Search

Identifying complete response (CR) after rectal cancer preoperative treatment is critical to deciding subsequent management. Imaging techniques, including endorectal ultrasound and MRI, have been investigated but have low negative predictive values. By imaging post-treatment vascular normalization using photoacoustic microscopy, we hypothesize that co-registered ultrasound and photoacoustic imaging will better identify complete responders. In this study, we used in vivo data from 21 patients to develop a robust deep learning model (US-PAM DenseNet) based on co-registered dual-modality ultrasound (US) and photoacoustic microscopy (PAM) images and individualized normal reference images. We tested the model’s accuracy in differentiating malignant from non-cancer tissue. Compared to models based on US alone (classification accuracy 82.9 ± 1.3%, AUC 0.917(95%CI: 0.897-0.937)), the addition of PAM and normal reference images improved the model performance significantly (accuracy 92.4 ± 0.6%, AUC 0.968(95%CI: 0.960-0.976)) without increasing model complexity. Additionally, while US models could not reliably differentiate images of cancer from those of normalized tissue with complete treatment response, US-PAM DenseNet made accurate predictions from these images. For use in the clinical settings, US-PAM DenseNet was extended to classify entire US-PAM B-scans through sequential ROI classification. Finally, to help focus surgical evaluation in real time, we computed attention heat maps from the model predictions to highlight suspicious cancer regions. We conclude that US-PAM DenseNet could improve the clinical care of rectal cancer patients by identifying complete responders with higher accuracy than current imaging techniques.

"Difference imaging," which reconstructs target optical properties using measurements with and without target information, is often used in diffuse optical tomography (DOT) in vivo imaging. However, taking additional reference measurements is time consuming, and mismatches between the target medium and the reference medium can cause inaccurate reconstruction.We aim to streamline the data acquisition and mitigate the mismatch problems in DOT difference imaging using a deep learning-based approach to generate data from target measurements only.We train an artificial neural network to output data for difference imaging from target measurements only. The model is trained and validated on simulation data and tested with simulations, phantom experiments, and clinical data from 56 patients with breast lesions.The proposed method has comparable performance to the traditional approach using measurements without mismatch between the target side and the reference side, and it outperforms the traditional approach using measurements when there is a mismatch. It also improves the target-to-artifact ratio and lesion localization in patient data.The proposed method can simplify the data acquisition procedure, mitigate mismatch problems, and improve reconstructed image quality in DOT difference imaging.

Curvilinear endocavity ultrasound images capture a wide field of view with a miniature probe. In adapting photoacoustic imaging (PAI) to work with such ultrasound systems, light delivery is challenged by the trade-off between image quality and laser safety concerns. Here, we present two novel, to the best of our knowledge, designs based on cylindrical lenses that are optimized for transvaginal PAI B-scan imaging. Our simulation and experimental results demonstrate that, compared to conventional light delivery methods for PAI imaging, the proposed designs are safer for higher pulse energies and provide deeper imaging and a wider lateral field of view. The proposed designs could also improve the performance of endoscopic co-registered ultrasound/photoacoustic imaging in other clinical applications.

Diffuse optical tomography (DOT) is a promising technique that provides functional information related to tumor angiogenesis. However, reconstructing the DOT function map of a breast lesion is an ill-posed and underdetermined inverse process. A co-registered ultrasound (US) system that provides structural information about the breast lesion can improve the localization and accuracy of DOT reconstruction. Additionally, the well-known US characteristics of benign and malignant breast lesions can further improve cancer diagnosis based on DOT alone. Inspired by a fusion model deep learning approach, we combined US features extracted by a modified VGG-11 network with images reconstructed from a DOT deep learning auto-encoder-based model to form a new neural network for breast cancer diagnosis. The combined neural network model was trained with simulation data and fine-tuned with clinical data: it achieved an AUC of 0.931 (95% CI: 0.919-0.943), superior to those achieved using US images alone (0.860) or DOT images alone (0.842).

Optical coherence tomography (OCT) can differentiate normal colonic mucosa from neoplasia, potentially offering a new mechanism of endoscopic tissue assessment and biopsy targeting, with a high optical resolution and an imaging depth of ~1 mm. Recent advances in convolutional neural networks (CNN) have enabled application in ophthalmology, cardiology, and gastroenterology malignancy detection with high sensitivity and specificity. Here, we describe a miniaturized OCT catheter and a residual neural network (ResNet)-based deep learning model manufactured and trained to perform automatic image processing and real-time diagnosis of the OCT images. The OCT catheter has an outer diameter of 3.8 mm, a lateral resolution of ~7 μm, and an axial resolution of ~6 μm. A customized ResNet is utilized to classify OCT catheter colorectal images. An area under the receiver operating characteristic (ROC) curve (AUC) of 0.975 is achieved to distinguish between normal and cancerous colorectal tissue images.

Objectives To investigate the laser safety of photoacoustic imaging. In photoacoustic imaging, a pulsed laser of several nanoseconds is used to illuminate biological tissue, and photoacoustic waves generated by optical absorption are used to form images of the tissue. Photoacoustic imaging is emerging in clinical applications; however, its potential use in reproductive medicine has yet to be reported. Design Assessment of photoacoustic laser safety before its adoption by clinical reproductive medicine. Setting Academic medical center. Animals Blastocyst-stage mouse embryos. Interventions Potential DNA damage of photoacoustic laser exposure on preimplantation mouse blastocyst stage embryos was examined. Different embryos groups were exposed to either 5- or 10-minute 15-Hz laser doses (typical clinical doses) and 1-minute 1-kHz laser dose (significantly higher dose), respectively. Main Outcome Measures A terminal deoxynucleotidyl transferase dUTP nick end labeling (TUNEL) assay was used to identify the rate of DNA damage in the laser-exposed blastocysts. Results The negative control blastocyst group (no laser exposure) had a mean of 10.7 TUNEL-positive nuclei. The 5- and 10-minute 15-Hz laser−exposed groups had a mean of 11.25 and 12.89 TUNEL-positive nuclei, respectively. The embryos exposed to the 1-kHz laser for 1 minute had an average mean of 12.0 TUNEL-positive nuclei. Conclusion We demonstrated that typical lasers and exposure times used for photoacoustic imaging do not induce increased cell death in mouse blastocysts.

We demonstrate a novel fiber endface photoacoustic (PA) generator using infrared (IR) 144 laser dye dispersed within an ultraviolet adhesive. The generator provides a wide acoustic bandwidth in the transducer frequency range of 2–7 MHz, high thermal conversion efficiency ( > 90 % ), good PA signal controllability (well-controlled IR 144 concentration), and high feasibility (simple procedures). Through a series of experimental validations, we show that this fiber-based endface PA generator can be a useful tool for a broad range of biomedical applications such as calibrating the local absorption coefficient of biological tissue for quantitative PA tomography.

PURPOSE: To assess the impact of adjunctive ultrasound guided diffuse optical tomography (US-guided DOT) on BI-RADS assessment in women undergoing US-guided breast biopsy. METHOD: This prospective study enrolled women referred for US-guided breast biopsy between 3/5/2019 and 3/19/2020. Participants underwent US-guided DOT immediately before biopsy. The US-guided DOT acquisition generated average maximum total hemoglobin (HbT) spatial maps and quantitative HbT values. Four radiologists blinded to histopathology assessed conventional imaging (CI) to assign a CI BI-RADS assessment and then integrated DOT information in assigning a CI&DOT BI-RADS assessment. HbT was compared between benign and malignant lesions using an ANOVA test and Tukey’s test. Benign biopsies were tabulated, deeming BI-RADS ≥ 4A as positive. Reader agreement was assessed. RESULTS: Among 61 included women (mean age 48 years), biopsy demonstrated 15 (24.6%) malignant and 46 (75.4%) benign lesions. Mean HbT was 55.3 ± 22.6 μM in benign lesions versus 85.4 ± 15.6 μM in cancers (p < .001). HbT threshold of 78.5 μM achieved sensitivity 80% (12/15) and specificity 89% (41/46) for malignancy. Across readers and patients, 197 pairs of CI BI-RADS and CI&DOT BI-RADS assessments were assigned. Adjunctive US-guided DOT achieved a net decrease in 23.5% (31/132) of suspicious (CI BI-RADS ≥ 4A) assessments of benign lesions (34 correct downgrades and 3 incorrect upgrades). 38.3% (31/81) of 4A assessments were appropriately downgraded. No cancer was downgraded to a non-actionable assessment. Interreader agreement analysis demonstrated kappa = 0.48–0.53 for CI BI-RADS and kappa = 0.28–0.44 for CI&DOT BI-RADS. CONCLUSIONS: Integration of US-guided DOT information achieved a 23.5% reduction in suspicious BI-RADS assessments for benign lesions. Larger studies are warranted, with attention to improved reader agreement.

Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated potential value for breast cancer diagnosis and treatment response assessment. However, in clinical use, the chest wall, poor probe-tissue contact, and tissue heterogeneity can all cause image artifacts. These image artifacts, appearing commonly as hot spots in the non-lesion regions (edge artifacts), can decrease the reconstruction accuracy and cause misinterpretation of lesion images. Here we introduce an iterative, connected component analysis-based image artifact reduction algorithm. A convolutional neural network (CNN) is used to segment co-registered US images to extract the lesion location and size to guide the artifact reduction. We demonstrate its performance using Monte Carlo simulations on VICTRE digital breast phantoms and breast patient images. In simulated tissue mismatch models, this algorithm successfully reduces edge artifacts without significantly changing the reconstructed target absorption coefficients. With clinical data it improves the optical contrast between malignant and benign groups, from 1.55 without artifact reduction to 1.91 with artifact reduction. The proposed algorithm has a broad range of applications in other modality-guided DOT imaging.

Significance: In general, image reconstruction methods used in diffuse optical tomography (DOT) are based on diffusion approximation, and they consider the breast tissue as a homogenous, semi-infinite medium. However, the semi-infinite medium assumption used in DOT reconstruction is not valid when the chest wall is underneath the breast tissue. Aim: We aim to reduce the chest wall’s effect on the estimated average optical properties of breast tissue and obtain accurate forward model for DOT reconstruction. Approach: We propose a deep learning-based neural network approach where a convolution neural network (CNN) is trained to simultaneously obtain accurate optical property values for both the breast tissue and the chest wall. Results: The CNN model shows great promise in reducing errors in estimating the optical properties of the breast tissue in the presence of a shallow chest wall. For patient data, the CNN model predicted the breast tissue optical absorption coefficient, which was independent of chest wall depth. Conclusions: Our proposed method can be readily used in DOT and diffuse spectroscopy measurements to improve the accuracy of estimated tissue optical properties.

Ovarian cancer is the deadliest of all gynecological malignancies. When ovarian cancer is detected at an early, localized stage, surgery and chemotherapy can cure 70%-90% of patients, compared with 20% or fewer when it is diagnosed at later stages. Clearly, early detection is critical, yet the lack of early symptoms and effective screening tools means that only 20-25% of ovarian cancers are diagnosed early. Photoacoustic imaging (PAI) is an emerging modality that uses a short-pulsed laser to excite tissue. The resulting photoacoustic waves are used to image tissue optical contrast, which is directly related to tissue microvasculature and thus to cancer growth. When co-registered with transvaginal ultrasound (US), PAI offers great promise in diagnosing earlier stage ovarian cancers and distinguishing benign processes from malignant ovarian masses. In this article, we review the limitations of the current imaging tools for early ovarian cancer diagnosis and present recent advances in co-registered PAI/US.

Purpose To assess transvaginal coregistered photoacoustic tomography (PAT) and pulse-echo US for diagnosis of ovarian cancer based on functional parameters provided by PAT. Materials and Methods Between February 2017 and December 2017, 26 ovarian masses from 16 participants were successfully imaged in vivo by multispectral photoacoustic imaging, including nine invasive epithelial ovarian cancers (six serous carcinomas and three endometroid adenocarcinomas), three other tumors (two borderline serous tumors and one sex cord-stromal tumor), and 14 benign and normal (hereafter referred to as benign/normal) ovaries. The relative total hemoglobin concentration (rHbT) and mean oxygen saturation (sO2) shown at PAT were used to characterize the ovaries identified at US. Results The average rHbT was 1.9 times higher for invasive epithelial cancers than for the benign/normal ovaries (P = .01). Additionally, the rHbT distribution was extensive in invasive epithelial cancers, but was scattered in benign/normal ovaries. However, the rHbT of two borderline serous tumors and one stromal tumor was in the same range as that of benign/normal ovaries. The mean sO2 of invasive epithelial cancers, and of the borderline and stromal tumors, was 8.2% lower than that of benign/normal ovaries (P = .003). Discussion Invasive epithelial ovarian cancers showed higher and extensive tumor vascularity and lower oxygen saturation than benign and normal ovaries. Two borderline noninvasive serous and one stromal tumor showed low oxygen saturation compared with benign and normal ovaries. ©RSNA, 2018 Online supplemental material is available for this article.

Background Conventional radiologic modalities perform poorly in the radiated rectum and are often unable to differentiate residual cancer from treatment scarring. Purpose To report the development and initial patient study of an imaging system comprising an endorectal coregistered photoacoustic (PA) microscopy (PAM) and US system paired with a convolution neural network (CNN) to assess the rectal cancer treatment response. Materials and Methods In this prospective study (ClinicalTrials.gov identifier NCT04339374), participants completed radiation and chemotherapy from September 2019 to September 2020 and images were obtained with the PAM/US system prior to surgery. Another group's colorectal specimens were studied ex vivo. The PAM/US system consisted of an endorectal imaging probe, a 1064-nm laser, and one US ring transducer. The PAM CNN and US CNN models were trained and validated to distinguish normal from malignant colorectal tissue using ex vivo and in vivo patient data. The PAM CNN and US CNN were then tested using additional in vivo patient data that had not been seen by the CNNs during training and validation. Results Twenty-two patients' ex vivo specimens and five patients' in vivo images (a total of 2693 US regions of interest [ROIs] and 2208 PA ROIs) were used for CNN training and validation. Data from five additional patients were used for testing. A total of 32 participants (mean age, 60 years; range, 35-89 years) were evaluated. Unique PAM imaging markers of the complete tumor response were found, specifically including recovery of normal submucosal vascular architecture within the treated tumor bed. The PAM CNN model captured this recovery process and correctly differentiated these changes from the residual tumor. The imaging system remained highly capable of differentiating tumor from normal tissue, achieving an area under the receiver operating characteristic curve of 0.98 (95% CI: 0.98, 0.99) for data from five participants. By comparison, the US CNN had an area under the receiver operating characteristic curve of 0.71 (95% CI: 0.70, 0.73). Conclusion An endorectal coregistered photoacoustic microscopy/US system paired with a convolutional neural network model showed high diagnostic performance in assessing the rectal cancer treatment response and demonstrated potential for optimizing posttreatment management. © RSNA, 2021

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 ex vivo study, we report the first use of texture features and computer vision-based image features acquired from en face scattering coefficient maps to diagnose colorectal diseases. From these maps, texture features were extracted from a gray-level co-occurrence matrix algorithm, and computer vision-based image features were derived using a scale-invariant feature transform algorithm. Twenty-five features were obtained and thirty-three patients were recruited. Machine learning models were trained using an optimal feature set. The trained models achieved 94.7% sensitivity and 94.0% specificity for differentiating abnormal from normal, and 86.9% sensitivity and 85.0% specificity when distinguishing adenomatous polyp from cancer.

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.

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.

Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated potential value for screening and treatment monitoring of breast cancers. However, in clinical cases, the chest wall, bad probe-tissue contact, and tissue heterogeneity can create image artifacts, causing misinterpretation of lesion images. In the current work, realistic and flexible threedimensional numerical breast phantoms were generated using the Virtual Imaging Clinical Trials for Regulatory Evaluation (VICTRE) tools developed by U.S. Food and Drug Administration (FDA). By selecting physical attributes and tissue optical properties, the VICTRE breast phantoms were, for the first time, adopted in DOT for in silico studies. Monte Carlo simulations were conducted to generate the forward data. Edge artifacts (hot spots on the edge of the regions of interests) were found on the reconstructed images when there was a mismatch between the lesion-side breast and the contralateral reference-side breast. We propose a fully automated, connected components analysis-based algorithm that can remove these edge artifacts and improve lesion reconstruction.

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.

Among women, ovarian cancer is fifth most common cause of death due to cancer. In clinical ovarian cancer diagnosis via photoacoustic tomography, we face several challenges such as poor image resolution and signal-to-noise ratio (SNR). To address these concerns, we proposed a novel beamformer named lag-based delay multiply and sum combined with coherent factor (DMAS_LAG_CF). The simulations, phantom experiments and ovarian cancer patient data have demonstrated that compared with the delay and sum algorithm (DAS), the new algorithm can achieve better resolution, SNR, and improved hemoglobin contrast of malignant vs. benign ovarian lesions.

The purpose of the study was to assess the utility of tumor biomarkers, ultrasound (US) and US-guided diffuse optical tomography (DOT) in early prediction of breast cancer response to neoadjuvant therapy (NAT). This prospective HIPAA compliant study was approved by the institutional review board. Forty one patients were imaged with US and US-guided DOT prior to NAT, at completion of the first three treatment cycles, and prior to definitive surgery from February 2017 to January 2020. Miller-Payne grading was used to assess pathologic response. Receiver operating characteristic curves (ROCs) were derived from logistic regression using independent variables, including: tumor biomarkers, US maximum diameter, percentage reduction of the diameter (%US), pretreatment maximum total hemoglobin concentration (HbT) and percentage reduction in HbT (%HbT) at different treatment time points. Resulting ROCs were compared using area under the curve (AUC). Statistical significance was tested using two-sided two-sample student t-test with P