Browse Articles

Osteosarcoma is a type of bone cancer that affects young adults and children. Early diagnosis of osteosarcoma is crucial to successful treatment. The current methods of diagnosis, which include imaging tests and biopsy, are time consuming and prone to human error. Hence, we used deep learning to extract patterns and detect osteosarcoma from histological images. We hypothesized that the combination of two different technologies (transfer learning and data augmentation) would improve the efficacy of osteosarcoma detection in histological images. The dataset used for the study consisted of histological images for osteosarcoma and was quite imbalanced as it contained very few images with tumors. Since transfer learning uses existing knowledge for the purpose of classification and detection, we hypothesized it would be proficient on such an imbalanced dataset. To further improve our learning, we used data augmentation to include variations in the dataset. We further evaluated the efficacy of different convolutional neural network models on this task. We obtained an accuracy of 91.18% using the transfer learning model MobileNetV2 as the base model with various geometric transformations, outperforming the state-of-the-art convolutional neural network based approach.

In the United States, there are currently 17.8 million affected by atopic dermatitis (AD), commonly known as eczema. It is characterized by itching and skin inflammation. AD patients are at higher risk for infections, depression, cancer, and suicide. Genetics, environment, and stress are some of the causes of the disease. With the rise of personalized medicine and the acceptance of gene-editing technologies, AD-related variations need to be identified for treatment. Genome-wide association studies (GWAS) have associated the Filaggrin (FLG) gene with AD but have not identified specific problematic single nucleotide polymorphisms (SNPs). This research aimed to refine known SNPs of FLG for gene editing technologies to establish a causal link between specific SNPs and the diseases and to target the polymorphisms. The research utilized R and its Bioconductor packages to refine data from the National Center for Biotechnology Information's (NCBI's) Variation Viewer. The algorithm filtered the dataset by coding regions and conserved domains. The algorithm also removed synonymous variations and treated non-synonymous, frameshift, and nonsense separately. The non-synonymous variations were refined and ordered by the BLOSUM62 substitution matrix. Overall, the analysis removed 96.65% of data, which was redundant or not the focus of the research and ordered the remaining relevant data by impact. The code for the project can also be repurposed as a tool for other diseases. The research can help solve GWAS's imprecise identification challenge. This research is the first step in providing the refined databases required for gene-editing treatment.

The disinterested willingness a person has for helping others is known as altruism. But is this willingness to help others dependent on external factors that make you more or less inclined to be generous? We hypothesized that generosity in adolescents would depend on external factors and that these factors would change the amount of help given. To evaluate altruism and generosity, we conducted non-anonymous and anonymous variations of the dictator game and ultimatum game experiments and explored the role of anonymity, fairness, and reciprocity in high school students.

In this article, the authors investigate whether coolant temperature affects soil cooling curves of soil with otherwise identical properties. The coolant temperature is representative of environmental temperature, and the authors hypothesized that differences in this temperature would not affect the freezing temperature of soil. Their findings validated their hypothesis providing helpful information relevant to understanding how frost heaves happen and how to predict their occurrence more accurately.

This study explores the link between fingerprints and genetics by analyzing familial fingerprints to show how the fingerprints between family members, and in particular siblings, could be very similar. The hypothesis was that the fingerprints between siblings would be very similar and the dominant fingerprint features within the family would be the same throughout the generations. Fingerprints between the siblings showed a trend of similarity, with only very small differences which makes these fingerprints unique. This work helps to support the link between fingerprints and genetics while providing a modern technological application.

This study analyzes genetic alterations and expression patterns of protein kinases involved in phagocytosis across multiple cancers using TCGA data.

Advertising platforms like Google Ads use AI to drive the algorithms used to maximize advertisers benefits. This study shows that AI does not adjust it strategy based on auction type and highlights the limitations of AI running without explicit guidance.

Here, the authors wanted to explore mathematical paradoxes in which there are multiple contradictory interpretations or analyses for a problem. They used ChatGPT to generate a novel dataset of fairy tales. They found statistical differences between the artificially generated text and human produced text based on the distribution of parts of speech elements.

The authors use machine learning to analyze electroencephalogram data and identify slowing patterns that can indicate undetected disorders like epilepsy or dementia

The authors looked at different models of semantic segmentation to determine which may be best used in the future for segmentation of CT scans to help diagnose certain conditions.