Segmentation and Classification Approaches of Clinically Relevant Curvilinear Structures: A Review.

Detection of curvilinear structures from microscopic images, which help the clinicians to make an unambiguous diagnosis is assuming paramount importance in recent clinical practice. Appearance and size of dermatophytic hyphae, keratitic fungi, corneal and retinal vessels vary widely making their automated detection cumbersome. Automated deep learning methods, endowed with superior self-learning capacity, have superseded the traditional machine learning methods, especially in complex images with challenging background. Automatic feature learning ability using large input data with better generalization and recognition capability, but devoid of human interference and excessive pre-processing, is highly beneficial in the above context. Varied attempts have been made by researchers to overcome challenges such as thin vessels, bifurcations and obstructive lesions in retinal vessel detection as revealed through several publications reviewed here. Revelations of diabetic neuropathic complications such as tortuosity, changes in the density and angles of the corneal fibers have been successfully sorted in many publications reviewed here. Since artifacts complicate the images and affect the quality of analysis, methods addressing these challenges have been described. Traditional and deep learning methods, that have been adapted and published between 2015 and 2021 covering retinal vessels, corneal nerves and filamentous fungi have been summarized in this review. We find several novel and meritorious ideas and techniques being put to use in the case of retinal vessel segmentation and classification, which by way of cross-domain adaptation can be utilized in the case of corneal and filamentous fungi also, making suitable adaptations to the challenges to be addressed.

Knitting Thread Devices: Detecting Candida albicans Using Napkins and Tampons.

Reproducible and in situ microbial detection, particularly of microbes significant in urinary tract infections (UTIs) such as Candida albicans, provides a unique opportunity to bring equity in the healthcare outcomes of disenfranchised groups like women in low-resource settings. Here, we demonstrate a system to potentially detect vulvovaginal candidiasis by leveraging the properties of multifilament cotton threads in the form of microfluidic-thread-based analytical devices (µTADs) to develop a frugal microbial identification assay. A facile mercerization method using heptane wash to boost reagent absorption and penetration is also performed and is shown to be robust compared to other existing conventional mercerization methods. Furthermore, the twisted mercerized fibers are drop-cast with media consisting of l-proline ß-naphthylamide, which undergoes hydrolysis by the enzyme l-proline aminopeptidase secreted by C. albicans, hence signaling the presence of the pathogen via simple color change with a limit of detection of 0.58 × 106 cfu/mL. The flexible and easily disposable thread-based detection device when integrated with menstrual hygiene products showed a detection time of 10 min using spiked vaginal discharge. The developed method boasts a long shelf life and high stability, making it a discreet detection device for testing, which provides new vistas for self-testing multiple diseases that are considered taboo in certain societies.

Thread integrated smart-phone imaging facilitates early turning point colorimetric assay for microbes.

This study employs a commercial multifilament cotton thread as a low-cost microbial identification assay integrated with smartphone-based imaging for high throughput and rapid detection of pathogens. The thread device with inter-twined fibers was drop-cast with test media and a pH indicator. The target pathogens scavenge the media components with different sugars and release acidic by-products, which in turn act as markers for pH-based color change. The developed thread-based proof-of-concept was demonstrated for the visual color detection (red to yellow) of Candida albicans (≈16 hours) and Escherichia coli (≈5 hours). Besides that, using a smart-phone to capture images of the thread-based colorimetric assay facilitates early detection of turning point of the pH-based color change and further reduces the detection time of pathogens viz. Candida albicans (≈10 hours) and Escherichia coli (≈1.5 hours). The reported thread and smartphone integrated image analysis works towards identifying the turning point of the colorimetric change rather than the end-point analysis. Using this approach, the interpretation time can be significantly reduced compared to the existing conventional microbial methods (≈24 hours). The thread-based colorimetric microbial assay represents a ready-to-use, low-cost and straightforward technology with applicability in resource-constrained environments, surpassing the need for frequent fresh media preparation, expensive instrumentation, complex fabrication techniques and expert intervention. The proposed method possesses high scalability and reproducibility, which can be further extended to bio(chemical) assays.