A novel transfer learning approach for the classification of histological images of colorectal cancer

Ohata, Elene Firmeza; Chagas, João Victor Souza das; Bezerra, Gabriel Maia; Hassan, Mohammad Mehedi; Albuquerque, Victor Hugo C. de

doi:10.1007/s11227-020-03575-6

Cited by 40 publications

(19 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Ohata et al (2021) , the authors use CNN to extract features of colorectal histological images. They employed various pretrained models, i.e., VGG16 and Inception, to extract deep features from the input images.…”

Section: Literature Reviewmentioning

confidence: 99%

Ensemble of adapted convolutional neural networks (CNN) methods for classifying colon histopathological images

Albashish

2022

PeerJ Computer Science

View full text Add to dashboard Cite

Deep convolutional neural networks (CNN) manifest the potential for computer-aided diagnosis systems (CADs) by learning features directly from images rather than using traditional feature extraction methods. Nevertheless, due to the limited sample sizes and heterogeneity in tumor presentation in medical images, CNN models suffer from training issues, including training from scratch, which leads to overfitting. Alternatively, a pre-trained neural network’s transfer learning (TL) is used to derive tumor knowledge from medical image datasets using CNN that were designed for non-medical activations, alleviating the need for large datasets. This study proposes two ensemble learning techniques: E-CNN (product rule) and E-CNN (majority voting). These techniques are based on the adaptation of the pretrained CNN models to classify colon cancer histopathology images into various classes. In these ensembles, the individuals are, initially, constructed by adapting pretrained DenseNet121, MobileNetV2, InceptionV3, and VGG16 models. The adaptation of these models is based on a block-wise fine-tuning policy, in which a set of dense and dropout layers of these pretrained models is joined to explore the variation in the histology images. Then, the models’ decisions are fused via product rule and majority voting aggregation methods. The proposed model was validated against the standard pretrained models and the most recent works on two publicly available benchmark colon histopathological image datasets: Stoean (357 images) and Kather colorectal histology (5,000 images). The results were 97.20% and 91.28% accurate, respectively. The achieved results outperformed the state-of-the-art studies and confirmed that the proposed E-CNNs could be extended to be used in various medical image applications.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Ensemble of adapted convolutional neural networks (CNN) methods for classifying colon histopathological images

Albashish

2022

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…For colorectal cancer tissue classification, a CNN based frameworks and various machine learning techniques were suggested by Ohata et al [23]. For deep feature extraction, the transfer learning based various CNNs such as inception, VGG, Densenet etc.…”

Section: Literature Reviewmentioning

confidence: 99%

Colorectal Cancer Disease Classification and Segmentation Using A Novel Deep Learning Approach

2022

IJIES

View full text Add to dashboard Cite

In the world, with a death rate of about 35% of colorectal cancer aids as the most widespread type of tumor. The third most commonly diagnosed cancer compared to breast and lung cancer is colorectal cancer. Specifically, in the minimization of health inequalities, it can be supported by the clinical care of AI guidance. Therefore in this paper an effective classification is performed by the deep learning technique called MobileNetV2. Before the classification task, cycle GAN based data augmentation technique is applied to solve the data imbalance problem. Moreover, Mask R-CNN based segmentation is applied to improve the classifier's performance. For the classification of colorectal cancer, the proposed method is examined on a colorectal histopathological dataset (MNIST). The performance of the work will be estimated using precision, accuracy, F-score and recall metrics and the simulation results shows that the proposed classifier achieves 99.91% accuracy, 100% precision, 99.87% recall and 0.999% f1-score over the other state-of-art techniques.

show abstract

“…Despite the small number of published works on colorectal WSI diagnosis (Table 2), there is a myriad of other articles also working on CRC classification using information from smaller tissue regions, that can be exploited as a basis for general diagnostic systems. Despite the different task, these works that use image crops, or even small patches [48][49][50][51][52] , can be leveraged for slide diagnosis, in combination with aggregation methods that combine all the extracted information in a single prediction.…”

Section: Computational Pathology On Colorectal Cancermentioning

confidence: 99%

CAD systems for colorectal cancer from WSI are still not ready for clinical acceptance

Oliveira

Neto

Fraga³

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Most oncological cases can be detected by imaging techniques, but diagnosis is based on pathological assessment of tissue samples. In recent years, the pathology field has evolved to a digital era where tissue samples are digitised and evaluated on screen. As a result, digital pathology opened up many research opportunities, allowing the development of more advanced image processing techniques, as well as artificial intelligence (AI) methodologies. Nevertheless, despite colorectal cancer (CRC) being the second deadliest cancer type worldwide, with increasing incidence rates, the application of AI for CRC diagnosis, particularly on whole-slide images (WSI), is still a young field. In this review, we analyse some relevant works published on this particular task and highlight the limitations that hinder the application of these works in clinical practice. We also empirically investigate the feasibility of using weakly annotated datasets to support the development of computer-aided diagnosis systems for CRC from WSI. Our study underscores the need for large datasets in this field and the use of an appropriate learning methodology to gain the most benefit from partially annotated datasets. The CRC WSI dataset used in this study, containing 1,133 colorectal biopsy and polypectomy samples, is available upon reasonable request.

show abstract

A novel transfer learning approach for the classification of histological images of colorectal cancer

Cited by 40 publications

References 50 publications

Ensemble of adapted convolutional neural networks (CNN) methods for classifying colon histopathological images

Ensemble of adapted convolutional neural networks (CNN) methods for classifying colon histopathological images

Colorectal Cancer Disease Classification and Segmentation Using A Novel Deep Learning Approach

CAD systems for colorectal cancer from WSI are still not ready for clinical acceptance

Contact Info

Product

Resources

About