Automatic three-dimensional segmentation of endoscopic airway OCT images

ATN-Res2Unet: an advanced deep learning network for the elimination of saturation artifacts in endoscopy optical coherence tomography

Endoscopic optical coherence tomography (OCT) possesses the capability to non-invasively image internal lumens; however, it is susceptible to saturation artifacts arising from robust reflective structures. In this study, we introduce an innovative deep learning network, ATN-Res2Unet, designed to mitigate saturation artifacts in endoscopic OCT images. This is achieved through the integration of multi-scale perception, multi-attention mechanisms, and frequency domain filters. To address the challenge of obtaining ground truth in endoscopic OCT, we propose a method for constructing training data pairs. Experimental in vivo data substantiates the effectiveness of ATN-Res2Unet in reducing diverse artifacts while preserving structural information. Comparative analysis with prior studies reveals a notable enhancement, with average quantitative indicators increasing by 45.4-83.8%. Significantly, this study marks the inaugural exploration of leveraging deep learning to eradicate artifacts from endoscopic OCT images, presenting considerable potential for clinical applications.

CylinGCN: Cylindrical structures segmentation in 3D biomedical optical imaging by a contour-based graph convolutional network

Cylindrical organs, e.g., blood vessels, airways, and intestines, are ubiquitous structures in biomedical optical imaging analysis. Image segmentation of these structures serves as a vital step in tissue physiology analysis. Traditional model-driven segmentation methods seek to fit the structure by constructing a corresponding topological geometry based on domain knowledge. Classification-based deep learning methods neglect the geometric features of the cylindrical structure and therefore cannot ensure the continuity of the segmentation surface. In this paper, by treating the cylindrical structures as a 3D graph, we introduce a novel contour-based graph neural network for 3D cylindrical structure segmentation in biomedical optical imaging. Our proposed method, which we named CylinGCN, adopts a novel learnable framework that extracts semantic features and complex topological relationships in the 3D volumetric data to achieve continuous and effective 3D segmentation. Our CylinGCN consists of a multiscale 3D semantic feature extractor for extracting inter-frame multiscale semantic features, and a residual graph convolutional network (GCN) contour generator that combines the semantic features and cylindrical topological priors to generate segmentation contours. We tested the CylinGCN framework on two types of optical tomographic imaging data, small animal whole body photoacoustic tomography (PAT) and endoscopic airway optical coherence tomography (OCT), and the results show that CylinGCN achieves state-of-the-art performance. Code will be released at https://github.com/lzc-smu/CylinGCN.git.

Automatic 3D reconstruction of an anatomically correct upper airway from endoscopic long range OCT images

Endoscopic airway optical coherence tomography (OCT) is a non-invasive and high resolution imaging modality for the diagnosis and analysis of airway-related diseases. During OCT imaging of the upper airway, in order to reliably characterize its 3D structure, there is a need to automatically detect the airway lumen contour, correct rotational distortion and perform 3D airway reconstruction. Based on a long-range endoscopic OCT imaging system equipped with a magnetic tracker, we present a fully automatic framework to reconstruct the 3D upper airway model with correct bending anatomy. Our method includes an automatic segmentation method for the upper airway based on dynamic programming algorithm, an automatic initial rotation angle error correction method for the detected 2D airway lumen contour, and an anatomic bending method combined with the centerline detected from the magnetically tracked imaging probe. The proposed automatic reconstruction framework is validated on experimental datasets acquired from two healthy adults. The result shows that the proposed framework allows the full automation of 3D airway reconstruction from OCT images and thus reveals its potential to improve analysis efficiency of endoscopic OCT images.

Wavelet attention network for the segmentation of layer structures on OCT images

Automatic segmentation of layered tissue is critical for optical coherence tomography (OCT) image analysis. The development of deep learning techniques provides various solutions to this problem, while most existing methods suffer from topological errors such as outlier prediction and label disconnection. The channel attention mechanism is a powerful technique to address these problems due to its simplicity and robustness. However, it relies on global average pooling (GAP), which only calculates the lowest frequency component and leaves other potentially useful information unexplored. In this study, we use the discrete wavelet transform (DWT) to extract multi-spectral information and propose the wavelet attention network (WATNet) for tissue layer segmentation. The DWT-based attention mechanism enables multi-spectral analysis with no complex frequency-selection process and can be easily embedded to existing frameworks. Furthermore, the various wavelet bases make the WATNet adaptable to different tasks. Experiments on a self-collected esophageal dataset and two public retinal OCT dataset demonstrated that the WATNet achieved better performance compared to several widely used deep networks, confirming the advantages of the proposed method.

Automatic correction of the initial rotation angle error improves 3D reconstruction in endoscopic airway optical coherence tomography

Endoscopic airway optical coherence tomography (OCT) is an advanced imaging modality capable of capturing the internal anatomy and geometry of the airway. Due to fiber-optic catheter bending and friction, the rotation speed of the endoscopic probe is usually non-uniform: at each B-scan image, the initial rotation angle of the probe is easily misaligned with that of the previous slices. During the pullback operation, this initial rotation angle error (IRAE) will be accumulated and will result in distortion and deformation of the reconstructed 3D airway structure. Previous attempts to correct this error were mainly manual corrections, which are time-consuming and suffered from observer variation. In this paper, we present a method to correct the IRAE for anatomically improved visualization of the airway. Our method derived the rotation angular difference of adjacent B-scans by measuring their contour similarity and then tracks the IRAE by formulating its continuous drift as a graph-based problem. The algorithm was tested on a simulated airway contour dataset, and also on experimental datasets acquired by two different long range endoscopic airway OCT platforms. Effective and smooth compensation of the frame-by-frame initial angle difference was achieved. Our method has real-time capability and thus has the potential to improve clinical imaging efficiency.

Automatic 3-D segmentation and volumetric light fluence correction for photoacoustic tomography based on optimal 3-D graph search

Preclinical imaging with photoacoustic tomography (PAT) has attracted wide attention in recent years since it is capable of providing molecular contrast with deep imaging depth. The automatic extraction and segmentation of the animal in PAT images is crucial for improving image analysis efficiency and enabling advanced image post-processing, such as light fluence (LF) correction for quantitative PAT imaging. Previous automatic segmentation methods are mostly two-dimensional approaches, which failed to conserve the 3-D surface continuity because the image slices were processed separately. This discontinuity problem further hampers LF correction, which, ideally, should be carried out in 3-D due to spatially diffused illumination. Here, to solve these problems, we propose a volumetric auto-segmentation method for small animal PAT imaging based on the 3-D optimal graph search (3-D GS) algorithm. The 3-D GS algorithm takes into account the relation among image slices by constructing a 3-D node-weighted directed graph, and thus ensures surface continuity. In view of the characteristics of PAT images, we improve the original 3-D GS algorithm on graph construction, solution guidance and cost assignment, such that the accuracy and smoothness of the segmented animal surface were guaranteed. We tested the performance of the proposed method by conducting in vivo nude mice imaging experiments with a commercial preclinical cross-sectional PAT system. The results showed that our method successfully retained the continuous global surface structure of the whole 3-D animal body, as well as smooth local subcutaneous tumor boundaries at different development stages. Moreover, based on the 3-D segmentation result, we were able to simulate volumetric LF distribution of the entire animal body and obtained LF corrected PAT images with enhanced structural visibility and uniform image intensity.

Dynamic programming and automated segmentation of optical coherence tomography images of the neonatal subglottis: enabling efficient diagnostics to manage subglottic stenosis

Subglottic stenosis (SGS) is a challenging disease to diagnose in neonates. Long-range optical coherence tomography (OCT) is an optical imaging modality that has been described to image the subglottis in intubated neonates. A major challenge associated with OCT imaging is the lack of an automated method for image analysis and micrometry of large volumes of data that are acquired with each airway scan (1 to 2 Gb). We developed a tissue segmentation algorithm that identifies, measures, and conducts image analysis on tissue layers within the mucosa and submucosa and compared these automated tissue measurements with manual tracings. We noted small but statistically significant differences in thickness measurements of the mucosa and submucosa layers in the larynx (p  <  0.001), subglottis (p  =  0.015), and trachea (p  =  0.012). The automated algorithm was also shown to be over 8 times faster than the manual approach. Moderate Pearson correlations were found between different tissue texture parameters and the patient’s gestational age at birth, age in days, duration of intubation, and differences with age (mean age 17 days). Automated OCT data analysis is necessary in the diagnosis and monitoring of SGS, as it can provide vital information about the airway in real time and aid clinicians in making management decisions for intubated neonates.

Automatic proximal airway volume segmentation using optical coherence tomography for assessment of inhalation injury

BACKGROUND

Acute respiratory distress syndrome (ARDS) is a severe form of acute lung injury with a mortality rate of up to 40%. Early management of ARDS has been difficult due to the lack of sensitive imaging tools and robust analysis software. We previously designed an optical coherence tomography (OCT) system to evaluate mucosa thickness (MT) after smoke inhalation, but the analysis relied on manual segmentation. The aim of this study is to assess in vivo proximal airway volume (PAV) after inhalation injury using automated OCT segmentation and correlate the PAV to lung function for rapid indication of ARDS.

METHODS

Anesthetized female Yorkshire pigs (n = 14) received smoke inhalation injury (SII) and 40% total body surface area thermal burns. Measurements of PaO2-to-FiO2 ratio (PFR), peak inspiratory pressure (PIP), dynamic compliance, airway resistance, and OCT bronchoscopy were performed at baseline, postinjury, 24 hours, 48 hours, 72 hours after injury. A tissue segmentation algorithm based on graph theory was used to reconstruct a three-dimensional (3D) model of lower respiratory tract and estimate PAV. Proximal airway volume was correlated with PFR, PIP, compliance, resistance, and MT measurement using a linear regression model.

RESULTS

Proximal airway volume decreased after the SII: the group mean of proximal airway volume at baseline, postinjury, 24 hours, 48 hours, 72 hours were 20.86 cm (±1.39 cm), 17.61 cm (±0.99 cm), 14.83 cm (±1.20 cm), 14.88 cm (±1.21 cm), and 13.11 cm (±1.59 cm), respectively. The decrease in the PAV was more prominent in the animals that developed ARDS after 24 hours after the injury. PAV was significantly correlated with PIP (r = 0.48, p < 0.001), compliance (r = 0.55, p < 0.001), resistance (r = 0.35, p < 0.01), MT (r = 0.60, p < 0.001), and PFR (r = 0.34, p < 0.01).

CONCLUSION

Optical coherence tomography is a useful tool to quantify changes in MT and PAV after SII and burns, which can be used as predictors of developing ARDS at an early stage.

LEVEL OF EVIDENCE

Prognostic, level III.

Endoscopic Optical Coherence Tomography for Assessing Inhalation Airway Injury: A Technical Review

Diagnosis of inhalation injury has been clinically challenging. Currently, assessment of inhalation injury relies on subjective clinical exams and bronchoscopy, which provides little understanding of tissue conditions and results in limited prognostics. Endoscopic Optical coherence tomography (OCT) technology has been recently utilized in the airway for direct assessment of respiratory tract disorders and injuries. Endoscopic OCT is capable of capturing high-resolution images of tissue morphology 1-3 mm beneath the surface as well as the complex 3D anatomical shape. Previous studies indicate that changes in airway histopathology can be found in the OCT image almost immediately after inhalation of smoke and other toxic chemicals, which correlates well with histology and pulmonary function tests. This review summarizes the recent development of endoscopic OCT technology for airway imaging, current uses of OCT for inhalation injury, and possible future directions.