Publications by authors named "Rose G McHardy"
Background: A rapid, low-cost blood test that can be applied to reliably detect multiple different cancer types would be transformational.
Methods: In this large-scale discovery study (n = 2092 patients) we applied the Dxcover® Cancer Liquid Biopsy to examine eight different cancers. The test uses Fourier transform infrared (FTIR) spectroscopy and machine-learning algorithms to detect cancer.
Article Synopsis
- Deep learning (DL) is increasingly applied in cancer diagnostics, but it often needs large datasets to avoid overfitting, which can be tough to gather.
- This study investigates data augmentation techniques using ATR-FTIR spectra from patient serum samples, comparing non-generative methods with Wasserstein generative adversarial networks (WGANs) to enhance a convolutional neural network (CNN) for distinguishing pancreatic cancer from non-cancer samples.
- Results show WGAN significantly improved CNN performance, boosting the area under the receiver operating characteristic curve (AUC) for pancreatic cancer detection from 0.661 to 0.757, while also enhancing colorectal cancer model AUC from 0.905 to 0.955, highlighting the