Data Stream Stabilization for Optical Coherence Tomography Volumetric Scanning

Liao, Guiqiu; Mora, Oscar Caravaca; Rosa, Benoît; Zanne, Philippe; Asch, Alexandre; Dall'Alba, Diego; Fiorini, Paolo; Mathelin, Michel de; Nageotte, Florent; Gora, Michalina J.

doi:10.1109/tmrb.2021.3093434

Cited by 4 publications

(7 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use two publicly-available endoscopic datasets (including gastrointestinal tract 8 (648 images) and sponge surface 9 (240 images)) for evaluating our trained model. Moreover, we also evaluate the correction performance using a vessel phantom pull-back sequence (336 images) collected from our home-built endoscopic SD-OCT system (840 nm, 80kHz, ~34 rps rotation speed).…”

Section: Results and Conclusionmentioning

confidence: 99%

“…Figure 1(a) presents a comparison between the results of our proposed method and three other representative approaches, including two feature-based methods 1,2 (referred to as DP and FT, respectively) and the CNN-based method 7 (referred to as De-NURD). Two public endoscopic OCT datasets 8,9 and a private dataset collected on our home-built endoscopic OCT system are used in this evaluation. Orange bars are their standard deviation (STD), which is commonly used to represent the correction performance 7 (smaller means better).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-time correction of nonuniform rotational distortion in endoscopic OCT

Zhang,

Yang,

Zhang

et al. 2024

Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXVIII

View full text Add to dashboard Cite

Endoscopic optical coherence tomography (OCT) is progressively used in endoluminal imaging because of its high scanning speed and near-cellular spatial resolution. Scanning of the endoscopic probe is implemented mechanically to achieve circumferential rotation and axial pullback. However, this scanning suffers from nonuniform rotational distortion (NURD) due to mechanical friction between the rotating probe and protecting sheath, irregular motor rotation, and so on. Correction of NURD is a prerequisite for endoscopic OCT imaging and its functional extensions, such as angiography and elastography. Previous work requires time-consuming feature tracking or cross-correlation calculations and thus sacrifices temporal resolution. In this work, we propose a cross-attention learning method for accelerating the NURD correction in endoscopic OCT. Our method is inspired by the recent success of the self-attention mechanism in natural language processing and computer vision. By leveraging its ability to model long-range dependencies, we can directly obtain the correlation between OCT A-lines at any distance, thus accelerating the NURD correction. We develop an endto-end stacked cross-attention network and design three types of optimization constraints. We compare our method with two traditional feature-based methods and a CNN-based method, on two publicly-available endoscopic OCT datasets and a private dataset collected on our home-built endoscopic OCT system. Our method achieved a ~3 times speedup to realtime (26±3 fps), and superior correction performance.

show abstract

Section: Results and Conclusionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Real-time correction of nonuniform rotational distortion in endoscopic OCT

Zhang,

Yang,

Zhang

et al. 2024

Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXVIII

View full text Add to dashboard Cite

show abstract

“…It acquires circumferential, cross-sectional images at 20 frames s −1 using a total of 2,048 axial (depth) scans per image. (2) A volumetric scanning OCT system for general luminal organ diagnosis [29]. It was built around the Axsun swept-source engine, with a 1310 nm center wavelength-swept source laser and 100 kHz A-line rate.…”

Section: Discussionmentioning

confidence: 99%

“…Because most of them are from clinical acquisition, the temporal and spatial characteristics of the distortion vectors are consistent with real application scenarios. We then use another two synthetic endoscopic datasets and two real publicly-available endoscopic datasets [28,29] for evaluating our trained model. Note that we train our model in one go and evaluate it on external test datasets.…”

Section: Datasets and Implementationsmentioning

confidence: 99%

See 1 more Smart Citation

Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT

Yang,

Zhang,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Nonuniform rotational distortion (NURD) correction is vital for endoscopic optical coherence tomography (OCT) imaging and its functional extensions, such as angiography and elastography. Current NURD correction methods require time-consuming feature tracking/registration or cross-correlation calculations and thus sacrifice temporal resolution. Here we propose a cross-attention learning method for the NURD correction in OCT. Our method is inspired by the recent success of the self-attention mechanism in natural language processing and computer vision. By leveraging its ability to model long-range dependencies, we can directly obtain the correlation between OCT A-lines at any distance, thus accelerating the NURD correction. We develop an end-to-end stacked cross-attention network and design three types of optimization constraints. We compare our method with two traditional feature-based methods and a CNN-based method on two publicly-available endoscopic OCT datasets. We further verify the NURD correction performance of our method on 3D stent reconstruction using a home-built endoscopic OCT system. Our method achieves a ×3 speedup to real time (26±3 fps), and superior correction performance.

show abstract

Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT

Zhang,

Yang,

Zhang

et al. 2023

Biomed. Opt. Express

View full text Add to dashboard Cite

Nonuniform rotational distortion (NURD) correction is vital for endoscopic optical coherence tomography (OCT) imaging and its functional extensions, such as angiography and elastography. Current NURD correction methods require time-consuming feature tracking/registration or cross-correlation calculations and thus sacrifice temporal resolution. Here we propose a cross-attention learning method for the NURD correction in OCT. Our method is inspired by the recent success of the self-attention mechanism in natural language processing and computer vision. By leveraging its ability to model long-range dependencies, we can directly obtain the spatial correlation between OCT A-lines at any distance, thus accelerating the NURD correction. We develop an end-to-end stacked cross-attention network and design three types of optimization constraints. We compare our method with two traditional feature-based methods and a CNN-based method on two publicly-available endoscopic OCT datasets. We further verify the NURD correction performance of our method on 3D stent reconstruction using a home-built endoscopic OCT system. Our method achieves a ∼3 × speedup to real time (26 ± 3 fps), and superior correction performance.

show abstract

Data Stream Stabilization for Optical Coherence Tomography Volumetric Scanning

Cited by 4 publications

References 50 publications

Real-time correction of nonuniform rotational distortion in endoscopic OCT

Real-time correction of nonuniform rotational distortion in endoscopic OCT

Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT

Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT

Contact Info

Product

Resources

About