1
|
Vahdati S, Khosravi B, Mahmoudi E, Zhang K, Rouzrokh P, Faghani S, Moassefi M, Tahmasebi A, Andriole KP, Chang P, Farahani K, Flores MG, Folio L, Houshmand S, Giger ML, Gichoya JW, Erickson BJ. A Guideline for Open-Source Tools to Make Medical Imaging Data Ready for Artificial Intelligence Applications: A Society of Imaging Informatics in Medicine (SIIM) Survey. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01083-0. [PMID: 38558368 DOI: 10.1007/s10278-024-01083-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/11/2024] [Revised: 02/29/2024] [Accepted: 03/08/2024] [Indexed: 04/04/2024]
Abstract
In recent years, the role of Artificial Intelligence (AI) in medical imaging has become increasingly prominent, with the majority of AI applications approved by the FDA being in imaging and radiology in 2023. The surge in AI model development to tackle clinical challenges underscores the necessity for preparing high-quality medical imaging data. Proper data preparation is crucial as it fosters the creation of standardized and reproducible AI models while minimizing biases. Data curation transforms raw data into a valuable, organized, and dependable resource and is a fundamental process to the success of machine learning and analytical projects. Considering the plethora of available tools for data curation in different stages, it is crucial to stay informed about the most relevant tools within specific research areas. In the current work, we propose a descriptive outline for different steps of data curation while we furnish compilations of tools collected from a survey applied among members of the Society of Imaging Informatics (SIIM) for each of these stages. This collection has the potential to enhance the decision-making process for researchers as they select the most appropriate tool for their specific tasks.
Collapse
Affiliation(s)
- Sanaz Vahdati
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, 200 1st Street, SW, Rochester, MN, 55905, USA
| | - Bardia Khosravi
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, 200 1st Street, SW, Rochester, MN, 55905, USA
| | - Elham Mahmoudi
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, 200 1st Street, SW, Rochester, MN, 55905, USA
| | - Kuan Zhang
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, 200 1st Street, SW, Rochester, MN, 55905, USA
| | - Pouria Rouzrokh
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, 200 1st Street, SW, Rochester, MN, 55905, USA
| | - Shahriar Faghani
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, 200 1st Street, SW, Rochester, MN, 55905, USA
| | - Mana Moassefi
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, 200 1st Street, SW, Rochester, MN, 55905, USA
| | - Aylin Tahmasebi
- Department of Radiology, Thomas Jefferson University, Philadelphia, PA, USA
| | - Katherine P Andriole
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Peter Chang
- Department of Radiological Sciences, Irvine Medical Center, University of California, Orange, CA, USA
| | - Keyvan Farahani
- Center for Biomedical Informatics and Information Technology, National Cancer Institute, Bethesda, MD, USA
| | | | - Les Folio
- Diagnostic Imaging & Interventional Radiology Moffitt Cancer Center, Tampa, FL, USA
| | - Sina Houshmand
- Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA
| | - Maryellen L Giger
- Department of Radiology, The University of Chicago, Chicago, IL, USA
| | - Judy W Gichoya
- Department of Radiology, Emory University School of Medicine, Atlanta, GA, USA
| | - Bradley J Erickson
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, 200 1st Street, SW, Rochester, MN, 55905, USA.
| |
Collapse
|
2
|
CT-like MR-derived Images for the Assessment of Craniosynostosis and other Pathologies of the Pediatric Skull. Clin Neuroradiol 2023; 33:57-64. [PMID: 35763060 PMCID: PMC10014729 DOI: 10.1007/s00062-022-01182-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: 02/17/2022] [Accepted: 05/25/2022] [Indexed: 11/03/2022]
Abstract
PURPOSE To evaluate the diagnostic value of CT-like images based on a 3D T1-weighted spoiled gradient echo-based sequence (T1SGRE) for the visualization of the pediatric skull and the identification of pathologies, such as craniosynostosis or fractures. METHODS In this prospective study, 20 patients with suspected craniosynostosis (mean age 1.26 ± 1.38 years, 10 females) underwent MR imaging including the T1SGRE sequence and 2 more patients were included who presented with skull fractures (0.5 and 6.3 years, both male). Additionally, the skull of all patients was assessed using radiography or CT in combination with ultrasound. Two radiologists, blinded to the clinical information, evaluated the CT-like images. The results were compared to the diagnosis derived from the other imaging modalities and intraoperative findings. Intrarater and interrater agreement was calculated using Cohen's κ. RESULTS Of the 22 patients 8 had a metopic, 4 a coronal and 2 a sagittal craniosynostosis and 2 patients showed a complex combination of craniosynostoses. The agreement between the diagnosis based on the T1SGRE and the final diagnosis was substantial (Cohen's κ = 0.92, 95% confidence interval (CI) 0.77-1.00 for radiologist 1 and κ = 0.76, CI 0.51-1.00 for radiologist 2). Of the patients with fractures, one presented with a ping pong fracture and one with a fracture of the temporal bone. Both radiologists could identify the fractures using the T1SGRE. CONCLUSION The visualization of the pediatric skull and the assessment of sutures using a CT-like T1SGRE MR-sequence is feasible and comparable to other imaging modalities, and thus may help to reduce radiation exposure in pediatric patients. The technique may also be a promising imaging tool for other pathologies, such as fractures.
Collapse
|
3
|
Vyas KS, Suchyta MA, Hunt CH, Gibreel W, Mardini S. Black Bone MRI for Virtual Surgical Planning in Craniomaxillofacial Surgery. Semin Plast Surg 2022; 36:192-198. [PMID: 36506277 PMCID: PMC9729059 DOI: 10.1055/s-0042-1756451] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
Advances in computer-aided design and computer-aided manufacturing software have improved translational applications of virtual surgical planning (VSP) in craniomaxillofacial surgery, allowing for precise and accurate fabrication of cutting guides, stereolithographic models, and custom implants. High-resolution computed tomography (CT) imaging has traditionally been the gold standard imaging modality for VSP in craniomaxillofacial surgery but delivers ionizing radiation. Black bone magnetic resonance imaging (MRI) reduces the risks related to radiation exposure and has comparable functionality when compared with CT for VSP. Our group has studied the accuracy of utilizing black bone MRI in planning and executing several types of craniofacial surgeries, including cranial vault remodeling, maxillary advancement, and mandibular reconstruction using fibular bone. Here, we review clinical applications of black bone MRI pertaining to VSP and three-dimensional (3D)-printed guide creation for craniomaxillofacial surgery. Herein, we review the existing literature and our institutional experience comparing black bone MRI and CT in VSP-generated 3D model creation in cadaveric craniofacial surgeries including cranial vault reconstruction, maxillary advancement, and mandibular reconstruction with fibular free flap. Cadaver studies have demonstrated the ability to perform VSP and execute the procedure based on black bone MRI data and achieve outcomes similar to CT when performed for cranial vault reshaping, maxillary advancement, and mandibular reconstruction with free fibula. Limitations of the technology include increased time and costs of the MRI compared with CT and the possible need for general anesthesia or sedation in the pediatric population. VSP and 3D surgical guide creation can be performed using black bone MRI with comparable accuracy to high-resolution CT scans in a wide variety of craniofacial reconstructions. Successful segmentation, VSP, and 3D printing of accurate guides from black bone MRI demonstrate potential to change the preoperative planning standard of care. Black bone MRI also reduces exposure to ionizing radiation, which is of particular concern for the pediatric population or patients undergoing multiple scans.
Collapse
Affiliation(s)
- Krishna S. Vyas
- Division of Plastic Surgery, Department of Surgery, Mayo Clinic, Rochester, Minnesota
| | - Marissa A. Suchyta
- Division of Plastic Surgery, Department of Surgery, Mayo Clinic, Rochester, Minnesota
| | | | - Waleed Gibreel
- Division of Plastic Surgery, Department of Surgery, Mayo Clinic, Rochester, Minnesota
| | - Samir Mardini
- Division of Plastic Surgery, Department of Surgery, Mayo Clinic, Rochester, Minnesota,Department of Radiology, Mayo Clinic, Rochester, Minnesota,Essam and Dalal Obaid Center for Reconstructive Transplant Surgery, Mayo Clinic, Rochester, Minnesota,Address for correspondence Samir Mardini, MD Division of Plastic Surgery, Department of Surgery, Essam and Dalal Obaid Center for Reconstructive Transplant SurgeryMayo Clinic, MA12-44W, 200 First Street SouthwestRochester, MN 55905
| |
Collapse
|
4
|
Geoffroy M, François PM, Khonsari RH, Laporte S. Paediatric skull growth models: A systematic review of applications to normal skulls and craniosynostoses. JOURNAL OF STOMATOLOGY, ORAL AND MAXILLOFACIAL SURGERY 2022; 123:e533-e543. [PMID: 35007781 DOI: 10.1016/j.jormas.2022.01.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/13/2021] [Revised: 12/21/2021] [Accepted: 01/04/2022] [Indexed: 06/14/2023]
Abstract
INTRODUCTION Craniosynostoses affect 1/2000 births and their incidence is currently increasing. Without surgery, craniosynostosis can lead to neurological issues due to restrained brain growth and social stigma due to abnormal head shapes. Understanding growth patterns is essential to develop surgical planning approaches and predict short- and long-term post-operative results. Here we provide a systematic review of normal and pathological cranial vault growth models. MATERIAL AND METHODS The systematic review of the literature identified descriptive and comprehensive skull growth models with the following criteria: full text articles dedicated to the skull vault of children under 2 years of age, without focus on molecular and cellular mechanisms. Models were analysed based on initial geometry, numerical method, age determination method and validation process. RESULTS A total of 14 articles including 17 models was reviewed. Four descriptive models were assessed, including 3 models using statistical analyses and 1 based on deformational methods. Thirteen comprehensive models were assessed including 7 finite element models and 6 diffusion models. Results from the current literature showed that successful models combined analyses of cranial vault shape and suture bone formation. DISCUSSION Growth modelling is central when assessing craniofacial architecture in young patients and will be a key factor in the development of future customized treatment strategies. Recurrent technical difficulties were encountered by most authors when generalizing a specific craniosynostosis model to all types of craniosynostoses, when assessing the role of the brain and when attempting to relate the age with different stages of growth.
Collapse
Affiliation(s)
- Maya Geoffroy
- Arts et Métiers Institute of Technology, Université Paris Nord, IBHGC - Institut de Biomécanique Humaine Georges Charpak, HESAM Université, F-75013, Paris, France; Service de Chirurgie Maxillofaciale et Chirurgie Plastique, Hôpital Necker - Enfants Malades, Assistance Publique - Hôpitaux de Paris; Faculté de Médecine, Université de Paris; 149 Rue de Sèvres, 75015 Paris, France; BONE 3D; 14 Rue Jean Antoine de Baïf, 75013 Paris, France.
| | | | - Roman Hossein Khonsari
- Service de Chirurgie Maxillofaciale et Chirurgie Plastique, Hôpital Necker - Enfants Malades, Assistance Publique - Hôpitaux de Paris; Faculté de Médecine, Université de Paris; 149 Rue de Sèvres, 75015 Paris, France.
| | - Sébastien Laporte
- Arts et Métiers Institute of Technology, Université Paris Nord, IBHGC - Institut de Biomécanique Humaine Georges Charpak, HESAM Université, F-75013, Paris, France.
| |
Collapse
|
5
|
Eley KA, Delso G. Imaging of Bone in the Head and Neck Region, is There More Than CT? CURRENT RADIOLOGY REPORTS 2022; 10:69-82. [PMID: 35463479 PMCID: PMC9013214 DOI: 10.1007/s40134-022-00396-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/10/2022] [Indexed: 01/22/2023]
Abstract
Purpose of Review The objective of this review is to document the advances in non-ionising imaging alternatives to CT for the head and neck. Recent Findings The main alternative to CT for imaging bone of the head and neck region is MRI, particularly techniques which incorporate gradient echo imaging (Black Bone technique) and ultra-short or zero-echo time imaging. Since these techniques can provide high resolution isometric voxels, they can be used to provide multi-planar reformats and, following post processing, 3D reconstructed images of the craniofacial skeleton. As expected, the greatest advancements in recent years have been focused on enhanced image processing techniques and attempts to address the difficulties encountered at air-bone interfaces. Summary This article will review the imaging techniques and recent advancements which are bringing non-ionising alternatives to CT imaging of the bone of the head and neck region into the realm of routine clinical application.
Collapse
Affiliation(s)
- Karen A. Eley
- Department of Radiology, School of Clinical Medicine, University of Cambridge, Cambridge Biomedical Campus, Box 218, Cambridge, CB2 0QQ UK
| | - Gaspar Delso
- MR Applications & Workflow, GE Healthcare, Barcelona, Spain
| |
Collapse
|
6
|
Main Applications and Recent Research Progresses of Additive Manufacturing in Dentistry. BIOMED RESEARCH INTERNATIONAL 2022; 2022:5530188. [PMID: 35252451 PMCID: PMC8894006 DOI: 10.1155/2022/5530188] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/20/2021] [Revised: 12/16/2021] [Accepted: 01/28/2022] [Indexed: 12/13/2022]
Abstract
In recent ten years, with the fast development of digital and engineering manufacturing technology, additive manufacturing has already been more and more widely used in the field of dentistry, from the first personalized surgical guides to the latest personalized restoration crowns and root implants. In particular, the bioprinting of teeth and tissue is of great potential to realize organ regeneration and finally improve the life quality. In this review paper, we firstly presented the workflow of additive manufacturing technology. Then, we summarized the main applications and recent research progresses of additive manufacturing in dentistry. Lastly, we sketched out some challenges and future directions of additive manufacturing technology in dentistry.
Collapse
|
7
|
Florkow MC, Willemsen K, Mascarenhas VV, Oei EHG, van Stralen M, Seevinck PR. Magnetic Resonance Imaging Versus Computed Tomography for Three-Dimensional Bone Imaging of Musculoskeletal Pathologies: A Review. J Magn Reson Imaging 2022; 56:11-34. [PMID: 35044717 PMCID: PMC9305220 DOI: 10.1002/jmri.28067] [Citation(s) in RCA: 23] [Impact Index Per Article: 11.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2021] [Revised: 12/31/2021] [Accepted: 01/05/2022] [Indexed: 12/18/2022] Open
Abstract
Magnetic resonance imaging (MRI) is increasingly utilized as a radiation‐free alternative to computed tomography (CT) for the diagnosis and treatment planning of musculoskeletal pathologies. MR imaging of hard tissues such as cortical bone remains challenging due to their low proton density and short transverse relaxation times, rendering bone tissues as nonspecific low signal structures on MR images obtained from most sequences. Developments in MR image acquisition and post‐processing have opened the path for enhanced MR‐based bone visualization aiming to provide a CT‐like contrast and, as such, ease clinical interpretation. The purpose of this review is to provide an overview of studies comparing MR and CT imaging for diagnostic and treatment planning purposes in orthopedic care, with a special focus on selective bone visualization, bone segmentation, and three‐dimensional (3D) modeling. This review discusses conventional gradient‐echo derived techniques as well as dedicated short echo time acquisition techniques and post‐processing techniques, including the generation of synthetic CT, in the context of 3D and specific bone visualization. Based on the reviewed literature, it may be concluded that the recent developments in MRI‐based bone visualization are promising. MRI alone provides valuable information on both bone and soft tissues for a broad range of applications including diagnostics, 3D modeling, and treatment planning in multiple anatomical regions, including the skull, spine, shoulder, pelvis, and long bones.
Collapse
Affiliation(s)
- Mateusz C Florkow
- Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Koen Willemsen
- Department of Orthopedics, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Vasco V Mascarenhas
- Musculoskeletal Imaging Unit, Imaging Center, Hospital da Luz, Lisbon, Portugal
| | - Edwin H G Oei
- Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Marijn van Stralen
- Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands.,MRIguidance BV, Utrecht, The Netherlands
| | - Peter R Seevinck
- Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands.,MRIguidance BV, Utrecht, The Netherlands
| |
Collapse
|
8
|
Probst FA, Burian E, Malenova Y, Lyutskanova P, Stumbaum MJ, Ritschl LM, Kronthaler S, Karampinos D, Probst M. Geometric accuracy of magnetic resonance imaging-derived virtual 3-dimensional bone surface models of the mandible in comparison to computed tomography and cone beam computed tomography: A porcine cadaver study. Clin Implant Dent Relat Res 2021; 23:779-788. [PMID: 34318580 DOI: 10.1111/cid.13033] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2021] [Accepted: 04/29/2021] [Indexed: 12/16/2022]
Abstract
BACKGROUND Providing accurate 3-dimensional virtual bone surface models is a prerequisite for virtual surgical planning and additive manufacturing in craniomaxillofacial surgery. For this purpose, magnetic resonance imaging (MRI) may be a radiation-free alternative to computed tomography (CT) and cone beam computed tomography (CBCT). PURPOSE The aim of this study was to assess the geometric accuracy of 3-dimensional T1-weighted MRI-derived virtual bone surface models of the mandible in comparison to CT and CBCT. MATERIALS AND METHODS Specimens of the mandible from porcine cadavers were scanned with (1) a 3-dimensional T1-weighted MRI sequence (0.6 mm isotropic voxel) optimized for bone imaging, (2) CT, and (3) CBCT. Cortical mandibular structures (n = 10) were segmented using semiautomated and manual techniques. Imaging-based virtual 3-dimensional models were aligned with a high-resolution optical 3-dimensional surface scan of the dissected bone (=ground truth) and global geometric deviations were calculated (mean surface distance [MSD]/root-mean-square distance [RMSD]). Agreement between the imaging modalities was assessed by equivalence testing and Bland-Altman analysis. RESULTS Intra- and inter-rater agreement was on a high level for all modalities. Global geometric deviations (MSD/RMSD) between optical scans and imaging modalities were 0.225 ± 0.020 mm/0.345 ± 0.074 mm for CT, 0.280 ± 0.067 mm/0.371 ± 0.074 mm for MRI, and 0.352 ± 0.076 mm/0.454 ± 0.071 mm for CBCT. All imaging modalities were statistically equivalent within an equivalence margin of ±0.3 mm, and Bland-Altman analysis indicated high agreement as well. CONCLUSIONS The results of this study indicate that the accuracy and reliability of MRI-derived virtual 3-dimensional bone surface models is equal to CT and CBCT. MRI may be considered as a reliable alternative to CT and CBCT in computer-assisted craniomaxillofacial surgery.
Collapse
Affiliation(s)
- Florian Andreas Probst
- Department of Oral and Maxillofacial Surgery and Facial Plastic Surgery, University Hospital, LMU München, Munich, Germany
| | - Egon Burian
- Department of Diagnostic and Interventional Neuroradiology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Yoana Malenova
- Department of Oral and Maxillofacial Surgery and Facial Plastic Surgery, University Hospital, LMU München, Munich, Germany
| | - Plamena Lyutskanova
- Department of Oral and Maxillofacial Surgery and Facial Plastic Surgery, University Hospital, LMU München, Munich, Germany
| | | | - Lucas Maximilian Ritschl
- Department of Oral and Maxillofacial Surgery, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Sophia Kronthaler
- Department of Diagnostic and Interventional Radiology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Dimitrios Karampinos
- Department of Diagnostic and Interventional Radiology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Monika Probst
- Department of Diagnostic and Interventional Neuroradiology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| |
Collapse
|
9
|
Smith M, Bambach S, Selvaraj B, Ho ML. Zero-TE MRI: Potential Applications in the Oral Cavity and Oropharynx. Top Magn Reson Imaging 2021; 30:105-115. [PMID: 33828062 DOI: 10.1097/rmr.0000000000000279] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
ABSTRACT Zero-echo time (ZTE) magnetic resonance imaging (MRI) is the newest in a family of MRI pulse sequences that involve ultrafast sequence readouts, permitting visualization of short-T2 tissues such as cortical bone. Inherent sequence properties enable rapid, high-resolution, quiet, and artifact-resistant imaging. ZTE can be performed as part of a "one-stop-shop" MRI examination for comprehensive evaluation of head and neck pathology. As a potential alternative to computed tomography for bone imaging, this approach could help reduce patient exposure to ionizing radiation and improve radiology resource utilization. Because ZTE is not yet widely used clinically, it is important to understand the technical limitations and pitfalls for diagnosis. Imaging cases are presented to demonstrate potential applications of ZTE for imaging of oral cavity, oropharynx, and jaw anatomy and pathology in adult and pediatric patients. Emerging studies indicate promise for future clinical implementation based on synthetic computed tomography image generation, 3D printing, and interventional applications.
Collapse
Affiliation(s)
- Mark Smith
- Department of Radiology, Nationwide Children's Hospital, Columbus, OH
| | - Sven Bambach
- Abigail Wexner Research Institute at Nationwide Children's Hospital, Columbus, OH
| | - Bhavani Selvaraj
- Department of Radiology, Nationwide Children's Hospital, Columbus, OH
| | - Mai-Lan Ho
- Department of Radiology, Nationwide Children's Hospital, Columbus, OH
| |
Collapse
|
10
|
Eley KA, Delso G. Automated 3D MRI rendering of the craniofacial skeleton: using ZTE to drive the segmentation of black bone and FIESTA-C images. Neuroradiology 2020; 63:91-98. [PMID: 32772120 PMCID: PMC7803710 DOI: 10.1007/s00234-020-02508-7] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2020] [Accepted: 07/28/2020] [Indexed: 11/29/2022]
Abstract
Purpose Automated bone segmentation from MRI datasets would have a profound impact on clinical utility, particularly in the craniofacial skeleton where complex anatomy is coupled with radiosensitive organs. Techniques such as gradient echo black bone (GRE-BB) and short echo time (UTE, ZTE) have shown potential in this quest. The objectives of this study were to ascertain (1) whether the high-contrast of zero echo time (ZTE) could drive segmentation of high-resolution GRE-BB data to enhance 3D-output and (2) if these techniques could be extrapolated to ZTE driven segmentation of a routinely used non bone-specific sequence (FIESTA-C). Methods Eleven adult volunteers underwent 3T MRI examination with sequential acquisition of ZTE, GRE-BB and FIESTA-C imaging. Craniofacial bone segmentation was performed using a fully automated segmentation algorithm. Segmentation was completed individually for GRE-BB and a modified version of the algorithm was subsequently implemented, wherein the bone mask yielded by ZTE segmentation was used to initialise segmentation of GRE-BB. The techniques were subsequently applied to FIESTA-C datasets. The resulting 3D reconstructions were evaluated for areas of unexpected bony defects and discrepancies. Results The automated segmentation algorithm yielded acceptable 3D outputs for all GRE-BB datasets. These were enhanced with the modified algorithm using ZTE as a driver, with improvements in areas of air/bone interface and dense muscular attachments. Comparable results were obtained with ZTE+FIESTA-C. Conclusion Automated 3D segmentation of the craniofacial skeleton is enhanced through the incorporation of a modified segmentation algorithm utilising ZTE. These techniques are transferrable to FIESTA-C imaging which offers reduced acquisition time and therefore improved clinical utility.
Collapse
Affiliation(s)
- Karen A Eley
- Department of Radiology, University of Cambridge School of Clinical Medicine, Box 218, Cambridge Biomedical Campus, Hills Road, Cambridge, CB2 0QQ, UK.
| | - Gaspar Delso
- Department of Radiology, University of Cambridge School of Clinical Medicine, Box 218, Cambridge Biomedical Campus, Hills Road, Cambridge, CB2 0QQ, UK
| |
Collapse
|