KEYWORDS: Polyps, Optical coherence tomography, In vivo imaging, Deep learning, Visual process modeling, Tumor growth modeling, Error control coding, Resection, Endoscopy, Visualization
We present the development of an optical coherence tomography (OCT) catheter designed for in vivo subsurface imaging during colonoscopy, along with the results of a clinical pilot study involving 36 subjects to assess its ability to characterize colorectal polyps real-time. High-resolution cross-sectional OCT imaging of polyp microsctructure revealed distinct morphological structures that correlated with histological findings, including tubular adenoma, tubulovillous adenoma, sessile serrated polyps, and cancer. To enhance the in vivo diagnostic capabilities, we integrated a Vision Transformer (ViT) based deep learning classifier to differentiate between cancerous and complex benign polyps, and achieved a 100% accuracy for 5 test cases. Our findings suggest that the OCT catheter combined with deep learning complements standard-of-care imaging and has the potential to enhance real-time polyp characterization and improve clinical decision-making.
SignificancePhotoacoustic Doppler flowmetry offers quantitative blood perfusion information in addition to photoacoustic vascular contrast for rectal cancer assessment.AimWe aim to develop and validate a correlational Doppler flowmetry utilizing an acoustic resolution photoacoustic microscopy (AR-PAM) system for blood perfusion analysis.ApproachTo extract blood perfusion information, we implemented AR-PAM Doppler flowmetry consisting of signal filtering and conditioning, A-line correlation, and angle compensation. We developed flow phantoms and contrast agent to systemically investigate the flowmetry’s efficacy in a series of phantom studies. The developed correlational Doppler flowmetry was applied to images collected during in vivo AR-PAM for post-treatment rectal cancer evaluation.ResultsThe linearity and accuracy of the Doppler flow measurement system were validated in phantom studies. Imaging rectal cancer patients treated with chemoradiation demonstrated the feasibility of using correlational Doppler flowmetry to assess treatment response and distinguish residual cancer from cancer-free tumor bed tissue and normal rectal tissue.ConclusionsA new correlational Doppler flowmetry was developed and validated through systematic phantom evaluations. The results of its application to in vivo patients suggest it could be a useful addition to photoacoustic endoscopy for post-treatment rectal cancer assessment.
Data from our recent clinical trial of patients with adnexal/ovarian lesions revealed that total hemoglobin concentration (HbT) and blood oxygen saturation (%sO2) obtained from photoacoustic imaging (PAI) are important predictors of malignancy. A model utilizing the co-registered US and PAI HbT and %sO2 has achieved superior performance with the area under the receiver operating curve of 0.97 (95% CI: 0.932-1).
We present initial results of OCT images of human fallopian tubes obtained from miniature OCT catheters. Two OCT catheters were fabricated to image from the outside and inside of the fallopian tube. The OCT catheter used to image from outside has an outer diameter of 3.8 mm, a lateral resolution of ~10 um, and an axial resolution of 6 um. Special attention was paid to the fimbriated end. The smaller OCT catheter used to image inner mucosa layer has an outer diameter of 1.5 mm. 3D structures of the normal and malignant human fallopian tubes were revealed.
In this study, we propose to combine miniaturized optical coherence tomography (OCT) catheter with a residual neural network (ResNet)-based deep learning model for differentiation of normal from cancerous colorectal tissue in fresh ex vivo specimens. The OCT catheter has an outer diameter of 3.8 mm, a lateral resolution of ~10 um, and an axial resolution of 6 um. A customized ResNet-based neural network structure was trained on both benchtop and catheter images. An AUC of 0.97 was achieved to distinguish between normal and cancerous colorectal tissue when testing on the rest of catheter images.
Currently, post-therapy evaluation of colorectal cancer relies on functional MRI, which does not possess resolution and sensitivity well-suited for the task. Endorectal photoacoustic microscopy offers blood contrast and much higher resolution in imaging residual tumor vasculature. Correlational acoustic resolution photoacoustic doppler flowmetry with amplitude dependent masking was implemented, validated with simulations and phantom experiments, and put into use on colorectal patient scanning data. Doppler velocity map demonstrated potential in highlighting flow in the photoacoustic signal region while removing stationary absorber signals, showing vascular density and distribution in agreement with current understanding of colorectal cancer pathology.
In this study, we propose to combine miniaturized optical coherence tomography (OCT) catheter with pattern recognition (PR) OCT for differentiation of normal from neoplastic colorectal tissue in real-time. The OCT catheter has a lateral resolution of 17.15 um and an axial resolution of 6 um. The PR-OCT system is trained by RetinaNet for pattern recognition tasks. Our method leverages the recent advancement in object detection, which localizes and classifies the diagnostic features at real-time, and the integration of an endoscopy, which promises future in vivo studies. According to our previous reports, a sensitivity of 100% and specificity of 99.7% can be reached.
In photoacoustic tomography (PAT), measurement errors arise from optical fluence spatial and temporal variations caused by tissue optical absorption and scattering heterogeneities, system noise, and motion. These errors influence the estimation accuracy of blood oxygenation saturation (sO2). In this study, we introduce a sliding multi-pixel approach to mitigate the effect of measurement errors before computing sO2 maps. As a result, the sO2 estimation is both more accurate, as evaluated by residual fitting errors, as well as smoother. We conclude by presenting diagnostic results from PAT of 33 patients with ovarian masses imaged by our coregistered PAT and ultrasound system.
Homogeneous laser illumination is critical for side view photoacoustic tomography. In this paper, two homogeneous fiber side illumination methods are proposed by utilizing diffuser coating made of ultraviolet adhesive mixed with silica microspheres. One method is the gradient side diffuser, manufactured by dip coating fiber core with consecutive diffuser sections of different silica microsphere concentrations. The other method is the partially peeled-off diffuser, generated by peeling off part of the diffuser coating section on a single concentration fiber diffuser. Both methods show homogeneous laser side illumination according to simulation and experiment, with adjustable illumination length by design.
Rectal adenocarcinoma is a common cancer in the United States. Current standard of care techniques (colonoscopy and MRI) have notable drawbacks and surgeons have aggressively put most patients into surgical intervention. Here we have developed a new handheld co-registered ultrasound and acoustic-resolution photoacoustic endoscope (AR-PAE) to evaluate rectal cancer in vivo. The PAE - convolutional neuron network (PAE-CNN) models were trained, validated, and tested. Hyperparameters of PAE-CNN including convolutional kernel size, max pooling kernel size, convolution layers and fully connected layers which connect to amount of imaging information preserved were carefully tuned to optimize classification performance.
Rectal adenocarcinoma is a common cancer in the United States. Current standard of care techniques (colonoscopy and MRI) have notable drawbacks and surgeons have aggressively put most patients into surgical intervention. Developing an efficient and sensitive method to evaluate rectal cancer is urgently needed. Here we have developed a new handheld co-registered ultrasound and acoustic-resolution photoacoustic endoscope (AR-PAE) to evaluate human rectal cancer in vivo. Normal rectal ultrasound images revealed typical layered structure, while photoacoustic images resolved rich vascular supply of submucosa. Our pilot patient data suggest that AR-PAE is effective to distinguish rectal cancer from normal rectum.
Colorectal cancer is the second most common malignancy diagnosed globally and the 4th leading cause of cancer mortality. Critical gaps exist in diagnostic and surveillance imaging modalities for colorectal neoplasia. We have conducted a pilot study using a real-time co-registered photoacoustic (PAT) and ultrasound (US) tomography system. A total of 23 ex vivo human colorectal tissue samples (19 colon and 4 rectum) were imaged immediately after surgical resection. These results indicate potential of using PAT/US for future cancer screening and post-treatment surveillance of colon and rectum. The image resolution of the current system is low (~ 250 μm axial resolution) due to the commercial endo-cavity ultrasound transducer array (6 MHz central frequency, 80% bandwidth). To solve the problem of image resolution, we decoded the pin configuration of a high-frequency transducer array (15 MHz central frequency, 9-18 MHz bandwidth) and adapted it to our home-made 128 channels ultrasound pulsing and receiving system to perform high-frequency PAT/US imaging. We achieved a lateral resolution of ~ 150 μm and axial resolution of ~ 120 μm. We also imaged a post-treated human rectum sample to evaluate the system performance.
One of the challenges of quantitative Photoacoustic (PA) imaging is unmixing the optical absorption (μa) of the tissue from system response (C) and Grüneisen parameter (Γ). In this study, we have calculated the absorption coefficient and functional parameters, i.e. total hemoglobin (tHb) and oxygen saturation (sO2) of 5 blood tubes with sO2 values ranging from 24.9% to 97.6% at different depths in intralipid solution. Beer’s law is used to calculate the optical fluence in the target area. Initial values for μa and C×Γ are found by fitting a line to the log of PA beam data. These initial values are iteratively updated using a conjugate gradient method. This process is repeated for all 11 wavelengths. The absorption coefficient spectrum follows the molar extinction coefficient spectrum of deoxy hemoglobin for lower sO2 percentages, and it becomes closer to the spectrum of oxy hemoglobin when the sO2 percentage increases. The calculated absorption coefficients at 11 wavelengths are used to estimate the absolute value of the tHb and sO2 of each blood sample at different depths. The mean error of the estimated tHb values for blood tubes at all depths with respect to the real values are less than 13%. Moreover, the largest sO2 estimation error is 7.5% for the blood sample with sO2 of 24.9%. Our quantitative PA method performed well for the data collected from blood samples. We are investigating this method on our clinical data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.