Browse Articles

Microwave energy (ME) is used in the medical field to denature protein structures, resulting in inactivation or destruction of abnormal cells. Identifying the extent of destruction of abnormal tissue (cancer tissue or tissue with abnormal electrical activity) is essential for accomplishing successful therapy and reducing collateral damage. Our study was an ex vivo assessment of the changes on ultrasound scans (US) in chicken tissue exposed to ME. We hypothesized that any changes in tissue structures would be recognized on the reflected ultrasound waves. Ultrasound scans of tissues change with exposure to microwaves with increasing reflection of ultrasound waves. With exposure to microwaves, surface level brightness on the ultrasound scans increases statistically significantly. The findings could be used in heat related (ME and radiofrequency) procedures where clinicians would be able to actively assess lesions in real-time. Further studies are required to assess changes in tissue during active exposure to different types of energies.

To best identify tuberculosis and pneumonia diagnoses in chest x-rays, the authors compare different deep learning convolution neural networks.

Cell segmentation is the task of identifying cell nuclei instances in fluorescence microscopy images. The goal of this paper is to benchmark the performance of representative deep learning techniques for cell nuclei segmentation using standard datasets and common evaluation criteria. This research establishes an important baseline for cell nuclei segmentation, enabling researchers to continually refine and deploy neural models for real-world clinical applications.

In this study the author undertakes a careful characterization of a special type of chemical reaction, called an oscillating Belousov-Zhabotinsky (or B-Z) reaction, which has a number of existing applications in biomedical engineering as well as the potential to be useful in future developments in other fields of science and engineering. Specifically, she uses experimental measurements in combination with computational analysis to investigate whether the reaction is cohesive – that is, whether the oscillations between chemical states will remain consistent or change over time as the reaction progresses. Her results indicate that the reaction is not cohesive, providing an important foundation for the development of future technologies using B-Z reactions.

In this report, Bhardwaj and Sharma tested whether placing specific plants indoors can reduce levels of indoor air pollution that can lead to lung-related illnesses. Using machine learning, they show that plants improved overall indoor air quality and reduced levels of particulate matter. They suggest that plant-based interventions coupled with sensors may be a useful long-term solution to reducing and maintaining indoor air pollution.

In this study, the authors investigate the antimicrobial effects of berberine and berberine analogs. Berberine is extracted from plants and is a naturally occurring alkaloid, and is also excited photochemically. Using three different assays, the authors tested whether these compounds would inhibit bacterial growth. They found that these compounds were antibacterial and even more so when used with photoirradiation. This study has important antibacterial implications.

The application of machine learning techniques has facilitated the automatic annotation of behavior in video sequences, offering a promising approach for ethological studies by reducing the manual effort required for annotating each video frame. Nevertheless, before solely relying on machine-generated annotations, it is essential to evaluate the accuracy of these annotations to ensure their reliability and applicability. While it is conventionally accepted that there cannot be a perfect annotation, the degree of error associated with machine-generated annotations should be commensurate with the error between different human annotators. We hypothesized that machine learning supervised with adequate human annotations would be able to accurately predict body parts from video sequences. Here, we conducted a comparative analysis of the quality of annotations generated by humans and machines for the body parts of sheep during treadmill walking. For human annotation, two annotators manually labeled six body parts of sheep in 300 frames. To generate machine annotations, we employed the state-of-the-art pose-estimating library, DeepLabCut, which was trained using the frames annotated by human annotators. As expected, the human annotations demonstrated high consistency between annotators. Notably, the machine learning algorithm also generated accurate predictions, with errors comparable to those between humans. We also observed that abnormal annotations with a high error could be revised by introducing Kalman Filtering, which interpolates the trajectory of body parts over the time series, enhancing robustness. Our results suggest that conventional transfer learning methods can generate behavior annotations as accurate as those made by humans, presenting great potential for further research.

In this study, the authors develop a new hydrogel using photochemical crosslinking with bovine serum albumin and methylene blue. They find that this new hydrogel has some useful applications!

Parkinson’s disease (PD) is a prevalent neurodegenerative disorder in the U.S., second only to Alzheimer’s disease. Current diagnostic methods are often inefficient and dependent on clinical exams. This study explored using machine and deep learning to enhance PD diagnosis by analyzing spiral drawings affected by hand tremors, a common PD symptom.