Deep learning based radiomics for gastrointestinal cancer diagnosis and treatment: A minireview

Convolutional neural networks (CNNs) have received increased attention in endoscopic images due to their outstanding advantages. Clinically, some gastric polyps are related to gastric cancer, and accurate identification and timely removal are critical. CNN-based semantic segmentation can delineate each polyp region precisely, which is beneficial to endoscopists in the diagnosis and treatment of gastric polyps. At present, just a few studies have used CNN to automatically diagnose gastric polyps, and studies on their semantic segmentation are lacking. Therefore, we contribute pioneering research on gastric polyp segmentation in endoscopic images based on CNN. Seven classical semantic segmentation models, including U-Net, UNet++, DeepLabv3, DeepLabv3+, Pyramid Attention Network (PAN), LinkNet, and Muti-scale Attention Net (MA-Net), with the encoders of ResNet50, MobineNetV2, or EfficientNet-B1, are constructed and compared based on the collected dataset. The integrated evaluation approach to ascertaining the optimal CNN model combining both subjective considerations and objective information is proposed since the selection from several CNN models is difficult in a complex problem with conflicting multiple criteria. UNet++ with the MobineNet v2 encoder obtains the best scores in the proposed integrated evaluation method and is selected to build the automated polyp-segmentation system. This study discovered that the semantic segmentation model has a high clinical value in the diagnosis of gastric polyps, and the integrated evaluation approach can provide an impartial and objective tool for the selection of numerous models. Our study can further advance the development of endoscopic gastrointestinal disease identification techniques, and the proposed evaluation technique has implications for mathematical model-based selection methods for clinical technologies.

Gastroesophageal reflux disease (GERD) has been a ubiquitous health problem for centuries. Its symptoms are hard to distinguish and endoscopists with less experience usually find it difficult to diagnose the severity of GERD, and this disease might progress to more severe diseases like Barrett’s esophagus without adequate treatment. Therefore, we proposed a multi-class classification system, which comprised a deep learning (DL) model and graphical user interface (GUI), to classify GERD grading from endoscopic images so as to provide finer predictions on erosive esophagus and easier assessment to the system. The Los Angeles Classification system (LACS) was selected as the standard for severity grading. We collected 3,654 white light (WL) esophagoscopic images from the database engine of Xiangyang Centre Hospital. We built the DL model using pre-trained convolutional neural network (CNN) model as the backbone, and different pre-trained models were used and compared. We also evaluated the effectiveness of applying data resampling and attention map to the DL model for optimizing model performance. Besides, data augmentation was also employed. After the best model was selected, we built the GUI using HuggingFace. Experimental results showed that DenseNet121 with oversampling and attention map achieved the best results with an accuracy of 0.7469, recall of 0.7057 and Cohen’s kappa of 0.7757. It was also discovered that the experimental groups using both techniques outperformed the others, while using DenseNet121 obtained better results considering all experimental groups. The model outputs were displayed in terms of the predicted label, probabilities for each grade and a heatmap containing highlighted attention. In conclusion, a multi-class DL classification system was developed for GERD grading classification, and it exhibited its potentially acceptable efficacy for GERD diagnosis based on the LACS.

Colorectal polyps are potential precursor lesions of colorectal cancer. Accurate classification of colorectal polyps during endoscopy is crucial for early diagnosis and effective treatment. Automatic and accurate classification of colorectal polyps based on convolutional neural networks (CNNs) during endoscopy is vital for assisting endoscopists in diagnosis and treatment. However, this task remains challenging due to difficulties in the data acquisition and annotation processes, the poor interpretability of the data output, and the lack of widespread acceptance of the CNN models by clinicians. This study proposes an innovative approach that utilizes gaze attention information from endoscopists as an auxiliary supervisory signal to train a CNN-based model for the classification of colorectal polyps. Gaze information from the reading of endoscopic images was first recorded through an eye-tracker. Then, the gaze information was processed and applied to supervise the CNN model’s attention via an attention consistency module. Comprehensive experiments were conducted on a dataset that contained three types of colorectal polyps. The results showed that EfficientNet_b1 with supervised gaze information achieved an overall test accuracy of 86.96%, a precision of 87.92%, a recall of 88.41%, an F1 score of 88.16%, the area under the receiver operating characteristic (ROC) curve (AUC) is 0.9022. All evaluation metrics surpassed those of EfficientNet_b1 without gaze information supervision. The class activation maps generated by the proposed network also indicate that the endoscopist’s gaze-attention information, as auxiliary prior knowledge, increases the accuracy of colorectal polyp classification, offering a new solution to the field of medical image analysis.