Binary and Multiclass Classification of Histopathological Images Using Machine Learning Techniques

2020 ◽  
Vol 10 (9) ◽  
pp. 2252-2258
Author(s):  
Jiatong Wang ◽  
Tiantian Zhu ◽  
Shan Liang ◽  
R. Karthiga ◽  
K. Narasimhan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Color Image ◽  
Multiclass Classification ◽  
Automated System ◽  
Machine Learning Techniques ◽  
Tubular Adenoma ◽  
Magnification Factor ◽  
Tree Classifier ◽  
Histopathological Images

Background and Objective: Breast cancer is fairly common and widespread form of cancer among women. Digital mammogram, thermal images of breast and digital histopathological images serve as a major tool for the diagnosis and grading of cancer. In this paper, a novel attempt has been proposed using image analysis and machine learning algorithm to develop an automated system for the diagnosis and grading of cancer. Methods: BreaKHis dataset is employed for the present work where images are available with different magnification factor namely 40×, 100×, 200×, 400× and 200× magnification factor is utilized for the present work. Accurate preprocessing steps and precise segmentation of nuclei in histopathology image is a necessary prerequisite for building an automated system. In this work, 103 images from benign and 103 malignant images are used. Initially color image is reshaped to gray scale format by applying Otsu thresholding, followed by top hat, bottom hat transform in preprocessing stage. The threshold value selected based on Ridler and calvard algorithm, extended minima transform and median filtering is applied for doing further steps in preprocessing. For segmentation of nuclei distance transform and watershed are used. Finally, for feature extraction, two different methods are explored. Result: In binary classification benign and malignant classification is done with the highest accuracy rate of 89.7% using ensemble bagged tree classifier. In case of multiclass classification 5-class are taken which are adenosis, fibro adenoma, tubular adenoma, mucinous carcinoma and papillary carcinoma the combination of multiclass classification gives the accuracy of 88.1% using ensemble subspace discriminant classifier. To the best of author’s knowledge, it is the first made in a novel attempt made for binary and multiclass classification of histopathology images. Conclusion: By using ensemble bagged tree and ensemble subspace discriminant classifiers the proposed method is efficient and outperform the state of art method in the literature.

scholarly journals Diabetic retinopathy detection and classification using capsule networks

2021 ◽  
Author(s):  
G. Kalyani ◽  
B. Janakiramaiah ◽  
A. Karuna ◽  
L. V. Narasimha Prasad
Keyword(s):  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Good Prognosis ◽  
Automated System ◽  
Machine Learning Techniques ◽  
Specific Class ◽  
Fundus Images ◽  
The People ◽  
Recent Developments

AbstractNowadays, diabetic retinopathy is a prominent reason for blindness among the people who suffer from diabetes. Early and timely detection of this problem is critical for a good prognosis. An automated system for this purpose contains several phases like identification and classification of lesions in fundus images. Machine learning techniques based on manual extraction of features and automatic extraction of features with convolution neural network have been presented for diabetic retinopathy detection. The recent developments like capsule networks in deep learning and their significant success over traditional machine learning methods for a variety of applications inspired the researchers to apply them for diabetic retinopathy diagnosis. In this paper, a reformed capsule network is developed for the detection and classification of diabetic retinopathy. Using the convolution and primary capsule layer, the features are extracted from the fundus images and then using the class capsule layer and softmax layer the probability that the image belongs to a specific class is estimated. The efficiency of the proposed reformed network is validated concerning four performance measures by considering the Messidor dataset. The constructed capsule network attains an accuracy of 97.98%, 97.65%, 97.65%, and 98.64% on the healthy retina, stage 1, stage 2, and stage 3 fundus images.

A Brief Survey on Text Classification Using Various Machine Learning Techniques

2018 ◽  
Vol 8 (1) ◽  
pp. 14
Author(s):  
Padmavathi .S ◽  
M. Chidambaram
Keyword(s):  
Machine Learning ◽  
Text Classification ◽  
Fixed Number ◽  
Machine Learning Techniques ◽  
Online Information ◽  
Rule Based ◽  
Learning Techniques ◽  
Machine Learning Approach ◽  
Rule Based Approach

Text classification has grown into more significant in managing and organizing the text data due to tremendous growth of online information. It does classification of documents in to fixed number of predefined categories. Rule based approach and Machine learning approach are the two ways of text classification. In rule based approach, classification of documents is done based on manually defined rules. In Machine learning based approach, classification rules or classifier are defined automatically using example documents. It has higher recall and quick process. This paper shows an investigation on text classification utilizing different machine learning techniques.

scholarly journals Feasibility of Machine Learning Algorithms for Predicting the Deformation of Anodic Titanium Films by Modulating Anodization Processes

Materials ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1089
Author(s):  
Sung-Hee Kim ◽  
Chanyoung Jeong
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Multiclass Classification ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Smart Manufacturing ◽  
Gradient Boosting ◽  
Experimental Conditions ◽  
Learning Techniques ◽  
Tio2 Nanostructures

This study aims to demonstrate the feasibility of applying eight machine learning algorithms to predict the classification of the surface characteristics of titanium oxide (TiO2) nanostructures with different anodization processes. We produced a total of 100 samples, and we assessed changes in TiO2 nanostructures’ thicknesses by performing anodization. We successfully grew TiO2 films with different thicknesses by one-step anodization in ethylene glycol containing NH4F and H2O at applied voltage differences ranging from 10 V to 100 V at various anodization durations. We found that the thicknesses of TiO2 nanostructures are dependent on anodization voltages under time differences. Therefore, we tested the feasibility of applying machine learning algorithms to predict the deformation of TiO2. As the characteristics of TiO2 changed based on the different experimental conditions, we classified its surface pore structure into two categories and four groups. For the classification based on granularity, we assessed layer creation, roughness, pore creation, and pore height. We applied eight machine learning techniques to predict classification for binary and multiclass classification. For binary classification, random forest and gradient boosting algorithm had relatively high performance. However, all eight algorithms had scores higher than 0.93, which signifies high prediction on estimating the presence of pore. In contrast, decision tree and three ensemble methods had a relatively higher performance for multiclass classification, with an accuracy rate greater than 0.79. The weakest algorithm used was k-nearest neighbors for both binary and multiclass classifications. We believe that these results show that we can apply machine learning techniques to predict surface quality improvement, leading to smart manufacturing technology to better control color appearance, super-hydrophobicity, super-hydrophilicity or batter efficiency.

Sign in / Sign up

Export Citation Format

Share Document