Deep learning techniques for cancer classification using microarray gene expression data

Gupta, Surbhi; Gupta, Manoj Kumar; Shabaz, Mohammad; Sharma, Ashutosh

doi:10.3389/fphys.2022.952709

Cited by 33 publications

(11 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several publications have presented tailored GAN architectures and workflows for segmentation tasks that are mortal-trained to generate accurate model of segmentation from a particular medical picture dataset. With reference to image conversion between modes, [17] a conditional GAN model is used to create MRI pictures from T1-weighted ones and conversely. To enhance the training set size for various DL models, efforts have been made to create phone medical images, a project more carefully akin to the one looked at in this study.…”

Section: B Data Augmentationmentioning

confidence: 99%

Classification of Breast Masses Using Ultrasound Images by Approaching GAN, Transfer Learning and Deep Learning Techniques

Chaudhury

2023

JAIT

View full text Add to dashboard Cite

Breast cancer is a common cause of death among women worldwide. Ultrasonic imaging is a valuable diagnostic tool in breast cancer detection. However, the accuracy of computer-aided diagnosis systems for breast cancer classification is limited due to the lack of well-annotated datasets. This study proposes a deep learning-based framework for breast mass classification using ultrasound images, which incorporates a novel data augmentation technique, Generative Adversarial Network (GAN), and Transfer Learning (TL). Automating early tumor identification and classification in breast cancer diagnosis can save lives by improving the accuracy of diagnoses and reducing the need for invasive procedures. However, the limited availability of well-annotated datasets for ultrasound images of breast cancer has hampered the development of accurate computer-aided diagnosis systems. The accuracy of breast mass classification using ultrasound images is limited due to the lack of well-annotated datasets. Conventional data augmentation techniques have limitations in applications with strict guidelines, such as medical datasets. Therefore, there is a need to develop a novel data augmentation technique to improve the accuracy of breast mass classification using ultrasound images. The proposed framework can be extended to other medical imaging applications, where the availability of well-annotated datasets is limited. The GAN-based data augmentation technique and TL-based feature extraction can be used to improve the accuracy of classification models in other medical imaging applications. Additionally, the proposed framework can be used to develop accurate computer-aided diagnosis systems for breast cancer detection in clinical settings. The proposed framework incorporates a deep learning-based approach for breast mass classification using ultrasound images. The framework includes a GAN-based data augmentation technique and TL for feature extraction. The dataset used for training and testing the model is the Breast Ultrasound Images (BUSI) dataset, which includes 1311 images with normal and abnormal breast masses. The proposed framework achieved an accuracy of 99.6% for breast mass classification using ultrasound images, which outperformed existing methods. The GAN-based data augmentation technique and TL-based feature extraction improved the accuracy of the classification model. The results suggest that deep learning algorithms can be effectively applied for breast ultrasound categorization. The proposed framework presents a novel approach for breast mass classification using ultrasound images, which incorporates a GAN-based data augmentation technique and TL-based feature extraction. The results demonstrate that the proposed framework outperforms existing methods and achieves high accuracy in breast mass classification using ultrasound images. This framework can be useful for developing accurate computer-aided diagnosis systems for breast cancer detection.

show abstract

Section: B Data Augmentationmentioning

confidence: 99%

Classification of Breast Masses Using Ultrasound Images by Approaching GAN, Transfer Learning and Deep Learning Techniques

Chaudhury

2023

JAIT

View full text Add to dashboard Cite

show abstract

“…these methods have provided the foundation for cancer diagnosis and treatment, they are nonspecific, costly, and heavily dependent on the growth rate of cancer tumors. [27] In addition, a wide variety of techniques within the field of molecular biology, such as enzyme-linked immunosorbent assay, [28] radioimmunoassay, [29] immunohistochemistry, [30,31] flow cytometry, [32] and DNA/RNA-based hybridization/sequencing approaches, [33][34][35][36] have also been widely used to detect molecular signatures/biomarkers in cancer cells. Although current molecular diagnostic techniques have been clinically validated, they frequently exhibit low sensitivity, extended detection times, potential health risks, and the requirement for sophisticated equipment and skilled operators.…”

Section: Introductionmentioning

confidence: 99%

Emerging Multifunctional Carbon‐Nanomaterial‐Based Biosensors for Cancer Diagnosis

Britto,

Guan,

Tran

et al. 2024

Small Science

View full text Add to dashboard Cite

Despite significant advancements in medical technology, cancer remains the world's second‐leading cause of death, largely attributed to late‐stage diagnoses. While traditional cancer detection methodologies offer foundational insights, they often lack the specificity, affordability, and sensitivity for early‐stage identification. In this context, the development of biosensors offers a distinct possibility for the precise and rapid identification of cancer biomarkers. Carbon nanomaterials, including graphene, carbon nitride, carbon quantum dots, and other carbon‐based nanostructures, are highly promising for cancer detection. Their simplicity, high sensitivity, and cost‐effectiveness contribute to their potential in this field. This review aims to elucidate the potential of emerging carbon‐nanomaterial‐based biosensors for early cancer diagnosis. The relevance of the various biosensor mechanisms and their performance to the physicochemical properties of carbon nanomaterials is discussed in depth, focusing on demonstrating broad methodologies for creating performance biosensors. Diverse carbon‐nanomaterial‐based detection techniques, such as electrochemical, fluorescence, surface plasmon resonance, electrochemiluminescence, and quartz crystal microbalance, are emphasized for early cancer detection. At last, a summary of existing challenges and future outlook in this promising field is elaborated.

show abstract

“…The research motivation is to assure and implement the progression of dataset dimensionality mapping via bio-makers and attribute-based patterns. The proposed technique assures that the medical dataset will retain its originality and compute the digitalized sequence of patterns and information, thus choosing CNN over other potential machine learning algorithms for feature extraction and classification [6]. Comparative analysis is shown Table 1.…”

Section: Introductionmentioning

confidence: 99%

Classification of Lung Adenocarcinoma Using Convolutional Neural Networks: A Bioinformatics Approach

Aharonu,

Kumar

2024

View full text Add to dashboard Cite

Lung cancer, recognized as one of the most lethal malignancies globally, manifests predominantly as lung adenocarcinoma (LUAD) within the broader classification of nonsmall cell lung cancer (NSCLC). The imperative for accurate and prompt diagnosis to facilitate efficacious treatment underscores the significance of advancements in diagnostic methodologies. This study introduces a convolutional neural network (CNN) framework tailored for the interpretation of bioinformatics datasets, specifically focusing on the classification of lung adenocarcinoma. Emphasizing the integration of gene-based biomarker informatics, this approach endeavors to mitigate hierarchical discrepancies inherent within similarity indices encountered during dataset processing. Through the utilization of three gene expression datasets-GSE118370, GSE85841, and GSE32863sourced from the Gene Expression Omnibus (GEO), key features indicative of lung adenocarcinoma were meticulously analyzed. This methodology not only facilitates the precise categorization of data samples into lung adenocarcinoma but also enhances the reliability of the findings. The implementation of this CNN framework on the specified datasets yielded a classification accuracy of 93.32% and a precision of 94.56%, thereby surpassing the performance metrics of existing techniques. This research underscores the potential of integrating CNNs with bioinformatics for the refined classification of lung adenocarcinoma, heralding a significant step forward in the precise identification of this prevalent form of lung cancer.

show abstract

Deep learning techniques for cancer classification using microarray gene expression data

Cited by 33 publications

References 48 publications

Classification of Breast Masses Using Ultrasound Images by Approaching GAN, Transfer Learning and Deep Learning Techniques

Classification of Breast Masses Using Ultrasound Images by Approaching GAN, Transfer Learning and Deep Learning Techniques

Emerging Multifunctional Carbon‐Nanomaterial‐Based Biosensors for Cancer Diagnosis

Classification of Lung Adenocarcinoma Using Convolutional Neural Networks: A Bioinformatics Approach

Contact Info

Product

Resources

About