Deniz Apalan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Deniz Apalan has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Irfan Atik
Department of Radiology, Faculty of Medicine, Sivas Cumhuriyet University, Sivas, Turkey
3 shared publications - Seda Atik
Sivas Cumhuriyet University, Turkey
3 shared publications - Enes Gul
Department of Radiology, Faculty of Medicine, Sivas Cumhuriyet University, Sivas, Turkey
2 shared publications - Özlem Polat
Department of Mechatronics Engineering, Faculty of Technology, Sivas Cumhuriyet University, Sivas 58140, Turkey
2 shared publications - Aykut Insan
Haseki Training and Research Hospital, Department of Radiology , Istanbul, Turkey
1 shared publication - Bulent Yildiz
Department of Radiology, Faculty of Medicine, Sivas Cumhuriyet University, Sivas, Turkey
1 shared publication
Latest Publications
- Open Access
- 8 April 2026
- Published by Springer Nature in Irish Journal of Medical Science (1971 -)
- Vol. 195 (3) , 1347-1357
Cervical spinal cord enlargement and systemic inflammation in diabetic peripheral neuropathy: a cross-sectional MRI study
Background Diabetic peripheral neuropathy (DPN) is one of the most common and disabling complications of type 2 diabetes mellitus (T2DM). Although traditionally considered a peripheral disorder, recent evidence indicates concomitant central nervous system (CNS) involvement. The systemic immune-inflammation index (SII) has emerged as a biomarker reflecting inflammatory activity in diabetes. This study aimed to assess cervical spinal cord cross-sectional area (CSA) using magnetic resonance imaging (MRI) in diabetic patients with and without DPN and to examine its association with systemic inflammation and metabolic parameters. Methods This retrospective, cross-sectional study included 299 participants: 100 healthy controls, 100 diabetic patients without DPN, and 99 with DPN. Cervical spinal CSA was measured on MRI, and fasting plasma glucose (FPG), glycated hemoglobin (HbA1c), complete blood count parameters, and SII values were analyzed. Intergroup comparisons and correlations were evaluated using nonparametric tests and multivariate models. Results Both diabetic groups showed significantly higher HbA1c, FPG, and SII levels compared with the control group (p < 0.05). Cervical spinal CSA was significantly greater in diabetic groups, particularly in those with DPN (p = 0.004). CSA correlated weakly and positively with HbA1c and FPG, but not with SII. Conclusion Diabetic patients, especially with DPN, exhibit cervical spinal cord enlargement accompanied by elevated systemic inflammation. The CSA increase may represent an early phase of neuroinflammation preceding atrophy. Combining MRI-derived CSA with SII may improve early detection and risk stratification, supporting an integrated assessment of central and peripheral neuroinvolvement in diabetes.
- 8 April 2026
- Published by Springer Nature in Irish Journal of Medical Science (1971 -)
- Vol. 195 (3) , 1347-1357
Open AccessCervical spinal cord enlargement and systemic inflammation in diabetic peripheral neuropathy: a cross-sectional MRI study
Background Diabetic peripheral neuropathy (DPN) is one of the most common and disabling complications of type 2 diabetes mellitus (T2DM). Although traditionally considered a peripheral disorder, recent evidence indicates concomitant central nervous system (CNS) involvement. The systemic immune-inflammation index (SII) has emerged as a biomarker reflecting inflammatory activity in diabetes. This study aimed to assess cervical spinal cord cross-sectional area (CSA) using magnetic resonance imaging (MRI) in diabetic patients with and without DPN and to examine its association with systemic inflammation and metabolic parameters. Methods This retrospective, cross-sectional study included 299 participants: 100 healthy controls, 100 diabetic patients without DPN, and 99 with DPN. Cervical spinal CSA was measured on MRI, and fasting plasma glucose (FPG), glycated hemoglobin (HbA1c), complete blood count parameters, and SII values were analyzed. Intergroup comparisons and correlations were evaluated using nonparametric tests and multivariate models. Results Both diabetic groups showed significantly higher HbA1c, FPG, and SII levels compared with the control group (p < 0.05). Cervical spinal CSA was significantly greater in diabetic groups, particularly in those with DPN (p = 0.004). CSA correlated weakly and positively with HbA1c and FPG, but not with SII. Conclusion Diabetic patients, especially with DPN, exhibit cervical spinal cord enlargement accompanied by elevated systemic inflammation. The CSA increase may represent an early phase of neuroinflammation preceding atrophy. Combining MRI-derived CSA with SII may improve early detection and risk stratification, supporting an integrated assessment of central and peripheral neuroinvolvement in diabetes.
- 5 January 2026
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (5) , 4157-4167
Osteoarthritis Severity Classification in Knee X-Rays Using Optimized Deep Learning Approaches
Osteoarthritis (OA) is a common, progressive joint disease that significantly reduces quality of life and limits mobility, especially in older adults. It is essential to accurately classify the disease in its early stages to develop effective treatments and slow its progression. This study introduces a deep learning-based system for classifying OA severity using knee joint X-ray images. EfficientNetB1, DenseNet169, and Xception architectures were employed for five-class OA classification (asymptomatic, early, mild, moderate, and severe), with hyperparameters in the fully connected layers optimized through the Gray Wolf Optimization (GWO) algorithm. By automatically selecting the most suitable parameters with GWO, the model learns more effectively and provides more accurate results in distinguishing OA levels. The dataset includes knee X-ray images from patients at University Training and Research Hospital, comprising 1000 images-200 per class. Model performance was assessed using accuracy, precision, recall, F1 score, and ROC curves. The experiments consisted of two stages: the first involved a five-class classification, and the second involved binary classification to distinguish between mild and severe OA. Correctly identifying moderate and severe stages, which are particularly serious, is vital for determining the need for surgical intervention. The best results were achieved with the DenseNet169 model: 74% in multi-class classification and 93.75% in binary classification. These findings show that the optimized models deliver high accuracy and effectiveness in OA diagnosis. This system helps specialists determine OA severity levels early, allowing for more informed treatment and surgical decisions.
- 5 January 2026
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (5) , 4157-4167
Osteoarthritis Severity Classification in Knee X-Rays Using Optimized Deep Learning Approaches
Osteoarthritis (OA) is a common, progressive joint disease that significantly reduces quality of life and limits mobility, especially in older adults. It is essential to accurately classify the disease in its early stages to develop effective treatments and slow its progression. This study introduces a deep learning-based system for classifying OA severity using knee joint X-ray images. EfficientNetB1, DenseNet169, and Xception architectures were employed for five-class OA classification (asymptomatic, early, mild, moderate, and severe), with hyperparameters in the fully connected layers optimized through the Gray Wolf Optimization (GWO) algorithm. By automatically selecting the most suitable parameters with GWO, the model learns more effectively and provides more accurate results in distinguishing OA levels. The dataset includes knee X-ray images from patients at University Training and Research Hospital, comprising 1000 images-200 per class. Model performance was assessed using accuracy, precision, recall, F1 score, and ROC curves. The experiments consisted of two stages: the first involved a five-class classification, and the second involved binary classification to distinguish between mild and severe OA. Correctly identifying moderate and severe stages, which are particularly serious, is vital for determining the need for surgical intervention. The best results were achieved with the DenseNet169 model: 74% in multi-class classification and 93.75% in binary classification. These findings show that the optimized models deliver high accuracy and effectiveness in OA diagnosis. This system helps specialists determine OA severity levels early, allowing for more informed treatment and surgical decisions.
- 12 September 2024
- Published by Wiley in Sonography
- Vol. 12 (1) , 129-132
Sonographic and magnetic resonance imaging findings in post‐traumatic median nerve neuroma: A case report
Nerves are frequently damaged in cases of blunt or penetrating injuries to the limbs. Post‐traumatic neuromas arising from peripheral nerves are formations that emerge after nerve injury, potentially leading to swollen and agonizing nerve terminations upon severance. Post‐traumatic neuromas commonly appear as irregular, non‐cancerous nodules formed due to injury‐induced damage. The most common clinical symptom is neuralgic pain significantly the patient's quality of life. The main peripheral nerve abnormalities that lead to a referral for imaging are benign peripheral nerve tumors such as schwannoma, neurofibroma, and traumatic pathologies. This case report discusses a 35‐year‐old woman who presented with a neuroma in her wrist months after a laceration and trauma, with typical imaging findings on sonographic and magnetic resonance imaging.
- 12 September 2024
- Published by Wiley in Sonography
- Vol. 12 (1) , 129-132
Sonographic and magnetic resonance imaging findings in post‐traumatic median nerve neuroma: A case report
Nerves are frequently damaged in cases of blunt or penetrating injuries to the limbs. Post‐traumatic neuromas arising from peripheral nerves are formations that emerge after nerve injury, potentially leading to swollen and agonizing nerve terminations upon severance. Post‐traumatic neuromas commonly appear as irregular, non‐cancerous nodules formed due to injury‐induced damage. The most common clinical symptom is neuralgic pain significantly the patient's quality of life. The main peripheral nerve abnormalities that lead to a referral for imaging are benign peripheral nerve tumors such as schwannoma, neurofibroma, and traumatic pathologies. This case report discusses a 35‐year‐old woman who presented with a neuroma in her wrist months after a laceration and trauma, with typical imaging findings on sonographic and magnetic resonance imaging.
- Open Access
- 30 April 2024
- Published by Cumhuriyet University in Cumhuriyet Üniversitesi Sağlık Bilimleri Enstitüsü Dergisi
- Vol. 9 (1) , 56-60
Diagnostic Contribution of Hematological Parameters in Patients with Lung İnvolvement in Rheumatoid Arthritis
Rheumatoid arthritis (RA) is a prevalent autoimmune condition, with lung involvement being its most frequent extra-articular manifestation. Our study aims to investigate the contribution of hematological parameters to diagnosing lung involvement in patients with RA. Individuals with RA were divided into two groups according to lung involvement in thorax computed tomography. C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), neutrophil, lymphocyte, monocyte, platelet, neutrophil/lymphocyte ratio (NLR), monocyte/lymphocyte ratio (MLR) and systemic immune-inflammatory index (SII) were evaluated in all patients. Twenty-nine of the seventy-five RA patients were found to have lung involvement, and lung involvement was not observed in forty-six patients. CRP, ESR, and neutrophils were high in patients with lung involvement and a statistically notable distinction was observed. Lymphocyte count was low in patients with lung involvement and was statistically significant. NLR, NMO, and SII rates were high in patients with lung involvement and were statistically significant. It is observed that hematological parameters contribute to diagnosing RA lung involvement.
- 30 April 2024
- Published by Cumhuriyet University in Cumhuriyet Üniversitesi Sağlık Bilimleri Enstitüsü Dergisi
- Vol. 9 (1) , 56-60
Open AccessDiagnostic Contribution of Hematological Parameters in Patients with Lung İnvolvement in Rheumatoid Arthritis
Rheumatoid arthritis (RA) is a prevalent autoimmune condition, with lung involvement being its most frequent extra-articular manifestation. Our study aims to investigate the contribution of hematological parameters to diagnosing lung involvement in patients with RA. Individuals with RA were divided into two groups according to lung involvement in thorax computed tomography. C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), neutrophil, lymphocyte, monocyte, platelet, neutrophil/lymphocyte ratio (NLR), monocyte/lymphocyte ratio (MLR) and systemic immune-inflammatory index (SII) were evaluated in all patients. Twenty-nine of the seventy-five RA patients were found to have lung involvement, and lung involvement was not observed in forty-six patients. CRP, ESR, and neutrophils were high in patients with lung involvement and a statistically notable distinction was observed. Lymphocyte count was low in patients with lung involvement and was statistically significant. NLR, NMO, and SII rates were high in patients with lung involvement and were statistically significant. It is observed that hematological parameters contribute to diagnosing RA lung involvement.
- Open Access
- 6 April 2023
- Published by Academician Publishing
Nörovasküler Radyoloji
Bu kitap temel ve ileri nörovasküler radyoloji konularını içerecek şekilde hazırlandı. Nörovasküler radyoloji konusunda bilgi edinmek isteyen tüm öğrenci, asistan ve uzmanlara faydalı olacağını ümit etmekteyiz.
- 6 April 2023
- Published by Academician Publishing
Open AccessNörovasküler Radyoloji
Bu kitap temel ve ileri nörovasküler radyoloji konularını içerecek şekilde hazırlandı. Nörovasküler radyoloji konusunda bilgi edinmek isteyen tüm öğrenci, asistan ve uzmanlara faydalı olacağını ümit etmekteyiz.