Performance Analysis of Deep Learning Models for Binary Classification of Cancer Gene Expression Data

Majumder, Subhasree; Yogita, .; Pal, Vipin; Yadav, Anju; Chakrabarty, Amitabha

doi:10.1155/2022/1122536

Cited by 6 publications

(7 citation statements)

References 20 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The set of differential calculus equations used by the algorithm in updating the population of Quarantine (Q), susceptible (S), Infected (I), Recovered (R), Vaccinated (V), Dead (D), Funeral (F), Exposed (E), and Hospitalized (H) individuals as in Eqs. ( 6), ( 7), ( 8), ( 9), ( 10), ( 11) and (12). Equations ( 6), ( 7), ( 8), ( 9), ( 10), ( 11) and ( 12) ∂I(t) ∂t = (β 1 I + β 3 D + β 4 R + β 2 (PE) )S − (Ŵ + γ)I − (τ)S are scalar functions.…”

Section: Ebola Optimization Search Algorithm Cnn Model (Eosa-cnn)mentioning

confidence: 99%

“…This shift has marked a significant transformation in personalized medicine, departing from traditional descriptive "morphological" classification approaches towards a more comprehensive strategy that considers clinical characteristics and immunohistochemical biomarkers. Today, gene expression profiling has become well-integrated into routine clinical practice 11 , 12 . Breast cancer researchers have examined gene expression profiling in-depth, and clinical oncologists are starting to use the findings of these studies in their daily practices.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A bio-inspired convolution neural network architecture for automatic breast cancer detection and classification using RNA-Seq gene expression data

Mohamed,

Ezugwu,

Fonou-Dombeu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Breast cancer is considered one of the significant health challenges and ranks among the most prevalent and dangerous cancer types affecting women globally. Early breast cancer detection and diagnosis are crucial for effective treatment and personalized therapy. Early detection and diagnosis can help patients and physicians discover new treatment options, provide a more suitable quality of life, and ensure increased survival rates. Breast cancer detection using gene expression involves many complexities, such as the issue of dimensionality and the complicatedness of the gene expression data. This paper proposes a bio-inspired CNN model for breast cancer detection using gene expression data downloaded from the cancer genome atlas (TCGA). The data contains 1208 clinical samples of 19,948 genes with 113 normal and 1095 cancerous samples. In the proposed model, Array-Array Intensity Correlation (AAIC) is used at the pre-processing stage for outlier removal, followed by a normalization process to avoid biases in the expression measures. Filtration is used for gene reduction using a threshold value of 0.25. Thereafter the pre-processed gene expression dataset was converted into images which were later converted to grayscale to meet the requirements of the model. The model also uses a hybrid model of CNN architecture with a metaheuristic algorithm, namely the Ebola Optimization Search Algorithm (EOSA), to enhance the detection of breast cancer. The traditional CNN and five hybrid algorithms were compared with the classification result of the proposed model. The competing hybrid algorithms include the Whale Optimization Algorithm (WOA-CNN), the Genetic Algorithm (GA-CNN), the Satin Bowerbird Optimization (SBO-CNN), the Life Choice-Based Optimization (LCBO-CNN), and the Multi-Verse Optimizer (MVO-CNN). The results show that the proposed model determined the classes with high-performance measurements with an accuracy of 98.3%, a precision of 99%, a recall of 99%, an f1-score of 99%, a kappa of 90.3%, a specificity of 92.8%, and a sensitivity of 98.9% for the cancerous class. The results suggest that the proposed method has the potential to be a reliable and precise approach to breast cancer detection, which is crucial for early diagnosis and personalized therapy.

show abstract

Section: Ebola Optimization Search Algorithm Cnn Model (Eosa-cnn)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A bio-inspired convolution neural network architecture for automatic breast cancer detection and classification using RNA-Seq gene expression data

Mohamed,

Ezugwu,

Fonou-Dombeu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In general, DL has made a major contribution to the mining process for big data [17]. DL also has a pretty good performance based on the level of positivity, precision, F1 scores, and accuracy values [18]. Thus, the concept of DL is used in the classification of Otitis disease.…”

Section: Introductionmentioning

confidence: 99%

Optimization deep learning with rough set approach model classification Otitis

Arief Wisky,

Ade Putra

2023

IJEECS

View full text Add to dashboard Cite

<span>Otitis is a disease that occurs in the middle ear in the form of inflammation. This research aims to develop an analysis model for the classification of Otitis disease based on knowledge patterns based on symptoms and type of disease. The analysis methods used include the performance of the certainty factor (CF), rough set (RS), artificial neural network (ANN), and decision tree (DT) methods. CF and RS performance can be used to generate classification rule patterns. These rule patterns become new knowledge in the classification analysis process using the concept of deep learning (DL). DL analysis with ANN and DT performance can work optimally in exploring and discovering hidden knowledge. Based on the results of performance testing, the combination of CF and RS in preprocessing can present a classification pattern of 106 rules. The output of DL analysis results is proven to produce precise and accurate classification results with an accuracy of 89%. Based on these results, the analytical model developed was proven to be effective in classifying Otitis disease. Not only that, this research is also able to contribute to updating the knowledge-based system in the classification process.</span>

show abstract

“…Xiao et al [ 14 ] proposed a deep learning model based on the Wasserstein generative adversarial network for unbalanced gene expression data in the same year by increasing the sample sizes in a few categories to achieve balance and further expanding the samples to improve the model performance. Majumder et al [ 15 ] considered a combination of three deep learning models (the multilayer perceptron (MLP) and two convolutional networks) and two feature selection methods in 2022 and performed experimental analyses on four cancer datasets, achieving good performance.…”

Section: Introductionmentioning

confidence: 99%

Deep learning approach for cancer subtype classification using high-dimensional gene expression data

et al. 2022

View full text Add to dashboard Cite

Motivation Studies have shown that classifying cancer subtypes can provide valuable information for a range of cancer research, from aetiology and tumour biology to prognosis and personalized treatment. Current methods usually adopt gene expression data to perform cancer subtype classification. However, cancer samples are scarce, and the high-dimensional features of their gene expression data are too sparse to allow most methods to achieve desirable classification results. Results In this paper, we propose a deep learning approach by combining a convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU): our approach, DCGN, aims to achieve nonlinear dimensionality reduction and learn features to eliminate irrelevant factors in gene expression data. Specifically, DCGN first uses the synthetic minority oversampling technique algorithm to equalize data. The CNN can handle high-dimensional data without stress and extract important local features, and the BiGRU can analyse deep features and retain their important information; the DCGN captures key features by combining both neural networks to overcome the challenges of small sample sizes and sparse, high-dimensional features. In the experiments, we compared the DCGN to seven other cancer subtype classification methods using breast and bladder cancer gene expression datasets. The experimental results show that the DCGN performs better than the other seven methods and can provide more satisfactory classification results.

show abstract

Performance Analysis of Deep Learning Models for Binary Classification of Cancer Gene Expression Data

Cited by 6 publications

References 20 publications

A bio-inspired convolution neural network architecture for automatic breast cancer detection and classification using RNA-Seq gene expression data

A bio-inspired convolution neural network architecture for automatic breast cancer detection and classification using RNA-Seq gene expression data

Optimization deep learning with rough set approach model classification Otitis

Deep learning approach for cancer subtype classification using high-dimensional gene expression data

Contact Info

Product

Resources

About