Publications by authors named "J C Cusack"
Article Synopsis
- Logged and disturbed forests, often seen as degraded, actually harbor significant biodiversity and should not be dismissed in conservation efforts.
- A study in Sabah, Malaysia examined the effects of logging intensity on 1,681 species, revealing two important conservation thresholds.
- Lightly logged forests (less than 29% biomass removed) can recover well, while heavily degraded forests (over 68% biomass removed) may need more intensive recovery efforts, highlighting the varying conservation values of logged forests.
Traditionally considered a disease common in the older population, colorectal cancer is increasing in incidence among younger demographics. Evidence suggests that populational- and generational-level shifts in the composition of the human gut microbiome may be tied to the recent trends in gastrointestinal carcinogenesis. This review provides an overview of current research and putative mechanisms behind the rising incidence of colorectal cancer in the younger population, with insight into future interventions that may prevent or reverse the rate of early-onset colorectal carcinoma.
View Article and Find Full Text PDFPurpose: Interpretability is essential for reliable convolutional neural network (CNN) image classifiers in radiological applications. We describe a weakly supervised segmentation model that learns to delineate the target object, trained with only image-level labels ("image contains object" or "image does not contain object"), presenting a different approach towards explainable object detectors for radiological imaging tasks.
Methods: A weakly supervised Unet architecture (WSUnet) was trained to learn lung tumour segmentation from image-level labelled data.