Use of topical methylene blue to image nuclear morphometry with a low-cost scanning darkfield microendoscope.

Significance: Fiber-optic microendoscopy is a promising approach to noninvasively visualize epithelial nuclear morphometry for early cancer and precancer detection. However, the broader clinical application of this approach is limited by a lack of topical contrast agents available for in vivo use. Aim: The aim of this study was to evaluate the ability to image nuclear morphometry in vivo with a novel fiber-optic microendoscope used together with topical application of methylene blue (MB), a dye with FDA approval for use in chromoendoscopy in the gastrointestinal tract. Approach: The low-cost, high-resolution microendoscope implements scanning darkfield imaging without complex optomechanical components by leveraging programmable illumination and the rolling shutter of the image sensor. We validate the integration of our system and MB staining for visualizing epithelial cell nuclei by performing ex vivo imaging on fresh animal specimens and in vivo imaging on healthy volunteers. Results: The results indicate that scanning darkfield imaging significantly reduces specular reflection and resolves epithelial nuclei with enhanced image contrast and spatial resolution compared to non-scanning widefield imaging. The image quality of darkfield images with MB staining is comparable to that of fluorescence images with proflavine staining. Conclusions: Our approach enables real-time microscopic evaluation of nuclear patterns and has the potential to be a powerful noninvasive tool for early cancer detection.

Multiscale Optical Imaging Fusion for Cervical Precancer Diagnosis: Integrating Widefield Colposcopy and High-Resolution Endomicroscopy.

OBJECTIVE: Early detection and treatment of cervical precancers can prevent disease progression. However, in low-resource communities with a high incidence of cervical cancer, high equipment costs and a shortage of specialists hinder preventative strategies. This manuscript presents a low-cost multiscale in vivo optical imaging system coupled with a computer-aided diagnostic system that could enable accurate, real-time diagnosis of high-grade cervical precancers. METHODS: The system combines portable colposcopy and high-resolution endomicroscopy (HRME) to acquire spatially registered widefield and microscopy videos. A multiscale imaging fusion network (MSFN) was developed to identify cervical intraepithelial neoplasia grade 2 or more severe (CIN 2+). The MSFN automatically identifies and segments the ectocervix and lesions from colposcopy images, extracts nuclear morphology features from HRME videos, and integrates the colposcopy and HRME information. RESULTS: With a threshold value set to achieve sensitivity equal to clinical impression (0.98 [p = 1.0]), the MSFN achieved a significantly higher specificity than clinical impression (0.75 vs. 0.43, p = 0.000006). CONCLUSION: Our findings show that multiscale optical imaging of the cervix allows the highly sensitive and specific detection of high-grade precancers. SIGNIFICANCE: The multiscale imaging system and MSFN could facilitate the accurate, real-time diagnosis of cervical precancers in low-resource settings.

Deployment and assessment of a deep learning model for real-time detection of anal precancer with high frame rate high-resolution microendoscopy.

Anal cancer incidence is significantly higher in people living with HIV as HIV increases the oncogenic potential of human papillomavirus. The incidence of anal cancer in the United States has recently increased, with diagnosis and treatment hampered by high loss-to-follow-up rates. Novel methods for the automated, real-time diagnosis of AIN 2+ could enable "see and treat" strategies, reducing loss-to-follow-up rates. A previous retrospective study demonstrated that the accuracy of a high-resolution microendoscope (HRME) coupled with a deep learning model was comparable to expert clinical impression for diagnosis of AIN 2+ (sensitivity 0.92 [P = 0.68] and specificity 0.60 [P = 0.48]). However, motion artifacts and noise led to many images failing quality control (17%). Here, we present a high frame rate HRME (HF-HRME) with improved image quality, deployed in the clinic alongside a deep learning model and evaluated prospectively for detection of AIN 2+ in real-time. The HF-HRME reduced the fraction of images failing quality control to 4.6% by employing a high frame rate camera that enhances contrast and limits motion artifacts. The HF-HRME outperformed the previous HRME (P < 0.001) and clinical impression (P < 0.0001) in the detection of histopathologically confirmed AIN 2+ with a sensitivity of 0.91 and specificity of 0.87.

Scanning darkfield high-resolution microendoscope for label-free microvascular imaging.

Characterization of microvascular changes during neoplastic progression has the potential to assist in discriminating precancer and early cancer from benign lesions. Here, we introduce a novel high-resolution microendoscope that leverages scanning darkfield reflectance imaging to characterize angiogenesis without exogenous contrast agents. Scanning darkfield imaging is achieved by coupling programmable illumination with a complementary metal-oxide semiconductor (CMOS) camera rolling shutter, eliminating the need for complex optomechanical components and making the system portable, low-cost (<$5,500) and simple to use. Imaging depth is extended by placing a gradient-index (GRIN) lens at the distal end of the imaging fiber to resolve subepithelial microvasculature. We validated the capability of the scanning darkfield microendoscope to visualize microvasculature at different anatomic sites in vivo by imaging the oral cavity of healthy volunteers. Images of cervical specimens resected for suspected neoplasia reveal distinct microvascular patterns in columnar and squamous epithelium with different grades of precancer, indicating the potential of scanning darkfield microendoscopy to aid in efforts to prevent cervical cancer through early diagnosis.

Design and field evaluation of a lateral flow cassette device for point-of-care bilirubin measurement.

Neonatal jaundice is an important cause of morbidity and mortality worldwide, and neonates born in low and middle-income countries bear a disproportionate burden. We previously developed a low-cost, point-of-care system to measure total serum bilirubin (TSB) in neonates. This device was effective at detecting and monitoring jaundice; however, the disposable strips were difficult to produce at scale. Here, we report a new lateral flow cassette design, called BiliDx, that was produced at scale using traditional manufacturing techniques. We evaluated the performance of BiliDx at sites in Nigeria and Malawi. The lateral flow strip consists of plasma separation membranes, nitrocellulose, and a plastic cassette. We evaluated the performance of the strips and reader at two hospitals located in Nigeria and Malawi compared to reference standard TSB. We also assessed performance for samples with high direct bilirubin (DB) and high hematocrit (HCT). We collected 1,144 samples from 758 neonates (TSB ranged from 0.2 to 45.9 mg/dL). The mean bias of BiliDx measurements in the validation set was +0.75 mg/dL, and 95% limits of agreement were -2.57 to 4.07 mg/dL. The mean bias and limits of agreement were comparable for samples with HCT < 60% and HCT ≥ 60%, and for samples with low and intermediate DB levels; the samples with high DB levels had wider 95% limits of agreement (-4.50 to +3.03 mg/dL). Error grid analysis shows that 96.9% of samples measured with BiliDx would have resulted in the same clinical decision as the reference standard. This performance is comparable to previous results that used a handmade two-dimensional strip. Additionally, error grid analysis shows that all 20 samples with high DB levels would have resulted in the same clinical decision as the reference standard. This evaluation supports the use of BiliDx lateral flow cassettes to provide accurate point-of-care measurements in low-resource settings.

Automated In Vivo High-Resolution Imaging to Detect Human Papillomavirus-Associated Anal Precancer in Persons Living With HIV.

INTRODUCTION: In the United States, the effectiveness of anal cancer screening programs has been limited by a lack of trained professionals proficient in high-resolution anoscopy (HRA) and a high patient lost-to-follow-up rate between diagnosis and treatment. Simplifying anal intraepithelial neoplasia grade 2 or more severe (AIN 2+) detection could radically improve the access and efficiency of anal cancer prevention. Novel optical imaging providing point-of-care diagnoses could substantially improve existing HRA and histology-based diagnosis. This work aims to demonstrate the potential of high-resolution microendoscopy (HRME) coupled with a novel machine learning algorithm for the automated, in vivo diagnosis of anal precancer. METHODS: The HRME, a fiber-optic fluorescence microscope, was used to capture real-time images of anal squamous epithelial nuclei. Nuclear staining is achieved using 0.01% wt/vol proflavine, a topical contrast agent. HRME images were analyzed by a multitask deep learning network (MTN) that computed the probability of AIN 2+ for each HRME image. RESULTS: The study accrued data from 77 people living with HIV. The MTN achieved an area under the receiver operating curve of 0.84 for detection of AIN 2+. At the AIN 2+ probability cutoff of 0.212, the MTN achieved comparable performance to expert HRA impression with a sensitivity of 0.92 ( P = 0.68) and specificity of 0.60 ( P = 0.48) when using histopathology as the gold standard. DISCUSSION: When used in combination with HRA, this system could facilitate more selective biopsies and promote same-day AIN2+ treatment options by enabling real-time diagnosis.

Multimodal optical imaging with real-time projection of cancer risk and biopsy guidance maps for early oral cancer diagnosis and treatment.

Significance: Despite recent advances in multimodal optical imaging, oral imaging systems often do not provide real-time actionable guidance to the clinician who is making biopsy and treatment decisions. Aim: We demonstrate a low-cost, portable active biopsy guidance system (ABGS) that uses multimodal optical imaging with deep learning to directly project cancer risk and biopsy guidance maps onto oral mucosa in real time. Approach: Cancer risk maps are generated based on widefield autofluorescence images and projected onto the at-risk tissue using a digital light projector. Microendoscopy images are obtained from at-risk areas, and multimodal image data are used to calculate a biopsy guidance map, which is projected onto tissue. Results: Representative patient examples highlight clinically actionable visualizations provided in real time during an imaging procedure. Results show multimodal imaging with cancer risk and biopsy guidance map projection offers a versatile, quantitative, and precise tool to guide biopsy site selection and improve early detection of oral cancers. Conclusions: The ABGS provides direct visible guidance to identify early lesions and locate appropriate sites to biopsy within those lesions. This represents an opportunity to translate multimodal imaging into real-time clinically actionable visualizations to help improve patient outcomes.

Optical imaging technologies for in vivo cancer detection in low-resource settings.

Cancer continues to affect underserved populations disproportionately. Novel optical imaging technologies, which can provide rapid, non-invasive, and accurate cancer detection at the point of care, have great potential to improve global cancer care. This article reviews the recent technical innovations and clinical translation of low-cost optical imaging technologies, highlighting the advances in both hardware and software, especially the integration of artificial intelligence, to improve in vivo cancer detection in low-resource settings. Additionally, this article provides an overview of existing challenges and future perspectives of adapting optical imaging technologies into clinical practice, which can potentially contribute to novel insights and programs that effectively improve cancer detection in low-resource settings.

A synthetic cell density signal can drive proliferation in chick embryonic tendon cells and tendon cells from a full size rooster can produce high levels of procollagen in cell culture.

Cell density signaling drives tendon morphogenesis by regulating both procollagen production and cell proliferation. The signal is composed of a small, highly conserved protein (SNZR P) tightly bound to a tissue-specific, unique lipid (SNZR L). This allows the complex (SNZR PL) to bind to the membrane of the cell and locally diffuse over a radius of ~1 mm. The cell produces low levels of this signal but the binding to the membrane increases with the number of tendon cells in the local environment. In this article SNZR P was produced in E.coli and SNZR L was chemically synthesized. The two bind together when heated to 60 °C in the presence of Ca++ and Mg++ and the synthesized SNZR PL at ng/ml levels can replace serum. Adding SNZR PL to the medium was also tested on primary tendon cells from adult roosters. The older cells were in a maintenance state in vivo and in cell culture they proliferate more slowly than embryonic cells. Nevertheless, after reaching a moderately high cell density, they produced high levels of procollagen similar to the embryonic cells. This data was not expected from older cells but suggests that adult tendon cells can regenerate the tissue after injury when given the correct signals.

Development of a multimodal mobile colposcope for real-time cervical cancer detection.

Cervical cancer remains a leading cause of cancer death among women in low-and middle-income countries. Globally, cervical cancer prevention programs are hampered by a lack of resources, infrastructure, and personnel. We describe a multimodal mobile colposcope (MMC) designed to diagnose precancerous cervical lesions at the point-of-care without the need for biopsy. The MMC integrates two complementary imaging systems: 1) a commercially available colposcope and 2) a high speed, high-resolution, fiber-optic microendoscope (HRME). Combining these two image modalities allows, for the first time, the ability to locate suspicious cervical lesions using widefield imaging and then to obtain co-registered high-resolution images across an entire lesion. The MMC overcomes limitations of high-resolution imaging alone; widefield imaging can be used to guide the placement of the high-resolution imaging probe at clinically suspicious regions and co-registered, mosaicked high-resolution images effectively increase the field of view of high-resolution imaging. Representative data collected from patients referred for colposcopy at Barretos Cancer Hospital in Brazil, including 22,800 high resolution images and 9,900 colposcope images, illustrate the ability of the MMC to identify abnormal cervical regions, image suspicious areas with subcellular resolution, and distinguish between high-grade and low-grade dysplasia.

Mildly dysplastic oral lesions with optically-detectable abnormalities share genetic similarities with severely dysplastic lesions.

OBJECTIVE: Optical imaging studies of oral premalignant lesions have shown that optical markers, including loss of autofluorescence and altered morphology of epithelial cell nuclei, are predictive of high-grade pathology. While these optical markers are consistently positive in lesions with moderate/severe dysplasia or cancer, they are positive only in a subset of lesions with mild dysplasia. This study compared the gene expression profiles of lesions with mild dysplasia (stratified by optical marker status) to lesions with severe dysplasia and without dysplasia. MATERIALS AND METHODS: Forty oral lesions imaged in patients undergoing oral surgery were analyzed: nine without dysplasia, nine with severe dysplasia, and 22 with mild dysplasia. Samples were submitted for high throughput gene expression analysis. RESULTS: The analysis revealed 116 genes differentially expressed among sites without dysplasia and sites with severe dysplasia; 50 were correlated with an optical marker quantifying altered nuclear morphology. Ten of 11 sites with mild dysplasia and positive optical markers (91%) had gene expression similar to sites with severe dysplasia. Nine of 11 sites with mild dysplasia and negative optical markers (82%) had similar gene expression as sites without dysplasia. CONCLUSION: This study suggests that optical imaging may help identify patients with mild dysplasia who require more intensive clinical follow-up. If validated, this would represent a significant advance in patient care for patients with oral premalignant lesions.

Evaluation of a Point-of-Care Test for Bilirubin in Malawi.

OBJECTIVES: BiliSpec is a low-cost spectrophotometric reader and disposable paper-based strip to quantify total serum bilirubin from several blood drops. This study was a prospective evaluation of BiliSpec in 2 neonatal wards in Malawi compared with a reference standard bilirubinometer over a large range of bilirubin and hematocrit levels. METHODS: The accuracy of BiliSpec and a transcutaneous bilirubinometer were compared with the reference standard of spectrophotometry for 475 blood samples collected from 375 subjects across a range of total serum bilirubin concentrations from 0.0 to 33.7 mg/dL. The development of error grids to assess the clinical effects of measurement differences is reported. RESULTS: BiliSpec was found to have a mean bias of -0.48 mg/dL and 95% limits of agreement of -5.09 mg/dL to +4.12 mg/dL. Results show 90.7% of BiliSpec measurements would have resulted in the same clinical decision as the reference standard, whereas 55.0% of transcutaneous bilirubin measurements would have resulted in the same clinical decision as the reference standard. CONCLUSIONS: This evaluation supports use of BiliSpec to provide accurate, low-cost, point-of-care bilirubin measurements in low-resource hospitals. Future work is needed to evaluate BiliSpec among a larger number of users.

Rapid Range Expansion of a Marine Ectotherm Reveals the Demographic and Ecological Consequences of Short-Term Variability in Seawater Temperature and Dissolved Oxygen.

AbstractThe distributions of marine ectotherms are governed by physiological sensitivities to long-term trends in seawater temperature and dissolved oxygen. Short-term variability in these parameters has the potential to facilitate rapid range expansions, and the resulting ecological and socioeconomic consequences may portend those of future marine communities. Here, we combine physiological experiments with ecological and demographic surveys to assess the causes and consequences of sudden but temporary poleward range expansions of a marine ectotherm with considerable life history plasticity (California market squid, Doryteuthis opalescens). We show that sequential factors related to resource accessibility in the core range-the buildup of large populations as a result of competitive release and climate-associated temperature increase and oxygen loss that constrain aerobic activity-may drive these expansions. We also reveal that poleward range expansion alters the body size-and therefore trophic role-of invading populations, with potential negative implications for socioeconomically valuable resident species. To help forecast rapid range expansions of marine ectotherms, we advocate that research efforts focus on factors impacting resource accessibility in core ranges. Determining how environmental conditions in receiving ecosystems affect body size and how body size is related to trophic role will help refine estimates of the impacts of future marine communities.

High frame rate video mosaicking microendoscope to image large regions of intact tissue with subcellular resolution.

High-resolution microendoscopy (HRME) is a low-cost strategy to acquire images of intact tissue with subcellular resolution at frame rates ranging from 11 to 18 fps. Current HRME imaging strategies are limited by the small microendoscope field of view (∼0.5 mm2); multiple images must be acquired and reliably registered to assess large regions of clinical interest. Image mosaics have been assembled from co-registered frames of video acquired as a microendoscope is slowly moved across the tissue surface, but the slow frame rate of previous HRME systems made this approach impractical for acquiring quality mosaicked images from large regions of interest. Here, we present a novel video mosaicking microendoscope incorporating a high frame rate CMOS sensor and optical probe holder to enable high-speed, high quality interrogation of large tissue regions of interest. Microendoscopy videos acquired at >90 fps are assembled into an image mosaic. We assessed registration accuracy and image sharpness across the mosaic for images acquired with a handheld probe over a range of translational speeds. This high frame rate video mosaicking microendoscope enables in vivo probe translation at >15 millimeters per second while preserving high image quality and accurate mosaicking, increasing the size of the region of interest that can be interrogated at high resolution from 0.5 mm2 to >30 mm2. Real-time deployment of this high-frame rate system is demonstrated in vivo and source code made publicly available.

Cervical lesion assessment using real-time microendoscopy image analysis in Brazil: The CLARA study.

We conducted a prospective evaluation of the diagnostic performance of high-resolution microendoscopy (HRME) to detect cervical intraepithelial neoplasia (CIN) in women with abnormal screening tests. Study participants underwent colposcopy, HRME and cervical biopsy. The prospective diagnostic performance of HRME using an automated morphologic image analysis algorithm was compared to that of colposcopy using histopathologic detection of CIN as the gold standard. To assess the potential to further improve performance of HRME image analysis, we also conducted a retrospective analysis assessing performance of a multi-task convolutional neural network to segment and classify HRME images. One thousand four hundred eighty-six subjects completed the study; 435 (29%) subjects had CIN Grade 2 or more severe (CIN2+) diagnosis. HRME with morphologic image analysis for detection of CIN Grade 3 or more severe diagnoses (CIN3+) was similarly sensitive (95.6% vs 96.2%, P = .81) and specific (56.6% vs 58.7%, P = .18) as colposcopy. HRME with morphologic image analysis for detection of CIN2+ was slightly less sensitive (91.7% vs 95.6%, P < .01) and specific (59.7% vs 63.4%, P = .02) than colposcopy. Images from 870 subjects were used to train a multi-task convolutional neural network-based algorithm and images from the remaining 616 were used to validate its performance. There were no significant differences in the sensitivity and specificity of HRME with neural network analysis vs colposcopy for detection of CIN2+ or CIN3+. Using a neural network-based algorithm, HRME has comparable sensitivity and specificity to colposcopy for detection of CIN2+. HRME could provide a low-cost, point-of-care alternative to colposcopy and biopsy in the prevention of cervical cancer.

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.

Cervical cancer prevention in El Salvador: A prospective evaluation of screening and triage strategies incorporating high-resolution microendoscopy to detect cervical precancer.

Cervical cancer remains a leading cause of cancer death for women in low- and middle-income countries. The goal of our study was to evaluate screening and triage strategies, including high-resolution microendoscopy (HRME), to detect cervical abnormalities concerning for precancer at the point of care. Women (n = 1824) were enrolled at the Instituto de Cáncer de El Salvador. All underwent screening by both human papillomavirus (HPV) testing using careHPV and visual inspection with acetic acid (VIA). Screen-positives, along with 10% of screen-negatives, were invited to return for a follow-up examination that included triage with VIA, colposcopy and HRME imaging. Biopsies were taken of any abnormalities identified. If no abnormalities were identified, then the worst scoring site by HRME was biopsied. The sensitivities of HPV testing and VIA to screen for cervical intraepithelial neoplasia Grade 2 or more severe diagnoses (CIN2+) were 82.1% and 75% (P = .77), while the specificities were 90.4% and 80.9% (P < .001), respectively. The sensitivities of VIA, colposcopy and HRME as triage tests for CIN2+ were 82.1%, 82.1% and 71.4%, respectively (P ≥ .38). HRME had a significantly higher specificity (66.7%) than VIA (51.9%) (P < .001) and colposcopy (53.3%) (P < .001). When evaluating different theoretical screening and triage strategies, screening with HPV testing followed by triage with HRME would result in more women receiving appropriate care (97%) compared to screening with VIA (75%) or HPV alone (90%). Our findings demonstrate that screening with HPV is superior to VIA, and that triage with HRME imaging increases the specificity of detecting CIN2+ at the point of care in a low-resource setting.

Initial Results of First In Vivo Imaging of Bladder Lesions Using a High-Resolution Confocal Microendoscope.

Purpose: Conventional cystoscopy plays an important role in detection of bladder cancer; however, it is difficult to differentiate benign and neoplastic lesions based on cystoscopic appearance alone. Advanced microscopic modalities, such as confocal laser endomicroscopy and optical coherence tomography, have been shown to provide critical histopathologic information to help identify neoplastic bladder lesions in real time, but their availability and clinical adoption are limited due to a high cost. In this study, we present the first use of a novel and low-cost ($ <5000) confocal high-resolution microendoscope (confocal HRME) for in vivo imaging of bladder lesions. Materials and Methods: In a cohort of 15 patients undergoing white light cystoscopy as part of their standard of care, high-resolution images of proflavine-stained bladder lesions were acquired in vivo using the confocal HRME. Based on these images, we evaluated the ability of the confocal HRME to visualize uroepithelium with subcellular resolution and high contrast. Furthermore, we analyzed the cellular architecture and staining patterns of benign and neoplastic bladder lesions in confocal HRME images and compared results to that of standard cystoscopy and histopathology. Results:In vivo imaging in the pilot study demonstrates that the confocal HRME resolved subcellular structures of bladder uroepithelium with high contrast. In a wide range of clinical conditions from normal bladder wall to benign and neoplastic lesions, confocal HRME images revealed important diagnostic features that correlated to histopathology. Conclusions: The confocal HRME provides an affordable, portable, and easy-to-use tool to allow real-time and high-contrast subcellular characterization of bladder lesions, well suited for bladder cancer detection in community and resource-constrained settings. The ClinicalTrials.gov Identifier: NCT02340650.

Algorithm to quantify nuclear features and confidence intervals for classification of oral neoplasia from high-resolution optical images.

Purpose: In vivo optical imaging technologies like high-resolution microendoscopy (HRME) can image nuclei of the oral epithelium. In principle, automated algorithms can then calculate nuclear features to distinguish neoplastic from benign tissue. However, images frequently contain regions without visible nuclei, due to biological and technical factors, decreasing the data available to and accuracy of image analysis algorithms. Approach: We developed the nuclear density-confidence interval (ND-CI) algorithm to determine if an HRME image contains sufficient nuclei for classification, or if a better image is required. The algorithm uses a convolutional neural network to exclude image regions without visible nuclei. Then the remaining regions are used to estimate a confidence interval (CI) for the number of abnormal nuclei per mm 2 , a feature used by a previously developed algorithm (called the ND algorithm), to classify images as benign or neoplastic. The range of the CI determines whether the ND-CI algorithm can classify an image with confidence, and if so, the predicted category. The ND and ND-CI algorithm were compared by calculating their positive predictive value (PPV) and negative predictive value (NPV) on 82 oral biopsies with histopathologically confirmed diagnoses. Results: After excluding the images that could not be classified with confidence, the ND-CI algorithm had higher PPV (65% versus 59%) and NPV (78% versus 75%) than the ND algorithm. Conclusions: The ND-CI algorithm could improve the real-time classification of HRME images of the oral epithelium by informing the user if an improved image is required for diagnosis.