1
|
van Houdt PJ, Ragunathan S, Berks M, Ahmed Z, Kershaw LE, Gurney-Champion OJ, Tadimalla S, Arvidsson J, Sun Y, Kallehauge J, Dickie B, Lévy S, Bell L, Sourbron S, Thrippleton MJ. Contrast-agent-based perfusion MRI code repository and testing framework: ISMRM Open Science Initiative for Perfusion Imaging (OSIPI). Magn Reson Med 2024; 91:1774-1786. [PMID: 37667526 DOI: 10.1002/mrm.29826] [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: 03/24/2023] [Revised: 06/30/2023] [Accepted: 07/25/2023] [Indexed: 09/06/2023]
Abstract
PURPOSE Software has a substantial impact on quantitative perfusion MRI values. The lack of generally accepted implementations, code sharing and transparent testing reduces reproducibility, hindering the use of perfusion MRI in clinical trials. To address these issues, the ISMRM Open Science Initiative for Perfusion Imaging (OSIPI) aimed to establish a community-led, centralized repository for sharing open-source code for processing contrast-based perfusion imaging, incorporating an open-source testing framework. METHODS A repository was established on the OSIPI GitHub website. Python was chosen as the target software language. Calls for code contributions were made to OSIPI members, the ISMRM Perfusion Study Group, and publicly via OSIPI websites. An automated unit-testing framework was implemented to evaluate the output of code contributions, including visual representation of the results. RESULTS The repository hosts 86 implementations of perfusion processing steps contributed by 12 individuals or teams. These cover all core aspects of DCE- and DSC-MRI processing, including multiple implementations of the same functionality. Tests were developed for 52 implementations, covering five analysis steps. For T1 mapping, signal-to-concentration conversion and population AIF functions, different implementations resulted in near-identical output values. For the five pharmacokinetic models tested (Tofts, extended Tofts-Kety, Patlak, two-compartment exchange, and two-compartment uptake), differences in output parameters were observed between contributions. CONCLUSIONS The OSIPI DCE-DSC code repository represents a novel community-led model for code sharing and testing. The repository facilitates the re-use of existing code and the benchmarking of new code, promoting enhanced reproducibility in quantitative perfusion imaging.
Collapse
Affiliation(s)
- Petra J van Houdt
- Department of Radiation Oncology, The Netherlands Cancer Institute, Amsterdam, The Netherlands
| | | | - Michael Berks
- Quantitative Biomedical Imaging Laboratory, Division of Cancer Sciences, The University of Manchester, Manchester, UK
| | - Zaki Ahmed
- Corewell Health William Beaumont University Hospital, Diagnostic Radiology, Royal Oak, USA
| | - Lucy E Kershaw
- Edinburgh Imaging and Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK
| | - Oliver J Gurney-Champion
- Department of Radiology and Nuclear Medicine, Amsterdam UMC location University of Amsterdam, Amsterdam, The Netherlands
- Cancer Center Amsterdam, Imaging and Biomarkers, Amsterdam, The Netherlands
| | - Sirisha Tadimalla
- Institute of Medical Physics, The University of Sydney, Sydney, Australia
| | - Jonathan Arvidsson
- Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Yu Sun
- Institute of Medical Physics, The University of Sydney, Sydney, Australia
| | - Jesper Kallehauge
- Aarhus University Hospital, Danish Centre for Particle Therapy, Aarhus, Denmark
- Aarhus University, Department of Clinical Medicine, Aarhus, Denmark
| | - Ben Dickie
- Division of Informatics, Imaging, and Data Science, School of Health Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, UK
- Geoffrey Jefferson Brain Research Centre, Manchester Academic Health Science Centre, Northern Care Alliance NHS Group, The University of Manchester, Manchester, UK
| | - Simon Lévy
- MR Research Collaborations, Siemens Healthcare Pty Ltd, Melbourne, Australia
| | - Laura Bell
- Genentech, Inc, Clinical Imaging Group, South San Francisco, USA
| | - Steven Sourbron
- University of Sheffield, Department of Infection, Immunity and Cardiovascular Disease, Sheffield, UK
| | - Michael J Thrippleton
- University of Edinburgh, Edinburgh Imaging and Centre for Clinical Brain Sciences, Edinburgh, UK
| |
Collapse
|
2
|
Abdulrashid I, Friji H, Topuz K, Ghazzai H, Delen D, Massoud Y. An analytical approach to evaluate the impact of age demographics in a pandemic. STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT : RESEARCH JOURNAL 2023; 37:1-15. [PMID: 37362847 PMCID: PMC10248992 DOI: 10.1007/s00477-023-02477-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Accepted: 05/13/2023] [Indexed: 06/28/2023]
Abstract
The time required to identify and confirm risk factors for new diseases and to design an appropriate treatment strategy is one of the most significant obstacles medical professionals face. Traditionally, this approach entails several clinical studies that may last several years, during which time strict preventative measures must be in place to contain the epidemic and limit the number of fatalities. Analytical tools may be used to direct and accelerate this process. This study introduces a six-state compartmental model to explain and assess the impact of age demographics by designing a dynamic, explainable analytics model of the SARS-CoV-2 coronavirus. An age-stratified mathematical model taking the form of a deterministic system of ordinary differential equations divides the population into different age groups to better understand and assess the impact of age on mortality. It also provides a more accurate and effective interpretation of the disease evolution, specifically in terms of the cumulative numbers of infected cases and deaths. The proposed Kermack-Mckendrick model is incorporated into a non-linear least-squares optimization curve-fitting problem whose optimized parameters are numerically obtained using the Levenberg-Marquard algorithm. The curve-fitting model's efficiency is proved by testing the age-stratified model's performance on three U.S. states: Connecticut, North Dakota, and South Dakota. Our results confirm that splitting the population into different age groups leads to better fitting and forecasting results overall as compared to those achieved by the traditional method, i.e., without age groups. By using comprehensive models that account for age, gender, and ethnicity, regional public health authorities may be able to avoid future epidemics from inflicting more fatalities and establish a public health policy that reduces the burden on the elderly population.
Collapse
Affiliation(s)
- Ismail Abdulrashid
- School of Finance and Operations Management, The University of Tulsa, 800 South Tucker Drive, Tulsa, OK 74104 USA
| | - Hamdi Friji
- School of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ 07030 USA
| | - Kazim Topuz
- School of Finance and Operations Management, The University of Tulsa, 800 South Tucker Drive, Tulsa, OK 74104 USA
| | - Hakim Ghazzai
- Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), 23955-6900 Thuwal, Saudi Arabia
| | - Dursun Delen
- Department of Management Science and Information Systems, Oklahoma State University, Tulsa, OK 74106 USA
- Faculty of Engineering and Natural Sciences, Department of Industrial Engineering, Istinye University, Istanbul, Turkey
| | - Yehia Massoud
- Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), 23955-6900 Thuwal, Saudi Arabia
| |
Collapse
|
3
|
Moya-Sáez E, Peña-Nogales Ó, Luis-García RD, Alberola-López C. A deep learning approach for synthetic MRI based on two routine sequences and training with synthetic data. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021; 210:106371. [PMID: 34525411 DOI: 10.1016/j.cmpb.2021.106371] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/10/2021] [Accepted: 08/18/2021] [Indexed: 06/13/2023]
Abstract
BACKGROUND AND OBJECTIVE Synthetic magnetic resonance imaging (MRI) is a low cost procedure that serves as a bridge between qualitative and quantitative MRI. However, the proposed methods require very specific sequences or private protocols which have scarcely found integration in clinical scanners. We propose a learning-based approach to compute T1, T2, and PD parametric maps from only a pair of T1- and T2-weighted images customarily acquired in the clinical routine. METHODS Our approach is based on a convolutional neural network (CNN) trained with synthetic data; specifically, a synthetic dataset with 120 volumes was constructed from the anatomical brain model of the BrainWeb tool and served as the training set. The CNN learns an end-to-end mapping function to transform the input T1- and T2-weighted images to their underlying T1, T2, and PD parametric maps. Then, conventional weighted images unseen by the network are analytically synthesized from the parametric maps. The network can be fine tuned with a small database of actual weighted images and maps for better performance. RESULTS This approach is able to accurately compute parametric maps from synthetic brain data achieving normalized squared error values predominantly below 1%. It also yields realistic parametric maps from actual MR brain acquisitions with T1, T2, and PD values in the range of the literature and with correlation values above 0.95 compared to the T1 and T2 maps obtained from relaxometry sequences. Further, the synthesized weighted images are visually realistic; the mean square error values are always below 9% and the structural similarity index is usually above 0.90. Network fine tuning with actual maps improves performance, while training exclusively with a small database of actual maps shows a performance degradation. CONCLUSIONS These results show that our approach is able to provide realistic parametric maps and weighted images out of a CNN that (a) is trained with a synthetic dataset and (b) needs only two inputs, which are in turn obtained from a common full-brain acquisition that takes less than 8 min of scan time. Although a fine tuning with actual maps improves performance, synthetic data is crucial to reach acceptable performance levels. Hence, we show the utility of our approach for both quantitative MRI in clinical viable times and for the synthesis of additional weighted images to those actually acquired.
Collapse
Affiliation(s)
- Elisa Moya-Sáez
- Laboratorio de Procesado de Imagen, Universidad de Valladolid, Valladolid, Spain. http://www.lpi.tel.uva.es
| | - Óscar Peña-Nogales
- Laboratorio de Procesado de Imagen, Universidad de Valladolid, Valladolid, Spain
| | | | | |
Collapse
|
4
|
Magnetic Resonance Simulation in Education: Quantitative Evaluation of an Actual Classroom Experience. SENSORS 2021; 21:s21186011. [PMID: 34577231 PMCID: PMC8468339 DOI: 10.3390/s21186011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Revised: 08/30/2021] [Accepted: 09/04/2021] [Indexed: 11/17/2022]
Abstract
Magnetic resonance is an imaging modality that implies a high complexity for radiographers. Despite some simulators having been developed for training purposes, we are not aware of any attempt to quantitatively measure their educational performance. The present study gives an answer to the question: Does an MRI simulator built on specific functional and non-functional requirements help radiographers learn MRI theoretical and practical concepts better than traditional educational method based on lectures? Our study was carried out in a single day by a total of 60 students of a main hospital in Madrid, Spain. The experiment followed a randomized pre-test post-test design with a control group that used a traditional educational method, and an experimental group that used our simulator. Knowledge level was assessed by means of an instrument with evidence of validity in its format and content, while its reliability was analyzed after the experiment. Statistical differences between both groups were measured. Significant statistical differences were found in favor of the participants who used the simulator for both the post-test score and the gain (difference between post-test and pre-test scores). The effect size turned out to be significant as well. In this work we evaluated a magnetic resonance simulation paradigm as a tool to help in the training of radiographers. The study shows that a simulator built on specific design requirements is a valuable complement to traditional education procedures, backed up with significant quantitative results.
Collapse
|
5
|
van Zandwijk JK, Simonis FFJ, Heslinga FG, Hofmeijer EIS, Geelkerken RH, ten Haken B. Comparing the signal enhancement of a gadolinium based and an iron-oxide based contrast agent in low-field MRI. PLoS One 2021; 16:e0256252. [PMID: 34403442 PMCID: PMC8370648 DOI: 10.1371/journal.pone.0256252] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2021] [Accepted: 08/04/2021] [Indexed: 12/25/2022] Open
Abstract
Recently, there has been a renewed interest in low-field MRI. Contrast agents (CA) in MRI have magnetic behavior dependent on magnetic field strength. Therefore, the optimal contrast agent for low-field MRI might be different from what is used at higher fields. Ultra-small superparamagnetic iron-oxides (USPIOs), commonly used as negative CA, might also be used for generating positive contrast in low-field MRI. The purpose of this study was to determine whether an USPIO or a gadolinium based contrast agent is more appropriate at low field strengths. Relaxivity values of ferumoxytol (USPIO) and gadoterate (gadolinium based) were used in this research to simulate normalized signal intensity (SI) curves within a concentration range of 0–15 mM. Simulations were experimentally validated on a 0.25T MRI scanner. Simulations and experiments were performed using spin echo (SE), spoiled gradient echo (SGE), and balanced steady-state free precession (bSSFP) sequences. Maximum achievable SIs were assessed for both CAs in a range of concentrations on all sequences. Simulations at 0.25T showed a peak in SIs at low concentrations ferumoxytol versus a wide top at higher concentrations for gadoterate in SE and SGE. Experiments agreed well with the simulations in SE and SGE, but less in the bSSFP sequence due to overestimated relaxivities in simulations. At low magnetic field strengths, ferumoxytol generates similar signal enhancement at lower concentrations than gadoterate.
Collapse
Affiliation(s)
- Jordy K. van Zandwijk
- Magnetic Detection & Imaging, TechMed Centre, University of Twente, Enschede, Netherlands
- Department of Vascular Surgery, Medisch Spectrum Twente, Enschede, Netherlands
- * E-mail:
| | - Frank F. J. Simonis
- Magnetic Detection & Imaging, TechMed Centre, University of Twente, Enschede, Netherlands
| | - Friso G. Heslinga
- Magnetic Detection & Imaging, TechMed Centre, University of Twente, Enschede, Netherlands
| | - Elfi I. S. Hofmeijer
- Magnetic Detection & Imaging, TechMed Centre, University of Twente, Enschede, Netherlands
| | - Robert H. Geelkerken
- Department of Vascular Surgery, Medisch Spectrum Twente, Enschede, Netherlands
- Multimodality Medical Imaging Group, TechMed Centre, University of Twente, Enschede, Netherlands
| | - Bennie ten Haken
- Magnetic Detection & Imaging, TechMed Centre, University of Twente, Enschede, Netherlands
| |
Collapse
|
6
|
Maggioni MB, Krämer M, Reichenbach JR. Optimized gradient spoiling of UTE VFA-AFI sequences for robust T 1 estimation with B 1-field correction. Magn Reson Imaging 2021; 82:1-8. [PMID: 34147596 DOI: 10.1016/j.mri.2021.06.011] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2020] [Revised: 05/21/2021] [Accepted: 06/15/2021] [Indexed: 10/21/2022]
Abstract
Quantifying T1 relaxation times is a challenge because inhomogeneities of the B1 field have to be corrected to obtain proper values. It is a particular challenge in tissues with short T2⁎ values, for which conventional MRI techniques do not provide sufficient signal. Recently, a B1-field correction technique called AFI (Actual Flip angle Imaging) has been introduced that can be combined with UTE (ultra-short echo-time) sequences, which have much shorter echo times compared to conventional MRI techniques, allowing quantification of signal in short T2⁎ tissues. A disadvantage of AFI is that it requires very long relaxation delays between repetitions to minimize the influence of imperfect spoiling of transverse magnetization on signal behavior. In this work, we propose a novel spoiling scheme for the AFI sequence that efficiently provides accurate B1 correction maps with strongly reduced acquisition time. We validated the method with both phantom and preliminary in vivo results.
Collapse
Affiliation(s)
- Marta B Maggioni
- Medical Physics Group, Institute of Diagnostic and Interventional Radiology, Jena University Hospital - Friedrich Schiller University Jena, Germany.
| | - Martin Krämer
- Medical Physics Group, Institute of Diagnostic and Interventional Radiology, Jena University Hospital - Friedrich Schiller University Jena, Germany
| | - Jürgen R Reichenbach
- Medical Physics Group, Institute of Diagnostic and Interventional Radiology, Jena University Hospital - Friedrich Schiller University Jena, Germany.
| |
Collapse
|
7
|
Friji H, Hamadi R, Ghazzai H, Besbes H, Massoud Y. A Generalized Mechanistic Model for Assessing and Forecasting the Spread of the COVID-19 Pandemic. IEEE ACCESS : PRACTICAL INNOVATIONS, OPEN SOLUTIONS 2021; 9:13266-13285. [PMID: 34976570 PMCID: PMC8675554 DOI: 10.1109/access.2021.3051929] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/08/2021] [Accepted: 01/09/2021] [Indexed: 05/07/2023]
Abstract
Since early 2020, the world has been afflicted with an unprecedented global pandemic. The SARS-CoV-19 (COVID-19) has levied massive economic and public health costs across many countries. Due to its virulence, the pathogen is rapidly propagating throughout the world in such a way that makes it incredibly challenging for officials to contain its spread. Therefore, there is a pressing need for national and local authorities to have tools that aid in their ability to assess and extrapolate the future trends of the spread of COVID-19, so they may make rational and informed decisions that minimize public harm. Mechanistic models are prominent mathematical tools that are used to characterize epidemics. In this paper, we propose a generalized mechanistic model with eight states characterizing the COVID-19 pandemic evolution from a susceptible state to discharged states while passing by quarantined and hospitalized states. The parameters of the model are determined by solving a fitting optimization problem with three observed inputs: the number of infected, deceased, and reported cases. The model's objective function is weighted over the training days so as to guide the fitting algorithm towards the latest pandemic period and lead to more accurate trend predictions for a stronger forecast. We solve the fitting problem with the Levenberg-Marquardt algorithm; we compare the performance of the model generated from this algorithm to the one of another state-of-the-art fitting algorithm as well as to the one of another compartmental model widely used in literature. We test the model on the COVID-19 data from four highly afflicted countries. The fitting algorithm has been validated graphically and through numerical metrics, and results show significantly accurate results for most of the countries. Once the model's parameters are estimated, forecasting results are derived and uncertainty regions of the expected scenarios are provided.
Collapse
Affiliation(s)
- Hamdi Friji
- School of Systems and EnterprisesStevens Institute of Technology Hoboken NJ 07030 USA
| | - Raby Hamadi
- School of Systems and EnterprisesStevens Institute of Technology Hoboken NJ 07030 USA
| | - Hakim Ghazzai
- School of Systems and EnterprisesStevens Institute of Technology Hoboken NJ 07030 USA
| | - Hichem Besbes
- Higher School of Communication of TunisUniversity of Carthage Tunis 2083 Tunisia
| | - Yehia Massoud
- School of Systems and EnterprisesStevens Institute of Technology Hoboken NJ 07030 USA
| |
Collapse
|
8
|
Bianchini L, Botta F, Origgi D, Rizzo S, Mariani M, Summers P, García-Polo P, Cremonesi M, Lascialfari A. PETER PHAN: An MRI phantom for the optimisation of radiomic studies of the female pelvis. Phys Med 2020; 71:71-81. [PMID: 32092688 DOI: 10.1016/j.ejmp.2020.02.003] [Citation(s) in RCA: 25] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/14/2019] [Revised: 01/29/2020] [Accepted: 02/04/2020] [Indexed: 01/26/2023] Open
Abstract
PURPOSE To develop a phantom for methodological radiomic investigation on Magnetic Resonance (MR) images of female patients affected by pelvic cancer. METHODS A pelvis-shaped container was filled with a MnCl2 solution reproducing the relaxation times (T1, T2) of muscle surrounding pelvic malignancies. Inserts simulating multi-textured lesions were embedded in the phantom. The relaxation times of muscle and tumour were measured on an MR scanner on healthy volunteers and patients; T1 and T2 of MnCl2 solutions were evaluated with a relaxometer to find the concentrations providing a match to in vivo relaxation times. Radiomic features were extracted from the phantom inserts and the patients' lesions. Their repeatability was assessed by multiple measurements. RESULTS Muscle T1 and T2 were 1128 (806-1378) and 51 (40-65) ms, respectively. The phantom reproduced in vivo values within 13% (T1) and 12% (T2). T1 and T2 of tumour tissue were 1637 (1396-2121) and 94 (79-101) ms, respectively. The phantom insert best mimicking the tumour agreed within 7% (T1) and 24% (T2) with in vivo values. Out of 1034 features, 75% (95%) had interclass correlation coefficient greater than 0.9 on T1 (T2)-weighted images, reducing to 33% (25%) if the phantom was repositioned. The most repeatable features on phantom showed values in agreement with the features extracted from patients' lesions. CONCLUSIONS We developed an MR phantom with inserts mimicking both relaxation times and texture of pelvic tumours. As exemplified with repeatability assessment, such phantom is useful to investigate features robustness and optimise the radiomic workflow on pelvic MR images.
Collapse
Affiliation(s)
- Linda Bianchini
- Department of Physics and INSTM RU, Università degli Studi di Milano, Italy.
| | - Francesca Botta
- Medical Physics Unit, IEO, European Institute of Oncology IRCCS, Milan, Italy
| | - Daniela Origgi
- Medical Physics Unit, IEO, European Institute of Oncology IRCCS, Milan, Italy
| | - Stefania Rizzo
- Clinica di Radiologia EOC, Istituto di Imaging della Svizzera Italiana, Sede Ospedale Regionale di Lugano, Switzerland
| | - Manuel Mariani
- Department of Physics and INSTM RU, Università degli Studi di Pavia, Italy
| | - Paul Summers
- Division of Radiology, IEO, European Institute of Oncology IRCCS, Milan, Italy
| | - Pablo García-Polo
- Southern Europe Global Research Organization, GE Healthcare, Madrid, Spain
| | - Marta Cremonesi
- Radiation Research Unit, IEO, European Institute of Oncology IRCCS, Milan, Italy
| | - Alessandro Lascialfari
- Department of Physics and INSTM RU, Università degli Studi di Milano, Italy; Department of Physics and INSTM RU, Università degli Studi di Pavia, Italy
| |
Collapse
|
9
|
Zavala Bojorquez JA, Jodoin PM, Bricq S, Walker PM, Brunotte F, Lalande A. Automatic classification of tissues on pelvic MRI based on relaxation times and support vector machine. PLoS One 2019; 14:e0211944. [PMID: 30794559 PMCID: PMC6386287 DOI: 10.1371/journal.pone.0211944] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2018] [Accepted: 01/23/2019] [Indexed: 02/07/2023] Open
Abstract
Tissue segmentation and classification in MRI is a challenging task due to a lack of signal intensity standardization. MRI signal is dependent on the acquisition protocol, the coil profile, the scanner type, etc. While we can compute quantitative physical tissue properties independent of the hardware and the sequence parameters, it is still difficult to leverage these physical properties to segment and classify pelvic tissues. The proposed method integrates quantitative MRI values (T1 and T2 relaxation times and pure synthetic weighted images) and machine learning (Support Vector Machine (SVM)) to segment and classify tissues in the pelvic region, i.e.: fat, muscle, prostate, bone marrow, bladder, and air. Twenty-two men with a mean age of 30±14 years were included in this prospective study. The images were acquired with a 3 Tesla MRI scanner. An inversion recovery-prepared turbo spin echo sequence was used to obtain T1-weighted images at different inversion times with a TR of 14000 ms. A 32-echo spin echo sequence was used to obtain the T2-weighted images at different echo times with a TR of 5000 ms. T1 and T2 relaxation times, synthetic T1- and T2-weighted images and anatomical probabilistic maps were calculated and used as input features of a SVM for segmenting and classifying tissues within the pelvic region. The mean SVM classification accuracy across subjects was calculated for the different tissues: prostate (94.2%), fat (96.9%), muscle (95.8%), bone marrow (91%) and bladder (82.1%) indicating an excellent classification performance. However, the segmentation and classification for air (within the rectum) may not always be successful (mean SVM accuracy 47.5%) due to the lack of air data in the training and testing sets. Our findings suggest that SVM can reliably segment and classify tissues in the pelvic region.
Collapse
Affiliation(s)
| | | | | | - Paul Michael Walker
- Le2i, Université Bourgogne Franche-Comte, Dijon, France
- Centre Hospitalier Universitaire, Dijon, France
| | - François Brunotte
- Le2i, Université Bourgogne Franche-Comte, Dijon, France
- Centre Hospitalier Universitaire, Dijon, France
| | - Alain Lalande
- Le2i, Université Bourgogne Franche-Comte, Dijon, France
- Centre Hospitalier Universitaire, Dijon, France
- * E-mail:
| |
Collapse
|