1
|
Anita JN, Kumaran S. A Deep Learning Architecture for Meningioma Brain Tumor Detection and Segmentation. J Cancer Prev 2022; 27:192-198. [PMID: 36258715 PMCID: PMC9537580 DOI: 10.15430/jcp.2022.27.3.192] [Citation(s) in RCA: 0] [Impact Index Per Article: 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: 03/11/2022] [Revised: 09/09/2022] [Accepted: 09/16/2022] [Indexed: 11/03/2022] Open
Abstract
The meningioma brain tumor detection and segmentation method is a complex process due to its low intensity pixel profile. In this article, the meningioma brain tumor images were detected and tumor regions were segmented using a convolutional neural network (CNN) classification approach. The source brain MRI images were decomposed using the discrete wavelet transform and these decomposed sub bands were fused using an arithmetic fusion technique. The fused image was data augmented in order to increase the sample size. The data augmented images were classified into either healthy or malignant using a CNN classifier. Then, the tumor region in the classified meningioma brain image was segmented using an connection component analysis algorithm. The tumor region segmented meningioma brain image was compressed using a lossless compression technique. The proposed method stated in this article was experimentally tested with the sets of meningioma brain images from an open access dataset. The experimental results were compared with existing methods in terms of sensitivity, specificity and tumor segmentation accuracy.
Collapse
Affiliation(s)
- John Nisha Anita
- Department of Electronics and Communication Engineering, Sathyabama Institute of Science and Technology, Chennai, India,Correspondence to John Nisha Anita, E-mail: , https://orcid.org/0000-0003-4777-2123
| | - Sujatha Kumaran
- Department of Electrical and Electronics Engineering, Sathyabama Institute of Science and Technology, Chennai, India
| |
Collapse
|
2
|
Li Z, Li H, Braimah A, Dillman JR, Parikh NA, He L. A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants. Neuroimage 2022; 260:119484. [PMID: 35850161 PMCID: PMC9483989 DOI: 10.1016/j.neuroimage.2022.119484] [Citation(s) in RCA: 0] [Impact Index Per Article: 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: 05/12/2022] [Revised: 07/05/2022] [Accepted: 07/12/2022] [Indexed: 01/07/2023] Open
Abstract
Structural magnetic resonance imaging studies have shown that brain anatomical abnormalities are associated with cognitive deficits in preterm infants. Brain maturation and geometric features can be used with machine learning models for predicting later neurodevelopmental deficits. However, traditional machine learning models would suffer from a large feature-to-instance ratio (i.e., a large number of features but a small number of instances/samples). Ensemble learning is a paradigm that strategically generates and integrates a library of machine learning classifiers and has been successfully used on a wide variety of predictive modeling problems to boost model performance. Attribute (i.e., feature) bagging method is the most commonly used feature partitioning scheme, which randomly and repeatedly draws feature subsets from the entire feature set. Although attribute bagging method can effectively reduce feature dimensionality to handle the large feature-to-instance ratio, it lacks consideration of domain knowledge and latent relationship among features. In this study, we proposed a novel Ontology-guided Attribute Partitioning (OAP) method to better draw feature subsets by considering the domain-specific relationship among features. With the better-partitioned feature subsets, we developed an ensemble learning framework, which is referred to as OAP-Ensemble Learning (OAP-EL). We applied the OAP-EL to predict cognitive deficits at 2 years of age using quantitative brain maturation and geometric features obtained at term equivalent age in very preterm infants. We demonstrated that the proposed OAP-EL approach significantly outperformed the peer ensemble learning and traditional machine learning approaches.
Collapse
Affiliation(s)
- Zhiyuan Li
- Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Department of Electronic Engineering and Computer Science, University of Cincinnati, Cincinnati, OH, USA
| | - Hailong Li
- Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Center for Prevention of Neurodevelopmental Disorders, Perinatal Institute, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Artificial Intelligence Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA
| | - Adebayo Braimah
- Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA
| | - Jonathan R Dillman
- Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA; Artificial Intelligence Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA
| | - Nehal A Parikh
- Center for Prevention of Neurodevelopmental Disorders, Perinatal Institute, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, USA
| | - Lili He
- Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA; Center for Prevention of Neurodevelopmental Disorders, Perinatal Institute, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Artificial Intelligence Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA.
| |
Collapse
|
3
|
Saito G, Kono M, Koyanagi Y, Miyashita K, Tsutsumi A, Kobayashi T, Miki Y, Hashimoto D, Nakamura T, Nozue M, Nakamura H. Significance of Brain Imaging for Staging in Patients With Clinical Stage T1-2 N0 Non-Small-Cell Lung Cancer on Positron Emission Tomography/Computed Tomography. Clin Lung Cancer 2021:S1525-7304(21)00145-5. [PMID: 34253472 DOI: 10.1016/j.cllc.2021.06.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2021] [Revised: 06/03/2021] [Accepted: 06/04/2021] [Indexed: 11/20/2022]
Abstract
BACKGROUND Routine positron emission tomography/computed tomography (PET/CT) has been recommended even for clinical stage I non-small-cell lung cancer (NSCLC). In spite of the progress in the screening procedure, and revisions to TNM classification, there is no evidence to support brain imaging screening of patients assessed with the current staging protocol including PET/CT. MATERIALS AND METHODS We retrospectively investigated the frequency of extrathoracic metastasis in 466 consecutive patients with clinical stage T1-2 N0 NSCLC with the complete staging assessment comprised of thin-section CT, PET/CT, and brain contrast-enhanced magnetic resonance imaging between 2008 and 2016. All patients were reclassified according to the eighth edition of the tumor, node, and metastasis (TNM) classification. RESULTS Among all patients, 70% of the tumors were pure solid and 30% had part-solid ground-glass opacity on thin-section CT, and 388 (83%) and 78 (17%) were classified into clinical stages T1 and T2, respectively. Eight patients (1.7%) had extrathoracic metastasis, including 3 (0.6%) with brain metastasis, and all showed pure-solid tumors. The frequency of extrathoracic and brain metastasis was 1.0% and 0.5% in 388 T1 patients, and 5.0% and 3.0% in 78 T2 patients. Although brain metastases were detected in 2 of 7 patients (29%) with PET/CT detectable extrathoracic metastases and 1 of 459 patients (0.2%) without PET/CT detectable extrathoracic metastasis, there were no neurologically asymptomatic brain metastases in patients with early-stage NSCLC confirmed by PET/CT. CONCLUSION Routine screening of brain imaging is unnecessary in patients with early-stage NSCLC, assessed with the current staging protocol including PET/CT.
Collapse
|
4
|
Wang LJ, Lin LC, Lee SY, Wu CC, Chou WJ, Hsu CF, Tseng HH, Lin WC. l-Cystine is associated with the dysconnectivity of the default-mode network and salience network in attention-deficit/hyperactivity disorder. Psychoneuroendocrinology 2021; 125:105105. [PMID: 33338922 DOI: 10.1016/j.psyneuen.2020.105105] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/19/2020] [Revised: 11/04/2020] [Accepted: 12/06/2020] [Indexed: 11/16/2022]
Abstract
Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder. Distributed dysconnectivity within both the default-mode network (DMN) and the salience network (SN) has been observed in ADHD. L-cystine may serve as a neuroprotective molecule and signaling pathway, as well as a biomarker of ADHD. The purpose of this study was to explore whether differential brain network connectivity is associated with peripheral L-cystine levels in ADHD patients. We recruited a total of 31 drug-naïve patients with ADHD (mean age: 10.4 years) and 29 healthy controls (mean age: 10.3 years) that underwent resting state functional magnetic resonance imaging scans. Functional connectomes were generated for each subject, and we examined the cross-sectional group difference in functional connectivity (FC) within and between DMN and SN. L-cystine plasma levels were determined using high-performance chemical isotope labeling (CIL)-based liquid chromatography-mass spectrometry (LC-MS). Compared to the control group, the ADHD group showed decreased FC of dorsal DMN (p = 0.031), as well as decreased FC of precuneus-post SN (p = 0.006) and ventral DMN-post SN (p = 0.001). The plasma L-cystine levels of the ADHD group were significantly higher than in the control group (p = 0.002). Furthermore, L-cystine levels were negatively correlated with FC of precuneus-post SN (r = -0.404, p = 0.045) and ventral DMN-post SN (r = -0.540, p = 0.007). The findings suggest that decreased synergies of DMN and SN may serve as neurobiomarkers for ADHD, while L-cystine may be involved in the pathophysiology of network dysconnectivity. Future studies on the molecular mechanism of the cystine-glutamate system in brain network connectivity are warranted.
Collapse
Affiliation(s)
- Liang-Jen Wang
- Department of Child and Adolescent Psychiatry, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan
| | - Liang-Chun Lin
- Department of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital, Taiwan; Chang Gung University College of Medicine, Taiwan
| | - Sheng-Yu Lee
- Department of Psychiatry, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan; Department of Psychiatry, College of Medicine, Graduate Institute of Medicine, School of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Chih-Ching Wu
- Department of Medical Biotechnology and Laboratory Science, Chang Gung University, Taoyuan, Taiwan; Department of Otolaryngology-Head & Neck Surgery, Linkou Chang Gung Memorial Hospital, Taoyuan, Taiwan; Molecular Medicine Research Center, Chang Gung University, Taoyuan, Taiwan; Research Center for Emerging Viral Infections, College of Medicine, Chang Gung University, Taoyuan, Taiwan
| | - Wen-Jiun Chou
- Department of Child and Adolescent Psychiatry, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan
| | - Chia-Fen Hsu
- Division of Clinical Psychology, Graduate Institute of Behavioral Sciences, Chang Gung University, Taoyuan, Taiwan; Department of Child Psychiatry, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan
| | - Huai-Hsuan Tseng
- Department of Psychiatry, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan
| | - Wei-Che Lin
- Department of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital, Taiwan; Chang Gung University College of Medicine, Taiwan.
| |
Collapse
|
5
|
Selvapandian A, Manivannan K. Fusion based Glioma brain tumor detection and segmentation using ANFIS classification. Comput Methods Programs Biomed 2018; 166:33-38. [PMID: 30415716 DOI: 10.1016/j.cmpb.2018.09.006] [Citation(s) in RCA: 32] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/17/2018] [Revised: 09/05/2018] [Accepted: 09/11/2018] [Indexed: 06/09/2023]
Abstract
The detection of tumor regions in Glioma brain image is a challenging task due to its low sensitive boundary pixels. In this paper, Non-Sub sampled Contourlet Transform (NSCT) is used to enhance the brain image and then texture features are extracted from the enhanced brain image. These extracted features are trained and classified using Adaptive Neuro Fuzzy Inference System (ANFIS) approach to classify the brain image into normal and Glioma brain image. Then, the tumor regions in Glioma brain image is segmented using morphological functions. The proposed Glioma brain tumor detection methodology is applied on the Brain Tumor image Segmentation challenge (BRATS) open access dataset in order to evaluate the performance.
Collapse
Affiliation(s)
- A Selvapandian
- Department of Electronics and Communication Engineering, PSNA College of Engineering and Technology, Dindigul,Tamil Nadu 624001, India.
| | - K Manivannan
- Department of Computer Science and Engineering, PSNA College of Engineering and Technology, Dindigul, Tamil Nadu 624001, India
| |
Collapse
|
6
|
Kido J, Kawasaki T, Mitsubuchi H, Kamohara H, Ohba T, Matsumoto S, Endo F, Nakamura K. Hyperammonemia crisis following parturition in a female patient with ornithine transcarbamylase deficiency. World J Hepatol 2017; 9:343-348. [PMID: 28293384 PMCID: PMC5332424 DOI: 10.4254/wjh.v9.i6.343] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/05/2016] [Revised: 01/02/2017] [Accepted: 01/14/2017] [Indexed: 02/06/2023] Open
Abstract
Ornithine transcarbamylase deficiency (OTCD) is an X-linked disorder, with an estimated prevalence of 1 per 80000 live births. Female patients with OTCD develop metabolic crises that are easily provoked by non-predictable common disorders, such as genetic (private mutations and lyonization) and external factors; however, the outcomes of these conditions may differ. We resuscitated a female patient with OTCD from hyperammonemic crisis after she gave birth. Hyperammonemia after parturition in a female patient with OTCD can be fatal, and this type of hyperammonemia persists for an extended period of time. Here, we describe the cause and treatment of hyperammonemia in a female patient with OTCD after parturition. Once hyperammonemia crisis occurs after giving birth, it is difficult to improve the metabolic state. Therefore, it is important to perform an early intervention before hyperammonemia occurs in patients with OTCD or in carriers after parturition.
Collapse
|
7
|
Huang YS, Liu FY, Lin CY, Hsiao IT, Guilleminault C. Brain imaging and cognition in young narcoleptic patients. Sleep Med 2016; 24:137-144. [PMID: 27663355 DOI: 10.1016/j.sleep.2015.11.023] [Citation(s) in RCA: 29] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/20/2015] [Revised: 11/17/2015] [Accepted: 11/20/2015] [Indexed: 02/03/2023]
Abstract
The relationship between functional brain images and performances in narcoleptic patients and controls is a new field of investigation. We studied 71 young, type 1 narcoleptic patients and 20 sex- and age-matched control individuals using brain positron emission tomography (PET) images and neurocognitive testing. Clinical investigation was carried out using sleep-wake evaluation questionnaires; a sleep-wake study was conducted with actigraphy, polysomnography, multiple sleep latency test (MSLT), and blood tests (with human leukocyte antigen typing). The continuous performance test (CPT) and Wisconsin card sorting test (WCST) were administered on the same day as the PET study. PET data were analyzed using Statistical Parametric Mapping (version 8) software. Correlation of brain imaging and neurocognitive function was performed by Pearson's correlation. Statistical analyses (Student's t-test) were conducted with SPSS version-18. Seventy-one narcoleptic patients (mean age: 16.15 years, 41 boys (57.7%)) and 20 controls (mean age: 15.1 years, 12 boys (60%)) were studied. Results from the CPT and WCST showed significantly worse scores in narcoleptic patients than in controls (P < 0.05). Compared to controls, narcoleptic patients presented with hypometabolism in the right mid-frontal lobe and angular gyrus (P < 0.05) and significant hypermetabolism in the olfactory lobe, hippocampus, parahippocampus, amygdala, fusiform, left inferior parietal lobe, left superior temporal lobe, striatum, basal ganglia and thalamus, right hypothalamus, and pons (P < 0.05) in the PET study. Changes in brain metabolic activity in narcoleptic patients were positively correlated with results from the sleepiness scales and performance tests. Young, type 1 narcoleptic patients face a continuous cognitive handicap. Our imaging cognitive test protocol can be useful for investigating the effects of treatment trials in these patients.
Collapse
Affiliation(s)
- Yu-Shu Huang
- Department of Child Psychiatry and Sleep Center, Chang Gung Memorial Hospital and College of Medicine, Taoyuan, Taiwan; Department of Clinical Psychology College of Medicine, FU JEN Catholic University, Taipei, Taiwan
| | - Feng-Yuan Liu
- Department of Nuclear Medicine, Chang Gung Memorial Hospital and College of Medicine, Taoyuan, Taiwan
| | - Chin-Yang Lin
- Department of Child Psychiatry and Sleep Center, Chang Gung Memorial Hospital and College of Medicine, Taoyuan, Taiwan
| | - Ing-Tsung Hsiao
- Department of Medical Imaging and Radiological Sciences, Chang Gung Memorial Hospital and College of Medicine, Taoyuan, Taiwan
| | | |
Collapse
|