A New Deep Learning Model Selection Method for Colorectal Cancer Classification

Dif, Nassima; Elberrichi, Zakaria

doi:10.4018/ijsir.2020070105

Cited by 21 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another study ( Dif & Elberrichi, 2020a ), a framework was proposed for the colon histopathological image classification task. The authors employed a CNN based on transferred learning from Resnet121 generating a set of models followed by a dynamic model selection using the particle swarm optimization (PSO) metaheuristic.…”

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

“…An accuracy of 82% is achieved for 10280 images. In [18], a dynamic ensemble learning method is proposed for a multiclass CHIC task. This approach first uses transfer learning to train each model and then a particle swarm optimisation algorithm to select and integrate the models.…”

Section: Classification Tasks In Colorectal Histopathology Researchmentioning

confidence: 99%

IL-MCAM: An interactive learning and multi-channel attention mechanism-based weakly supervised colorectal histopathology image classification approach

Chen,

Li,

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, colorectal cancer has become one of the most significant diseases that endanger human health. Deep learning methods are increasingly important for the classification of colorectal histopathology images. However, existing approaches focus more on end-to-end automatic classification using computers rather than human-computer interaction. In this paper, we propose an IL-MCAM framework. It is based on attention mechanisms and interactive learning. The proposed IL-MCAM framework includes two stages: automatic learning (AL) and interactivity learning (IL). In the AL stage, a multi-channel attention mechanism model containing three different attention mechanism channels and convolutional neural networks is used to extract multi-channel features for classification. In the IL stage, the proposed IL-MCAM framework continuously adds misclassified images to the training set in an interactive approach, which improves the classification ability of the MCAM model. We carried out a comparison experiment on our dataset and an extended experiment on the HE-NCT-CRC-100K dataset to verify the performance of the proposed IL-MCAM framework, achieving classification accuracies of 98.98% and 99.77%, respectively. In addition, we conducted an ablation experiment and an interchangeability experiment to verify the ability and interchangeability of the three channels. The experimental results show that the proposed IL-MCAM framework has excellent performance in the colorectal histopathological image classification tasks.

show abstract

“…In Figure S5 in Multimedia Appendix 1, a significant visual difference between the training and the testing data can be observed for some classes with single-patient data (ie, one video per class). Nevertheless, to highlight the superiority of our method, we also evaluated the results of some existing state-of-the-art methods [5,8,10,[36][37][38][39][40][41][42][43][44][45][46][47] based on the same data set and experimental protocol. Additionally, online data augmentation [48] (with random rotation and translation in both directions) was applied (only in training the first-stage network) to resolve the class imbalance problem [49].…”

Section: Data Set and Preprocessingmentioning

confidence: 99%

“…However, we accomplished our goal to incorporate a large number of GI diseases in a single deep learning-based CAD framework and provided an initial pretrained network in the field of GI diagnostics. To highlight the superiority of our proposed solution, we used a similar data splitting and experimental protocol to evaluate the results of various existing methods [5,8,10,[36][37][38][39][40][41][42][43][44][45][46][47]. Finally, we provided a novel baseline solution in the emergent clinical setting as a supporting tool that can be further evolved in future studies.…”

Section: Limitations and Future Workmentioning

confidence: 99%

Automated Diagnosis of Various Gastrointestinal Lesions Using a Deep Learning–Based Classification and Retrieval Framework With a Large Endoscopic Database: Model Development and Validation (Preprint)

Owais¹,

Arsalan²,

Mahmood³

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND The early diagnosis of various gastrointestinal (GI) diseases can lead to effective treatment and also reduce the risk of many life-threatening conditions. Unfortunately, various small GI lesions are undetectable during early-stage examination by medical experts. In previous studies, various deep learning (DL)-based computer-aided diagnosis (CAD) tools were used to make a significant contribution to the effective diagnosis and treatment of GI diseases. However, most of these methods were designed to detect a limited number of GI diseases such as polyps, tumors, or cancers in a specific part of the human GI tract. OBJECTIVE Therefore, the aim of this study was to develop a comprehensive CAD tool to assist medical experts in diagnosing various types of GI diseases. METHODS Our proposed framework is comprised of a deep learning-based classification network, which is followed by the retrieval method. In the first step, the classification network predicts the disease type for the current medical condition, and then the retrieval part shows the relevant cases (in terms of endoscopic images) from the previous database. In this way, past cases help the medical expert to validate the current prediction by the computer in a subjective way, which ultimately results in better diagnosis and treatment. In the case of a wrong prediction by the computer, the medical expert can check other relevant cases (i.e., second-, third-, or fourth-best matches) which may be more relevant than the first best match. RESULTS All the experiments were performed using two endoscopic datasets with a total of 52,471 frames and 37 different classes. The optimal performances obtained by our proposed method in terms of accuracy, F1 score, mean average precision (mAP), and mean average recall (mAR) were 96.19%, 96.99%, 98.18%, and 95.86%, respectively. The overall performance of our proposed diagnostic framework significantly outperforms state-of-the-art methods. CONCLUSIONS This study provides a comprehensive computer-aided diagnosis framework for identifying various types of GI diseases. The obtained results show the superiority of our proposed method over the various state-of-the-art methods and illustrate its potential for clinical diagnosis and treatment. In addition, our proposed network can also be applicable to other classifications domains in medical imaging, such as computed tomography (CT) scan, magnetic resonance imaging (MRI), and ultrasound sequences.

show abstract

A New Deep Learning Model Selection Method for Colorectal Cancer Classification

Cited by 21 publications

References 41 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

IL-MCAM: An interactive learning and multi-channel attention mechanism-based weakly supervised colorectal histopathology image classification approach

Automated Diagnosis of Various Gastrointestinal Lesions Using a Deep Learning–Based Classification and Retrieval Framework With a Large Endoscopic Database: Model Development and Validation (Preprint)

Contact Info

Product

Resources

About