Search for: All records

Breast cancer is the leading cancer affecting women globally. Despite deep learning models making significant strides in diagnosing and treating this disease, ensuring fair outcomes across diverse populations presents a challenge, particularly when certain demographic groups are underrepresented in training datasets. Addressing the fairness of AI models across varied demographic backgrounds is crucial. This study analyzes demographic representation within the publicly accessible Emory Breast Imaging Dataset (EMBED), which includes de-identified mammography and clinical data. We spotlight the data disparities among racial and ethnic groups and assess the biases in mammography image classification models trained on this dataset, specifically ResNet-50 and Swin Transformer V2. Our evaluation of classification accuracies across these groups reveals significant variations in model performance, highlighting concerns regarding the fairness of AI diagnostic tools. This paper emphasizes the imperative need for fairness in AI and suggests directions for future research aimed at increasing the inclusiveness and dependability of these technologies in healthcare settings. Code is available at: https://github.com/kuanhuang0624/EMBEDFairModels. 

Conductive polymers, owing to their tunable mechanical and electrochemical properties, are viable candidates to replace metallic components for the development of biosensors and bioelectronics. However, conducting fibers/wires fabricated from these intrinsically conductive and mechanically flexible polymers are typically produced without protective coatings for physiological environments. Providing sheathed conductive fibers/wires can open numerous opportunities for fully organic biodevices. In this work, we report on a facile method to fabricate core-sheath poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate) PEDOT:PSS-silk fibroin conductive wires. The conductive wires are formed through a wet-spinning process, and then coated with an optically transparent, photocrosslinkable silk fibroin sheath for insulation and protection in a facile and scalable process. The sheathed fibers were evaluated for their mechanical and electrical characteristics and overall stability. These wires can serve as flexible connectors to an organic electrode biosensor. The entire, fully organic, biodegradable, and free-standing flexible biosensor demonstrated a high sensitivity and rapid response for the detection of ascorbic acid as a model analyte. The entire system can be proteolytically biodegraded in a few weeks. Such organic systems can therefore provide promising solutions to address challenges in transient devices and environmental sustainability.