Semi-automatic Brain Lesion Segmentation in Gamma Knife Treatments Using an Unsupervised Fuzzy C-Means Clustering Technique

NeXt for neuro‐radiosurgery: A fully automatic approach for necrosis extraction in brain tumor MRI using an unsupervised machine learning technique

“…NeXt should be considered as a second step after the GTV segmentation for a more precise brain cancer characterization. We exploit an accurate brain tumor segmentation, obtained by our validated GTV segmentation methods for supporting neuro‐radiosurgery treatment planning in Militello et al and Rundo et al. These computer‐assisted segmentation approaches—the former based on the FCM clustering algorithm and the latter on a CA model—have shown to be effective and operator independent solutions.…”

“…Starting from the preliminary complete tumor region segmentation results that include all tumor structures, obtained by using our previous GTV segmentation methods, necrotic parts are distinguished from the tumor enhancing region.…”

“…Only automatic or semi‐automatic methods, which assist the clinicians in the segmentation task, can enable the repeatability of the delineated lesion boundaries, representing an operator‐independent solution for the assessment of the treatment response during patient's follow‐up and cancer staging. Nevertheless, specific issues regarding GTV segmentation for supporting stereotactic neuro‐radiosurgery have been addressed by a limited number of works in literature, such as (Hamamci et al, Militello et al; Rundo et al).…”

MedGA: A novel evolutionary method for image enhancement in medical imaging systems

“…4.3b. Moreover, rectangular o circular settings [525] (i.e., resizing and moving) are more complex than free-hand selection during lesion enclosing under critical conditions. In order to avoid this issue, a free-draw selection enables a more precise contour containing the tumor [413].…”

A Survey on Nature-Inspired Medical Image Analysis: A Step Further in Biomedical Data Integration

“…In the original method [29], the known nodes are marked by user input, whilst an automatic seed-selection procedure makes the method more reliable [31]. The study presented in [32] investigated the impact of BTV segmentation, using [ 11 C]-Methionine PET imaging, and the subsequent co-registration with Magnetic Resonance Imaging (MRI), utilised to delineate the Gross Tumour Volume (GTV) [33,34], in stereotactic neuro-radiosurgery treatment planning. The main goal was to present a novel PET/MRI automatic segmentation method, combining complementary multimodal information, and encouraging its use in clinical practice.…”