A classification of MRI brain tumor based on two stage feature level ensemble of deep CNN models

Aurna, Nahid Ferdous; Yousuf, Mohammad Abu; Taher, Kazi Abu; Azad, A. K. M.; Moni, Mohammad Ali

doi:10.1016/j.compbiomed.2022.105539

Cited by 85 publications

(49 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it should be noted that the sample size included in our study was limited. According to recent reports[ 38 , 39 ], using computerized deep learning methods may help elucidate the relationship between SPOCD1 and NOA in large samples. A recent study showed that conditional silencing of the SPOCD1 gene in mouse testes resulted in blocked spermatogenesis at the pachytene spermatocyte stage[ 29 ].…”

Section: Discussionmentioning

confidence: 99%

SPOC domain-containing protein 1 regulates the proliferation and apoptosis of human spermatogonial stem cells through adenylate kinase 4

Zhou¹,

Zhu²,

Huang³

et al. 2022

World J Stem Cells

View full text Add to dashboard Cite

BACKGROUND Spermatogonial stem cells (SSCs) are the origin of male spermatogenesis, which can reconstruct germ cell lineage in mice. However, the application of SSCs for male fertility restoration is hindered due to the unclear mechanisms of proliferation and self-renewal in humans. AIM To investigate the role and mechanism of SPOC domain-containing protein 1 (SPOCD1) in human SSC proliferation. METHODS We analyzed publicly available human testis single-cell RNA sequencing (RNA-seq) data and found that SPOCD1 is predominantly expressed in SSCs in the early developmental stages. Small interfering RNA was applied to suppress SPOCD1 expression to detect the impacts of SPOCD1 inhibition on SSC proliferation and apoptosis. Subsequently, we explored the target genes of SPOCD1 using RNA-seq and confirmed their role by restoring the expression of the target genes. In addition, we examined SPOCD1 expression in some non-obstructive azoospermia (NOA) patients to explore the correlation between SPOCD1 and NOA. RESULTS The uniform manifold approximation and projection clustering and pseudotime analysis showed that SPOCD1 was highly expressed in the early stages of SSC, and immunohistological results showed that SPOCD1 was mainly localized in glial cell line-derived neurotrophic factor family receptor alpha-1 positive SSCs. SPOCD1 knockdown significantly inhibited cell proliferation and promoted apoptosis. RNA-seq results showed that SPOCD1 knockdown significantly downregulated genes such as adenylate kinase 4 (AK4). Overexpression of AK4 in SPOCD1 knockdown cells partially reversed the phenotypic changes, indicating that AK4 is a functional target gene of SPOCD1. In addition, we found a significant downregulation of SPOCD1 expression in some NOA patients, suggesting that the downregulation of SPOCD1 may be relevant for NOA. CONCLUSION Our study broadens the understanding of human SSC fate determination and may offer new theories on the etiology of male infertility.

show abstract

Section: Discussionmentioning

confidence: 99%

SPOC domain-containing protein 1 regulates the proliferation and apoptosis of human spermatogonial stem cells through adenylate kinase 4

Zhou¹,

Zhu²,

Huang³

et al. 2022

World J Stem Cells

View full text Add to dashboard Cite

show abstract

“…It is well known that meningiomas' histological origin is derived from arachnoid cap cells of the meninges in the brain periphery. Meningiomas include a broad spectrum of histosub-types (transitional, meningotheliomatous, fibrous, psammomatus, angiomatous, anaplastic, and atypical) (16). The most crucial histopathological sign correlated to an aggressive biological behavior is brain tissue invasion.…”

Section: Discussionmentioning

confidence: 99%

P53 Suppressor Gene Tissue Microarray-based Protein Expression Analysis in Meningiomas

Roukas

Kouzoupis

Spyropoulou

et al. 2022

In Vivo

View full text Add to dashboard Cite

Background/Aim: Meningiomas represent the main intracranial primary central nervous system (CNS) tumour in adults worldwide. Oncogenes' over-activation combined with suppressor genes' silencing affect negatively the biological behavior of these neoplasms. This study aimed to explore the impact of p53 suppressor gene expression in meningiomas' clinic-pathological features based on a combination of sophisticated techniques. Materials and Methods: Fifty (n=50) meningiomas were included in the study, comprising a broad spectrum of histopathological subtypes. An immunohistochemistry assay was applied on tissue microarray cores followed by digital image analysis. Results: p53 protein over-expression (high staining intensity levels) was observed in 27/50 (54%) cases, whereas the rest (23/50-/46%) demonstrated moderate to low levels of the protein. p53 over-expression was statistically significantly correlated to the mitotic index of the examined cases (p-value=0.001). Interestingly, the atypical/anaplastic group of histotypes demonstrated the strongest p53 expression rates compared to the others (p-value=0.001). Conclusion: p53 overexpression is observed in a broad spectrum of meningiomas. High expression levels lead to an aggressive biological behavior of the malignancy (combined with increased mitotic rates), especially in atypical and anaplastic sub-types that also have a high recurrence rate.Neoplastic formation and malignant transformation are based on a cataract of abnormal intra-and extra-cellular reactions inside the corresponding epithelia (1). Up-regulation of proliferation combined with apoptosis inhibition critically influences the carcinogenetic process (2). Among genes that significantly modify crucial cell functions, p53 is one of high importance (3). Concerning cell cycle, p53 acts as a key regulator, stabilizing the genome domain and regulating its function. The corresponding gene -located on chromosome's 17 (Chr 17) short (p) arm at position 13.1 (17p13.1) -encodes for a 53 kDa nuclear phosphoprotein. p53 protein acts as a strong transcription/suppressor factor controlling cell proliferation. It is also implicated in different cell-signaling pathways that regulate cell cycle phases, programmed cell death, and DNA replication/repair (4). MDM2, a protooncogene (12q14.3) that encodes for a nuclear-localized E3 ubiquitin ligase, controls p53 protein expression levels in a p53-MDM2 auto-regulatory pathway. In fact, MDM2 binds 2205

show abstract

“…For example, Khatun et al [ 41 ] proposed a DCNN-LSTM classifier with self-attention model, which was capable of attaining an accuracy of 99.93% for human activity recognition purposes. In another study for classifying MRI brain tumor, authors implemented CNN with PCA in the feature extraction step and fed these features to different machine learning classification algorithms, which yielded a remarkable 99.76% accuracy [ 42 ].…”

Section: Related Workmentioning

confidence: 99%

Newborn Cry-Based Diagnostic System to Distinguish between Sepsis and Respiratory Distress Syndrome Using Combined Acoustic Features

2022

View full text Add to dashboard Cite

Crying is the only means of communication for a newborn baby with its surrounding environment, but it also provides significant information about the newborn’s health, emotions, and needs. The cries of newborn babies have long been known as a biomarker for the diagnosis of pathologies. However, to the best of our knowledge, exploring the discrimination of two pathology groups by means of cry signals is unprecedented. Therefore, this study aimed to identify septic newborns with Neonatal Respiratory Distress Syndrome (RDS) by employing the Machine Learning (ML) methods of Multilayer Perceptron (MLP) and Support Vector Machine (SVM). Furthermore, the cry signal was analyzed from the following two different perspectives: 1) the musical perspective by studying the spectral feature set of Harmonic Ratio (HR), and 2) the speech processing perspective using the short-term feature set of Gammatone Frequency Cepstral Coefficients (GFCCs). In order to assess the role of employing features from both short-term and spectral modalities in distinguishing the two pathology groups, they were fused in one feature set named the combined features. The hyperparameters (HPs) of the implemented ML approaches were fine-tuned to fit each experiment. Finally, by normalizing and fusing the features originating from the two modalities, the overall performance of the proposed design was improved across all evaluation measures, achieving accuracies of 92.49% and 95.3% by the MLP and SVM classifiers, respectively. The MLP classifier was outperformed in terms of all evaluation measures presented in this study, except for the Area Under Curve of Receiver Operator Characteristics (AUC-ROC), which signifies the ability of the proposed design in class separation. The achieved results highlighted the role of combining features from different levels and modalities for a more powerful analysis of the cry signals, as well as including a neural network (NN)-based classifier. Consequently, attaining a 95.3% accuracy for the separation of two entangled pathology groups of RDS and sepsis elucidated the promising potential for further studies with larger datasets and more pathology groups.

show abstract

A classification of MRI brain tumor based on two stage feature level ensemble of deep CNN models

Cited by 85 publications

References 32 publications

SPOC domain-containing protein 1 regulates the proliferation and apoptosis of human spermatogonial stem cells through adenylate kinase 4

SPOC domain-containing protein 1 regulates the proliferation and apoptosis of human spermatogonial stem cells through adenylate kinase 4

P53 Suppressor Gene Tissue Microarray-based Protein Expression Analysis in Meningiomas

Newborn Cry-Based Diagnostic System to Distinguish between Sepsis and Respiratory Distress Syndrome Using Combined Acoustic Features

Contact Info

Product

Resources

About