Despite all the expectations for photoacoustic endoscopy (PAE), there are still several technical issues that must be resolved before the technique can be successfully translated into clinics. Among these, electromagnetic interference (EMI) noise, in addition to the limited signal-to-noise ratio (SNR), have hindered the rapid development of related technologies. Unlike endoscopic ultrasound, in which the SNR can be increased by simply applying a higher pulsing voltage, there is a fundamental limitation in leveraging the SNR of PAE signals because they are mostly determined by the optical pulse energy applied, which must be within the safety limits. Moreover, a typical PAE hardware situation requires a wide separation between the ultrasonic sensor and the amplifier, meaning that it is not easy to build an ideal PAE system that would be unaffected by EMI noise. With the intention of expediting the progress of related research, in this study, we investigated the feasibility of deep-learning-based EMI noise removal involved in PAE image processing. In particular, we selected four fully convolutional neural network architectures, U-Net, Segnet, FCN-16s, and FCN-8s, and observed that a modified U-Net architecture outperformed the other architectures in the EMI noise removal. Classical filter methods were also compared to confirm the superiority of the deep-learning-based approach. Still, it was by the U-Net architecture that we were able to successfully produce a denoised 3D vasculature map that could even depict the mesh-like capillary networks distributed in the wall of a rat colorectum. As the development of a low-cost laser diode or LED-based photoacoustic tomography (PAT) system is now emerging as one of the important topics in PAT, we expect that the presented AI strategy for the removal of EMI noise could be broadly applicable to many areas of PAT, in which the ability to apply a hardware-based prevention method is limited and thus EMI noise appears more prominently due to poor SNR.
Early diagnosis is critical for treating bladder cancer, as this cancer is very aggressive and lethal if detected too late. To address this important clinical issue, a photoacoustic tomography (PAT)-based transabdominal imaging approach was suggested in previous reports, in which its in vivo feasibility was also demonstrated based on a small animal model. However, successful translation of this approach to real clinical settings would be challenging because the human bladder is located at a depth that far exceeds the typical penetration depth of PAT (∼3 cm for in vivo cases). In this study, we developed a tapered catheter-based, transurethral photoacoustic and ultrasonic endoscopic probe with a 2.8 mm outer diameter to investigate whether the well-known benefits of PAT can be harnessed to resolve unmet urological issues, including early diagnosis of bladder cancer. To demonstrate the in vivo imaging capability of the proposed imaging probe, we performed a rabbit model-based urinary system imaging experiment and acquired a 3D microvasculature map distributed in the wall of the urinary system, which is a first in PAT, to the best of our knowledge. We believe that the results strongly support the use of this transurethral imaging approach as a feasible strategy for addressing urological diagnosis issues.
In order for photoacoustic endoscopy to make a significant contribution to clinical gastroenterology, the relevant probes must be implemented in a form that can pass through the instrument channel of a clinical video endoscope or one that has its own camera-based self-steering capability at its distal section to effectively approach a target point. In line with the first direction, multiple probes with a diameter smaller than standard channel sizes have been reported in biomedical photoacoustics research thus far. However, no actual in vivo image acquisition via the instrument channel has been demonstrated yet. In this study, we developed a torque coil-based highly-flexible mini-probe that can provide coregistered optical resolution photoacoustic and ultrasonic images via the standard instrument channel of a video endoscope. With the probe, we were able to acquire in vivo photoacoustic and ultrasonic endoscopic images from a swine esophagus via the instrument channel of a clinical video endoscope, which is the first demonstration in biomedical photoacoustics to the best of our knowledge. In this paper, we describe several useful aspects that we learned from this study and discuss future hardware development directions that must be pursued for the full clinical translation of the mini-probe technology.
The minimally invasive application of photoacoustic (optoacoustic) tomography (PAT) has been mainly focused on gastrointestinal endoscopy and the imaging of cardiovascular and reproductive systems, such as the uterus, ovaries, and prostate, in relation to the diagnosis of atherosclerotic plaques (e.g., in coronary arteries) and reproductive cancers. However, the miniature probe technology involved could also make a considerable contribution to the diagnosis and post-treatment follow-ups of urinary diseases. PAT can provide a variety of anatomical, functional, and molecular information that is not producible with conventional imaging methods, such as MRI and ultrasound. Among the related clinical issues, the development of a new diagnostic paradigm for the early detection of bladder cancer is urgently needed, because it is known to be very aggressive and lethal if found after stage 2 (T2). In this study, we developed a transurethral photoacoustic and ultrasonic endoscopic probe with an outer diameter of 2.8 mm to contribute to the early diagnosis of bladder cancer in clinical urology. From a live rabbit, we successfully acquired the first high-resolution 3D vasculature map of more than 50% of the bladder wall, which we believe is a completely new type of image information never acquired before from a vertebrate urinary system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.