Multi-Class Breast Cancer Histopathological Image Classification Using Multi-Scale Pooled Image Feature Representation (MPIFR) and One-Versus-One Support Vector Machines
نویسندگان
چکیده
Breast cancer (BC) is currently the most common form of diagnosed worldwide with an incidence estimated at 2.26 million in 2020. Additionally, BC leading cause death. Many subtypes breast exist distinct biological features and which respond differently to various treatment modalities have different clinical outcomes. To ensure that sufferers receive lifesaving patients-tailored early, it crucial accurately distinguish dangerous malignant (ductal carcinoma, lobular mucinous papillary carcinoma) tumors from adenosis, fibroadenoma, phyllodes tumor, tubular adenoma benign harmless subtypes. An excellent automated method for detecting desirable since doctors do not identify 10% 30% cancers during regular examinations. While several computerized methods classification been proposed, deep convolutional neural networks (DCNNs) demonstrated superior performance. In this work, we proposed ensemble four variants DCNNs combined support vector machines classifier classify histopathological images into eight classes: malignant. The utilizes power extract highly predictive multi-scale pooled image feature representation (MPIFR) resolutions (40×, 100×, 200×, 400×) are then classified using SVM. Eight pre-trained DCNN architectures (Inceptionv3, InceptionResNetv2, ResNet18, ResNet50, DenseNet201, EfficientNetb0, shuffleNet, SqueezeNet) were individually trained best-performing models (ResNet50, EfficientNetb0) was utilized extraction. One-versus-one SVM model 8-class classifier. Our work novel because while some prior has CNNs 2- 4-class classification, only one other a solution classification. A 6B-Net CNN utilized, achieving accuracy 90% rigorous evaluation, MPIFR achieved average 97.77%, 97.48% sensitivity, 98.45% precision on BreakHis dataset, outperforming state-of-the-art multi-class comprehensive set baseline models.
منابع مشابه
Support Vector Machines for Multi-class Classification
A b s t r a c t : Support vector machines (SVMs) are primarily designed for 2-class classification problems. Although in several papers it is mentioned that the combination of K SVMs can be used to solve a K-class classification problem, such a procedure requires some care. In this paper, the scaling problem of different SVMs is highlighted. Various normalization methods are proposed to cope wi...
متن کاملFeature Selection for Multi-class Problems Using Support Vector Machines
Since feature selection can remove the irrelevant features and improve the performance of learning systems, it is an crucial step in machine learning. The feature selection methods using support vector machines have obtained satisfactory results, but the previous works are usually for binary classification, and needs auxiliary techniques to be extended to multiple classification. In this paper,...
متن کاملHierarchical Image Classification Using Support Vector Machines
Image classification is a very challenging problem in the image management and retrieval systems. The traditional classifiers are not effective to the image classification due to the high dimensionality of the image feature space. In this paper, we investigate the application of Support Vector Machines (SVMs) in the hierarchical semantic image classification. The image database is classified wi...
متن کاملAn Efficient Gabor Feature-Based Multi-task Joint Support Vector Machines Framework for Hyperspectral Image Classification
In this paper, a novel multi-task learning (MTL) framework for a series of Gabor features via joint probabilistic outputs of support vector machines (SVM), abbreviated as GF-MTJSVM, has been proposed for Hyperspectral image (HSI) classification. Specifically, we firstly use a series of Gabor wavelet filters with different scales and frequencies to extract spectral-spatial-combined features from...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied sciences
سال: 2022
ISSN: ['2076-3417']
DOI: https://doi.org/10.3390/app13010156