Bag of feature based classification of bone from MR images

Abstract

Traumatic and degenerative shoulder pathologies of which treatment strategy and success depends on correct diagnosis are more commonly encountered at the present time. The aim of this study is to help clinicians by using computer based decision support systems to diagnose correctly the degenerative and traumatic conditions of shoulder from MR images which is not an easy task in practice. Image patches containing the humeral head were generated from PD weighted MR images of patients presented with pain by automatic segmentation with the region-based active contour method. Discriminative features required to classify humeral heads as normal, edematous and Hill-Sachs deformity were extracted by bag of features method and classified with decision support machines with a success rate of 92%.

Keywords

Artificial intelligence Discriminative model Computer science Feature (linguistics) Pattern recognition (psychology) Segmentation Feature extraction Task (project management) Active contour model Image segmentation Deformity Contextual image classification Computer vision Medicine Image (mathematics) Radiology Engineering

Subject Areas

Medical Imaging and Analysis ·Biomedical Engineering ·Physical Sciences

Dental Radiography and Imaging ·Oral Surgery ·Health Sciences

COVID-19 diagnosis using AI ·Radiology, Nuclear Medicine and Imaging ·Health Sciences

OpenAlex SDG Match

SDGs auto-classified by OpenAlex (score ≥ 0.4 shown).

Reduced inequalities 74%

Bag of feature based classification of bone from MR images

Abstract

Keywords

Subject Areas

OpenAlex SDG Match

References (13)

Related Articles

Model-independent measurement of the Higgs boson associated production with two jets and decaying to a pair of W bosons in proton-proton collisions at $$ \sqrt{s}=13 $$ TeV

Search for low-mass hidden-valley dark showers with non-prompt muon pairs in proton-proton collisions at $$ \sqrt{s}=13 $$ TeV

Measurements of the inclusive W and Z boson production cross sections and their ratios in proton-proton collisions at $$\sqrt{s}=13.6$$ TeV

Measurements of $$ \textrm{t}\overline{\textrm{t}}\textrm{W} $$ differential cross sections and the leptonic charge asymmetry at $$ \sqrt{s}=13 $$ TeV