Comparison of automated and expert human grading of diabetic retinopathy using smartphone-based retinal photography.

PURPOSE: The aim of this study is to investigate the efficacy of a mobile platform that combines smartphone-based retinal imaging with automated grading for determining the presence of referral-warranted diabetic retinopathy (RWDR). METHODS: A smartphone-based camera (RetinaScope) was used by non-ophthalmic personnel to image the retina of patients with diabetes. Images were analyzed with the Eyenuk EyeArt® system, which generated referral recommendations based on presence of diabetic retinopathy (DR) and/or markers for clinically significant macular oedema. Images were independently evaluated by two masked readers and categorized as refer/no refer. The accuracies of the graders and automated interpretation were determined by comparing results to gold standard clinical diagnoses. RESULTS: A total of 119 eyes from 69 patients were included. RWDR was present in 88 eyes (73.9%) and in 54 patients (78.3%). At the patient-level, automated interpretation had a sensitivity of 87.0% and specificity of 78.6%; grader 1 had a sensitivity of 96.3% and specificity of 42.9%; grader 2 had a sensitivity of 92.5% and specificity of 50.0%. At the eye-level, automated interpretation had a sensitivity of 77.8% and specificity of 71.5%; grader 1 had a sensitivity of 94.0% and specificity of 52.2%; grader 2 had a sensitivity of 89.5% and specificity of 66.9%. DISCUSSION: Retinal photography with RetinaScope combined with automated interpretation by EyeArt achieved a lower sensitivity but higher specificity than trained expert graders. Feasibility testing was performed using non-ophthalmic personnel in a retina clinic with high disease burden. Additional studies are needed to assess efficacy of screening diabetic patients from general population.

A Smartphone-Based Tool for Rapid, Portable, and Automated Wide-Field Retinal Imaging.

PURPOSE: High-quality, wide-field retinal imaging is a valuable method for screening preventable, vision-threatening diseases of the retina. Smartphone-based retinal cameras hold promise for increasing access to retinal imaging, but variable image quality and restricted field of view can limit their utility. We developed and clinically tested a smartphone-based system that addresses these challenges with automation-assisted imaging. METHODS: The system was designed to improve smartphone retinal imaging by combining automated fixation guidance, photomontage, and multicolored illumination with optimized optics, user-tested ergonomics, and touch-screen interface. System performance was evaluated from images of ophthalmic patients taken by nonophthalmic personnel. Two masked ophthalmologists evaluated images for abnormalities and disease severity. RESULTS: The system automatically generated 100° retinal photomontages from five overlapping images in under 1 minute at full resolution (52.3 pixels per retinal degree) fully on-phone, revealing numerous retinal abnormalities. Feasibility of the system for diabetic retinopathy (DR) screening using the retinal photomontages was performed in 71 diabetics by masked graders. DR grade matched perfectly with dilated clinical examination in 55.1% of eyes and within 1 severity level for 85.2% of eyes. For referral-warranted DR, average sensitivity was 93.3% and specificity 56.8%. CONCLUSIONS: Automation-assisted imaging produced high-quality, wide-field retinal images that demonstrate the potential of smartphone-based retinal cameras to be used for retinal disease screening. TRANSLATIONAL RELEVANCE: Enhancement of smartphone-based retinal imaging through automation and software intelligence holds great promise for increasing the accessibility of retinal screening.

Transient external force induces phenotypic reversion of malignant epithelial structures via nitric oxide signaling.

Non-malignant breast epithelial cells cultured in three-dimensional laminin-rich extracellular matrix (lrECM) form well organized, growth-arrested acini, whereas malignant cells form continuously growing disorganized structures. While the mechanical properties of the microenvironment have been shown to contribute to formation of tissue-specific architecture, how transient external force influences this behavior remains largely unexplored. Here, we show that brief transient compression applied to single malignant breast cells in lrECM stimulated them to form acinar-like structures, a phenomenon we term 'mechanical reversion.' This is analogous to previously described phenotypic 'reversion' using biochemical inhibitors of oncogenic pathways. Compression stimulated nitric oxide production by malignant cells. Inhibition of nitric oxide production blocked mechanical reversion. Compression also restored coherent rotation in malignant cells, a behavior that is essential for acinus formation. We propose that external forces applied to single malignant cells restore cell-lrECM engagement and signaling lost in malignancy, allowing them to reestablish normal-like tissue architecture.

Mobile microscopy as a screening tool for oral cancer in India: A pilot study.

Oral cancer is the most common type of cancer among men in India and other countries in South Asia. Late diagnosis contributes significantly to this mortality, highlighting the need for effective and specific point-of-care diagnostic tools. The same regions with high prevalence of oral cancer have seen extensive growth in mobile phone infrastructure, which enables widespread access to telemedicine services. In this work, we describe the evaluation of an automated tablet-based mobile microscope as an adjunct for telemedicine-based oral cancer screening in India. Brush biopsy, a minimally invasive sampling technique was combined with a simplified staining protocol and a tablet-based mobile microscope to facilitate local collection of digital images and remote evaluation of the images by clinicians. The tablet-based mobile microscope (CellScope device) combines an iPad Mini with collection optics, LED illumination and Bluetooth-controlled motors to scan a slide specimen and capture high-resolution images of stained brush biopsy samples. Researchers at the Mazumdar Shaw Medical Foundation (MSMF) in Bangalore, India used the instrument to collect and send randomly selected images of each slide for telepathology review. Evaluation of the concordance between gold standard histology, conventional microscopy cytology, and remote pathologist review of the images was performed as part of a pilot study of mobile microscopy as a screening tool for oral cancer. Results indicated that the instrument successfully collected images of sufficient quality to enable remote diagnoses that show concordance with existing techniques. Further studies will evaluate the effectiveness of oral cancer screening with mobile microscopy by minimally trained technicians in low-resource settings.

Point-of-care quantification of blood-borne filarial parasites with a mobile phone microscope.

Parasitic helminths cause debilitating diseases that affect millions of people in primarily low-resource settings. Efforts to eliminate onchocerciasis and lymphatic filariasis in Central Africa through mass drug administration have been suspended because of ivermectin-associated serious adverse events, including death, in patients infected with the filarial parasite Loa loa. To safely administer ivermectin for onchocerciasis or lymphatic filariasis in regions co-endemic with L. loa, a strategy termed "test and (not) treat" has been proposed whereby those with high levels of L. loa microfilariae (>30,000/ml) that put them at risk for life-threatening serious adverse events are identified and excluded from mass drug administration. To enable this, we developed a mobile phone-based video microscope that automatically quantifies L. loa microfilariae in whole blood loaded directly into a small glass capillary from a fingerprick without the need for conventional sample preparation or staining. This point-of-care device automatically captures and analyzes videos of microfilarial motion in whole blood using motorized sample scanning and onboard motion detection, minimizing input from health care workers and providing a quantification of microfilariae per milliliter of whole blood in under 2 min. To validate performance and usability of the mobile phone microscope, we tested 33 potentially Loa-infected patients in Cameroon and confirmed that automated counts correlated with manual thick smear counts (94% specificity; 100% sensitivity). Use of this technology to exclude patients from ivermectin-based treatment at the point of care in Loa-endemic regions would allow resumption/expansion of mass drug administration programs for onchocerciasis and lymphatic filariasis in Central Africa.

Multicellular architecture of malignant breast epithelia influences mechanics.

Cell-matrix and cell-cell mechanosensing are important in many cellular processes, particularly for epithelial cells. A crucial question, which remains unexplored, is how the mechanical microenvironment is altered as a result of changes to multicellular tissue structure during cancer progression. In this study, we investigated the influence of the multicellular tissue architecture on mechanical properties of the epithelial component of the mammary acinus. Using creep compression tests on multicellular breast epithelial structures, we found that pre-malignant acini with no lumen (MCF10AT) were significantly stiffer than normal hollow acini (MCF10A) by 60%. This difference depended on structural changes in the pre-malignant acini, as neither single cells nor normal multicellular acini tested before lumen formation exhibited these differences. To understand these differences, we simulated the deformation of the acini with different multicellular architectures and calculated their mechanical properties; our results suggest that lumen filling alone can explain the experimentally observed stiffness increase. We also simulated a single contracting cell in different multicellular architectures and found that lumen filling led to a 20% increase in the "perceived stiffness" of a single contracting cell independent of any changes to matrix mechanics. Our results suggest that lumen filling in carcinogenesis alters the mechanical microenvironment in multicellular epithelial structures, a phenotype that may cause downstream disruptions to mechanosensing.

Quantitative imaging with a mobile phone microscope.

Use of optical imaging for medical and scientific applications requires accurate quantification of features such as object size, color, and brightness. High pixel density cameras available on modern mobile phones have made photography simple and convenient for consumer applications; however, the camera hardware and software that enables this simplicity can present a barrier to accurate quantification of image data. This issue is exacerbated by automated settings, proprietary image processing algorithms, rapid phone evolution, and the diversity of manufacturers. If mobile phone cameras are to live up to their potential to increase access to healthcare in low-resource settings, limitations of mobile phone-based imaging must be fully understood and addressed with procedures that minimize their effects on image quantification. Here we focus on microscopic optical imaging using a custom mobile phone microscope that is compatible with phones from multiple manufacturers. We demonstrate that quantitative microscopy with micron-scale spatial resolution can be carried out with multiple phones and that image linearity, distortion, and color can be corrected as needed. Using all versions of the iPhone and a selection of Android phones released between 2007 and 2012, we show that phones with greater than 5 MP are capable of nearly diffraction-limited resolution over a broad range of magnifications, including those relevant for single cell imaging. We find that automatic focus, exposure, and color gain standard on mobile phones can degrade image resolution and reduce accuracy of color capture if uncorrected, and we devise procedures to avoid these barriers to quantitative imaging. By accommodating the differences between mobile phone cameras and the scientific cameras, mobile phone microscopes can be reliably used to increase access to quantitative imaging for a variety of medical and scientific applications.

Mobile digital fluorescence microscopy for diagnosis of tuberculosis.

Access to sputum smear microscopy in high-tuberculosis (TB)-burden regions is limited by a scarcity of microscopes and experienced technicians. We evaluated the accuracy of CellScope, a novel digital fluorescence microscope that may expand access to microscopy. The study utilized smear microscopy slides prepared from sputum specimens submitted by consecutive adults with ≥ 2 weeks of cough who were admitted to Mulago Hospital (Kampala, Uganda). Conventional light-emitting diode (LED) fluorescence microscopy (FM) and mycobacterial culture were performed by experienced technicians. Two U.S.-based postgraduate researchers without prior microscopy experience restained, imaged, and interpreted the slides using CellScope. We assessed whether sensitivity and specificity of CellScope-based LED FM was noninferior to conventional LED FM by using a preselected margin of inferiority of 15%. Of 525 patients included, 72% were HIV seropositive and 39% had culture-confirmed TB. The proportions of positive results were similar with CellScope and conventional LED FM (34% versus 32%, respectively; P = 0.32), and agreement was substantial. CellScope accuracy was within the noninferiority margin for both sensitivity (63% versus 70%; difference, -7%; 95% confidence interval [CI], -13% to -1%) and specificity (85% versus 92%; difference, -7%; 95% CI, -12% to -3%). A subanalysis of 43 slides evaluated by each CellScope reader found substantial interreader reliability (custom-weighted kappa, 0.65) and variable intrareader reliability (custom-weighted kappa, 0.11 versus 0.48). CellScope offers promise for expanding microscopy services. Future studies should evaluate the device when operated by health workers in low-resource settings, the feasibility of image transmission and analysis by experienced microscopists, and the accuracy of automated image analysis algorithms.

Automated tuberculosis diagnosis using fluorescence images from a mobile microscope.

In low-resource areas, the most common method of tuberculosis (TB) diagnosis is visual identification of rod-shaped TB bacilli in microscopic images of sputum smears. We present an algorithm for automated TB detection using images from digital microscopes such as CellScope, a novel, portable device capable of brightfield and fluorescence microscopy. Automated processing on such platforms could save lives by bringing healthcare to rural areas with limited access to laboratory-based diagnostics. Our algorithm applies morphological operations and template matching with a Gaussian kernel to identify candidate TB-objects. We characterize these objects using Hu moments, geometric and photometric features, and histograms of oriented gradients and then perform support vector machine classification. We test our algorithm on a large set of CellScope images (594 images corresponding to 290 patients) from sputum smears collected at clinics in Uganda. Our object-level classification performance is highly accurate, with average precision of 89.2% +/- 2.1%. For slide-level classification, our algorithm performs at the level of human readers, demonstrating the potential for making a significant impact on global healthcare.