A weight perturbation-based regularisation technique for convolutional neural networks and the application in medical imaging

Khatami, Amin; Nazari, Asef; Khosravi, Abbas; Lim, Chee Peng; Nahavandi, Saeid

doi:10.1016/j.eswa.2020.113196

Cited by 30 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CNN model pool process reduces the input image matrix's space using an appropriate mask size of 2 × 2 or 3 × 3 and applies the kernel function on every part of the image. Then the maximum value of results is selected [27]. The next stage in the structure of the CNN model is the rule function.…”

Section: Methodsmentioning

confidence: 99%

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Mohammed

Hussain

2021

Computation

View full text Add to dashboard Cite

Accurate, fast, and automatic detection and classification of animal images is challenging, but it is much needed for many real-life applications. This paper presents a hybrid model of Mamdani Type-2 fuzzy rules and convolutional neural networks (CNNs) applied to identify and distinguish various animals using different datasets consisting of about 27,307 images. The proposed system utilizes fuzzy rules to detect the image and then apply the CNN model for the object’s predicate category. The CNN model was trained and tested based on more than 21,846 pictures of animals. The experiments’ results of the proposed method offered high speed and efficiency, which could be a prominent aspect in designing image-processing systems based on Type 2 fuzzy rules characterization for identifying fixed and moving images. The proposed fuzzy method obtained an accuracy rate for identifying and recognizing moving objects of 98% and a mean square error of 0.1183464 less than other studies. It also achieved a very high rate of correctly predicting malicious objects equal to recall = 0.98121 and a precision rate of 1. The test’s accuracy was evaluated using the F1 Score, which obtained a high percentage of 0.99052.

show abstract

Section: Methodsmentioning

confidence: 99%

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Mohammed

Hussain

2021

Computation

View full text Add to dashboard Cite

show abstract

“…Figure 4 shows our proposed CNN structure. A variety of choices is available for the CNN structure such as the convolution size, kind of activation function and number of hidden layers [42]. Each structure is examined to find out better performance.…”

Section: The Proposed Systemsmentioning

confidence: 99%

Nuclear atypia grading in breast cancer histopathological images based on CNN feature extraction and LSTM classification

Jafarbigloo

Danyali

2021

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Early diagnosis of breast cancer, the most common disease among women around the world, increases the chance of treatment and is highly important. Nuclear atypia grading in histopathological images plays an important role in the final diagnosis and grading of breast cancer. Grading images by pathologists is a time consuming and subjective task. Therefore, the existence of a computer-aided system for nuclear atypia grading is very useful and necessary. In this study, two automatic systems for grading nuclear atypia in breast cancer histopathological images based on deep learning methods are proposed. A patch-based approach is introduced due to the large size of the histopathological images and restriction of the training data. In the proposed system I, the most important patches in the image are detected first and then a three-hidden-layer convolutional neural network (CNN) is designed and trained for feature extraction and to classify the patches individually. The proposed system II is based on a combination of the CNN for feature extraction and a twolayer Long short-term memory (LSTM) network for classification. The LSTM network is utilised to consider all patches of an image simultaneously for image grading. The simulation results show the efficiency of the proposed systems for automatic nuclear atypia grading and outperform the current related studies in the literature. K E Y W O R D S breast cancer, CNN, histopathological image, LSTM networks, nuclear atypia | INTRODUCTIONBreast cancer is caused due to an outgrowth of abnormal cells in the breast. This disease is the second leading cause of death among women around the world [1] and is a serious problem for most human societies. Early diagnosis of this disease increases the chance of efficient treatment. After performing mammography and ultrasound imaging, if abnormal tissues are found, a biopsy examination is required. In this test, a small sample of the breast tissue is placed under a microscope to acquire histopathological images for further investigation. Histopathology refers to the visual examination of tissue [2]. Histopathological images are available in digital format which is analysed to detect the type and grade of cancer [3]. Various magnifications of histological images are available such as 10X, 20X and 40X.Traditional methods for grading breast cancer are manually performed by pathologists. Pathologists examine histologicalThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…The best way to overcome this problem is to regularize a fixed-sized model that considers the average of the predictions resulted from the various settings of the network parameters [52]. Henceforth, the necessity of a regularization method which adapts the selected parameters and ensures the generalization of the ANN is inevitable [29]. Typically, the regularization function F reg should be considered in evaluation of the network performance instead of the usual mean square error mse function.…”

Section: Training Function and Learning Processmentioning

confidence: 99%

Simulating the response of ionization chamber system to 137Cs irradiator using the artificial neural network modeling algorithm

Sadek

2020

SN Appl. Sci.

View full text Add to dashboard Cite

The artificial neural network algorithm has been used to simulate the response of an ionization chamber dosimetric system to the 137 Cs irradiator facility at the National Institute for Standards, Egypt. The performance of the designed model has been investigated over different processes functions and a wide range of parameters till the optimum performance has been approached. The standard uncertainty of the designed model has been evaluated for different dose-rate levels. It has been found that the dose-rate can be evaluated using the designed model with an uncertainty < 2.0% for the dose-rate level < 10 2 mGy/h and with an uncertainty < 0.5% for the dose-rate level [10 2 −10 3 ] mGy/h . The bias of the designed model has been evaluated and compared with the usual interpolation algorithms. The errors in the evaluated dose-rate using these methods have exceeded the 100% error level and approached the 20% error level for the dose rates less and greater than 10 mGy/h , respectively. While, the error in the evaluated dose-rate using the designed model did not exceed 7% and 2% for the same dose-rate levels, respectively.

show abstract

A weight perturbation-based regularisation technique for convolutional neural networks and the application in medical imaging

Cited by 30 publications

References 21 publications

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Nuclear atypia grading in breast cancer histopathological images based on CNN feature extraction and LSTM classification

Simulating the response of ionization chamber system to 137Cs irradiator using the artificial neural network modeling algorithm

Contact Info

Product

Resources

About