Publications by authors named "A G Casson"
Harrold et al. evaluate the fertility impact of checkpoint inhibitor blockade (ICB), demonstrating that unlike in utero exposure, post-exposure conception appears to result in uncomplicated pregnancies and healthy progeny. They demonstrate contemporaneous monitoring of temporal female hormonal fluctuations before, on, and post ICB exposure and prior to successful embryo implantation.
View Article and Find Full Text PDFArticle Synopsis
- A new AI model was developed for diagnosing invasive lobular carcinoma (ILC) in breast cancer, using CDH1 biallelic mutations as a reliable genetic ground truth instead of subjective histologic features.
- The model demonstrated high accuracy in predicting these mutations (95%) and diagnosing ILC (96%), with additional insights into other mechanisms of CDH1 inactivation found in some samples.
- Validation across various patient cohorts supported the model's effectiveness (accuracy of 0.95 and 0.89), showcasing the potential of using genetic data to improve AI diagnostics in pathology.
The analysis of histopathology images with artificial intelligence aims to enable clinical decision support systems and precision medicine. The success of such applications depends on the ability to model the diverse patterns observed in pathology images. To this end, we present Virchow, the largest foundation model for computational pathology to date.
View Article and Find Full Text PDFObjective: To remove signal contamination in electroencephalogram (EEG) traces coming from ocular, motion, and muscular artifacts which degrade signal quality. To do this in real-time, with low computational overhead, on a mobile platform in a channel count independent manner to enable portable Brain-Computer Interface (BCI) applications.
Methods: We propose a Deep AutoEncoder (DAE) neural network for single-channel EEG artifact removal, and implement it on a smartphone via TensorFlow Lite.