Bone metastasis detection method based on improving golden jackal optimization using whale optimization algorithm.

Area of Science:

• Medical Imaging
• Machine Learning
• Computational Biology

Background:

• Bone scintigraphy is crucial for detecting bone metastases.
• Accurate interpretation of these scans is vital for patient treatment.
• Existing methods may benefit from improved feature selection and optimization techniques.

Purpose of the Study:

• To develop and evaluate a novel machine learning technique for bone metastasis detection.
• To introduce and assess the performance of the GJOW feature selection method.
• To improve the accuracy and specificity of identifying bone metastases from gamma camera images.

Main Methods:

• Implemented a machine learning approach for bone scintigraphy image interpretation.
• Developed a new feature selection method, GJOW, integrating golden jackal optimization (GJO) and whale optimization (WOA).
• Validated the technique using 18 benchmark datasets and 581 gamma camera bone scan images (362 abnormal, 219 normal).

Main Results:

• The GJOW algorithm demonstrated superior predictive effectiveness in bone metastasis detection.
• Achieved an accuracy of 71.79% and a specificity of 91.14% in identifying bone metastases.
• The proposed method significantly improved the accuracy of bone metastasis identification.

Conclusions:

• The novel machine learning-based approach using GJOW offers improved accuracy for bone metastasis detection.
• This technique has practical implications for earlier diagnosis and intervention in cancer patients.
• Enhanced identification of bone metastases can lead to better patient management and outcomes.