Rebecca
Li
Sponsor: Mohsen Mesgaran, Ph.D. Plant Sciences The prognosis of breast cancer is critically dependent on the presence of metastases in sentinel lymph nodes (SLN). Traditional histopathological examination of these nodes, while standard, is labor-intensive and may miss small metastatic occurrences. Recent advances in pathology have seen the rise of convolutional neural networks (CNNs) as a transformative tool, particularly in automating the analysis of whole-slide images (WSIs). This study focuses on assessing the effectiveness of a CNN-based model in identifying lymph node metastases in breast cancer patients. The study utilized a public dataset from the PatchCamelyon (PCam), and a total of 80,000 patches of healthy tissue and 80,000 patches of metastatic tissue were assessed in the training set, while 57,458 patches of pathological tissue were evaluated in the test dataset. Considering the classification by board certified pathologists as a reference, the trained deep net showed high accuracy (0.937), precision (0.971), validation AUC (0.979), and a low validation loss of 0.016. Our data show that a deep learning system can be trained to recognize metastatic cancer, outperforming pathologists under time constraints (mean AUC of 0.810), showcasing its potential for clinical application. U.S. - China Trade War: A Global Value Chain Perspective
Abstract profile. Full document pending author claim.
Authors:
Rebecca Li
Date Created:
Not specified
Course Title:
Professor:
Not specified
About Paper:
In March 2018, former U.S. President Donald Trump implemented punitive tariffs on Chinese imports. In response, China imposed retaliatory tariffs on U.S. goods in April, leading to tariff escalations and counter-tariffs within a short time between the two largest economies in the world, which eventually turned into the U.S.- China trade war. This conflict, rooted in a deep-seated trade imbalance, has raised crucial questions about the global trade architecture and the role of national policies in shaping international economic relations. This research delves into the underlying causes of the trade war, particularly focusing on the significant trade imbalance between the U.S. and China. By employing the Global Value Chain (GVC) model to analyze the participation and position indices of both nations within global trade networks, this study offers a nuanced understanding of how and why this imbalance has contributed to the onset of the trade war. By calculating the global value chain participation and position indices of both countries, we will examine how the huge trade imbalance between the U.S. and China was created and how tariffs being used as a "weapon" in the trade war. Traffic Related Air Pollution, Stress and Lung Pathology Diane Li
Source:
UC Davis / Economics / 2024
Topics:
No topics listed
Co-authors:
Rebecca Li