PERFORMANCE OF SIMPLE NEURAL NETWORKS IN THE DETECTION OF RECTAL TUMORS
This study investigated the application of neural networks for detecting rectal tumor regions in patients using computed tomography (CT) images. The study included 138 patients, while two CT scans with a healthy rectum were included to balance the dataset, resulting in a total of 3566 images. For each image, pixel values along the contour and withi...
By Edib Dobardzic, Ivana Mišković, Bećko Kasalica, Mladen Marinković, Aleksandra Bibić
NONDESTRUCTIVE OPTICAL SPECTROSCOPY IN PLANT STRESS RESEARCH: CIRCADIAN RHYTHM AS A DIAGNOSTIC MARKER
In the context of environmental changes and the increasing demand for sustainable agricultural practices, real-time monitoring of plant health is increasingly important. This work provides an overview of the development and application of nondestructive optical spectroscopy for early detection of stress across a wide range of plant species. The app...
By Katarina Miletić, Sara Ristić, Marija Petković Benazzouz, Bećko Kasalica, Dejan Jeremić