1
|
Zhang R, Cai Z, Luo Y, Wang Z, Wang W. Preliminary exploration of response the course of radiotherapy for stage III non-small cell lung cancer based on longitudinal CT radiomics features. Eur J Radiol Open 2022; 9:100391. [PMID: 34977279 PMCID: PMC8688890 DOI: 10.1016/j.ejro.2021.100391] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2021] [Revised: 10/28/2021] [Accepted: 12/09/2021] [Indexed: 12/24/2022] Open
Abstract
Purpose Explore the longitudinal CT-based radiomics to demonstrate the changing trend of radiotherapy response and to determine at which point after the onset of treatment radiomics exhibit the greatest change for stage III NSCLC patients. Methods and materials Ten stage III NSCLC patients in line with inclusion criteria were enrolled retrospectively, each of whom received radiotherapy or concurrent chemo-radiotherapy and performed eight series of follow-up CT imaging. Longitudinal radiomics were extracted on region of interest from the eight registered images, then two steps were conducted to select significant features as indicators of tumor change: 1) stable features were selected by Kendall rank correlation; 2) texture feature types with a steadily changing trend were retained and intensity features with stable change trends were selected to represent the large number of them. Next, the trend and rate of tumor change were analyzed using the Delta method and Curve-fitting method. Finally, the statistics in the distribution of stable features in patients were calculated. Results 675 stable features were selected from a total number of 1371 radiomics features, then 12 texture features types were retained and three intensity features were chosen to represent their own category. Among the final selected feature types, it was found that the two time points were weeks 1 and 3 with the higher rate of change. One patient had very few stable tumor features out of a total of 101 features, and the rate of change of features of another patient was conspicuously higher than the average level with number of 301 features. Conclusion The longitudinal CT radiomics could demonstrate the change trend of tumor and at which point exhibit the greatest change during radiotherapy, and potentially be used for treatment decisions concerning adaptive radiotherapy.
Collapse
Key Words
- CBCT, Cone-beam Computed Tomography
- CT, Computed Tomography
- Computed tomography
- GLCM25/GLCM3, Gray Level Co-occurrence Matrix25/Gray Level Co-occurrence Matrix3
- GLRLM25, Gray Level Run Length Matrix25
- GTV, Gross Tumor Volume
- HU, Hounsfield Units
- IBEX, Imaging Biomarker Explorer
- LASSO, Least Absolute Shrinkage and Selection Operator
- Longitudinal radiomics features
- NID25/NID3, Neighborhood Intensity Difference25/Neighborhood Intensity Difference3
- NSCLC, Non-small cell lung carcinoma
- Non-small cell lung cancer
- PCA, Principle Component Analysis
- ROI, Region of Interest
- Radiation therapy
- VMAT, Volumetric Modulated Arc Therapy
Collapse
Affiliation(s)
- Ruiping Zhang
- Department of Radiation Oncology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Huanhu West Road, Hexi District, Tianjin 300060, China
| | - Zhengting Cai
- School of Automation (Artificial Intelligence), Hangzhou Dianzi University, Xiasha Higher Education Zone, Hangzhou, Zhejiang Province 310018, China
| | - Yan'an Luo
- Department of Physics, Nankai University, Weijin Road, Nankai District, Tianjin 300071, China
| | - Zhizhen Wang
- Department of Radiation Oncology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Huanhu West Road, Hexi District, Tianjin 300060, China
| | - Wei Wang
- Department of Radiation Oncology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Huanhu West Road, Hexi District, Tianjin 300060, China
| |
Collapse
|
2
|
Chu M, Wu P, Hong M, Zeng H, Wong CK, Feng Y, Cai Z, Lu WW. Lingzhi and San-Miao-San with hyaluronic acid gel mitigate cartilage degeneration in anterior cruciate ligament transection induced osteoarthritis. J Orthop Translat 2020; 26:132-140. [PMID: 33437632 PMCID: PMC7773973 DOI: 10.1016/j.jot.2020.07.008] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/11/2020] [Revised: 07/27/2020] [Accepted: 07/31/2020] [Indexed: 12/20/2022] Open
Abstract
Objective To investigate the mitigate efficacy of Chinese medicine Lingzhi (LZ) and San-Miao-San (SMS) combined with hyaluronic acid (HA)-gel in attenuating cartilage degeneration in traumatic osteoarthritis (OA). Methods The standardized surgery of anterior cruciate ligament transection (ACLT) was made from the medial compartment of right hind limbs of 8-week-old female SD rats and resulted in a traumatic OA. Rats (n = 5/group) were treated once intra-articular injection of 50 μl HA-gel, 50 μl HA-gel+50 μg LZ-SMS, 50 μl of saline+50 μg LZ-SMS and null (ACLT group) respectively, except sham group. Limbs were harvested for μCT scan and histopathological staining 3-month post-treatment. Inflammatory cytokines from plasma and synovial fluid were detected using Immunology Multiplex Assay kit. The putative targets of active compounds in LZ-SMS and known therapeutic targets for OA were combined to construct protein–protein interaction network. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis was adopted to predict the potential targets and signaling pathway of LZ-SMS in OA through the tool of DAVID Bioinformatics. Results In vivo, HA-gel + LZ-SMS treatment resulted in a higher volume ratio of hyaline cartilage (HC)/calcified cartilage (CC) and HC/Sum (total volume of cartilage), compared to ACLT and HA-gel groups. In addition, histological results showed the elevated cartilage matrix, chondrogenic and osteoblastic signals in HA-gel + LZ-SMS treatment. Treatment also significantly altered subchondral bone (SCB) structure including an increase in BV/TV, Tb.Th, BMD, Conn.Dn, Tb.N, and DA, as well as a significant decrease in Tb.Sp and Po(tot), which implied a protective effect on maintaining the stabilization of tibial SCB microstructure. Furthermore, there was also a down-regulated inflammatory cytokines and upregulated anti-inflammatory cytokine IL-10 in HA+LZ-SMS group. Finally, 64 shared targets from 37 active compounds in LZ-SMS related to the core genes for the development of OA. LZ-SMS has a putative role in regulating inflammatory circumstance through influencing the MAPK signaling pathway. Conclusion Our study elucidated a protective effect of HA-gel + LZ-SMS in mitigating cartilage degradation and putative interaction with targets and signaling pathway for the development of traumatic OA. The translational potential of this article Our results provide a biological rationale for the use of LZ-SMS as a potential candidate for OA treatment.
Collapse
Key Words
- 3D, Three-dimensional
- AC, Articular cartilage
- ACLT, Anterior cruciate ligament transection
- Acan, Aggrecan
- Articular cartilage
- BMD, Bone mineral density
- BV/TV, Bone volume fraction
- CC, Calcified cartilage
- Conn.Dn, Connectivity density
- DA, Degree of anisotropy
- DL, Drug-likeness
- ECM, Extracellular matrix
- FDR, False discovery rate
- GO, Gene ontology
- HA, Hyaluronic acid
- HC, Hyaline cartilage
- Hyaluronic acid gel
- KEGG, Kyoto Encyclopedia of Genes and Genomes
- LZ-SMS, Lingzhi-San-Miao-San
- Lingzhi and San-Miao-San
- MZ, Middle zone area of articular cartilage
- NC, Negative control
- OA, Osteoarthritis
- OB, Oral bioavailability
- OMIM, Online Mendelian Inheritance in Man
- Osteoarthritis
- PPI, Protein–protein interaction
- Po(tot), Total porosity
- ROI, Region of Interest
- SC, Superficial cartilage
- SCB, Subchondral bone
- SZ, Superficial zone of articular cartilage
- Subchondral trabecular bone
- Sum, Whole cartilage
- TCM, Traditional Chinese medicine
- TCMSP, Traditional Chinese Medicine Systems Pharmacology Database
- Tb.N, Trabecular number
- Tb.Pf, Trabecular bone pattern factor
- Tb.Sp, Trabecular separation
- Tb.Th, Trabecular thickness
Collapse
Affiliation(s)
- Man Chu
- Faulty of Medical Technology, Shaanxi University of Chinese Medicine, Xianyang, China
| | - Ping Wu
- Department of Allergy, Immunology and Rheumatology, Guangzhou Women and Children's Medical Center, Guangzhou, Guangdong, China
| | - Ming Hong
- Science and Technology Innovation Center, Guangzhou University of Chinese Medicine, Guangzhou, China.,Institute of Clinical Pharmacology, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Huasong Zeng
- Department of Allergy, Immunology and Rheumatology, Guangzhou Women and Children's Medical Center, Guangzhou, Guangdong, China
| | - Chun Kwok Wong
- Department of Chemical Pathology, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong, China
| | - Yu Feng
- Department of Traumatology, General Hospital of Ningxia Medical University, Yinchuan, Ningxia Hui Autonomous Region, China
| | - Zhe Cai
- Department of Allergy, Immunology and Rheumatology, Guangzhou Women and Children's Medical Center, Guangzhou, Guangdong, China.,Department of Chemical Pathology, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong, China.,The Joint Center for Infection and Immunity, Guangzhou Institute of Pediatrics, Guangzhou Women and Children's Medical Center, Guangzhou, China.,The Joint Center for Infection and Immunity, Institute Pasteur of Shanghai, Chinese Academy of Science, Shanghai, China
| | - William Weijia Lu
- Department of Orthopaedics and Traumatology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong.,Shenzhen Institutes of Advanced Technology, Chinese Academy of Science, Shenzhen, China
| |
Collapse
|
3
|
Stark AJ, Smith CT, Petersen KJ, Trujillo P, van Wouwe NC, Donahue MJ, Kessler RM, Deutch AY, Zald DH, Claassen DO. [ 18F]fallypride characterization of striatal and extrastriatal D 2/3 receptors in Parkinson's disease. Neuroimage Clin 2018; 18:433-442. [PMID: 29541577 PMCID: PMC5849871 DOI: 10.1016/j.nicl.2018.02.010] [Citation(s) in RCA: 20] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2017] [Revised: 01/15/2018] [Accepted: 02/07/2018] [Indexed: 12/11/2022]
Abstract
Parkinson's disease (PD) is characterized by widespread degeneration of monoaminergic (especially dopaminergic) networks, manifesting with a number of both motor and non-motor symptoms. Regional alterations to dopamine D2/3 receptors in PD patients are documented in striatal and some extrastriatal areas, and medications that target D2/3 receptors can improve motor and non-motor symptoms. However, data regarding the combined pattern of D2/3 receptor binding in both striatal and extrastriatal regions in PD are limited. We studied 35 PD patients off-medication and 31 age- and sex-matched healthy controls (HCs) using PET imaging with [18F]fallypride, a high affinity D2/3 receptor ligand, to measure striatal and extrastriatal D2/3 nondisplaceable binding potential (BPND). PD patients completed PET imaging in the off medication state, and motor severity was concurrently assessed. Voxel-wise evaluation between groups revealed significant BPND reductions in PD patients in striatal and several extrastriatal regions, including the locus coeruleus and mesotemporal cortex. A region-of-interest (ROI) based approach quantified differences in dopamine D2/3 receptors, where reduced BPND was noted in the globus pallidus, caudate, amygdala, hippocampus, ventral midbrain, and thalamus of PD patients relative to HC subjects. Motor severity positively correlated with D2/3 receptor density in the putamen and globus pallidus. These findings support the hypothesis that abnormal D2/3 expression occurs in regions related to both the motor and non-motor symptoms of PD, including areas richly invested with noradrenergic neurons.
Collapse
Affiliation(s)
- Adam J Stark
- Neurology, Vanderbilt University Medical Center, Nashville, TN, United States
| | | | - Kalen J Petersen
- Neurology, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Paula Trujillo
- Neurology, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Nelleke C van Wouwe
- Neurology, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Manus J Donahue
- Neurology, Vanderbilt University Medical Center, Nashville, TN, United States; Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, United States; Psychiatry and Behavioral Sciences, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Robert M Kessler
- Radiology, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Ariel Y Deutch
- Psychiatry and Behavioral Sciences, Vanderbilt University Medical Center, Nashville, TN, United States; Pharmacology, Vanderbilt University, Nashville, TN, United States
| | - David H Zald
- Psychology, Vanderbilt University, Nashville, TN, United States; Psychiatry and Behavioral Sciences, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Daniel O Claassen
- Neurology, Vanderbilt University Medical Center, Nashville, TN, United States.
| |
Collapse
|
4
|
Rondina JM, Ferreira LK, de Souza Duran FL, Kubo R, Ono CR, Leite CC, Smid J, Nitrini R, Buchpiguel CA, Busatto GF. Selecting the most relevant brain regions to discriminate Alzheimer's disease patients from healthy controls using multiple kernel learning: A comparison across functional and structural imaging modalities and atlases. Neuroimage Clin 2017; 17:628-641. [PMID: 29234599 PMCID: PMC5716956 DOI: 10.1016/j.nicl.2017.10.026] [Citation(s) in RCA: 33] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2016] [Revised: 10/12/2017] [Accepted: 10/24/2017] [Indexed: 12/11/2022]
Abstract
BACKGROUND Machine learning techniques such as support vector machine (SVM) have been applied recently in order to accurately classify individuals with neuropsychiatric disorders such as Alzheimer's disease (AD) based on neuroimaging data. However, the multivariate nature of the SVM approach often precludes the identification of the brain regions that contribute most to classification accuracy. Multiple kernel learning (MKL) is a sparse machine learning method that allows the identification of the most relevant sources for the classification. By parcelating the brain into regions of interest (ROI) it is possible to use each ROI as a source to MKL (ROI-MKL). METHODS We applied MKL to multimodal neuroimaging data in order to: 1) compare the diagnostic performance of ROI-MKL and whole-brain SVM in discriminating patients with AD from demographically matched healthy controls and 2) identify the most relevant brain regions to the classification. We used two atlases (AAL and Brodmann's) to parcelate the brain into ROIs and applied ROI-MKL to structural (T1) MRI, 18F-FDG-PET and regional cerebral blood flow SPECT (rCBF-SPECT) data acquired from the same subjects (20 patients with early AD and 18 controls). In ROI-MKL, each ROI received a weight (ROI-weight) that indicated the region's relevance to the classification. For each ROI, we also calculated whether there was a predominance of voxels indicating decreased or increased regional activity (for 18F-FDG-PET and rCBF-SPECT) or volume (for T1-MRI) in AD patients. RESULTS Compared to whole-brain SVM, the ROI-MKL approach resulted in better accuracies (with either atlas) for classification using 18F-FDG-PET (92.5% accuracy for ROI-MKL versus 84% for whole-brain), but not when using rCBF-SPECT or T1-MRI. Although several cortical and subcortical regions contributed to discrimination, high ROI-weights and predominance of hypometabolism and atrophy were identified specially in medial parietal and temporo-limbic cortical regions. Also, the weight of discrimination due to a pattern of increased voxel-weight values in AD individuals was surprisingly high (ranging from approximately 20% to 40% depending on the imaging modality), located mainly in primary sensorimotor and visual cortices and subcortical nuclei. CONCLUSION The MKL-ROI approach highlights the high discriminative weight of a subset of brain regions of known relevance to AD, the selection of which contributes to increased classification accuracy when applied to 18F-FDG-PET data. Moreover, the MKL-ROI approach demonstrates that brain regions typically spared in mild stages of AD also contribute substantially in the individual discrimination of AD patients from controls.
Collapse
Key Words
- 18F-FDG-PET, 18F-Fluorodeoxyglucose-Positron Emission Tomography
- AAL, Automated Anatomical Labeling (atlas)
- AD, Alzheimer's Disease
- Alzheimer's Disease
- BA, Brodmann's Area
- Brain atlas
- GM, Gray Matter
- MKL, Multiple Kernel Learning
- MKL-ROI, MKL based on regions of interest
- ML, Machine Learning
- MRI
- Multiple kernel learning
- NF, number of features
- NSR, Number of Selected Regions
- PET
- PVE, Partial Volume Effects
- ROI, Region of Interest
- SPECT
- SVM, Support Vector Machine
- T1-MRI, T1-weighted Magnetic Resonance Imaging
- TN, True Negative (specificity - proportion of healthy controls correctly classified)
- TP, True Positive (sensitivity - proportion of patients correctly classified)
- rAUC, Ratio between negative and positive Area Under Curve
- rCBF-SPECT, Regional Cerebral Blood Flow
Collapse
Affiliation(s)
- Jane Maryam Rondina
- Laboratory of Psychiatric Neuroimaging (LIM 21), Department of Psychiatry, Faculty of Medicine, University of São Paulo, São Paulo, Brazil; Sobell Department of Motor Neuroscience and Movement Disorders, Institute of Neurology, University College London, London, UK.
| | - Luiz Kobuti Ferreira
- Laboratory of Psychiatric Neuroimaging (LIM 21), Department of Psychiatry, Faculty of Medicine, University of São Paulo, São Paulo, Brazil; Núcleo de Apoio à Pesquisa em Neurociência Aplicada (NAPNA), University of São Paulo, São Paulo, Brazil
| | - Fabio Luis de Souza Duran
- Laboratory of Psychiatric Neuroimaging (LIM 21), Department of Psychiatry, Faculty of Medicine, University of São Paulo, São Paulo, Brazil
| | - Rodrigo Kubo
- Department of Radiology and Oncology, University of São Paulo Medical School, São Paulo, Brazil
| | - Carla Rachel Ono
- Department of Radiology and Oncology, University of São Paulo Medical School, São Paulo, Brazil
| | - Claudia Costa Leite
- Department of Radiology and Oncology, University of São Paulo Medical School, São Paulo, Brazil; Department of Radiology, University of North Carolina at Chapel Hill, NC, USA
| | - Jerusa Smid
- Department of Neurology and Cognitive Disorders Reference Center (CEREDIC), University of São Paulo, São Paulo, Brazil
| | - Ricardo Nitrini
- Department of Neurology and Cognitive Disorders Reference Center (CEREDIC), University of São Paulo, São Paulo, Brazil
| | | | - Geraldo F Busatto
- Laboratory of Psychiatric Neuroimaging (LIM 21), Department of Psychiatry, Faculty of Medicine, University of São Paulo, São Paulo, Brazil; Núcleo de Apoio à Pesquisa em Neurociência Aplicada (NAPNA), University of São Paulo, São Paulo, Brazil; Department and Institute of Psychiatry, University of São Paulo, São Paulo, Brazil
| |
Collapse
|
5
|
Shepherd TM, Kirov II, Charlson E, Bruno M, Babb J, Sodickson DK, Ben-Eliezer N. New rapid, accurate T 2 quantification detects pathology in normal-appearing brain regions of relapsing-remitting MS patients. Neuroimage Clin 2017; 14:363-70. [PMID: 28239545 DOI: 10.1016/j.nicl.2017.01.029] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/27/2016] [Revised: 01/18/2017] [Accepted: 01/25/2017] [Indexed: 01/22/2023]
Abstract
Introduction Quantitative T2 mapping may provide an objective biomarker for occult nervous tissue pathology in relapsing-remitting multiple sclerosis (RRMS). We applied a novel echo modulation curve (EMC) algorithm to identify T2 changes in normal-appearing brain regions of subjects with RRMS (N = 27) compared to age-matched controls (N = 38). Methods The EMC algorithm uses Bloch simulations to model T2 decay curves in multi-spin-echo MRI sequences, independent of scanner, and scan-settings. T2 values were extracted from normal-appearing white and gray matter brain regions using both expert manual regions-of-interest and user-independent FreeSurfer segmentation. Results Compared to conventional exponential T2 modeling, EMC fitting provided more accurate estimations of T2 with less variance across scans, MRI systems, and healthy individuals. Thalamic T2 was increased 8.5% in RRMS subjects (p < 0.001) and could be used to discriminate RRMS from healthy controls well (AUC = 0.913). Manual segmentation detected both statistically significant increases (corpus callosum & temporal stem) and decreases (posterior limb internal capsule) in T2 associated with RRMS diagnosis (all p < 0.05). In healthy controls, we also observed statistically significant T2 differences for different white and gray matter structures. Conclusions The EMC algorithm precisely characterizes T2 values, and is able to detect subtle T2 changes in normal-appearing brain regions of RRMS patients. These presumably capture both axon and myelin changes from inflammation and neurodegeneration. Further, T2 variations between different brain regions of healthy controls may correlate with distinct nervous tissue environments that differ from one another at a mesoscopic length-scale. EMC technique provides accurate and scanner-invariant T2 mapping in MS subjects. Thalamus T2 differences distinguish relapsing-remitting MS subjects from controls. Normal-appearing brain regions demonstrate T2 changes in MS patients compared to controls. T2 values reflect anatomic and function-specific differences in healthy controls.
Collapse
Key Words
- AUC, area under the curve
- B1 +, transmit field
- Biomarkers
- Demyelination
- EMC, echo modulation curve
- FLAIR, fluid-attenuated inversion recovery
- GM, gray matter
- MPRAGE, magnetization-prepared rapid gradient-echo
- MSE, multi-spin echo
- MWF, myelin water fraction
- Mesoscopic
- Neurodegeneration
- ROI, Region of Interest
- RRMS, relapsing-remitting multiple sclerosis
- Relaxation
- SPACE, sampling perfection with application-optimized contrasts using different flip angle evolution
- SSE, single spin echo
- WM, white matter
Collapse
|