Automatic stent struts detection in optical coherence tomography based on a multiple attention convolutional model.

Objective.Intravascular optical coherence tomography is a useful tool to assess stent adherence and dilation, thus guiding percutaneous coronary intervention and minimizing the risk of surgery. However, each pull-back OCT images may contain thousands of stent struts, which are tiny and dense, making manual stent labeling slow and costly for medical resources.Approach. This paper proposed a multiple attention convolutional model for automatic stent struts detection of OCT images. Multiple attention mechanisms were utilized to strengthen the feature extraction and feature fusion capabilities. In addition, to precisely detect tiny stent struts, the model integrated multiple anchor frames to predict targets in the output.Main results. The model was trained in 4625 frames OCT images of 37 patients and tested in 1156 frames OCT images of 9 patients, and achieved a precision of 0.9790 and a recall of 0.9541, which were significantly better than mainstream convolutional models. In terms of detection speed, the model achieved 25.2 ms per image. OCT images from different collection systems, collection times, and challenging scenarios were experimentally tested, and the model demonstrated stable robustness, achieving precision and recall higher than 0.9630. Meanwhile, clear 3D construction of the stent was achieved.Significance. In conclusion, the proposed model solves the problems of slow manual analysis and occupying a large amount of medical manpower resources. It enhances the detection efficiency of tiny and dense stent struts, thus facilitating the application of OCT quantitative analysis in real clinical scenarios.

Intravascular Optical Coherence Tomography Utilizing a Miniature Piezoelectric-Driven Probe.

Intravascular optical coherence tomography (IV-OCT) is crucial for evaluating lumen dimensions and guiding interventional procedures. However, traditional catheter-based IV-OCT faces challenges in achieving precise and full-field 360° imaging in tortuous vessels. Current IV-OCT catheters that employ proximal actuators and torque coils are susceptible to non-uniform rotational distortion (NURD) in tortuous vessels, while distal micromotor-driven catheters struggle with complete 360° imaging due to wiring artifacts. In this study, we developed a miniature optical scanning probe with an integrated piezoelectric-driven fiber optic slip ring (FOSR) to facilitate smooth navigation and precise imaging within tortuous vessels. The FOSR features a coil spring-wrapped optical lens serving as a rotor, enabling efficient 360° optical scanning. The structurally-and-functionally-integrated design significantly streamlines the probe (with a diameter of 0.85 mm and a length of 7 mm) while maintaining an excellent rotational speed of 10,000 rpm. High-precision 3D printing technology ensures accurate optical alignment of the fiber and lens inside the FOSR, with a maximum insertion loss variation of 2.67 dB during probe rotation. Finally, a vascular model demonstrated smooth probe insertion into the carotid artery, and imaging of oak leaf, metal rod phantoms, and ex vivo porcine vessels verified its capabilities for precise optical scanning, comprehensive 360° imaging, and artifact elimination. The FOSR probe exhibits small size, rapid rotation, and optical precision scanning, rendering it exceptionally promising for cutting-edge intravascular optical imaging techniques.

Automatic bifurcation detection utilizing pullback characteristics of bifurcation in intravascular optical coherence tomography.

Bifurcation detection in coronary arteries is significant since it influences the treatment strategy selection and optimization. Bifurcations are also reliable landmarks for image registration. Intravascular optical coherence tomography (IVOCT) is a high-resolution imaging modality that is very useful in percutaneous coronary intervention stenting optimization. We present a bifurcation identification method utilizing pullback characteristics for IVOCT, which can effectively identify the bifurcations with a small size. The longitudinal view of the pullback will appear as an outward discontinuity in the bifurcation area. By detecting this discontinuity, bifurcation can be identified with high accuracy. We also use the normal vectors method to extract the ostium of bifurcation. We compare the proposed method with the widely-used distance transformation method by clinical 5302 IVOCT images from 22 pullbacks. The average metrics of true positive rate (TPR), true negative rate (TNR), positive predictive value (PPV), and negative predictive value (NPV) for the proposed method are 86.97%, 98.50%, 85.56%, and 98.67%, respectively. TPR, PPV, and NPV by the proposed method are improved by 40.24%, 9.31%, 3.90%, and TNR is on par compared with the distance transformation method. Especially in the small bifurcation identification, TPR of the proposed method is 64.71% higher than the distance transformation method with a bifurcation area ratio less than 0.2.

A pilot and ex-vivo study of examination of endometrium tissue by catheter based optical coherence tomography.

OBJECTIVE: This study aimed to distinguish ex-vivo normal and abnormal endometrium tissue samples histologically by catheter based optical coherence tomography (OCT). METHODS: A total of 72 ex-vivo endometrium specimens were obtained from June 2018 to March 2021 and were imaged fresh after hysterectomy. The scanned region of endometrium was excised for histological examination and endometrium OCT images were precisely compared to corresponding histological images. Meanwhile endometrium OCT images were analyzed quantitatively with intensity of backscattered light in region of interest (ROI) and maximum penetration depth of the OCT signal. Blinded qualitative analysis on endometrium OCT images was performed by 2 assessors to determine accuracy rate and inter-rating reliability on the histopathological diagnosis. RESULTS: OCT images were performed successfully in 72 endometrium specimens. Five endometrium specimens developed OCT interpretation criteria and the rest 67 endometrium specimens validated qualitatively and analyzed quantitatively. We defined an OCT criteria to distinguish normal endometrium and five different abnormal endometrium phases including proliferative endometrium, secretory phase endometrium, atrophic endometrium, endometrial hyperplasia with atypia and endometrial carcinoma based on OCT imaging features. The overall diagnosis accuracy achieved by the two assessors was 72.4% based on the OCT criteria. The inter-rater reliability between assessors on overall OCT images was substantial (Kendall τb of 0.720, p < 0.05). The changes in ROI minimum intensity, ROI maximum intensity, ROI average intensity and OCT signal maximum penetration depth of five different abnormal endometrium phases were significantly different (all p < 0.001). These parameters of endometrium carcinomas were significantly different from the other four endometrium phases (all p < 0.001). CONCLUSION: OCT has the advantage of noninvasive and rapid diagnosis, which can contribute to the diagnosis of endometrial cancer and will be an indispensable complement to traditional biopsy. Future studies in vivo with larger samples are needed to confirm this conclusion.

Analysis and reduction of noise-induced depolarization in catheter based polarization sensitive optical coherence tomography.

In catheter based polarization sensitive optical coherence tomography (PS-OCT), a optical fiber with a rapid rotation in the catheter can cause low signal-to-noise ratio (SNR), polarization state instability, phase change of PS-OCT signals and then heavy noise-induced depolarization, which has a strong impact on the phase retardation measurement of the sample. In this paper, we analyze the noise-induced depolarization and find that the effect of depolarization can be reduced by polar decomposition after incoherent averaging in the Mueller matrix averaging (MMA) method. Namely, MMA can reduce impact of noise on phase retardation mapping. We present a Monte Carlo method based on PS-OCT to numerically describe noise-induced depolarization effect and contrast phase retardation imaging results by MMA and Jones matrix averaging (JMA) methods. The peak signal to noise ratio (PSNR) of simulated images processed by MMA is higher than about 8.9 dB than that processed by JMA. We also implement experiments of multiple biological tissues using the catheter based PS-OCT system. From the simulation and experimental results, we find the polarization contrasts processed by the MMA are better than those by JMA, especially at areas with high depolarization, because the MMA can reduce effect of noise-induced depolarization on the phase retardation measurement.

Automatic lumen segmentation using uniqueness of vascular connected region for intravascular optical coherence tomography.

We present an automatic lumen segmentation method using uniqueness of connected region for intravascular optical coherence tomography (IVOCT), which can effectively remove the effect on lumen segmentation caused by blood artifacts. Utilizing the uniqueness of vascular wall on A-lines, we detect the A-lines shared by multiple connected regions, identify connected regions generated by blood artifacts using traversal comparison of connected regions' location, shared ratio and area ratio and then remove all artifacts. We compare these three methods by 216 challenging images with severe blood artifacts selected from clinical 1076 IVOCT images. The metrics of the proposed method are evaluated including Dice index, Jaccard index and accuracy of 94.57%, 90.12%, 98.02%. Compared with automatic lumen segmentation based on the previous morphological feature method and widely used dynamic programming method, the metrics of the proposed method are significantly enhanced, especially in challenging images with severe blood artifacts.

Three-dimensional spatial reconstruction of coronary arteries based on fusion of intravascular optical coherence tomography and coronary angiography.

We present a three-dimensional (3D) spatial reconstruction of coronary arteries based on fusion of intravascular optical coherence tomography (IVOCT) and digital subtraction angiography (DSA). Centerline of vessel in DSA images is exacted by multi-scale filtering, adaptive segmentation, morphology thinning and Dijkstra's shortest path algorithm. We apply the cross-correction between lumen shapes of IVOCT and DSA images and match their stenosis positions to realize co-registration. By matching the location and tangent direction of the vessel centerline of DSA images and segmented lumen coordinates of IVOCT along pullback path, 3D spatial models of vessel lumen are reconstructed. Using 1121 distinct positions selected from eight vessels, the correlation coefficient between 3D IVOCT model and DSA image in measuring lumen radius is 0.94% and 97.7% of the positions fall within the limit of agreement by Bland-Altman analysis, which means that the 3D spatial reconstruction IVOCT models and DSA images have high matching level.

Catheter-Based Polarization Sensitive Optical Coherence Tomography Using Similar Mueller Matrix Method.

OBJECTIVE: Research of catheter-based polarization sensitive optical coherence tomography (PS-OCT) is a challenging field. In this paper, we present a new polarization determination method, similar Mueller matrix (SMM) method, for a catheter-based PS-OCT system using a standard clinical catheter probe with an outer diameter of 0.9 mm. METHODS: The SMM method can remove the diattenuation and depolarization compositions by polar decomposition. By constructing the similarity between the measured Mueller matrices and sample matrices, the phase retardance of the sample can be determined from the trace of the measured matrices. RESULTS: In the experiments, we find that images processed by the SMM method without any averaging or phase correction have a better polarization contrast of multiple biological tissues than those by the Jones matrix based method. We also preliminarily achieve phase retardance imaging of the ex vivo porcine cardiac blood vessel. CONCLUSION: Compared with the Jones matrix based method, the presented SMM method can provide a more robust birefringence imaging of biological tissues under low signal-to-noise ratio, depolarization, diattenuation, and phase instability. SIGNIFICANCE: The SMM method has a potential to become a widely accepted polarization determination method for catheter-based PS-OCT.