Evaluation of Diagnostic Accuracy of Machine Learning Algorithm for Computer Aided Diagnosis (CAD) of Space Occupying Lesions in Computed Tomography (CT) Images of Brain

Abstract

Objectives-Objective of this project was to formulate a low cost and userfriendly SOL detection computational model through machine learning and test its diagnostic efficacy through retrospective evaluation of radiologist confirmed normal and abnormal CT images. Materials & Methods-The neural network has been created in the Wolfram language, using our own dataset. A total of 249 images were obtained from a CT scan center’s human brain data. A database of 89 normal and 76 SOL images from 128 slice CT scan machines was used for formulating the model. The test trial was done using 50 different normal and 34 different abnormal images. Results-The sensitivity of ability to identify abnormal images was 97% and the specificity was 92%. Only one out of 34 images with tumor was reported wrongly and 4 normal images out of 50 normal test images were wrongly identified by the CAD system. The software was able to achieve a diagnostic accuracy higher than the confidence interval of 95% set for the diagnostic test. Conclusion - The CAD system is novel and innovative as it is a simple, lowcost and user-friendly computational model which can be used by doctors on their office PCs.

Authors and Affiliations

Rushank Goyal, Swati Goyal, Lovely Kaushal

Keywords

Related Articles

Results Of Fracture Neck Of Femur Treated With Modular Bipolar Hemiarthroplasty In Elderly-Our Experience In 70 Cases

Aim of the study: The treatment of fractures neck of femur has evolved over a period of time with osteosynthesis to prosthetic implantation. Early mobility, immediate pain reliefs are the major advantages of the bipolar...

Radiographic Morphometry Of Distal End Of Radius, A Retrospective, Observational Study In Indian Population

Background: Distal end of radius fracture is a common fracture due to fall on outstretched hand (15 per 100 fracture patients). Reduction of this fracture is generally assessed by four morphometric measurements of the di...

Evaluation Of Various Surgical Modalities For Treatment Of Fracture Distal End Radius

Background: A prospective study was conducted in the department of Orthopaedic & Traumatology in M.Y Hospital, Indore from November 2013 to October 2015. Methods: All the patients with fracture of distal end radius wit...

Clinical Evaluation Of Plantar Fascitis Treated With Prp Vs Corticosteroid Injection

Plantar fasciitis is one of the most common cause of heel pain. It is thought to result from chronic overload and is characterized by pain at the calcaneal origin of the plantar fascia, exacerbated by weight bearing af...

A Comparative Study On Management Of Colles’ Fracture By Closed Manipulation And Casting Versus Closed Manipulation, K-Wiring And Casting

Background: Colles’ fracture is one of the common injuriesin Orthopaedic practice. Since most of these are commonly managed by closed manipulation and casts, these invariably unite in malpositiondue to loss of reduction...

Download PDF file
  • EP ID EP540139
  • DOI -
  • Views 132
  • Downloads 0

How To Cite

Rushank Goyal, Swati Goyal, Lovely Kaushal (2018). Evaluation of Diagnostic Accuracy of Machine Learning Algorithm for Computer Aided Diagnosis (CAD) of Space Occupying Lesions in Computed Tomography (CT) Images of Brain. International Journal of Orthopaedics Traumatology & Surgical Sciences, 4(2), 218-222. https://europub.co.uk/articles/-A-540139