I am an American-Burmese senior at Edgemont Jr./Sr. High School with deep-rooted interests in the arts, medicine, and biomedical engineering. Much of my art focuses on exploring different aspects of my life including my Burmese cultural heritage and my relationship to different people and the world around me. My work in research reflects my passion for learning about the skin and its systemic relationship to other parts of the body. Through my work, I strive to make an impact in artistic, scientific, and cultural spaces.
Illustrates my Burmese roots, highlighting the tradition of thanaka. Symbolizes self-acceptance and cultural pride.
Represents the concept of sonder, exploring how people may feel disconnected despite close relationships.
Explores control and identity, depicting an individual experiencing body dysmorphia.
Reflects the impact of the pandemic on the elderly, conveying hope amidst trials.
A commentary on superficial judgment, emphasizing themes of identity and critique.
A tribute to my grandmother, symbolizing her legacy with flowers that represent family.
This piece symbolizes breaking through the monotony of everyday life to embrace the vividness of imagination and creativity.
This piece explores the communication gap between youth and the hidden struggles of aging.
Calciphylaxis is a rare and life-threatening disease characterized by calcium deposition in the small arteries of the skin and subcutaneous fatty tissue, primarily associated with advanced chronic kidney disease. This review article discusses the epidemiology, pathology, risk factors, diagnoses, and known management of calciphylaxis and also provides perspectives into further possible treatments of the disease.
Recent advances in machine learning and computer vision have enhanced skin cancer diagnostic models, yet their lack of interpretability remains a barrier to clinical use, as physicians may struggle to trust opaque, “black box” systems. This review article presents a novel diagnostic methodology leveraging Contrastive Language-Image Pre-training (CLIP), enabling physicians to input features in natural language and understand the weight each feature was given in the model’s diagnosis. This approach aims to improve communication between clinicians and machine learning models, allowing for greater trust in AI-driven diagnostics. The CLIP model demonstrates the ability to diagnose skin cancer in a zero-shot setting while providing transparency into the significance of each input feature.