Self-supervised monocular depth estimation for gastrointestinal endoscopy

LungDepth: Self-Supervised Multi-Frame Monocular Depth Estimation for Bronchoscopy

BACKGROUND

Bronchoscopy is an essential measure for conducting lung biopsies in clinical practice. It is crucial for advancing the intelligence of bronchoscopy to acquire depth information from bronchoscopic image sequences.

METHODS

A self-supervised multi-frame monocular depth estimation approach for bronchoscopy is constructed. Networks are trained by minimising the photometric reprojection error between the target frame and the reconstructed target frame. The adaptive dual attention module and the details emphasis module are introduced to better capture the edge contour and internal details. In addition, the approach is evaluated on a self-made dataset and compared against other established methods.

RESULTS

Experimental results demonstrate that the proposed method outperforms other self-supervised monocular depth estimation approaches in both quantitative measurement and qualitative analysis.

CONCLUSION

Our monocular depth estimation approach for bronchoscopy achieves superior performance in terms of error and accuracy, and passes physical model validations, which can facilitate further research into intelligent bronchoscopic procedures.

MonoLoT: Self-Supervised Monocular Depth Estimation in Low-Texture Scenes for Automatic Robotic Endoscopy

The self-supervised monocular depth estimation framework is well-suited for medical images that lack ground-truth depth, such as those from digestive endoscopes, facilitating navigation and 3D reconstruction in the gastrointestinal tract. However, this framework faces several limitations, including poor performance in low-texture environments, limited generalisation to real-world datasets, and unclear applicability in downstream tasks like visual servoing. To tackle these challenges, we propose MonoLoT, a self-supervised monocular depth estimation framework featuring two key innovations: point matching loss and batch image shuffle. Extensive ablation studies on two publicly available datasets, namely C3VD and SimCol, have shown that methods enabled by MonoLoT achieve substantial improvements, with accuracies of 0.944 on C3VD and 0.959 on SimCol, surpassing both depth-supervised and self-supervised baselines on C3VD. Qualitative evaluations on real-world endoscopic data underscore the generalisation capabilities of our methods, outperforming both depth-supervised and self-supervised baselines. To demonstrate the feasibility of using monocular depth estimation for visual servoing, we have successfully integrated our method into a proof-of-concept robotic platform, enabling real-time automatic intervention and control in digestive endoscopy. In summary, our method represents a significant advancement in monocular depth estimation for digestive endoscopy, overcoming key challenges and opening promising avenues for medical applications.

Self-Supervised Lightweight Depth Estimation in Endoscopy Combining CNN and Transformer

In recent years, an increasing number of medical engineering tasks, such as surgical navigation, pre-operative registration, and surgical robotics, rely on 3D reconstruction techniques. Self-supervised depth estimation has attracted interest in endoscopic scenarios because it does not require ground truth. Most existing methods depend on expanding the size of parameters to improve their performance. There, designing a lightweight self-supervised model that can obtain competitive results is a hot topic. We propose a lightweight network with a tight coupling of convolutional neural network (CNN) and Transformer for depth estimation. Unlike other methods that use CNN and Transformer to extract features separately and then fuse them on the deepest layer, we utilize the modules of CNN and Transformer to extract features at different scales in the encoder. This hierarchical structure leverages the advantages of CNN in texture perception and Transformer in shape extraction. In the same scale of feature extraction, the CNN is used to acquire local features while the Transformer encodes global information. Finally, we add multi-head attention modules to the pose network to improve the accuracy of predicted poses. Experiments demonstrate that our approach obtains comparable results while effectively compressing the model parameters on two datasets.

Improving image classification of gastrointestinal endoscopy using curriculum self-supervised learning

Endoscopy, a widely used medical procedure for examining the gastrointestinal (GI) tract to detect potential disorders, poses challenges in manual diagnosis due to non-specific symptoms and difficulties in accessing affected areas. While supervised machine learning models have proven effective in assisting clinical diagnosis of GI disorders, the scarcity of image-label pairs created by medical experts limits their availability. To address these limitations, we propose a curriculum self-supervised learning framework inspired by human curriculum learning. Our approach leverages the HyperKvasir dataset, which comprises 100k unlabeled GI images for pre-training and 10k labeled GI images for fine-tuning. By adopting our proposed method, we achieved an impressive top-1 accuracy of 88.92% and an F1 score of 73.39%. This represents a 2.1% increase over vanilla SimSiam for the top-1 accuracy and a 1.9% increase for the F1 score. The combination of self-supervised learning and a curriculum-based approach demonstrates the efficacy of our framework in advancing the diagnosis of GI disorders. Our study highlights the potential of curriculum self-supervised learning in utilizing unlabeled GI tract images to improve the diagnosis of GI disorders, paving the way for more accurate and efficient diagnosis in GI endoscopy.