Lossless compression-based detection of osteoporosis using bone X-ray imaging

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Orthopedics

Background:

• Digital X-ray imaging is crucial for osteoporosis diagnosis.
• Accurate differentiation between osteoporotic patients and healthy individuals from X-ray images is challenging.

Purpose of the Study:

• To introduce a novel deep learning method for enhanced osteoporosis diagnosis from bone X-ray images.
• To improve the accuracy and efficiency of osteoporosis detection.

Main Methods:

• Image analysis using a novel procedure involving segregation into regions of interest (ROI) and non-ROI to reduce redundancy.
• Enhancement of spatial and statistical features of the bone X-ray images.
• Classification of cases using a Support Vector Machine (SVM) classifier.

Main Results:

• The proposed method achieved a high diagnostic accuracy, indicated by an Area Under the Curve (AUC) of 90.8%.
• The technique demonstrated superior performance compared to existing methods in distinguishing osteoporosis.
• High accuracy in differentiating between osteoporotic and non-osteoporotic individuals was observed.

Conclusions:

• The developed method effectively distinguishes osteoporotic from non-osteoporotic cases using bone X-ray images.
• Feature enhancement and SVM classification contribute to a promising tool for efficient and accurate osteoporosis diagnosis.