Channel separation-based network for the automatic anatomical site recognition using endoscopic images

Deep learning-based differentiation of ventricular septal defect from tetralogy of Fallot in fetal echocardiography images

BACKGROUND

Congenital heart disease (CHD) seriously affects children's health and quality of life, and early detection of CHD can reduce its impact on children's health. Tetralogy of Fallot (TOF) and ventricular septal defect (VSD) are two types of CHD that have similarities in echocardiography. However, TOF has worse diagnosis and higher morality than VSD. Accurate differentiation between VSD and TOF is highly important for administrative property treatment and improving affected factors' diagnoses.

OBJECTIVE

TOF and VSD were differentiated using convolutional neural network (CNN) models that classified fetal echocardiography images.

METHODS

We collected 105 fetal echocardiography images of TOF and 96 images of VSD. Four CNN models, namely, VGG19, ResNet50, NTS-Net, and the weakly supervised data augmentation network (WSDAN), were used to differentiate the two congenital heart diseases. The performance of these four models was compared based on sensitivity, accuracy, specificity, and AUC.

RESULTS

VGG19 and ResNet50 performed similarly, with AUCs of 0.799 and 0.802, respectively. A superior performance was observed with NTS-Net and WSDAN specific for fine-grained image categorization tasks, with AUCs of 0.823 and 0.873, respectively. WSDAN had the best performance among all models tested.

CONCLUSIONS

WSDAN exhibited the best performance in differentiating between TOF and VSD and is worthy of further clinical popularization.

Evaluation of deep learning methods for early gastric cancer detection using gastroscopic images

BACKGROUND

A timely diagnosis of early gastric cancer (EGC) can greatly reduce the death rate of patients. However, the manual detection of EGC is a costly and low-accuracy task. The artificial intelligence (AI) method based on deep learning is considered as a potential method to detect EGC. AI methods have outperformed endoscopists in EGC detection, especially with the use of the different region convolutional neural network (RCNN) models recently reported. However, no studies compared the performances of different RCNN series models.

OBJECTIVE

This study aimed to compare the performances of different RCNN series models for EGC.

METHODS

Three typical RCNN models were used to detect gastric cancer using 3659 gastroscopic images, including 1434 images of EGC: Faster RCNN, Cascade RCNN, and Mask RCNN.

RESULTS

The models were evaluated in terms of specificity, accuracy, precision, recall, and AP. Fast RCNN, Cascade RCNN, and Mask RCNN had similar accuracy (0.935, 0.938, and 0.935). The specificity of Cascade RCNN was 0.946, which was slightly higher than 0.908 for Faster RCNN and 0.908 for Mask RCNN.

CONCLUSION

Faster RCNN and Mask RCNN place more emphasis on positive detection, and Cascade RCNN places more emphasis on negative detection. These methods based on deep learning were conducive to helping in early cancer diagnosis using endoscopic images.

Deep learning for differentiating benign from malignant tumors on breast-specific gamma image

BACKGROUND

Breast diseases are a significant health threat for women. With the fast-growing BSGI data, it is becoming increasingly critical for physicians to accurately diagnose benign as well as malignant breast tumors.

OBJECTIVE

The purpose of this study is to diagnose benign and malignant breast tumors utilizing the deep learning model, with the input of breast-specific gamma imaging (BSGI).

METHODS

A benchmark dataset including 144 patients with benign tumors and 87 patients with malignant tumors was collected and divided into a training dataset and a test dataset according to the ratio of 8:2. The convolutional neural network ResNet18 was employed to develop a new deep learning model. The model proposed was compared with neural network and autoencoder models. Accuracy, specificity, sensitivity and ROC were used to evaluate the performance of different models.

RESULTS

The accuracy, specificity and sensitivity of the model proposed are 99.1%, 98.8% and 99.3% respectively, which achieves the best performance among all methods. Additionally, the Grad-CAM method is used to analyze the interpretability of the diagnostic results based on the deep learning model.

CONCLUSION

This study demonstrates that the proposed deep learning method could help physicians diagnose benign and malignant breast tumors quickly as well as reliably.

Where do we stand in AI for endoscopic image analysis? Deciphering gaps and future directions

Recent developments in deep learning have enabled data-driven algorithms that can reach human-level performance and beyond. The development and deployment of medical image analysis methods have several challenges, including data heterogeneity due to population diversity and different device manufacturers. In addition, more input from experts is required for a reliable method development process. While the exponential growth in clinical imaging data has enabled deep learning to flourish, data heterogeneity, multi-modality, and rare or inconspicuous disease cases still need to be explored. Endoscopy being highly operator-dependent with grim clinical outcomes in some disease cases, reliable and accurate automated system guidance can improve patient care. Most designed methods must be more generalisable to the unseen target data, patient population variability, and variable disease appearances. The paper reviews recent works on endoscopic image analysis with artificial intelligence (AI) and emphasises the current unmatched needs in this field. Finally, it outlines the future directions for clinically relevant complex AI solutions to improve patient outcomes.

Artificial Intelligence for Upper Gastrointestinal Endoscopy: A Roadmap from Technology Development to Clinical Practice

Stomach cancer is the third deadliest type of cancer in the world (0.86 million deaths in 2017). In 2035, a 20% increase will be observed both in incidence and mortality due to demographic effects if no interventions are foreseen. Upper GI endoscopy (UGIE) plays a paramount role in early diagnosis and, therefore, improved survival rates. On the other hand, human and technical factors can contribute to misdiagnosis while performing UGIE. In this scenario, artificial intelligence (AI) has recently shown its potential in compensating for the pitfalls of UGIE, by leveraging deep learning architectures able to efficiently recognize endoscopic patterns from UGIE video data. This work presents a review of the current state-of-the-art algorithms in the application of AI to gastroscopy. It focuses specifically on the threefold tasks of assuring exam completeness (i.e., detecting the presence of blind spots) and assisting in the detection and characterization of clinical findings, both gastric precancerous conditions and neoplastic lesion changes. Early and promising results have already been obtained using well-known deep learning architectures for computer vision, but many algorithmic challenges remain in achieving the vision of AI-assisted UGIE. Future challenges in the roadmap for the effective integration of AI tools within the UGIE clinical practice are discussed, namely the adoption of more robust deep learning architectures and methods able to embed domain knowledge into image/video classifiers as well as the availability of large, annotated datasets.