IEEE Journal of Biomedical and Health Informatics, 2014
Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and ... more Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and diagnose tumor and edema in a quantitative way. In this study, we present a new tissue segmentation algorithm that segments brain MR images into tumor, edema, white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). The detection of the healthy tissues is performed simultaneously with the diseased tissues because examining the change caused by the spread of tumor and edema on healthy tissues is very important for treatment planning. We used T1, T2 and FLAIR MR images of 20 subjects suffering from glial tumor. We developed an algorithm for stripping the skull before the segmentation process. The segmentation is performed using self-organizing map (SOM) that is trained with unsupervised learning algorithm and fine-tuned with learning vector quantization (LVQ). Unlike other studies, we developed an algorithm for clustering the SOM instead of using an additional network. Input feature vector is constructed with the features obtained from stationary wavelet transform (SWT) coefficients. The results showed that average Dice similarity indexes are 91% for WM, 87% for GM, 96% for CSF, 61% for tumor, and 77% for edema.
The purpose of this study was to investigate the diagnostic accuracy of low-dose helical computed... more The purpose of this study was to investigate the diagnostic accuracy of low-dose helical computed tomography by comparing the number of nodules detected at low- and standard-dose CT. The prospective study included 25 patients who were referred to CT scan for the assessment of pulmonary metastases. All patients underwent CT examinations at both standard- (200 mA, 120 kV, collimation 5 mm, table feed 10 mm per rotation) and low-dose (50 mA, 120 kV, collimation 5 mm, table feed 10 mm per rotation). The number of nodules detected at each protocol was recorded. The size of the nodules was measured electronically and categorized as <3, 3-4.9, 5-6.9, 7-9.9, and >/=10 mm. Finally, the nodules detected at only standard- or low-dose CT were assessed for the underlying causes of discrepancy. In 25 patients, 533 nodules were detected at standard-dose, whereas 518 nodules were observed at low-dose CT. There were no statistically significant differences in the number of nodules detected at ...
We present a child with Wegener's granulomatosis who showed lung lesions progressing from nod... more We present a child with Wegener's granulomatosis who showed lung lesions progressing from nodules to cavities within a 1-month period on CT.
Piriformis syndrome is a rare neuromuscular disorder that occurs when the piriformis muscle compr... more Piriformis syndrome is a rare neuromuscular disorder that occurs when the piriformis muscle compresses or irritates the sciatic nerve. The treatment of piriformis syndrome includes injections into the piriformis muscle around the sciatic nerve. These invasive approaches have been used with various techniques to increase the safety of the procedure. Computed tomography (CT)-guided injection of the piriformis muscle and the clinical outcome of the patients are discussed. The authors presented 10 consecutive patients that underwent CT-guided piriformis injection between March and December 2007. Three patients had a history of a severe fall on the buttocks, one had gluteal abscess formation following deep intramuscular injection, and another one had a habit of prolonged sitting on the carpet. Etiology was not identified in the other patients. Main complaints of the patients were pain and numbness in the legs. Hypesthesia was the major neurological finding. Magnetic resonance imaging (MR...
IEEE Journal of Biomedical and Health Informatics, 2014
Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and ... more Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and diagnose tumor and edema in a quantitative way. In this study, we present a new tissue segmentation algorithm that segments brain MR images into tumor, edema, white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). The detection of the healthy tissues is performed simultaneously with the diseased tissues because examining the change caused by the spread of tumor and edema on healthy tissues is very important for treatment planning. We used T1, T2 and FLAIR MR images of 20 subjects suffering from glial tumor. We developed an algorithm for stripping the skull before the segmentation process. The segmentation is performed using self-organizing map (SOM) that is trained with unsupervised learning algorithm and fine-tuned with learning vector quantization (LVQ). Unlike other studies, we developed an algorithm for clustering the SOM instead of using an additional network. Input feature vector is constructed with the features obtained from stationary wavelet transform (SWT) coefficients. The results showed that average Dice similarity indexes are 91% for WM, 87% for GM, 96% for CSF, 61% for tumor, and 77% for edema.
IEEE Journal of Biomedical and Health Informatics, 2014
Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and ... more Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and diagnose tumor and edema in a quantitative way. In this study, we present a new tissue segmentation algorithm that segments brain MR images into tumor, edema, white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). The detection of the healthy tissues is performed simultaneously with the diseased tissues because examining the change caused by the spread of tumor and edema on healthy tissues is very important for treatment planning. We used T1, T2 and FLAIR MR images of 20 subjects suffering from glial tumor. We developed an algorithm for stripping the skull before the segmentation process. The segmentation is performed using self-organizing map (SOM) that is trained with unsupervised learning algorithm and fine-tuned with learning vector quantization (LVQ). Unlike other studies, we developed an algorithm for clustering the SOM instead of using an additional network. Input feature vector is constructed with the features obtained from stationary wavelet transform (SWT) coefficients. The results showed that average Dice similarity indexes are 91% for WM, 87% for GM, 96% for CSF, 61% for tumor, and 77% for edema.
The purpose of this study was to investigate the diagnostic accuracy of low-dose helical computed... more The purpose of this study was to investigate the diagnostic accuracy of low-dose helical computed tomography by comparing the number of nodules detected at low- and standard-dose CT. The prospective study included 25 patients who were referred to CT scan for the assessment of pulmonary metastases. All patients underwent CT examinations at both standard- (200 mA, 120 kV, collimation 5 mm, table feed 10 mm per rotation) and low-dose (50 mA, 120 kV, collimation 5 mm, table feed 10 mm per rotation). The number of nodules detected at each protocol was recorded. The size of the nodules was measured electronically and categorized as <3, 3-4.9, 5-6.9, 7-9.9, and >/=10 mm. Finally, the nodules detected at only standard- or low-dose CT were assessed for the underlying causes of discrepancy. In 25 patients, 533 nodules were detected at standard-dose, whereas 518 nodules were observed at low-dose CT. There were no statistically significant differences in the number of nodules detected at ...
We present a child with Wegener's granulomatosis who showed lung lesions progressing from nod... more We present a child with Wegener's granulomatosis who showed lung lesions progressing from nodules to cavities within a 1-month period on CT.
Piriformis syndrome is a rare neuromuscular disorder that occurs when the piriformis muscle compr... more Piriformis syndrome is a rare neuromuscular disorder that occurs when the piriformis muscle compresses or irritates the sciatic nerve. The treatment of piriformis syndrome includes injections into the piriformis muscle around the sciatic nerve. These invasive approaches have been used with various techniques to increase the safety of the procedure. Computed tomography (CT)-guided injection of the piriformis muscle and the clinical outcome of the patients are discussed. The authors presented 10 consecutive patients that underwent CT-guided piriformis injection between March and December 2007. Three patients had a history of a severe fall on the buttocks, one had gluteal abscess formation following deep intramuscular injection, and another one had a habit of prolonged sitting on the carpet. Etiology was not identified in the other patients. Main complaints of the patients were pain and numbness in the legs. Hypesthesia was the major neurological finding. Magnetic resonance imaging (MR...
IEEE Journal of Biomedical and Health Informatics, 2014
Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and ... more Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and diagnose tumor and edema in a quantitative way. In this study, we present a new tissue segmentation algorithm that segments brain MR images into tumor, edema, white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). The detection of the healthy tissues is performed simultaneously with the diseased tissues because examining the change caused by the spread of tumor and edema on healthy tissues is very important for treatment planning. We used T1, T2 and FLAIR MR images of 20 subjects suffering from glial tumor. We developed an algorithm for stripping the skull before the segmentation process. The segmentation is performed using self-organizing map (SOM) that is trained with unsupervised learning algorithm and fine-tuned with learning vector quantization (LVQ). Unlike other studies, we developed an algorithm for clustering the SOM instead of using an additional network. Input feature vector is constructed with the features obtained from stationary wavelet transform (SWT) coefficients. The results showed that average Dice similarity indexes are 91% for WM, 87% for GM, 96% for CSF, 61% for tumor, and 77% for edema.
Uploads
Papers by Mustafa Toru