ABSTRACT
BACKGROUND: Profiling the plant root architecture is vital for selecting resilient crops that can efficiently take up water and nutrients. The high-performance imaging tools available to study root-growth dynamics with the optimal resolution are costly and stationary. In addition, performing nondestructive high-throughput phenotyping to extract the structural and morphological features of roots remains challenging. RESULTS: We developed the MultipleXLab: a modular, mobile, and cost-effective setup to tackle these limitations. The system can continuously monitor thousands of seeds from germination to root development based on a conventional camera attached to a motorized multiaxis-rotational stage and custom-built 3D-printed plate holder with integrated light-emitting diode lighting. We also developed an image segmentation model based on deep learning that allows the users to analyze the data automatically. We tested the MultipleXLab to monitor seed germination and root growth of Arabidopsis developmental, cell cycle, and auxin transport mutants non-invasively at high-throughput and showed that the system provides robust data and allows precise evaluation of germination index and hourly growth rate between mutants. CONCLUSION: MultipleXLab provides a flexible and user-friendly root phenotyping platform that is an attractive mobile alternative to high-end imaging platforms and stationary growth chambers. It can be used in numerous applications by plant biologists, the seed industry, crop scientists, and breeding companies.
ABSTRACT
Tzanck smear test is a low-cost, rapid and reliable tool which can be used for the diagnosis of many erosive-vesiculobullous, tumoral and granulomatous diseases. Currently its use is limited mainly due to lack of experience in interpretation of the smears. We developed a deep learning model, TzanckNet, that can identify cells in Tzanck smear test findings. TzanckNet was trained on a retrospective development dataset of 2260 Tzanck smear images collected between December 2006 and December 2019. The finalized model was evaluated using a prospective validation dataset of 359 Tzanck smear images collected from 15 patients during January 2020. It is designed to recognize six cell types (acantholytic cells, eosinophils, hypha, multinucleated giant cells, normal keratinocytes and tadpole cells). For 359 images and 6 cell types, TzanckNet made 2154 predictions. The accuracy was 94.3% (95% CI 93.4-95.3), the sensitivity was 83.7% (95% CI 80.3-87.0) and the specificity was 97.3% (95% CI 96.5-98.1). The area under the receiver operating characteristic curve was 0.974. Our results show that TzanckNet has the potential to lower the experience barrier needed to use this test, broadening its user base, and hence improving patient well-being.
