We report the application of supervised machine learning to the automated classification of lipid droplets in label-free, quantitative-phase images. By comparing various machine learning methods commonly used in biomedical imaging and remote sensing, we found convolutional neural networks to outperform others, both quantitatively and qualitatively. We describe our imaging approach, all implemented machine learning methods, and their performance with respect to computational efficiency, required training resources, and relative method performance measured across multiple metrics. Overall, our results indicate that quantitative-phase imaging coupled to machine learning enables accurate lipid droplet classification in single living cells. As such, the present paradigm presents an excellent alternative of the more common fluorescent and Raman imaging modalities by enabling label-free, ultra-low phototoxicity, and deeper insight into the thermodynamics of metabolism of single cells.

Medical education faces the dual challenge of addressing cognitive overload and sustaining student engagement, particularly in complex subjects such as pharmacology. This study introduces Cinematic Clinical Narratives (CCNs) as an innovative approach to teaching antiparasitic pharmacology, combining generative artificial intelligence (genAI), edutainment, and mnemonic-based learning. The intervention involved two short films, Alien: Parasites Within and Wormquest, designed to teach antiparasitic pharmacology to first-year medical students. A control group of students only received traditional text-based clinical cases, while the experimental group engaged with the CCNs in an active learning environment. Students who received the CCN material scored an average of 8% higher on exam questions related to the material covered by the CCN compared to students in the control group. Results also showed that the CCNs improved engagement and interest among students, as evidenced by significantly higher scores on the Situational Interest Survey for Multimedia (SIS-M) compared to traditional methods. Notably, students preferred CCNs for their storytelling, visuals, and interactive elements. This study underscores the potential of CCNs as a supplementary educational tool, and suggests the potential for broader applications across other medical disciplines outside of antiparasitic pharmacology. By leveraging genAI and edutainment, CCNs represent a scalable and innovative approach to enhancing the medical learning experience.

Open science and open data within scholarly research programs are growing both in popularity and by requirement from grant funding agencies and journal publishers. A central component of open data management, especially on collaborative, multidisciplinary, and multi-institutional science projects, is documentation of complete and accurate metadata, workflow, and source code in addition to access to raw data and data products to uphold FAIR (Findable, Accessible, Interoperable, Reusable) principles. Although best practice in data/metadata management is to use established internationally accepted metadata schemata, many of these standards are discipline-specific making it difficult to catalog multidisciplinary data and data products in a way that is easily findable and accessible. Consequently, scattered and incompatible metadata records create a barrier to scientific innovation, as researchers are burdened to find and link multidisciplinary datasets. One possible solution to increase data findability, accessibility, interoperability, reproducibility, and integrity within multi-institutional and interdisciplinary projects is a centralized and integrated data management platform. Overall, this type of interoperable framework supports reproducible open science and its dissemination to various stakeholders and the public in a FAIR manner by providing direct access to raw data and linking protocols, metadata and supporting workflow materials.

Medical education faces the dual challenge of addressing cognitive overload and sustaining student engagement, particularly in complex subjects such as pharmacology. This study introduces Cinematic Clinical Narratives (CCNs) as an innovative approach to teaching antiparasitic pharmacology, combining generative artificial intelligence (genAI), edutainment, and mnemonic-based learning. The intervention involved two short films, Alien: Parasites Within and Wormquest, designed to teach antiparasitic pharmacology to first-year medical students. A control group of students only received traditional text-based clinical cases, while the experimental group engaged with the CCNs in an active learning environment. Students who received the CCN material scored an average of 8% higher on exam questions related to the material covered by the CCN compared to students in the control group. Results also showed that the CCNs improved engagement and interest among students, as evidenced by significantly higher scores on the Situational Interest Survey for Multimedia (SIS-M) compared to traditional methods. Notably, students preferred CCNs for their storytelling, visuals, and interactive elements. This study underscores the potential of CCNs as a supplementary educational tool, and suggests the potential for broader applications across other medical disciplines outside of antiparasitic pharmacology. By leveraging genAI and edutainment, CCNs represent a scalable and innovative approach to enhancing the medical learning experience.

Enhancing the reliability and reproducibility of optical microscopy by reducing specimen irradiance continues to be an important biotechnology target. As irradiance levels are reduced, however, the particle nature of light is heightened, giving rise to Poisson noise, or photon sparsity that restricts only a few (0.5%) image pixels to comprise a photon. Photon sparsity can be addressed by collecting approximately 200 photons per pixel; this, however, requires long acquisitions and, as such, suboptimal imaging rates. Here, we introduce near-zero photon bioimaging, a method that operates at kHz rates and 10,000-fold lower irradiance than standard microscopy. To achieve this level of performance, we uniquely combined a judiciously designed epifluorescence microscope enabling ultralow background levels and AI that learns to reconstruct biological images from as low as 0.01 photons per pixel. We demonstrate that near-zero photon bioimaging captures the structure of multicellular and subcellular features with high fidelity, including features represented by nearly zero photons. Beyond optical microscopy, the near-zero photon bioimaging paradigm can be applied in remote sensing, covert applications, and biomedical imaging that utilize damaging or quantum light.

We report the application of supervised machine learning to the automated classification of lipid droplets in label-free, quantitative-phase images. By comparing various machine learning methods commonly used in biomedical imaging and remote sensing, we found convolutional neural networks to outperform others, both quantitatively and qualitatively. We describe our imaging approach, all implemented machine learning methods, and their performance with respect to computational efficiency, required training resources, and relative method performance measured across multiple metrics. Overall, our results indicate that quantitative-phase imaging coupled to machine learning enables accurate lipid droplet classification in single living cells. As such, the present paradigm presents an excellent alternative of the more common fluorescent and Raman imaging modalities by enabling label-free, ultra-low phototoxicity, and deeper insight into the thermodynamics of metabolism of single cells. Author Summary: Recently, quantitative-phase imaging (QPI) has demonstrated the ability to elucidate novel parameters of cellular physiology and metabolism without the need for fluorescent staining. Here, we apply label-free, low photo-toxicity QPI to yeast cells in order to identify lipid droplets (LDs), an important organelle with key implications in human health and biofuel development. Because QPI yields low specificity, we explore the use of modern machine learning methods to rapidly identify intracellular LDs with high discriminatory power and accuracy. In recent years, machine learning has demonstrated exceptional abilities to recognize and segment objects in biomedical imaging, remote sensing, and other areas. Trained machine learning classifiers can be combined with QPI within high-throughput analysis pipelines, allowing for efficient and accurate identification and quantification of cellular components. Non-invasive, accurate and high-throughput classification of these organelles will accelerate research and improve our understanding of cellular functions with beneficial applications in biofuels, biomedicine, and more.