Automated software-assisted diagnosis of esophageal squamous cell neoplasia using high-resolution microendoscopy.

BACKGROUND AND AIMS: High-resolution microendoscopy (HRME) is an optical biopsy technology that provides subcellular imaging of esophageal mucosa but requires expert interpretation of these histopathology-like images. We compared endoscopists with an automated software algorithm for detection of esophageal squamous cell neoplasia (ESCN) and evaluated the endoscopists' accuracy with and without input from the software algorithm. METHODS: Thirteen endoscopists (6 experts, 7 novices) were trained and tested on 218 post-hoc HRME images from 130 consecutive patients undergoing ESCN screening/surveillance. The automated software algorithm interpreted all images as neoplastic (high-grade dysplasia, ESCN) or non-neoplastic. All endoscopists provided their interpretation (neoplastic or non-neoplastic) and confidence level (high or low) without and with knowledge of the software overlay highlighting abnormal nuclei and software interpretation. The criterion standard was histopathology consensus diagnosis by 2 pathologists. RESULTS: The endoscopists had a higher mean sensitivity (84.3%, standard deviation [SD] 8.0% vs 76.3%, P = .004), lower specificity (75.0%, SD 5.2% vs 85.3%, P < .001) but no significant difference in accuracy (81.1%, SD 5.2% vs 79.4%, P = .26) of ESCN detection compared with the automated software algorithm. With knowledge of the software algorithm, the specificity of the endoscopists increased significantly (75.0% to 80.1%, P = .002) but not the sensitivity (84.3% to 84.8%, P = .75) or accuracy (81.1% to 83.1%, P = .13). The increase in specificity was among novices (P = .008) but not experts (P = .11). CONCLUSIONS: The software algorithm had lower sensitivity but higher specificity for ESCN detection than endoscopists. Using computer-assisted diagnosis, the endoscopists maintained high sensitivity while increasing their specificity and accuracy compared with their initial diagnosis. Automated HRME interpretation would facilitate widespread usage in resource-poor areas where this portable, low-cost technology is needed.

Low-Cost High-Resolution Microendoscopy for the Detection of Esophageal Squamous Cell Neoplasia: An International Trial.

BACKGROUND & AIMS: Esophageal squamous cell neoplasia has a high mortality rate as a result of late detection. In high-risk regions such as China, screening is performed by Lugol's chromoendoscopy (LCE). LCE has low specificity, resulting in unnecessary tissue biopsy with a subsequent increase in procedure cost and risk. The purpose of this study was to evaluate the accuracy of a novel, low-cost, high-resolution microendoscope (HRME) as an adjunct to LCE. METHODS: In this prospective trial, 147 consecutive high-risk patients were enrolled from 2 US and 2 Chinese tertiary centers. Three expert and 4 novice endoscopists performed white-light endoscopy followed by LCE and HRME. All optical images were compared with the gold standard of histopathology. RESULTS: By using a per-biopsy analysis, the sensitivity of LCE vs LCE + HRME was 96% vs 91% (P = .0832), specificity was 48% vs 88% (P < .001), positive predictive value was 22% vs 45% (P < .0001), negative predictive value was 98% vs 98% (P = .3551), and overall accuracy was 57% vs 90% (P < .001), respectively. By using a per-patient analysis, the sensitivity of LCE vs LCE + HRME was 100% vs 95% (P = .16), specificity was 29% vs 79% (P < .001), positive predictive value was 32% vs 60%, 100% vs 98%, and accuracy was 47% vs 83% (P < .001). With the use of HRME, 136 biopsies (60%; 95% confidence interval, 53%-66%) could have been spared, and 55 patients (48%; 95% confidence interval, 38%-57%) could have been spared any biopsy. CONCLUSIONS: In this trial, HRME improved the accuracy of LCE for esophageal squamous cell neoplasia screening and surveillance. HRME may be a cost-effective optical biopsy adjunct to LCE, potentially reducing unnecessary biopsies and facilitating real-time decision making in globally underserved regions. ClinicalTrials.gov, NCT 01384708.

A tablet-interfaced high-resolution microendoscope with automated image interpretation for real-time evaluation of esophageal squamous cell neoplasia.

BACKGROUND AND AIMS: In recent years high-resolution microendoscopy (HRME) has shown potential to improve screening for esophageal squamous cell neoplasia. Furthering its utility in a clinical setting, especially in lower-resource settings, could be accomplished by reducing the size and cost of the system as well as incorporating the ability of real-time, objective feedback. This article describes a tablet-interfaced HRME with fully automated, real-time image analysis. METHODS: The performance of the tablet-interfaced HRME was assessed by acquiring images from the oral mucosa in a normal volunteer. An automated, real-time analysis algorithm was developed and evaluated using training, test, and validation images from a previous in vivo study of 177 patients referred for screening or surveillance endoscopy in China. The algorithm was then implemented in a tablet HRME that was used to obtain and analyze images from esophageal tissue in 3 patients. Images were displayed alongside the probability that the imaged region was neoplastic. RESULTS: The tablet-interfaced HRME demonstrated comparable imaging performance at a lower cost compared with first-generation laptop-interfaced HRME systems. In a post-hoc quantitative analysis, the algorithm identified neoplasia with a sensitivity and specificity of 95% and 91%, respectively, in the validation set compared with 84% and 95% achieved in the original study. CONCLUSIONS: The tablet-based HRME is a low-cost tool that provides quantitative diagnostic information to the endoscopist in real time. This could be especially beneficial in lower-resource settings for operators with less experience interpreting HRME images.

Fluorescence-based endoscopic imaging of Thomsen-Friedenreich antigen to improve early detection of colorectal cancer.

Thomsen-Friedenreich (TF) antigen belongs to the mucin-type tumor-associated carbohydrate antigen. Notably, TF antigen is overexpressed in colorectal cancer (CRC) but is rarely expressed in normal colonic tissue. Increased TF antigen expression is associated with tumor invasion and metastasis. In this study, we sought to validate a novel nanobeacon for imaging TF-associated CRC in a preclinical animal model. We developed and characterized the nanobeacon for use with fluorescence colonoscopy. In vivo imaging was performed on an orthotopic rat model of CRC. Both white light and fluorescence colonoscopy methods were utilized to establish the ratio-imaging index for the probe. The nanobeacon exhibited specificity for TF-associated cancer. Fluorescence colonoscopy using the probe can detect lesions at the stage which is not readily confirmed by conventional visualization methods. Further, the probe can report the dynamic change of TF expression as tumor regresses during chemotherapy. Data from this study suggests that fluorescence colonoscopy can improve early CRC detection. Supplemented by the established ratio-imaging index, the probe can be used not only for early detection, but also for reporting tumor response during chemotherapy. Furthermore, since the data obtained through in vivo imaging confirmed that the probe was not absorbed by the colonic mucosa, no registered toxicity is associated with this nanobeacon. Taken together, these data demonstrate the potential of this novel probe for imaging TF antigen as a biomarker for the early detection and prediction of the progression of CRC at the molecular level.

Quantitative analysis of high-resolution microendoscopic images for diagnosis of esophageal squamous cell carcinoma.

BACKGROUND & AIMS: High-resolution microendoscopy is an optical imaging technique with the potential to improve the accuracy of endoscopic screening for esophageal squamous neoplasia. Although these microscopic images can be interpreted readily by trained personnel, quantitative image analysis software could facilitate the use of this technology in low-resource settings. In this study, we developed and evaluated quantitative image analysis criteria for the evaluation of neoplastic and non-neoplastic squamous esophageal mucosa. METHODS: We performed an image analysis of 177 patients undergoing standard upper endoscopy for screening or surveillance of esophageal squamous neoplasia, using high-resolution microendoscopy, at 2 hospitals in China and at 1 hospital in the United States from May 2010 to October 2012. Biopsy specimens were collected from imaged sites (n = 375), and a consensus diagnosis was provided by 2 expert gastrointestinal pathologists and used as the standard. RESULTS: Quantitative information from the high-resolution images was used to develop an algorithm to identify high-grade squamous dysplasia or invasive squamous cell cancer, based on histopathology findings. Optimal performance was obtained using the mean nuclear area as the basis for classification, resulting in sensitivities and specificities of 93% and 92% in the training set, 87% and 97% in the test set, and 84% and 95% in an independent validation set, respectively. CONCLUSIONS: High-resolution microendoscopy with quantitative image analysis can aid in the identification of esophageal squamous neoplasia. Use of software-based image guides may overcome issues of training and expertise in low-resource settings, allowing for widespread use of these optical biopsy technologies.

Multi-modal diffuse optical spectroscopy for high-speed monitoring and wide-area mapping of tissue optical properties and hemodynamics.

SIGNIFICANCE: Diffuse optical spectroscopic imaging (DOSI) is a versatile technology sensitive to changes in tissue composition and hemodynamics and has been used for a wide variety of clinical applications. Specific applications have prompted the development of versions of the DOSI technology to fit specific clinical needs. This work describes the development and characterization of a multi-modal DOSI (MM-DOSI) system that can acquire metabolic, compositional, and pulsatile information at multiple penetration depths in a single hardware platform. Additionally, a 3D tracking system is integrated with MM-DOSI, which enables registration of the acquired data to the physical imaging area. AIM: We demonstrate imaging, layered compositional analysis, and metabolism tracking capabilities using a single MM-DOSI system on optical phantoms as well as in vivo human tissue. APPROACH: We characterize system performance with a silicone phantom containing an embedded object. To demonstrate multi-layer sensitivity, we imaged human calf tissue with a 4.8-mm skin-adipose thickness. Human thenar tissue was also measured using a combined broadband DOSI and continuous-wave near-infrared spectroscopy method (∼15 Hz acquisition rate). RESULTS: High-resolution optical property maps of absorption (µa) and reduced scattering (µs ' ) were recovered on the phantom by capturing over 1000 measurement points in under 5 minutes. On human calf tissue, we show two probing depth layers have significantly different (p < 0.001) total-hemo/myoglobin and µs ' composition. On thenar tissue, we calculate tissue arterial oxygen saturation, venous oxygen saturation, and tissue metabolic rate of oxygen consumption during baseline and after release of an arterial occlusion. CONCLUSIONS: The MM-DOSI can switch between collection of broadband spectra, high-resolution images, or multi-depth hemodynamics without any hardware reconfiguration. We conclude that MM-DOSI enables acquisition of high resolution, multi-modal data consolidated in a single platform, which can provide a more comprehensive understanding of tissue hemodynamics and composition for a wide range of clinical applications.

Review of the efficacy of infrared thermography for screening infectious diseases with applications to COVID-19.

Purpose: The recent coronavirus disease 2019 (COVID-19) pandemic, which spread across the globe in a very short period of time, revealed that the transmission control of disease is a crucial step to prevent an outbreak and effective screening for viral infectious diseases is necessary. Since the severe acute respiratory syndrome (SARS) outbreak in 2003, infrared thermography (IRT) has been considered a gold standard method for screening febrile individuals at the time of pandemics. The objective of this review is to evaluate the efficacy of IRT for screening infectious diseases with specific applications to COVID-19. Approach: A literature review was performed in Google Scholar, PubMed, and ScienceDirect to search for studies evaluating IRT screening from 2002 to present using relevant keywords. Additional literature searches were done to evaluate IRT in comparison to traditional core body temperature measurements and assess the benefits of measuring additional vital signs for infectious disease screening. Results: Studies have reported on the unreliability of IRT due to poor sensitivity and specificity in detecting true core body temperature and its inability to identify asymptomatic carriers. Airport mass screening using IRT was conducted during occurrences of SARS, Dengue, Swine Flu, and Ebola with reported sensitivities as low as zero. Other studies reported that screening other vital signs such as heart and respiratory rates can lead to more robust methods for early infection detection. Conclusions: Studies evaluating IRT showed varied results in its efficacy for screening infectious diseases. This suggests the need to assess additional physiological parameters to increase the sensitivity and specificity of non-invasive biosensors.

A mobile-phone based high-resolution microendoscope to image cervical precancer.

Nearly 90% of cervical cancer cases and deaths occur in low- and middle-income countries that lack comprehensive national HPV immunization and cervical cancer screening programs. In these settings, it is difficult to implement screening programs due to a lack of infrastructure and shortage of trained personnel. Screening programs based on visual inspection with acetic acid (VIA) have been successfully implemented in some low-resource settings. However, VIA has poor specificity and up to 90% of patients receiving treatment based on a positive VIA exam are over-treated. A number of studies have suggested that high-resolution cervical imaging to visualize nuclear morphology in vivo can improve specificity by better distinguishing precancerous and benign lesions. To enable high-resolution imaging in low-resource settings, we developed a portable, low-cost, high-resolution microendoscope that uses a mobile phone to detect and display images of cervical epithelium in vivo with subcellular resolution. The device was fabricated for less than $2,000 using commercially available optical components including filters, an LED and triplet lenses assembled in a 3D-printed opto-mechanical mount. We show that the mobile high-resolution microendoscope achieves similar resolution and signal-to-background ratio as previously reported high-resolution microendoscope systems using traditional cameras and computers to detect and display images. Finally, we demonstrate the ability of the mobile high-resolution microendoscope to image normal and precancerous squamous epithelium of the cervix in vivo in a gynecological referral clinic in Barretos, Brazil.

Development of an integrated multimodal optical imaging system with real-time image analysis for the evaluation of oral premalignant lesions.

Oral premalignant lesions (OPLs), such as leukoplakia, are at risk of malignant transformation to oral cancer. Clinicians can elect to biopsy OPLs and assess them for dysplasia, a marker of increased risk. However, it is challenging to decide which OPLs need a biopsy and to select a biopsy site. We developed a multimodal optical imaging system (MMIS) that fully integrates the acquisition, display, and analysis of macroscopic white-light (WL), autofluorescence (AF), and high-resolution microendoscopy (HRME) images to noninvasively evaluate OPLs. WL and AF images identify suspicious regions with high sensitivity, which are explored at higher resolution with the HRME to improve specificity. Key features include a heat map that delineates suspicious regions according to AF images, and real-time image analysis algorithms that predict pathologic diagnosis at imaged sites. Representative examples from ongoing studies of the MMIS demonstrate its ability to identify high-grade dysplasia in OPLs that are not clinically suspicious, and to avoid unnecessary biopsies of benign OPLs that are clinically suspicious. The MMIS successfully integrates optical imaging approaches (WL, AF, and HRME) at multiple scales for the noninvasive evaluation of OPLs.

Prospective Evaluation of Multimodal Optical Imaging with Automated Image Analysis to Detect Oral Neoplasia In Vivo.

The 5-year survival rate for patients with oral cancer remains low, in part because diagnosis often occurs at a late stage. Early and accurate identification of oral high-grade dysplasia and cancer can help improve patient outcomes. Multimodal optical imaging is an adjunctive diagnostic technique in which autofluorescence imaging is used to identify high-risk regions within the oral cavity, followed by high-resolution microendoscopy to confirm or rule out the presence of neoplasia. Multimodal optical images were obtained from 206 sites in 100 patients. Histologic diagnosis, either from a punch biopsy or an excised surgical specimen, was used as the gold standard for all sites. Histopathologic diagnoses of moderate dysplasia or worse were considered neoplastic. Images from 92 sites in the first 30 patients were used as a training set to develop automated image analysis methods for identification of neoplasia. Diagnostic performance was evaluated prospectively using images from 114 sites in the remaining 70 patients as a test set. In the training set, multimodal optical imaging with automated image analysis correctly classified 95% of nonneoplastic sites and 94% of neoplastic sites. Among the 56 sites in the test set that were biopsied, multimodal optical imaging correctly classified 100% of nonneoplastic sites and 85% of neoplastic sites. Among the 58 sites in the test set that corresponded to a surgical specimen, multimodal imaging correctly classified 100% of nonneoplastic sites and 61% of neoplastic sites. These findings support the potential of multimodal optical imaging to aid in the early detection of oral cancer. Cancer Prev Res; 10(10); 563-70. ©2017 AACR.

High-resolution microendoscopy: a point-of-care diagnostic for cervical dysplasia in low-resource settings.

Cervical cancer is the third leading cause of cancer-related death among women in low-to-middle income countries. Pap testing and pathological services are difficult to implement under these settings. Alternative techniques for the diagnosis of cervical precancer in these settings are needed to reduce the burden of the disease. The objective of this study was to evaluate the diagnostic accuracy of a low-cost, high-resolution microendoscope imaging system in identifying precancerous lesions of the cervix in vivo. A retrospective study of 59 patients undergoing colposcopy for an abnormal Pap test was performed at Hospital de Câncer de Barretos in Brazil. All patients underwent colposcopy as per standard of care, and acetowhite lesions were recorded. High-resolution microendoscopy (HRME) images were obtained from one colposcopically normal region and from all lesions observed on colposcopy. Biopsies of abnormal areas were obtained and reviewed by three independent, blinded pathologists and compared with HRME findings. The mean nuclear area and the median nuclear eccentricity were calculated from HRME images acquired from each site. A diagnostic algorithm to distinguish histopathologically diagnosed cervical intraepithelial neoplasias of grade 2 or more severe lesions (high grade) from less severe lesions (low grade) was developed using these parameters. A test of trend was used to analyze the relationship between HRME positivity and severity of histopathogical diagnosis. Fisher's exact test was used to analyze differences in HRME positivity between high-grade and low-grade lesions. Evaluable images were obtained from 108 of 143 discrete sites. Of these, 71 sites were colposcopically normal or low grade according to histopathology and 37 were diagnosed as high grade on the basis of histopathology. Using the mean nuclear area and the median nuclear eccentricity, HRME images from 59 colposcopically abnormal sites were classified as high grade or low grade with 92% sensitivity and 77% specificity compared with histopathological findings. Increasing HRME positivity showed a significant trend with increasing severity of diagnosis (Ptrend<0.001). We found a strong association (P<0.001) between HRME positivity and a histopathological diagnosis of cervical intraepithelial neoplasia of grade 2 or higher. HRME demonstrated an accurate in-situ diagnosis of high-grade dysplasia. In low-resource settings in which colposcopy and histopathology services are severely limited or unavailable, HRME may provide a low-cost, accurate method for diagnosis of cervical precancer without the need for biopsy, allowing for a single 'screen-and-treat' approach.

Operative margin control with high-resolution optical microendoscopy for head and neck squamous cell carcinoma.

OBJECTIVES/HYPOTHESIS: High-resolution microendoscopy (HRME) provides real-time visualization of the mucosal surface in the upper aerodigestive tract. This technology allows noninvasive discrimination of benign and neoplastic epithelium and has potential applications for intraoperative margin detection. STUDY DESIGN: Single institution, prospective, feasibility trial (phase I) of in vivo optical imaging. METHODS: The study was conducted on patients with squamous cell carcinoma of the upper aerodigestive tract. High-resolution microendoscopy images obtained during surgery were correlated with histopathologic diagnosis to determine the ability of HRME to differentiate between benign and malignant mucosa. Blinded reviewers evaluated HRME images and made determinations of the status of the mucosa. Accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and interrater agreement between multiple raters were calculated to determine the accuracy of HRME imaging. RESULTS: The mean accuracy of reviewers in differentiating neoplastic or benign mucosa was 95.1% (95% confidence interval [CI], 94%-96%). Sensitivity and specificity were 96% (95% CI, 94%-99%) and 95% (95 % CI, 90%-99%), respectively. The NPV was 98% (95% CI, 97%-99%), and PPV was 91% (95% CI, 85%-98%). The Fleiss kappa statistic for interrater reliability was 0.81, with a standard error of 0.014 and a 95% CI (0.78-0.84). CONCLUSION: High-resolution microendoscopy allows real-time discrimination between benign and neoplastic mucosa. High levels of sensitivity and specificity can be obtained with this technology when interrogating mucosal surfaces. Despite several technical limitations, HRME shows promise as a technique for intraoperative margin control and platform for molecular imaging technologies. LEVEL OF EVIDENCE: 3b.

High-resolution microendoscope for the detection of cervical neoplasia.

Cervical cancer causes 275,000 deaths each year with 85 % of these deaths occurring in the developing world. One of the primary reasons for the concentration of deaths in developing countries is a lack of effective screening methods suited for the infrastructure of these countries. In order to address this need, we have developed a high-resolution microendoscope (HRME). The HRME is a fiber-based fluorescence microscope with subcellular resolution. Using the vital stain proflavine, we are able to image cell nuclei in vivo and evaluate metrics such as nuclear-to-cytoplasmic ratio, critical to identifying precancerous epithelial regions. In this chapter, we detail the materials and methods necessary to build this system from commercially available parts.

Feasibility of transoral robotic-assisted high-resolution microendoscopic imaging of oropharyngeal squamous cell carcinoma.

BACKGROUND: Transoral robotic-assisted oncologic surgery of the head and neck offers promising functional results. Nonetheless, the efficacy of oncologic surgery remains critically dependent on obtaining negative margins. We aimed to integrate a miniaturized high-resolution fiber-optic microendoscope (HRME), which provides real-time histological assessment, with the da Vinci robotic system (Intuitive Surgical, Sunnyvale, CA). METHODS: Three patients undergoing transoral robotic surgery (TORS) were prospectively enrolled in this study. Optical imaging of the oropharynx was performed intraoperatively with the robotic-assisted HRME. RESULTS: All patients underwent the procedure successfully with no complications. The HRME was successfully integrated with the da Vinci robotic system. Several sites of the oropharynx and associated malignancy were imaged, which correlated with the standard histopathological analysis. CONCLUSION: Transoral robotic-assisted HRME imaging of the oropharynx is a safe and technically feasible approach, providing a real-time histological assessment and may serve as a valuable aid in oncologic surgery.

Optical molecular imaging in the gastrointestinal tract.

Recent developments in optical molecular imaging allow for real-time identification of morphologic and biochemical changes in tissue associated with gastrointestinal neoplasia. This review summarizes widefield and high-resolution imaging modalities in preclinical and clinical evaluation for the detection of colorectal cancer and esophageal cancer. Widefield techniques discussed include high-definition white light endoscopy, narrow band imaging, autofluoresence imaging, and chromoendoscopy; high-resolution techniques discussed include probe-based confocal laser endomicroscopy, high-resolution microendoscopy, and optical coherence tomography. New approaches to enhance image contrast using vital dyes and molecular-specific targeted contrast agents are evaluated.

Real-time video mosaicing with a high-resolution microendoscope.

Microendoscopes allow clinicians to view subcellular features in vivo and in real-time, but their field-of-view is inherently limited by the small size of the probe's distal end. Video mosaicing has emerged as an effective technique to increase the acquired image size. Current implementations are performed post-procedure, which removes the benefits of live imaging. In this manuscript we present an algorithm for real-time video mosaicing using a low-cost high-resolution microendoscope. We present algorithm execution times and show image results obtained from in vivo tissue.

Tissue phantoms in multicenter clinical trials for diffuse optical technologies.

Tissue simulating phantoms are an important part of instrumentation validation, standardization/training and clinical translation. Properly used, phantoms form the backbone of sound quality control procedures. We describe the development and testing of a series of optically turbid phantoms used in a multi-center American College of Radiology Imaging Network (ACRIN) clinical trial of Diffuse Optical Spectroscopic Imaging (DOSI). The ACRIN trial is designed to measure the response of breast tumors to neoadjuvant chemotherapy. Phantom measurements are used to determine absolute instrument response functions during each measurement session and assess both long and short-term operator and instrument reliability.