Author: Catal Reis, H.

Publishing Date: 2018

E-ISSN: 2548-0960

Volume 3 Issue 1


Photogrammetry has been used for medical diagnostic and treatment. Mostly used medical photogrammetric techniques are Ultrasound, Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) images. CT and MRI are the most effective method for the early detection of foot and ankle anomaly. Researchers have been developing various methods to detect anomaly. Many image segmentation techniques are available in the literature. Computer Aided Diagnosing (CAD) system has been proposed in this study for detection of foot bone anomaly by the analysis of CT images. In this study, a segmentation based on edge detection method is proposed for the classification of anomaly in foot CT images. Edge detection algorithms are the most commonly used techniques in image processing for edge detection. Canny edge detector is evaluated in this study

In this study, “.dicom” medical image standard format and ten male patient’s foot CT images (245 images and 50 test data) are used. The used parameters are detector collimation of 64 mm, scanning thickness of 1-5 mm, and pixel sizes of 512×512 in radiometric resolution of 16 bits’ gray levels.

The proposed method consists of five major steps: (i) calculating the horizontal & vertical gradient, (ii) determining gradient magnitude and gradient direction, (iii) applying non-maximal suppression, (iv) computing high and low thresholds, (v) hysteresis thresholding are applied to the multi-detector computed tomography to detect the bone anomaly.

In this study, automatic edge-based digital image processing techniques are applied to detect of foot bone anomaly. The proposed canny segmentation method enables users segment anomaly in MDCT of foot very quickly and efficiently. The results demonstrate that the proposed segmentation method is effective for segmenting anomaly. The proposed method obtains satisfactory performances in terms of accuracy and F-measure the area under Receiver Operating Characteristic curve (ROC curve (AUC)). The proposed segmentation method achieves an accuracy of 0.86 and F- measure of 0.92, respectively.

The purpose of our study is to detect the anomaly of the foot and it was the simplest and less time consuming process.

Keywords: Medical Photogrammetry, Medical Image Processing, Segmentation, Anomaly, CT

Full Text