Keywords:
CNS, Computer applications, Neuroradiology brain, MR, Neural networks, Computer Applications-Detection, diagnosis, Diagnostic procedure, Cancer
Authors:
P. Saponara, C. Detheridge, J. Bhangu, B. N. Bloch, K. Thomas; Boston/US
DOI:
10.1594/ecr2018/C-2825
Aims and objectives
This study sought to develop an AI approach to accurately and efficiently differentiate primary intracranial tumors.
Artificial Intelligence (AI) offers a way to aid clinicians in diagnostic accuracy.
AI machine learning algorithms for Computer Assisted Diagnosis are software packages that intake labeled images of different classes (i.e.
cancerous images and healthy images).
AI uses learning theories and training algorithms which mimic techniques used in clinical training.
Convolutional Neural Networks (CNN's) are a theory found in machine learning that entail a feed forward deep class approach of multi-layer space invariant artificial neural networks (5).
CNN's are introduced as a complex network of hidden layers that imitates human visual cortex image recognition.
The basis for such a complex system is formed through a large number of hidden architecture layers per each classification (5,
4).
This weighting architecture is then used to predict the multi-layer receptive image classification.
This automation paired with the feed forward approach of gradient descent classification forms a network that learns from classification filters (1,
2) .