 2022
Cited by 4 | Viewed by 3239
Abstract
Since the novel coronavirus disease 2019 (COVID-19) outbreak, there has been an unprecedented increase in the acquisition of chest computed tomography (CT) scans. Nearly 616 million people have been infected by COVID-19 worldwide to date, of whom many were subjected to CT scanning. [...] Read more.
Since the novel coronavirus disease 2019 (COVID-19) outbreak, there has been an unprecedented increase in the acquisition of chest computed tomography (CT) scans. Nearly 616 million people have been infected by COVID-19 worldwide to date, of whom many were subjected to CT scanning. CT exposes the patients to hazardous ionizing radiation, which can damage the genetic material in the cells, leading to stochastic health effects in the form of heritable genetic mutations and increased cancer risk. These probabilistic, long-term carcinogenic effects of radiation can be seen over a lifetime and may sometimes take several decades to manifest. This review briefly describes what is known about the health effects of radiation, the lowest dose for which there exists compelling evidence about increased radiation-induced cancer risk and the evidence regarding this risk at typical CT doses. The lifetime attributable risk (LAR) of cancer from low- and standard-dose chest CT scans performed in COVID-19 subjects is also discussed along with the projected number of future cancers that could be related to chest CT scans performed during the COVID-19 pandemic. The LAR of cancer Incidence from chest CT has also been compared with those from other radiation sources, daily life risks and lifetime baseline risk. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

18 pages, 3068 KiB  
Review
Applications of Explainable Artificial Intelligence in Diagnosis and Surgery
Diagnostics 2022, 12(2), 237; https://doi.org/10.3390/diagnostics12020237 - 19 Jan 2022
Cited by 77 | Viewed by 12154
Abstract
In recent years, artificial intelligence (AI) has shown great promise in medicine. However, explainability issues make AI applications in clinical usages difficult. Some research has been conducted into explainable artificial intelligence (XAI) to overcome the limitation of the black-box nature of AI methods. [...] Read more.
In recent years, artificial intelligence (AI) has shown great promise in medicine. However, explainability issues make AI applications in clinical usages difficult. Some research has been conducted into explainable artificial intelligence (XAI) to overcome the limitation of the black-box nature of AI methods. Compared with AI techniques such as deep learning, XAI can provide both decision-making and explanations of the model. In this review, we conducted a survey of the recent trends in medical diagnosis and surgical applications using XAI. We have searched articles published between 2019 and 2021 from PubMed, IEEE Xplore, Association for Computing Machinery, and Google Scholar. We included articles which met the selection criteria in the review and then extracted and analyzed relevant information from the studies. Additionally, we provide an experimental showcase on breast cancer diagnosis, and illustrate how XAI can be applied in medical XAI applications. Finally, we summarize the XAI methods utilized in the medical XAI applications, the challenges that the researchers have met, and discuss the future research directions. The survey result indicates that medical XAI is a promising research direction, and this study aims to serve as a reference to medical experts and AI scientists when designing medical XAI applications. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

Other

Jump to: Research, Review

17 pages, 579 KiB  
Systematic Review
Diagnostic Performance of Magnetic Resonance Imaging for Parathyroid Localization of Primary Hyperparathyroidism: A Systematic Review
Diagnostics 2024, 14(1), 25; https://doi.org/10.3390/diagnostics14010025 - 22 Dec 2023
Viewed by 508
Abstract
Accurate preoperative localization is crucial for successful minimally invasive parathyroidectomy in primary hyperparathyroidism (PHPT). Preoperative localization can be challenging in patients with recurrent and/or multigland disease (MGD). This has led clinicians to investigate multiple imaging techniques, most of which are associated with radiation [...] Read more.
Accurate preoperative localization is crucial for successful minimally invasive parathyroidectomy in primary hyperparathyroidism (PHPT). Preoperative localization can be challenging in patients with recurrent and/or multigland disease (MGD). This has led clinicians to investigate multiple imaging techniques, most of which are associated with radiation exposure. Magnetic resonance imaging (MRI) offers ionizing radiation-free and accurate imaging, making it an attractive alternative imaging modality. The objective of this systematic review is to provide an overview of the diagnostic performance of MRI in the localization of PHPT. PubMed and Embase libraries were searched from 1 January 2000 to 31 March 2023. Studies were included that investigated MRI techniques for the localization of PHPT. The exclusion criteria were (1) secondary/tertiary hyperparathyroidism, (2) studies that provided no diagnostic performance values, (3) studies published before 2000, and (4) studies using 0.5 Tesla MRI scanners. Twenty-four articles were included in the systematic review, with a total of 1127 patients with PHPT. In 14 studies investigating conventional MRI for PHPT localization, sensitivities varied between 39.1% and 94.3%. When employing more advanced MRI protocols like 4D MRI for PHPT localization in 11 studies, sensitivities ranged from 55.6% to 100%. The combination of MR imaging with functional techniques such as 18F-FCH-PET/MRI yielded the highest diagnostic accuracy, with sensitivities ranging from 84.2% to 100% in five studies. Despite the limitations of the available evidence, the results of this review indicate that the combination of MR imaging with functional imaging techniques such as 18F-FCH-PET/MRI yielded the highest diagnostic accuracy. Further research on emerging MR imaging modalities, such as 4D MRI and PET/MRI, is warranted, as MRI exposes patients to minimal or no ionizing radiation compared to other imaging modalities. Full article
(This article belongs to the Special Issue Machine Extractable Knowledge from the Shape of Anatomical Structures)
Show Figures

Figure 1

Back to TopTop