1
|
Srikrishna M, Heckemann RA, Pereira JB, Volpe G, Zettergren A, Kern S, Westman E, Skoog I, Schöll M. Comparison of Two-Dimensional- and Three-Dimensional-Based U-Net Architectures for Brain Tissue Classification in One-Dimensional Brain CT. Front Comput Neurosci 2022; 15:785244. [PMID: 35082608 PMCID: PMC8784554 DOI: 10.3389/fncom.2021.785244] [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] [Received: 09/28/2021] [Accepted: 12/02/2021] [Indexed: 11/13/2022] Open
Abstract
Brain tissue segmentation plays a crucial role in feature extraction, volumetric quantification, and morphometric analysis of brain scans. For the assessment of brain structure and integrity, CT is a non-invasive, cheaper, faster, and more widely available modality than MRI. However, the clinical application of CT is mostly limited to the visual assessment of brain integrity and exclusion of copathologies. We have previously developed two-dimensional (2D) deep learning-based segmentation networks that successfully classified brain tissue in head CT. Recently, deep learning-based MRI segmentation models successfully use patch-based three-dimensional (3D) segmentation networks. In this study, we aimed to develop patch-based 3D segmentation networks for CT brain tissue classification. Furthermore, we aimed to compare the performance of 2D- and 3D-based segmentation networks to perform brain tissue classification in anisotropic CT scans. For this purpose, we developed 2D and 3D U-Net-based deep learning models that were trained and validated on MR-derived segmentations from scans of 744 participants of the Gothenburg H70 Cohort with both CT and T1-weighted MRI scans acquired timely close to each other. Segmentation performance of both 2D and 3D models was evaluated on 234 unseen datasets using measures of distance, spatial similarity, and tissue volume. Single-task slice-wise processed 2D U-Nets performed better than multitask patch-based 3D U-Nets in CT brain tissue classification. These findings provide support to the use of 2D U-Nets to segment brain tissue in one-dimensional (1D) CT. This could increase the application of CT to detect brain abnormalities in clinical settings.
Collapse
Affiliation(s)
- Meera Srikrishna
- Wallenberg Centre for Molecular and Translational Medicine, University of Gothenburg, Gothenburg, Sweden
- Department of Psychiatry and Neurochemistry, Institute of Physiology and Neuroscience, University of Gothenburg, Gothenburg, Sweden
| | - Rolf A. Heckemann
- Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, Gothenburg, Sweden
| | - Joana B. Pereira
- Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
- Memory Research Unit, Department of Clinical Sciences, Malmö Lund University, Mälmo, Sweden
| | - Giovanni Volpe
- Department of Physics, University of Gothenburg, Gothenburg, Sweden
| | - Anna Zettergren
- Neuropsychiatric Epidemiology, Institute of Neuroscience and Physiology, Sahlgrenska Academy, Centre for Ageing and Health (AgeCap), University of Gothenburg, Gothenburg, Sweden
| | - Silke Kern
- Neuropsychiatric Epidemiology, Institute of Neuroscience and Physiology, Sahlgrenska Academy, Centre for Ageing and Health (AgeCap), University of Gothenburg, Gothenburg, Sweden
- Region Västra Götaland, Sahlgrenska University Hospital, Psychiatry, Cognition and Old Age Psychiatry Clinic, Gothenburg, Sweden
| | - Eric Westman
- Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
| | - Ingmar Skoog
- Neuropsychiatric Epidemiology, Institute of Neuroscience and Physiology, Sahlgrenska Academy, Centre for Ageing and Health (AgeCap), University of Gothenburg, Gothenburg, Sweden
- Region Västra Götaland, Sahlgrenska University Hospital, Psychiatry, Cognition and Old Age Psychiatry Clinic, Gothenburg, Sweden
| | - Michael Schöll
- Wallenberg Centre for Molecular and Translational Medicine, University of Gothenburg, Gothenburg, Sweden
- Department of Psychiatry and Neurochemistry, Institute of Physiology and Neuroscience, University of Gothenburg, Gothenburg, Sweden
- Dementia Research Centre, Institute of Neurology, University College London, London, United Kingdom
- Department of Clinical Physiology, Sahlgrenska University Hospital, Gothenburg, Sweden
- *Correspondence: Michael Schöll
| |
Collapse
|
2
|
Srikrishna M, Pereira JB, Heckemann RA, Volpe G, van Westen D, Zettergren A, Kern S, Wahlund LO, Westman E, Skoog I, Schöll M. Deep learning from MRI-derived labels enables automatic brain tissue classification on human brain CT. Neuroimage 2021; 244:118606. [PMID: 34571160 DOI: 10.1016/j.neuroimage.2021.118606] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2021] [Revised: 09/15/2021] [Accepted: 09/20/2021] [Indexed: 11/25/2022] Open
Abstract
Automatic methods for feature extraction, volumetry, and morphometric analysis in clinical neuroscience typically operate on images obtained with magnetic resonance (MR) imaging equipment. Although CT scans are less expensive to acquire and more widely available than MR scans, their application is currently limited to the visual assessment of brain integrity and the exclusion of co-pathologies. CT has rarely been used for tissue classification because the contrast between grey matter and white matter was considered insufficient. In this study, we propose an automatic method for segmenting grey matter (GM), white matter (WM), cerebrospinal fluid (CSF), and intracranial volume (ICV) from head CT images. A U-Net deep learning model was trained and validated on CT images with MRI-derived segmentation labels. We used data from 744 participants of the Gothenburg H70 Birth Cohort Studies for whom CT and T1-weighted MR images had been acquired on the same day. Our proposed model predicted brain tissue classes accurately from unseen CT images (Dice coefficients of 0.79, 0.82, 0.75, 0.93 and 0.98 for GM, WM, CSF, brain volume and ICV, respectively). To contextualize these results, we generated benchmarks based on established MR-based methods and intentional image degradation. Our findings demonstrate that CT-derived segmentations can be used to delineate and quantify brain tissues, opening new possibilities for the use of CT in clinical practice and research.
Collapse
Affiliation(s)
- Meera Srikrishna
- Wallenberg Centre for Molecular and Translational Medicine, University of Gothenburg, Gothenburg, Sweden; Department of Psychiatry and Neurochemistry, Institute of Physiology and Neuroscience, University of Gothenburg, Gothenburg, Sweden
| | - Joana B Pereira
- Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden; Clinical Memory Research Unit, Department of Clinical Sciences, Lund University, Malmo, Sweden
| | - Rolf A Heckemann
- Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, Gothenburg, Sweden
| | - Giovanni Volpe
- Department of Physics, University of Gothenburg, Gothenburg, Sweden
| | - Danielle van Westen
- Department of Clinical Sciences, Diagnostic Radiology, Lund University Sweden; Department of Imaging and Function, Skånes University Hospital, Lund, Sweden
| | - Anna Zettergren
- Neuropsychiatric Epidemiology, Institute of Neuroscience and Physiology, Sahlgrenska Academy, Centre for Ageing and Health (AgeCap), University of Gothenburg, Gothenburg, Sweden
| | - Silke Kern
- Department of Psychiatry and Neurochemistry, Institute of Neuroscience and Physiology, Sahlgrenska Academy, University of Gothenburg, Mölndal, Sweden
| | - Lars-Olof Wahlund
- Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
| | - Eric Westman
- Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
| | - Ingmar Skoog
- Neuropsychiatric Epidemiology, Institute of Neuroscience and Physiology, Sahlgrenska Academy, Centre for Ageing and Health (AgeCap), University of Gothenburg, Gothenburg, Sweden
| | - Michael Schöll
- Wallenberg Centre for Molecular and Translational Medicine, University of Gothenburg, Gothenburg, Sweden; Department of Psychiatry and Neurochemistry, Institute of Physiology and Neuroscience, University of Gothenburg, Gothenburg, Sweden; Dementia Research Centre, Institute of Neurology, University College London, London, UK; Department of Clinical Physiology, Sahlgrenska University Hospital, Gothenburg, Sweden.
| |
Collapse
|
3
|
Park HY, Park CR, Suh CH, Shim WH, Kim SJ. Diagnostic performance of the medial temporal lobe atrophy scale in patients with Alzheimer's disease: a systematic review and meta-analysis. Eur Radiol 2021; 31:9060-9072. [PMID: 34510246 DOI: 10.1007/s00330-021-08227-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2021] [Revised: 07/02/2021] [Accepted: 07/22/2021] [Indexed: 12/28/2022]
Abstract
OBJECTIVE To evaluate the diagnostic performance and reliability of the medial temporal lobe atrophy (MTA) scale in patients with Alzheimer's disease. METHODS A systematic literature search of MEDLINE and EMBASE databases was performed to select studies that evaluated the diagnostic performance or reliability of MTA scale, published up to January 21, 2021. Pooled estimates of sensitivity and specificity were calculated using a bivariate random-effects model. Pooled correlation coefficients for intra- and interobserver agreements were calculated using the random-effects model based on Fisher's Z transformation of correlations. Meta-regression was performed to explain the study heterogeneity. Subgroup analysis was performed to compare the diagnostic performance of the MTA scale and hippocampal volumetry. RESULTS Twenty-one original articles were included. The pooled sensitivity and specificity of the MTA scale in differentiating Alzheimer's disease from healthy control were 74% (95% CI, 68-79%) and 88% (95% CI, 83-91%), respectively. The area under the curve of the MTA scale was 0.88 (95% CI, 0.84-0.90). Meta-regression demonstrated that the difference in the method of rating the MTA scale was significantly associated with study heterogeneity (p = 0.04). No significant difference was observed in five studies regarding the diagnostic performance between MTA scale and hippocampal volumetry (p = 0.40). The pooled correlation coefficients for intra- and interobserver agreements were 0.85 (95% CI, 0.69-0.93) and 0.83 (95% CI, 0.66-0.92), respectively. CONCLUSIONS Our meta-analysis demonstrated a good diagnostic performance and reliability of the MTA scale in Alzheimer's disease. KEY POINTS • The pooled sensitivity and specificity of the MTA scale in differentiating Alzheimer's disease from healthy control were 74% and 88%, respectively. • There was no significant difference in the diagnostic performance between MTA scale and hippocampal volumetry. • The reliability of MTA scale was excellent based on the pooled correlation coefficient for intra- and interobserver agreements.
Collapse
Affiliation(s)
- Ho Young Park
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Chae Ri Park
- Department of Medical Science, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Chong Hyun Suh
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
| | - Woo Hyun Shim
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Sang Joon Kim
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| |
Collapse
|
4
|
Håkansson C, Tamaddon A, Andersson H, Torisson G, Mårtensson G, Truong M, Annertz M, Londos E, Björkman-Burtscher IM, Hansson O, van Westen D. Inter-modality assessment of medial temporal lobe atrophy in a non-demented population: application of a visual rating scale template across radiologists with varying clinical experience. Eur Radiol 2021; 32:1127-1134. [PMID: 34328536 PMCID: PMC8794965 DOI: 10.1007/s00330-021-08177-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2021] [Revised: 06/03/2021] [Accepted: 06/25/2021] [Indexed: 11/26/2022]
Abstract
OBJECTIVES To assess inter-modality agreement and accuracy for medial temporal lobe atrophy (MTA) ratings across radiologists with varying clinical experience in a non-demented population. METHODS Four raters (two junior radiologists and two senior neuroradiologists) rated MTA on CT and MRI scans using Scheltens' MTA scale. Ratings were compared to a consensus rating by two experienced neuroradiologists for estimation of true positive and negative rates (TPR and TNR) and over- and underestimation of MTA. Inter-modality agreement expressed as Cohen's κ (dichotomized data), Cohen's κw, and two-way mixed, single measures, consistency ICC (ordinal data) were determined. Adequate agreement was defined as κ/κw ≥ 0.80 and ICC ≥ 0.80 (significance level at 95% CI ≥ 0.65). RESULTS Forty-nine subjects (median age 72 years, 27% abnormal MTA) with cognitive impairment were included. Only junior radiologists achieved adequate agreement expressed as Cohen's κ. All raters achieved adequate agreement expressed as Cohen's κw and ICC. True positive rates varied from 69 to 100% and TNR varied from 85 to 100%. No under- or overestimation of MTA was observed. Ratings did not differ between radiologists. CONCLUSION We conclude that radiologists with varying experience achieve adequate inter-modality agreement and similar accuracy when Scheltens' MTA scale is used to rate MTA on a non-demented population. However, TPR varied between radiologists which could be attributed to rating style differences. KEY POINTS • Radiologists with varying experience achieve adequate inter-modality agreement with similar accuracy when Scheltens' MTA scale is used to rate MTA on a non-demented population. • Differences in rating styles might affect accuracy, this was most evident for senior neuroradiologists, and only junior radiologists achieved adequate agreement on dichotomized (abnormal/normal) ratings. • The use of an MTA scale template might compensate for varying clinical experience which could make it applicable for clinical use.
Collapse
Affiliation(s)
- Claes Håkansson
- Department of Imaging and Function, Skåne University Hospital, Lund, Sweden.
- Department of Clinical Sciences, Diagnostic Radiology, Lund University, Lund, Sweden.
| | - Ashkan Tamaddon
- Department of Imaging and Function, Skåne University Hospital, Lund, Sweden
| | - Henrik Andersson
- Department of Imaging and Function, Skåne University Hospital, Lund, Sweden
| | - Gustav Torisson
- Department of Translational Medicine, Clinical Infection Medicine, Lund University, Malmö, Sweden
- Department of Clinical Sciences Malmö, Clinical Memory Research Unit, Lund University, Malmö, Sweden
| | - Gustav Mårtensson
- Department of Neurobiology, Care Sciences and Society, Karolinska Institute, Stockholm, Sweden
| | - My Truong
- Department of Imaging and Function, Skåne University Hospital, Lund, Sweden
- Department of Clinical Sciences, Diagnostic Radiology, Lund University, Lund, Sweden
| | - Mårten Annertz
- Department of Imaging and Function, Skåne University Hospital, Lund, Sweden
| | - Elisabet Londos
- Department of Clinical Sciences Malmö, Clinical Memory Research Unit, Lund University, Malmö, Sweden
- Memory Clinic, Skåne University Hospital, Malmö, Sweden
| | | | - Oskar Hansson
- Department of Clinical Sciences Malmö, Clinical Memory Research Unit, Lund University, Malmö, Sweden
- Memory Clinic, Skåne University Hospital, Malmö, Sweden
| | - Danielle van Westen
- Department of Imaging and Function, Skåne University Hospital, Lund, Sweden
- Department of Clinical Sciences, Diagnostic Radiology, Lund University, Lund, Sweden
| |
Collapse
|
5
|
Akiba C, Gyanwali B, Villaraza S, Nakajima M, Miyajima M, Cheng CY, Wong TY, Venketasubramanian N, Hilal S, Chen C. The prevalence and clinical associations of disproportionately enlarged subarachnoid space hydrocephalus (DESH), an imaging feature of idiopathic normal pressure hydrocephalus in community and memory clinic based Singaporean cohorts. J Neurol Sci 2019; 408:116510. [PMID: 31810041 DOI: 10.1016/j.jns.2019.116510] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2019] [Revised: 09/03/2019] [Accepted: 09/27/2019] [Indexed: 12/30/2022]
Abstract
INTRODUCTION Disproportionately Enlarged Subarachnoid space Hydrocephalus (DESH) is considered as an important imaging feature of idiopathic normal pressure hydrocephalus (iNPH). METHOD Subjects aged 60 and over in a memory clinic and a community-based cohort were assessed for the presence of ventriculomegaly, Sylvian dilatation, and high convexity tightness by neuroimaging, and a clinical triad of iNPH symptoms, i.e. cognitive, gait and urinary symptoms. RESULTS In the memory clinic-based study (548 subjects), the prevalence of DESH was 1.1% and increased with age. The clinical triad was significantly more frequent in subjects with DESH (50%) compared to those with normal images (none), Sylvian dilatation (7%), and ventriculomegaly (12%). Gait disturbance was also significantly more frequent in DESH (83%) compared to those with normal images (2%), Sylvian dilatation (14%), and ventriculomegaly (26%). In the community-based cohort (946 subjects), the prevalence of DESH was 1.0% and increased with age. The clinical triad (11%) was significantly more common in subjects with DESH compared to those with normal images (none), Sylvian dilatation (2%), and ventriculomegaly (7%). Gait disturbance was also significantly more common in DESH (33%) compared to those with normal images (1%), Sylvian dilatation (4%), and ventriculomegaly (10%). CONCLUSION The reported prevalence of DESH was approximately 1%, and increased with age. DESH and high convexity tightness were specifically associated with the clinical triad of iNPH. Of the triad, gait disturbance was associated to DESH and high convexity tightness.
Collapse
Affiliation(s)
- Chihiro Akiba
- Memory Ageing and Cognition Centre, National University Health System, Singapore; Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore; Department of Neurosurgery, Juntendo University, Japan.
| | - Bibek Gyanwali
- Memory Ageing and Cognition Centre, National University Health System, Singapore; Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
| | - Steven Villaraza
- Memory Ageing and Cognition Centre, National University Health System, Singapore; Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
| | | | | | - Ching-Yu Cheng
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Academic Medicine Research Institute, Duke-NUS Graduate Medical School, Singapore.
| | - Tien Yin Wong
- Memory Ageing and Cognition Centre, National University Health System, Singapore; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Academic Medicine Research Institute, Duke-NUS Graduate Medical School, Singapore.
| | - Narayanaswamy Venketasubramanian
- Memory Ageing and Cognition Centre, National University Health System, Singapore; Raffles Neuroscience Centre, Raffles Hospital, Singapore
| | - Saima Hilal
- Memory Ageing and Cognition Centre, National University Health System, Singapore; Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
| | - Christopher Chen
- Memory Ageing and Cognition Centre, National University Health System, Singapore; Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| |
Collapse
|
6
|
Kaltoft NS, Marner L, Larsen VA, Hasselbalch SG, Law I, Henriksen OM. Hybrid FDG PET/MRI vs. FDG PET and CT in patients with suspected dementia - A comparison of diagnostic yield and propagated influence on clinical diagnosis and patient management. PLoS One 2019; 14:e0216409. [PMID: 31048902 PMCID: PMC6497285 DOI: 10.1371/journal.pone.0216409] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2018] [Accepted: 04/21/2019] [Indexed: 12/03/2022] Open
Abstract
Background Both 18F-fluoro-deoxy-glucose (FDG) positron emission tomography (PET), computed tomography (CT) and magnetic resonance imaging (MRI) are routinely used in the evaluation of memory clinic patients. Hybrid PET/MR systems now allow simultaneous PET and MRI imaging within the duration of the PET emission scan. Purpose To compare the diagnostic yield of PET/MRI using an abbreviated MR protocol with that of separate PET and CT in a mixed memory clinic population, and the propagated influences on clinical diagnosis and patient management. Material and methods Consecutive memory clinic patients (n = 78) undergoing both CT and hybrid FDG PET/MRI scans were identified retrospectively. MRI and CT were separately evaluated for vascular and structural pathology. PET scans were classified according to the presence of neurodegenerative or vascular disease using CT or MRI, respectively, for anatomical guiding. A memory clinic expert assessed the clinical impact of the additional findings and/or change of PET classification achieved by MRI anatomical guiding as compared to CT guiding. Results MRI lead to significantly higher Fazekas scores, higher medial temporal and global cortical atrophy scores, and identified more patients with infarcts (28 vs 8, p<0.001) compared to CT. MRI changed PET classification in 13 (17%) patients. Addition of MRI to CT had minor clinical impact in 4/78 (5%) and major clinical impact in 13/78 (17%) of patients. Conclusion The study demonstrates the capabilities of PET/MRI systems for routine clinical imaging of memory clinic patients, and that even an abbreviated hybrid PET/MRI protocol provides significant additional information influencing clinical diagnosis and patient management in a substantial fraction of patients when compared to separate PET and CT.
Collapse
Affiliation(s)
- Nicolai Stefan Kaltoft
- Department of Radiology, Rigshospitalet Blegdamsvej, Copenhagen University Hospital, Copenhagen, Denmark
| | - Lisbeth Marner
- Department of Clinical Physiology, Nuclear Medicine and PET, Rigshospitalet Blegdamsvej, Copenhagen University Hospital, Copenhagen, Denmark
| | - Vibeke Andree Larsen
- Department of Radiology, Rigshospitalet Blegdamsvej, Copenhagen University Hospital, Copenhagen, Denmark
| | - Steen Gregers Hasselbalch
- Danish Dementia Research Centre, Dept. of Neurology, Rigshospitalet Blegdamsvej, Copenhagen University Hospital, Copenhagen, Denmark
| | - Ian Law
- Department of Clinical Physiology, Nuclear Medicine and PET, Rigshospitalet Blegdamsvej, Copenhagen University Hospital, Copenhagen, Denmark
| | - Otto Mølby Henriksen
- Department of Clinical Physiology, Nuclear Medicine and PET, Rigshospitalet Blegdamsvej, Copenhagen University Hospital, Copenhagen, Denmark
- * E-mail:
| |
Collapse
|