1
|
Marcisz A, Polanska J. Can T1-Weighted Magnetic Resonance Imaging Significantly Improve Mini-Mental State Examination-Based Distinguishing Between Mild Cognitive Impairment and Early-Stage Alzheimer's Disease? J Alzheimers Dis 2023; 92:941-957. [PMID: 36806505 PMCID: PMC10116132 DOI: 10.3233/jad-220806] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 01/23/2023] [Indexed: 02/19/2023]
Abstract
BACKGROUND Detecting early-stage Alzheimer's disease (AD) is still problematic in clinical practice. This work aimed to find T1-weighted MRI-based markers for AD and mild cognitive impairment (MCI) to improve the screening process. OBJECTIVE Our assumption was to build a screening model that would be accessible and easy to use for physicians in their daily clinical routine. METHODS The multinomial logistic regression was used to detect status: AD, MCI, and normal control (NC) combined with the Bayesian information criterion for model selection. Several T1-weighted MRI-based radiomic features were considered explanatory variables in the prediction model. RESULTS The best radiomic predictor was the relative brain volume. The proposed method confirmed its quality by achieving a balanced accuracy of 95.18%, AUC of 93.25%, NPV of 97.93%, and PPV of 90.48% for classifying AD versus NC for the European DTI Study on Dementia (EDSD). The comparison of the two models: with the MMSE score only as an independent variable and corrected for the relative brain value and age, shows that the addition of the T1-weighted MRI-based biomarker improves the quality of MCI detection (AUC: 67.04% versus 71.08%) while maintaining quality for AD (AUC: 93.35% versus 93.25%). Additionally, among MCI patients predicted as AD inconsistently with the original diagnosis, 60% from ADNI and 76.47% from EDSD were re-diagnosed as AD within a 48-month follow-up. It shows that our model can detect AD patients a few years earlier than a standard medical diagnosis. CONCLUSION The created method is non-invasive, inexpensive, clinically accessible, and efficiently supports AD/MCI screening.
Collapse
Affiliation(s)
- Anna Marcisz
- Department of Data Science and Engineering, The Silesian University of Technology, Gliwice, Poland
| | | | - Joanna Polanska
- Department of Data Science and Engineering, The Silesian University of Technology, Gliwice, Poland
| |
Collapse
|
2
|
Suwalska A, Wang Y, Yuan Z, Jiang Y, Zhu D, Chen J, Cui M, Chen X, Suo C, Polanska J. CMB-HUNT: Automatic detection of cerebral microbleeds using a deep neural network. Comput Biol Med 2022; 151:106233. [PMID: 36370581 DOI: 10.1016/j.compbiomed.2022.106233] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2022] [Revised: 10/03/2022] [Accepted: 10/22/2022] [Indexed: 12/27/2022]
Abstract
Cerebral microbleeds (CMBs) are gaining increasing interest due to their importance in diagnosing cerebral small vessel diseases. However, manual inspection of CMBs is time-consuming and prone to human error. Existing automated or semi-automated solutions still have insufficient detection sensitivity and specificity. Furthermore, they frequently use more than one magnetic resonance imaging modality, but these are not always available. The majority of AI-based solutions use either numeric or image data, which may not provide sufficient information about the true nature of CMBs. This paper proposes a deep neural network with multi-type input data for automated CMB detection (CMB-HUNT) using only susceptibility-weighted imaging data (SWI). Combination of SWIs and radiomic-type numerical features allowed us to identify CMBs with high accuracy without the need for additional imaging modalities or complex predictive models. Two independent datasets were used: one with 304 patients (39 with CMBs) for training and internal system validation and one with 61 patients (21 with CMBs) for external validation. For the hold-out testing dataset, CMB-HUNT reached a sensitivity of 90.0%. As results of testing showed, CMB-HUNT outperforms existing methods in terms of the number of FPs per case, which is the lowest reported thus far (0.54 FPs/patient). The proposed system was successfully applied to the independent validation set, reaching a sensitivity of 91.5% with 1.9 false positives per patient and proving its generalization potential. The results were comparable to previous studies. Our research confirms the usefulness of deep learning solutions for CMB detection based only on one MRI modality.
Collapse
Affiliation(s)
- Aleksandra Suwalska
- Department of Data Science and Engineering, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland.
| | - Yingzhe Wang
- State Key Laboratory of Genetic Engineering, Human Phenome Institute, School of Life Sciences, Fudan University, Songhu Road, 2005, Shanghai, China; Taizhou Institute of Health Sciences, Fudan University, Yaocheng Road 799, Taizhou, Jiangsu, China
| | - Ziyu Yuan
- Taizhou Institute of Health Sciences, Fudan University, Yaocheng Road 799, Taizhou, Jiangsu, China
| | - Yanfeng Jiang
- State Key Laboratory of Genetic Engineering, Human Phenome Institute, School of Life Sciences, Fudan University, Songhu Road, 2005, Shanghai, China; Taizhou Institute of Health Sciences, Fudan University, Yaocheng Road 799, Taizhou, Jiangsu, China
| | - Dongliang Zhu
- Department of Epidemiology & Ministry of Education Key Laboratory of Public Health Safety, School of Public Health, Fudan University, Dongan Road 130, Shanghai, China
| | - Jinhua Chen
- Taizhou People's Hospital, Taihu Road 366, Taizhou, Jiangsu, China
| | - Mei Cui
- Department of Neurology, Huashan Hospital, Fudan University, Middle Wulumuqi Road 12, Shanghai, China
| | - Xingdong Chen
- State Key Laboratory of Genetic Engineering, Human Phenome Institute, School of Life Sciences, Fudan University, Songhu Road, 2005, Shanghai, China; Taizhou Institute of Health Sciences, Fudan University, Yaocheng Road 799, Taizhou, Jiangsu, China.
| | - Chen Suo
- Taizhou Institute of Health Sciences, Fudan University, Yaocheng Road 799, Taizhou, Jiangsu, China; Department of Epidemiology & Ministry of Education Key Laboratory of Public Health Safety, School of Public Health, Fudan University, Dongan Road 130, Shanghai, China.
| | - Joanna Polanska
- Department of Data Science and Engineering, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland
| |
Collapse
|
3
|
ASMCNN: An efficient brain extraction using active shape model and convolutional neural networks. Inf Sci (N Y) 2022. [DOI: 10.1016/j.ins.2022.01.011] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/18/2023]
|
4
|
van Hespen KM, Zwanenburg JJM, Dankbaar JW, Geerlings MI, Hendrikse J, Kuijf HJ. An anomaly detection approach to identify chronic brain infarcts on MRI. Sci Rep 2021; 11:7714. [PMID: 33833297 PMCID: PMC8032662 DOI: 10.1038/s41598-021-87013-4] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2020] [Accepted: 03/23/2021] [Indexed: 02/05/2023] Open
Abstract
The performance of current machine learning methods to detect heterogeneous pathology is limited by the quantity and quality of pathology in medical images. A possible solution is anomaly detection; an approach that can detect all abnormalities by learning how 'normal' tissue looks like. In this work, we propose an anomaly detection method using a neural network architecture for the detection of chronic brain infarcts on brain MR images. The neural network was trained to learn the visual appearance of normal appearing brains of 697 patients. We evaluated its performance on the detection of chronic brain infarcts in 225 patients, which were previously labeled. Our proposed method detected 374 chronic brain infarcts (68% of the total amount of brain infarcts) which represented 97.5% of the total infarct volume. Additionally, 26 new brain infarcts were identified that were originally missed by the radiologist during radiological reading. Our proposed method also detected white matter hyperintensities, anomalous calcifications, and imaging artefacts. This work shows that anomaly detection is a powerful approach for the detection of multiple brain abnormalities, and can potentially be used to improve the radiological workflow efficiency by guiding radiologists to brain anomalies which otherwise remain unnoticed.
Collapse
Affiliation(s)
- Kees M van Hespen
- Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan 100, Postbox 85500, 3584 CX, Utrecht, The Netherlands.
| | - Jaco J M Zwanenburg
- Department of Radiology, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| | - Jan W Dankbaar
- Department of Radiology, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| | - Mirjam I Geerlings
- Julius Center for Health Sciences and Primary Care, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| | - Jeroen Hendrikse
- Department of Radiology, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| | - Hugo J Kuijf
- Image Sciences Institute, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| |
Collapse
|
5
|
Suo C, Chen H, Binczyk F, Zhao R, Fan J, Yang X, Yuan Z, Kreil D, Łabaj P, Zhang T, Lu M, Jin L, Polańska J, Chen X, Ye W. Tumor infiltrating lymphocyte signature is associated with single nucleotide polymorphisms and predicts survival in esophageal squamous cell carcinoma patients. Aging (Albany NY) 2021; 13:10369-10386. [PMID: 33819921 PMCID: PMC8064198 DOI: 10.18632/aging.202798] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2020] [Accepted: 02/08/2021] [Indexed: 12/09/2022]
Abstract
Purpose: Esophageal cancer is the sixth leading cause of cancer-related death worldwide, and is associated with a poor prognosis. Stromal tumor infiltrating lymphocytes (sTIL) and certain single nucleotide polymorphisms (SNPs) have been found to be predictive of patient survival. In this study, we explored the association between SNPs and sTIL regarding the predictability of disease-free survival in patients with esophageal squamous cell carcinoma (ESCC). Materials and methods: We collected 969 pathologically confirmed ESCC patients from 2010 to 2013 and genotyped 101 SNPs from 59 genes. The number of sTIL for each patient was determined using an automatic algorithm. A Kruskal-Wallis test was used to determine the association between genotype and sTIL. The genotypes and clinical factors related to survival were analyzed using a Kaplan-Meier curve, Cox proportional hazards model, and log-rank test. Results: The median age of the patients was 67 (42-85 years), there was a median follow-up of 851.5 days and 586 patients died. The univariable analysis showed that 10 of the 101 SNPs were associated with sTIL. Six SNPs were also associated with disease-free survival. A multivariable analysis revealed that sTIL, rs1801131, rs25487, and rs8030672 were independent prognostic markers for ESCC patients. The model combining SNPs, clinical characteristics and sTIL outperformed the model with clinical characteristics alone for predicting outcomes in ESCC patients. Conclusion: We discovered 10 SNPs associated with sTIL in ESCC and we built a model of sTIL, SNPs and clinical characteristics with improved prediction of survival in ESCC patients.
Collapse
Affiliation(s)
- Chen Suo
- Department of Epidemiology and Ministry of Education Key Laboratory of Public Health Safety, School of Public Health, Fudan University, Shanghai, China.,Fudan University Taizhou Institute of Health Sciences, Taizhou, China
| | - Huiyao Chen
- Department of Epidemiology and Ministry of Education Key Laboratory of Public Health Safety, School of Public Health, Fudan University, Shanghai, China.,Center for Molecular Medicine of Children's Hospital of Fudan University, Institutes of Biomedical Sciences, Fudan University, Shanghai, China
| | - Franciszek Binczyk
- Silesian University of Technology, Data Mining Division, Gliwice, Poland
| | - Renjia Zhao
- Department of Epidemiology and Ministry of Education Key Laboratory of Public Health Safety, School of Public Health, Fudan University, Shanghai, China
| | - Jiahui Fan
- State Key Laboratory of Genetic Engineering and Collaborative Innovation Center for Genetics and Development, School of Life Sciences, Fudan University, Shanghai, China
| | - Xiaorong Yang
- Clinical Epidemiology Unit, Qilu Hospital of Shandong University, Jinan, China
| | - Ziyu Yuan
- Fudan University Taizhou Institute of Health Sciences, Taizhou, China
| | - David Kreil
- IMBT Bioinformatics Research, Boku University Vienn, Vienna, Austria
| | - Paweł Łabaj
- Malopolska Centre of Biotechnology, Jagiellonian University, Krakow, Poland
| | - Tiejun Zhang
- Department of Epidemiology and Ministry of Education Key Laboratory of Public Health Safety, School of Public Health, Fudan University, Shanghai, China.,Fudan University Taizhou Institute of Health Sciences, Taizhou, China
| | - Ming Lu
- Clinical Epidemiology Unit, Qilu Hospital of Shandong University, Jinan, China
| | - Li Jin
- Fudan University Taizhou Institute of Health Sciences, Taizhou, China.,Human Phenome Institute, Fudan University, Shanghai, China
| | - Joanna Polańska
- Silesian University of Technology, Data Mining Division, Gliwice, Poland
| | - Xingdong Chen
- Fudan University Taizhou Institute of Health Sciences, Taizhou, China.,Human Phenome Institute, Fudan University, Shanghai, China
| | - Weimin Ye
- Department of Medical Epidemiology and Biostatistics, Karolinska Institute, Stockholm, Sweden
| |
Collapse
|
6
|
Gryska E, Schneiderman J, Björkman-Burtscher I, Heckemann RA. Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review. BMJ Open 2021; 11:e042660. [PMID: 33514580 PMCID: PMC7849889 DOI: 10.1136/bmjopen-2020-042660] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/11/2020] [Revised: 01/09/2021] [Accepted: 01/12/2021] [Indexed: 12/11/2022] Open
Abstract
OBJECTIVES Medical image analysis practices face challenges that can potentially be addressed with algorithm-based segmentation tools. In this study, we map the field of automatic MR brain lesion segmentation to understand the clinical applicability of prevalent methods and study designs, as well as challenges and limitations in the field. DESIGN Scoping review. SETTING Three databases (PubMed, IEEE Xplore and Scopus) were searched with tailored queries. Studies were included based on predefined criteria. Emerging themes during consecutive title, abstract, methods and whole-text screening were identified. The full-text analysis focused on materials, preprocessing, performance evaluation and comparison. RESULTS Out of 2990 unique articles identified through the search, 441 articles met the eligibility criteria, with an estimated growth rate of 10% per year. We present a general overview and trends in the field with regard to publication sources, segmentation principles used and types of lesions. Algorithms are predominantly evaluated by measuring the agreement of segmentation results with a trusted reference. Few articles describe measures of clinical validity. CONCLUSIONS The observed reporting practices leave room for improvement with a view to studying replication, method comparison and clinical applicability. To promote this improvement, we propose a list of recommendations for future studies in the field.
Collapse
Affiliation(s)
- Emilia Gryska
- Medical Radiation Sciences, Goteborgs universitet Institutionen for kliniska vetenskaper, Goteborg, Sweden
| | - Justin Schneiderman
- Sektionen för klinisk neurovetenskap, Goteborgs Universitet Institutionen for Neurovetenskap och fysiologi, Goteborg, Sweden
| | | | - Rolf A Heckemann
- Medical Radiation Sciences, Goteborgs universitet Institutionen for kliniska vetenskaper, Goteborg, Sweden
| |
Collapse
|
7
|
Narayanan A, Rajasekaran MP, Zhang Y, Govindaraj V, Thiyagarajan A. Multi-channeled MR brain image segmentation: A novel double optimization approach combined with clustering technique for tumor identification and tissue segmentation. Biocybern Biomed Eng 2019. [DOI: 10.1016/j.bbe.2018.12.003] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
|
8
|
Increased white matter metabolic rates in autism spectrum disorder and schizophrenia. Brain Imaging Behav 2019; 12:1290-1305. [PMID: 29168086 DOI: 10.1007/s11682-017-9785-9] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Abstract
Both autism spectrum disorder (ASD) and schizophrenia are often characterized as disorders of white matter integrity. Multimodal investigations have reported elevated metabolic rates, cerebral perfusion and basal activity in various white matter regions in schizophrenia, but none of these functions has previously been studied in ASD. We used 18fluorodeoxyglucose positron emission tomography to compare white matter metabolic rates in subjects with ASD (n = 25) to those with schizophrenia (n = 41) and healthy controls (n = 55) across a wide range of stereotaxically placed regions-of-interest. Both subjects with ASD and schizophrenia showed increased metabolic rates across the white matter regions assessed, including internal capsule, corpus callosum, and white matter in the frontal and temporal lobes. These increases were more pronounced, more widespread and more asymmetrical in subjects with ASD than in those with schizophrenia. The highest metabolic increases in both disorders were seen in the prefrontal white matter and anterior limb of the internal capsule. Compared to normal controls, differences in gray matter metabolism were less prominent and differences in adjacent white matter metabolism were more prominent in subjects with ASD than in those with schizophrenia. Autism spectrum disorder and schizophrenia are associated with heightened metabolic activity throughout the white matter. Unlike in the gray matter, the vector of white matter metabolic abnormalities appears to be similar in ASD and schizophrenia, may reflect inefficient functional connectivity with compensatory hypermetabolism, and may be a common feature of neurodevelopmental disorders.
Collapse
|
9
|
Banerjee S, Mitra S, Uma Shankar B. Automated 3D segmentation of brain tumor using visual saliency. Inf Sci (N Y) 2018. [DOI: 10.1016/j.ins.2017.10.011] [Citation(s) in RCA: 25] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/22/2023]
|