Learning and combining image neighborhoods using random forests for neonatal brain disease classification

During early childhood, the brain undergoes complex structural changes, which makes it challenging to characterize and quantify normal and abnormal brain development. Depending on the condition occurring during the pregnancy, brain structure could have overt lesions or more subtle and general structural changes that could make it difficult to quantify these changes. The diagnostic and subsequent therapy, however, often relies only on one dimensional measurements, such as the width of the ventricles in a specific plane manually determined by the experts.

Source: Medical Image Analysis - August 9, 2017 Category: Radiology Authors: Veronika A. Zimmer, Ben Glocker, Nadine Hahner, Elisenda Eixarch, Gerard Sanroma, Eduard Gratac ós, Daniel Rueckert, Miguel Ángel González Ballester, Gemma Piella Source Type: research