Automatic Segmentation of Bone Canals in Histological Images.

Area of Science:

• Biomedical Engineering
• Medical Imaging Analysis
• Histopathology

Background:

• Cell nuclei segmentation in histological images is well-established.
• Automatic segmentation of bone canals remains an underexplored area in medical imaging.
• Accurate analysis of the bone vascular network is crucial for medical diagnosis.

Purpose of the Study:

• To present a novel automatic segmentation method for bone canals.
• To assist specialists in the detailed analysis of the bone vascular network.
• To evaluate the proposed method's performance against existing techniques.

Main Methods:

• Development of a new automatic segmentation algorithm for bone canals.
• Evaluation using sensitivity, specificity, accuracy, and Dice coefficient metrics.
• Comparison with established segmentation methods: Neighborhood Valley Emphasis (NVE), Valley Emphasis (VE), and Otsu.

Main Results:

• The proposed method achieved high performance in segmenting bone canals.
• Quantitative metrics demonstrated the method's effectiveness.
• The approach proved more efficient than NVE, VE, and Otsu methods.

Conclusions:

• The developed automatic segmentation method is a feasible and efficient tool for analyzing the bone vascular network.
• This technique offers a valuable alternative for specialists in histopathology and biomedical imaging.
• Further research can explore its application in various bone-related pathologies.