A novel stacked sparse denoising autoencoder for mammography restoration to visual interpretation of breast lesion

In recent years, we have witnessed the fast growth of deep learning, which involves deep neural networks, and the development of the computing capability of computer devices following the advance of graphics processing units (GPUs). Deep learning can prototypically and successfully categorize histopathological images, which involves imaging classification. Various research teams apply deep learning to medical diagnoses, especially cancer diseases. Convolutional neural networks (CNNs) detect the conventional visual features of disease diagnoses, e.g., lung, skin, brain, prostate, and breast cancer. A CNN has a procedure for perfectly investigating medicinal science images. This study assesses the main deep learning concepts relevant to medicinal image investigation and surveys several charities in the field. In addition, it covers the main categories of imaging procedures in medication. The survey comprises the usage of deep learning for object detection, classification, and human cancer categorization. In addition, the most popular cancer types have also been introduced. This article discusses the Vision-Based Deep Learning System among the dissimilar sorts of data mining techniques and networks. It then introduces the most extensively used DL network category, which is convolutional neural networks (CNNs) and investigates how CNN architectures have evolved. Starting with Alex Net and progressing with the Google and VGG networks, finally, a discussion of the revealed challenges and trends for upcoming research is held.

show abstract

“… Key component of building a (B) deep belief network is a (A) restricted Boltzmann machine (A) (Ghosh et al, 2021 ). …”

Section: Vision-based Deep Learning Systemmentioning

confidence: 99%

A Survey on Human Cancer Categorization Based on Deep Learning

Ahmad

Mohamed

Maher

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…This architecture can automatically extract the features of shear wave elastography and distinguish between benign and malignant tumors. Ghosh et al identified breast ultrasonography lesions using stacked denoising autoencoders, which is superior to conventional machine learning techniques (22). Yap et al employed three deep learning approaches (patch-based Lenet, U-net, and pre-trained FCN-AlexNet transfer learning method) for the detection of breast lesions by ultrasound, and then compared their performance to that of four cutting-edge algorithms, and their findings indicated that transfer learning has a superior learning effect (23).…”

Section: Intelligent Application Of Breast Ultrasound Imagingmentioning

confidence: 99%

Application of Artificial Intelligence to Ultrasonography

Santacruz-Yaah

2022

Sci Insights

View full text Add to dashboard Cite

The use of artificial intelligence (AI) technology in medicine has gained considerable attention, although its application in ultrasound medicine is still in its infancy. Deep learning, the main algorithm of AI technology, can be applied to intelligent ultrasound picture detection and classification. Describe the application status of AI in ultrasound imaging, including thyroid, breast, and liver disease applications. The merging of AI and ultrasound imaging can increase the accuracy and specificity of ultrasound diagnosis and decrease the percentage of incorrect diagnoses.

show abstract

“…To minimize the overfitting and increase the learning accuracy, dropout mechanism is applied in dense layers in random manners. 14,26 The fully connected layer (F c ) takes all neurons from the previous layer, either the convolution layer or another fully connected layer, and connects them to every single neuron in its layer. Suppose, given N training samples…”

Section: Building a Cnns For Mecnnifs Schemementioning

confidence: 99%

“…They performed better not only in case of image classification but also in some work of medical imaging including image segmentation, image enhancement, restoration, anomaly detection, and so on. [12][13][14] Basically, deep CNNs learn abstract features from raw pixel data through its hierarchical network properties. 12,15,16 Guo et al 17 developed the performance of multilayer perceptron as employed to image patches and acquired competitive outcomes than the state-of-the-art methods.…”

Section: Introductionmentioning

confidence: 99%

“…[13][14][15]17 It has already been proven that enhancement algorithms based on deep learning are easily outperforming than conventional methods. 8,[13][14][15] Most recently, Lore et al and Li et al have suggested deep learning-based low illuminated image enhancement algorithms "LLNeT" 18 and "LightenNet" 19 in literature. The LLNeT and LightenNet are better for the enhanced brightness of low-light image but they are computationally expensive and the fine details (edge, corner, and so on) are overexposed with enhanced results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of intuitionistic fuzzy special embedded convolutional neural network for mammography enhancement

Ghosh

Biswas

Ghosh³

2020

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

This article proposes a novel mammogram enhancement approach using adaptive intuitionistic fuzzy special set (IFSS) with deep convolutional neural network (called MECNNIFS) for visual interpretation of mammography lesions, lumps, and abnormal cells in low-dose X-ray images. The proposed MECNNIFS scheme utilizes the membership grade modification by IFSS on low-dose X-ray images (mammography). The suggested model attempts to increase the underexposed and abnormal structural regions such as breast lesions, lumps, and nodules on the mammogram. The proposed algorithm initially separates mammograms using convolutional neural networks (CNNs) into foreground and background areas and then fuzzifies the image by intuitionistic fuzzy set theory. Low-level features of a mammogram of the adjacent part are integrated with CNN in pixel classification during the separation task stage to improve the performance. Hyperbolic regularization and hesitant score have been applied on fuzzy plane to quantify the uncertainty and fuzziness in spatial domain for the proposed contrast enhancement. Finally, an enhanced mammogram is acquired through the process of defuzzification. The results show better quality and performance for improvement of contrast and Mammography Lesion Detection using IFSS and CNN.

show abstract

A novel stacked sparse denoising autoencoder for mammography restoration to visual interpretation of breast lesion

Cited by 6 publications

References 28 publications

A Survey on Human Cancer Categorization Based on Deep Learning

A Survey on Human Cancer Categorization Based on Deep Learning

Application of Artificial Intelligence to Ultrasonography

Development of intuitionistic fuzzy special embedded convolutional neural network for mammography enhancement

Contact Info

Product

Resources

About