Evaluating the performance of a low-cost mobile phone attachable microscope in cervical cytology

Developing a low-cost, open-source, locally manufactured workstation and computational pipeline for automated histopathology evaluation using deep learning

BACKGROUND

Deployment and access to state-of-the-art precision medicine technologies remains a fundamental challenge in providing equitable global cancer care in low-resource settings. The expansion of digital pathology in recent years and its potential interface with diagnostic artificial intelligence algorithms provides an opportunity to democratize access to personalized medicine. Current digital pathology workstations, however, cost thousands to hundreds of thousands of dollars. As cancer incidence rises in many low- and middle-income countries, the validation and implementation of low-cost automated diagnostic tools will be crucial to helping healthcare providers manage the growing burden of cancer.

METHODS

Here we describe a low-cost ($230) workstation for digital slide capture and computational analysis composed of open-source components. We analyze the predictive performance of deep learning models when they are used to evaluate pathology images captured using this open-source workstation versus images captured using common, significantly more expensive hardware. Validation studies assessed model performance on three distinct datasets and predictive models: head and neck squamous cell carcinoma (HPV positive versus HPV negative), lung cancer (adenocarcinoma versus squamous cell carcinoma), and breast cancer (invasive ductal carcinoma versus invasive lobular carcinoma).

FINDINGS

When compared to traditional pathology image capture methods, low-cost digital slide capture and analysis with the open-source workstation, including the low-cost microscope device, was associated with model performance of comparable accuracy for breast, lung, and HNSCC classification. At the patient level of analysis, AUROC was 0.84 for HNSCC HPV status prediction, 1.0 for lung cancer subtype prediction, and 0.80 for breast cancer classification.

INTERPRETATION

Our ability to maintain model performance despite decreased image quality and low-power computational hardware demonstrates that it is feasible to massively reduce costs associated with deploying deep learning models for digital pathology applications. Improving access to cutting-edge diagnostic tools may provide an avenue for reducing disparities in cancer care between high- and low-income regions.

FUNDING

Funding for this project including personnel support was provided via grants from NIH/NCIR25-CA240134, NIH/NCIU01-CA243075, NIH/NIDCRR56-DE030958, NIH/NCIR01-CA276652, NIH/NCIK08-CA283261, NIH/NCI-SOAR25CA240134, SU2C (Stand Up to Cancer) Fanconi Anemia Research Fund - Farrah Fawcett Foundation Head and Neck Cancer Research Team Grant, and the European UnionHorizon Program (I3LUNG).

Igniting children's enthusiasm for microbes with an origami paper microscope

The COVID-19 pandemic has underscored the urgent need for microbiology literacy in society. Microbiology knowledge, and its dissemination, can help inform and increase the objectivity of important decisions, such as treatment or vaccination. A microbiology learning experience titled "What you can't see can hurt you" was delivered as part of a larger outreach event where children were exposed to various aspects of medicine and health care fields. The activity involved an introduction to and a discussion of bacteria of clinical importance and the use of a smartphone-attachable paper-based foldable microscope. To explore the impact of this activity on participants' interest in science and microbiology, a pre- and post-activity survey of five questions on an emoji-based Likert scale was completed by the participants. A statistically significant increase in their interest in microbes and where to find them, as well as in microscopy, was observed after the event. Making microbes visible to children and allowing them to capture images of microbes exposes them directly and personally to microscopy and microbiology. An affordable low-cost paper-based microscope can become an alternative approach to teaching and learning to deliver clinical microbiology information to a wide audience range.

Utilization of accessible resources in the fabrication of an affordable, portable, high-resolution, 3D printed, digital microscope for Philippine diagnostic applications

Philippine clinical laboratory licensing requirements mandate that diagnostic microscopy for Tuberculosis (TB) sputum microscopy, urinalysis, pap smears, wet smears, an option for complete blood count, stool exams, and malaria thick and thin smears should be accessible and available in health facilities including primary care centers. However, access to these essential diagnostics is hampered by the lack of trained personnel, relatively high costs for supplies and equipment especially in rural and underserved areas. This served as motivation for our team to utilize accessible resources in the form of affordable 3D printers, available CAD software, and components to build our low-cost Openflexure microscope (OFM) prototype. We successfully fabricated our prototype for a total of 310$ with a weight of 525g. We used pathology teaching slides from the Ateneo School of Medicine and Public Health and examined the OFM prototype imaging capabilities. The calculated image resolution was 13% higher compared to an LED light microscope sample captured by a mobile phone at 40x and 15% for 100x. The sampled slide images had adequate clarity with some identifiable cellular features for Rheumatic Heart Disease (RHD), Tuberculosis in soft tissue, and Ascariasis. We were able to correct the color aberrations of the OFM we built and was able to scan images up to 1000x magnification without using oil. Given the features and cost, the OFM prototype can be an attractive and affordable option as an alternative or augmentation to diagnostic microscopy in Philippine primary care. Moreover, it may enable telepathology to support diagnostic microscopy in frontline care.

A review on low-cost microscopes for Open Science

This article presents a review after an exhaustive search that yielded 23 works carried out in the last decade for the availability of optical microscopes with open hardware as a low-cost alternative to commercial systems. These works were developed with the aim of covering needs within several areas such as: Bio Sciences research in institutions with limited resources, diagnosis of diseases and health screenings in large populations in developing countries, and training in educational contexts with a need for high availability of equipment and low replacement cost. The analysis of the selected works allows us to classify the analyzed solutions into two main categories, for which their essential characteristics are enumerated: portable field microscopes and multipurpose automated microscopes. Moreover, this work includes a discussion on the degree of maturity of the solutions in terms of the adoption of practices aligned with the development of Open Science. RESEARCH HIGHLIGHTS: Concise review on low-cost microscopes for developing Open Science, exposing the role of smartphone-based microscopy. The work classifies microscopes in two main categories: (1) portable field microscopes, and (2) multipurpose automated microscopes.

Fabricating a Low-Cost, Microscopy-Compatible Mechanical Testing Device

Most commercially-available mechanical testing devices are bulky, expensive, and unable to evaluate changes in sample microstructure under load. This leaves a crucial gap in understanding between material structure and bulk mechanical properties. Our objective was to fabricate a mechanical testing device small enough to fit in most upright or inverted microscopy stages and able to position samples to allow for simultaneous mechanical and microstructural characterization. Parts were 3D printed using the hobbyist-friendly Fused Filament Fabrication technique, then assembled with commercial fasteners and translation components to create a mechanical testing device that utilized the deflection of plastic posts to determine sample reaction forces under applied strain. Video of sample deformation was analyzed using a custom processing script to calculate stress and strain behavior in an automated and high-throughput manner. This device was able to perform mechanical characterization with an accuracy comparable to commercial mechanical testing devices for a wide range of nonlinear and viscoelastic samples under dry and hydrated conditions. Additionally, the device showed compatibility with different upright and inverted microscopes and was able to demonstrate accurate mechanical testing results when used with these instruments. We successfully developed a device capable of accurately testing a majority of soft materials in the field of Biomedical Engineering with the ability to perform additional microstructural characterization using microscopy at a price point of $600.

Innovations in infectious disease testing: Leveraging COVID-19 pandemic technologies for the future

Innovations in infectious disease testing have improved our abilities to detect and understand the microbial world. The 2019 novel coronavirus infectious disease (COVID-19) pandemic introduced new innovations including non-prescription “over the counter” infectious disease tests, mass spectrometry-based detection of COVID-19 host response, and the implementation of artificial intelligence (AI) and machine learning (ML) to identify individuals infected by the severe acute respiratory syndrome - coronavirus – 2 (SARS-CoV-2). As the world recovers from the COVID-19 pandemic; these innovative solutions will give rise to a new era of infectious disease tests extending beyond the detection of SARS-CoV-2. To this end, the purpose of this review is to summarize current trends in infectious disease testing and discuss innovative applications specifically in the areas of POC testing, MS, molecular diagnostics, sample types, and AI/ML.

Impact of mobile devices on cancer diagnosis in cytology

BACKGROUND

Digital pathology has widened pathologists' opportunities to examine both surgical and cytological samples. Recently, portable mobile devices like tablets and smartphones have been tested for application with digital technologies including static, dynamic, and more recently whole slide imaging. This study aimed to review the published literature on the impact of mobile devices on cancer diagnoses in cytology. This analysis focused on their diagnostic potential, technical details, critical issues and pitfalls, and economical aspects.

METHODS

A systematic search was carried out in the electronic databases Embase and PubMed. Studies dealing with the application of mobile devices for diagnosing cancer on cytological specimens were included. The quality of studies was assessed with the QUADAS-2 tool. The main themes addressed were the comparison of manual examination with light microscopy and the use of mobile tools for primary diagnosis. The technical features of different models of smartphones and tablets, software, and adapters were also studied in terms of feasibility and costs-analysis.

RESULTS

Of 2458 retrieved articles, 18 were included. Concordance with light microscopy was good and diagnostic performance comparable with an expert pathologist's diagnosis. The mobile devices studied differed, sometimes significantly, in terms of speed and cost. The utility was improved by employing specifically designed adapters. Image acquisition and transmission represent the main critical points in almost all studies.

CONCLUSION

The use of mobile devices demonstrated promising results regarding the digital evaluation of cytological samples. Widespread adoption even in underserved areas is anticipated following validation studies, technology improvements, and reduction in the costs.

Foldscope: A smartphone based diagnostic tool for fungal keratitis

Purpose:

Smartphone-based microscopy tool like foldscope (FS) may serve the purpose of a low-cost diagnostic alternative to the compound light microscope especially in areas with limited resources. The purpose of this study was to detect fungal pathogens causing keratitis on direct smear by smartphone-mounted FS and to evaluate the efficacy of FS against routine compound light microscope (CLM).

Methods:

The prospective study was conducted at a tertiary eye care center from September 2019 to March 2020. The study included 60 smear examinations (Gram stain [GM] n = 30, Lactophenol Cotton Blue [LCB] n = 30) to detect fungal pathogens from corneal scraping material of clinically suspected fungal keratitis (FK) cases. The diagnostic utility of FS was compared with CLM for both GM and LCB wet mount. Data collected were used to quantify the agreement using Cohen’s kappa between CLM and FS imaging.

Results:

Forty-six samples out of 60 were positive for fungi using CLM. GM stain and LCB showed 22/30 (73.33%) and 24/30 (80%) positive results with CLM, respectively. Moderate agreement (0.49) was observed between CLM and FS with the smartphone method. LCB mount showed high specificity of 1.00 over 0.87 of GM stain for FS with the smartphone.

Conclusion:

Direct smear can be an early and sensitive measure to diagnose FK other than clinical suspicion. The smartphone-mounted FS has limited sensitivity as an alternative to CLM, but excellent specificity in the present study for FK. The FS as a smartphone-based diagnostic tool is simple, portable, and inexpensive in resource-constrained rural or remote clinical and public health settings in the absence of CLM and other higher diagnostic modalities.

Foldscope: Diagnostic Accuracy and Feasibility of its Use in National Malaria Control Program

Background

Malaria has been an important public health all over the globe. Although conventional light microscopy is the gold standard of diagnosis, light microscopes are heavy, fragile, costly, and electricity dependent. Rapid diagnostic tests (RDTs) have become more popular but perform badly in temperate climate. This is because the RDT kits require maintenance of cold chain for its optimal use. In this regard, there is a recent interest in handheld malaria microscopy at the point of care in the field setting. Foldscopes are cheap, handy, nonfragile, and use mobile camera for illumination. The purpose of the study was to find whether foldscope can be used in the national vector borne disease control program (NVBDCP) in India.

Methods

Ten laboratory technicians were trained in identifying malaria parasites using foldscope and their mobiles. Later, they were provided with unassembled foldscope to document their test results for the preidentified malaria slides. The blood smears were stained as per the protocol of NVBDCP. The report of the index test (foldscope microscopy) was compared with the reference test (conventional microscopy).

Results

The sensitivity and specificity of the index test was found to be 13.3% (6.257-26.18), specificity of 97.78% (88.43-99.61), positive predictive value 85.71% (48.69-97.43), and negative predictive value 53.01% (42.38-63.38). The devise failure rate and test failure rate were 20% and 11.7%. The kappa agreement between the index and reference microscopy was only 11% and the McNemar P < 0.01.

Conclusion

The ×400 foldscope at its present magnification and illumination cannot be utilized in the field under NVBDCP.