Pathological image classification via embedded fusion mutual learning

Li, Guangli; Wu, Guangting; Xu, Guangxin; Li, Chuanxiu; Zhu, Zhiliang; Ye, Yiyuan; Zhang, Hongbin

doi:10.1016/j.bspc.2022.104181

Cited by 14 publications

(7 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors demonstrate the effectiveness of DML networks in classification and task‐recognition tasks through experiments on two large datasets. Li 44 proposed a new method called embedded fusion mutual learning (EFML) for pathology image classification task, introducing feature fusion classifiers and ensemble classifiers into EFML to learn different knowledge. Finally, the authors jointly supervise the model training by combining logits output and fused feature maps.…”

Section: Related Workmentioning

confidence: 99%

DML‐OFA: Deep mutual learning with online feature alignment for the detection of COVID‐19 from chest x‐ray images

Liang,

Lu,

Ming

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryCOVID‐19 is a novel coronavirus‐induced disease and automatic identification of COVID‐19 using computer‐assisted methods can facilitate faster diagnostic efficiency. Current research typically employs a single model for COVID‐19 identification, while implicit and complementary knowledge between heterogeneous networks is neglected. To address these issues, we propose a new model based on deep mutual learning with online feature alignment called DML‐OFA to more effectively diagnose COVID‐19. First, we use a traditional deep mutual learning (DML) framework to allow two parallel heterogeneous networks to learn from each other to form two effective feature extractors. In addition, we embed the adaptive feature fusion classifier and logits ensembling module in the proposed DML‐OFA, which can simultaneously learn implicit complementary knowledge from feature maps and logits. We evaluated DML‐OFA on four public datasets: Covid‐chestxray‐dataset, ChestXRay2017, Coronavirus‐dataset and COVIDx. The results showed that our model attains 97.10 Accuracy, 97.28 Specificity, 96.21 Recall, 97.45 Precision, and 96.82 F1‐score, which outperforms other previous related works.

show abstract

Section: Related Workmentioning

confidence: 99%

DML‐OFA: Deep mutual learning with online feature alignment for the detection of COVID‐19 from chest x‐ray images

Liang,

Lu,

Ming

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…The mean intensity value of the intensity-based set was found to be the second most significant feature. The ranking order was as follows: Feature number: 27,31,18,24,30,29,8,21,23,15,26,25,28,12,20,3,5,6,22,11,9,17,16,14,4,19,10,13,7, 32, 1, 2, 33. However, overall, directional features were found to be more significant than the geometrical and intensity-based features as 14 out of the 15 features in the ranking belonged to the directional features that were developed to represent the irregular border shape of the segmented cells in an image.…”

Section: Intensity-based Featuresmentioning

confidence: 99%

Deep Learning- and Expert Knowledge-Based Feature Extraction and Performance Evaluation in Breast Histopathology Images

Kode,

Barkana

2023

Cancers

View full text Add to dashboard Cite

Cancer develops when a single or a group of cells grows and spreads uncontrollably. Histopathology images are used in cancer diagnosis since they show tissue and cell structures under a microscope. Knowledge-based and deep learning-based computer-aided detection is an ongoing research field in cancer diagnosis using histopathology images. Feature extraction is vital in both approaches since the feature set is fed to a classifier and determines the performance. This paper evaluates three feature extraction methods and their performance in breast cancer diagnosis. Features are extracted by (1) a Convolutional Neural Network, (2) a transfer learning architecture VGG16, and (3) a knowledge-based system. The feature sets are tested by seven classifiers, including Neural Network (64 units), Random Forest, Multilayer Perceptron, Decision Tree, Support Vector Machines, K-Nearest Neighbors, and Narrow Neural Network (10 units) on the BreakHis 400× image dataset. The CNN achieved up to 85% for the Neural Network and Random Forest, the VGG16 method achieved up to 86% for the Neural Network, and the knowledge-based features achieved up to 98% for Neural Network, Random Forest, Multilayer Perceptron classifiers.

show abstract

“…Moreover, a variety of methods are available in ML to reduce the dimensions of features, including feature selection, feature projection, and feature reduction 22 . The implementation of DL to diagnose colon cancer has received more attention in most previous histopathological imaging studies because the disease has a high mortality rate 23 – 27 .…”

Section: Related Workmentioning

confidence: 99%

“… Authors Year Method Dataset No. of classes Performance Sakr et al 23 2022 CNN LC25000 2 Acc: 99.50% Wilm et al 24 2022 CNN Two HIs 7 Acc: 93.8–95.7% Moyes et al 25 2023 Multi-channel auto-encoder Synthetic dataset 9 F-score: 0.620738 Gavade et al 26 2023 ResNet-50 Kaggle 2 Acc: 98.9% Li et al 27 2023 Embedded fusion mutual learning LC25000 2 Acc: 98.96% AUC: 0.9973 Haj-Hassan et al 28 2017 CNN CHU Nancy Brabois Hospital 3 Acc: 99.17% Iizuka et al 29 2020 CNN and RNN Hiroshima University Hospital 3 AUC: 0.97–0.99 Masud et al 30 2021 CNN LC25000 5 Acc: 96.33% Kwak et al …”

Section: Related Workmentioning

confidence: 99%

Ensemble-based multi-tissue classification approach of colorectal cancer histology images using a novel hybrid deep learning framework

Fadafen

Rezaee

2023

Sci Rep

View full text Add to dashboard Cite

Colorectal cancer (CRC) is the second leading cause of cancer death in the world, so digital pathology is essential for assessing prognosis. Due to the increasing resolution and quantity of whole slide images (WSIs), as well as the lack of annotated information, previous methodologies cannot be generalized as effective decision-making systems. Since deep learning (DL) methods can handle large-scale applications, they can provide a viable alternative to histopathology image (HI) analysis. DL architectures, however, may not be sufficient to classify CRC tissues based on anatomical histopathology data. A dilated ResNet (dResNet) structure and attention module are used to generate deep feature maps in order to classify multiple tissues in HIs. In addition, neighborhood component analysis (NCA) overcomes the constraint of computational complexity. Data is fed into a deep support vector machine (SVM) based on an ensemble learning algorithm called DeepSVM after the features have been selected. CRC-5000 and NCT-CRC-HE-100 K datasets were analyzed to validate and test the hybrid procedure. We demonstrate that the hybrid model achieves 98.75% and 99.76% accuracy on CRC datasets. The results showed that only pathologists' labels could successfully classify unseen WSIs. Furthermore, the hybrid deep learning method outperforms state-of-the-art approaches in terms of computational efficiency and time. Using the proposed mechanism for tissue analysis, it will be possible to correctly predict CRC based on accurate pathology image classification.

show abstract

Pathological image classification via embedded fusion mutual learning

Cited by 14 publications

References 39 publications

DML‐OFA: Deep mutual learning with online feature alignment for the detection of COVID‐19 from chest x‐ray images

DML‐OFA: Deep mutual learning with online feature alignment for the detection of COVID‐19 from chest x‐ray images

Deep Learning- and Expert Knowledge-Based Feature Extraction and Performance Evaluation in Breast Histopathology Images

Ensemble-based multi-tissue classification approach of colorectal cancer histology images using a novel hybrid deep learning framework

Contact Info

Product

Resources

About