Deep learning-based automatic planning with risk minimization for brain tumor biopsy
Küçük Resim Yok
Tarih
2025
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Gazi Univ, Fac Engineering Architecture
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
iopsy emerges as a critical procedure for determining tumor types and establishing pathological diagnoses.This process encompasses two primary stages: planning and surgical intervention. During the planning stage,anatomical points in the patient's brain are marked based on MRI data, known to take an average of fourhours. However, the accuracy deficiencies, subjective variations, and time consumption associated withmanual marking reveal the critical need for an automated planning tool. In this study, we propose a biopsyplanning method, entirely automated and incorporating cutting-edge deep learning architectures, on MRIand MRA data. The suggested approach aims to execute biopsy planning rapidly, consistently, andrepeatably. The method consists of four main stages: 1) Removal of the brain's upper shell, 2) Tumordetection and target point determination, 3) Segmentation of the brain's vascular network, and 4) Combination of the three stages and risk calculation for optimal trajectory determination. This automaticmethod has been validated with 42 patient data in ITKTubeTK. Furthermore, this study, prepared as a 3DSlicer plugin, is offered as a free computer-assisted tool for clinics. In subsequent phases of the research,integration of fMRI data is planned to further enhance risk calculation
Açıklama
Anahtar Kelimeler
Stereotactic brain surgery, automatic surgical trajectory planning, surgical risk reduction, computer-assisted planning, deep learning
Kaynak
Journal of the Faculty of Engineering and Architecture of Gazi University
WoS Q Değeri
Q3
Scopus Q Değeri
Q2
Cilt
40
Sayı
1
