Caner Ünlüer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Caner Ünlüer has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Hayri Kertmen
Department of Neurosurgery, Diskapi Education and Research Hospital, University of Health Sciences, Ankara, Turkey
4 shared publications - Abdullah Emre Taçyıldız
Affiliation Department of Neurosurgery, Karabuk University Faculty of Medicine, Karabuk, Turkey
1 shared publication - Ata Turker Arikok
University of Health Sciences Türkiye, Ankara Etlik City Hospital, Clinic of Pathology, Ankara, Türkiye
1 shared publication - Atakan Sezgi
Department of Anesthesiology and Reanimation, Ankara Etlik City Hospital, Ankara, Turkey
1 shared publication - Bekir Ucan
Department of Endocrinology and Metabolism, Ankara Etlik City Hospital, Ankara, Türkiye
1 shared publication - Berrin Imge Erguder
Ankara University Faculty of Medicine, Department of Biochemistry, Ankara, Turkey
1 shared publication
Latest Publications
- Open Access
- 30 September 2026
- Published by Turkish Journal of Clinical Research in Turkish Journal of Clinical Research
- Vol. 2 (2) , 121-127
Evaluation of the effects of deep brain neurostimulation in parkinson's patients, analysis of MRI images via artificial intelligence and its use for early diagnosis
Aim: This study aimed to evaluate the early diagnostic potential of subthalamic nucleus (STN) radiomic features and machine learning algorithms to differentiate Parkinson's disease patients requiring Deep Brain Stimulation (DBS) from those managed solely with medical therapy. This approach seeks to provide a non-invasive imaging biomarker to assist in objective surgical decision-making. Methods: A retrospective analysis of 394 Parkinson’s disease patients (200 in the DBS surgical cohort and 194 in the medical treatment cohort) was conducted using preoperative MRI scans. Following meticulous manual segmentation of the STN, a comprehensive set of radiomic features—including shape, first-order statistics, and Gray Level Co-occurrence Matrix (GLCM) parameters—was extracted. A Random Forest classifier was trained on 70% of the dataset and validated on a 30% independent test set to classify the patients based on their microstructural STN signatures. Results: The Random Forest machine learning model achieved an exceptional overall classification accuracy of 93.10% on the test dataset. Receiver Operating Characteristic (ROC) analysis yielded an Area Under the Curve (AUC) of up to 0.938. The performance was perfectly unbiased, with precision, recall, and F1-scores reaching 0.93 for both the surgical and medical cohorts. Feature importance analysis revealed that morphological deformations, specifically STN flatness, and first-order signal intensity drops associated with iron deposition were the most highly discriminative biophysical biomarkers for identifying surgical candidates. Conclusion: The application of machine learning to STN radiomic features provides a highly accurate, non-invasive, and objective methodology to distinguish DBS candidates from medically managed Parkinson's patients. While these findings are promising, prospective and external validation is required before the model can be fully incorporated into routine clinical decision-making.
- 30 September 2026
- Published by Turkish Journal of Clinical Research in Turkish Journal of Clinical Research
- Vol. 2 (2) , 121-127
Open AccessEvaluation of the effects of deep brain neurostimulation in parkinson's patients, analysis of MRI images via artificial intelligence and its use for early diagnosis
Aim: This study aimed to evaluate the early diagnostic potential of subthalamic nucleus (STN) radiomic features and machine learning algorithms to differentiate Parkinson's disease patients requiring Deep Brain Stimulation (DBS) from those managed solely with medical therapy. This approach seeks to provide a non-invasive imaging biomarker to assist in objective surgical decision-making. Methods: A retrospective analysis of 394 Parkinson’s disease patients (200 in the DBS surgical cohort and 194 in the medical treatment cohort) was conducted using preoperative MRI scans. Following meticulous manual segmentation of the STN, a comprehensive set of radiomic features—including shape, first-order statistics, and Gray Level Co-occurrence Matrix (GLCM) parameters—was extracted. A Random Forest classifier was trained on 70% of the dataset and validated on a 30% independent test set to classify the patients based on their microstructural STN signatures. Results: The Random Forest machine learning model achieved an exceptional overall classification accuracy of 93.10% on the test dataset. Receiver Operating Characteristic (ROC) analysis yielded an Area Under the Curve (AUC) of up to 0.938. The performance was perfectly unbiased, with precision, recall, and F1-scores reaching 0.93 for both the surgical and medical cohorts. Feature importance analysis revealed that morphological deformations, specifically STN flatness, and first-order signal intensity drops associated with iron deposition were the most highly discriminative biophysical biomarkers for identifying surgical candidates. Conclusion: The application of machine learning to STN radiomic features provides a highly accurate, non-invasive, and objective methodology to distinguish DBS candidates from medically managed Parkinson's patients. While these findings are promising, prospective and external validation is required before the model can be fully incorporated into routine clinical decision-making.
- Open Access
- 16 June 2026
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in TURKISH JOURNAL OF MEDICAL SCIENCES
- Vol. 56 (3) , 718-729
Clinical, hormonal, and treatment outcomes in 247 patients with acromegaly: a single tertiary center experience
Background/aim: This study aimed to evaluate the demographic, clinical, and hormonal characteristics; comorbidities; surgical pathology; treatment modalities; and long-term clinical outcomes of patients diagnosed with and managed for acromegaly at our tertiary referral center over a 15-year period. Materials and methods: Between 2010 and 2024, 247 patients with acromegaly were evaluated. Diagnosis and biochemical remission were determined according to the 2024 Acromegaly Consensus Criteria. Results: The median follow-up duration was 8 years (IQR: 3–14). At the time of diagnosis, the most frequent pituitary hormone deficiency was secondary adrenal insufficiency, present in 17.8% of patients. The most common comorbidities were hypertension (HT, 42.1%) and diabetes mellitus (DM, 30.8%). At the time of diagnosis, macroadenomas were present in 153 of 193 patients (79.3%), and, according to the Knosp classification, 28.6% of tumors were grade 4. A total of 218 patients underwent surgical intervention; 86 (39.4%) achieved postoperative cure without the need for adjuvant medical therapy or radiotherapy. Postoperatively, one or more anterior pituitary hormone deficiencies were found in 34 patients (22.8%), with central hypothyroidism being the most common (52.9%). Patients who achieved biochemical remission were significantly older (p = 0.003), had a higher prevalence of HT and DM (both p < 0.05), and were more likely to exhibit positive growth hormone (GH) immunostaining (p = 0.017). In contrast, those who did not achieve remission were more likely to have higher Knosp grades (3–4) (p = 0.002). Conclusions: In this study, a favorable prognosis was associated with older age at diagnosis, lower baseline GH levels, positive GH immunostaining, smaller tumor size, and lower Knosp grade, underscoring the prognostic value of both biochemical and anatomical parameters. Further studies are warranted to refine prognostic markers and establish standardized treatment algorithms to improve long-term outcomes in acromegaly.
- 16 June 2026
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in TURKISH JOURNAL OF MEDICAL SCIENCES
- Vol. 56 (3) , 718-729
Open AccessClinical, hormonal, and treatment outcomes in 247 patients with acromegaly: a single tertiary center experience
Background/aim: This study aimed to evaluate the demographic, clinical, and hormonal characteristics; comorbidities; surgical pathology; treatment modalities; and long-term clinical outcomes of patients diagnosed with and managed for acromegaly at our tertiary referral center over a 15-year period. Materials and methods: Between 2010 and 2024, 247 patients with acromegaly were evaluated. Diagnosis and biochemical remission were determined according to the 2024 Acromegaly Consensus Criteria. Results: The median follow-up duration was 8 years (IQR: 3–14). At the time of diagnosis, the most frequent pituitary hormone deficiency was secondary adrenal insufficiency, present in 17.8% of patients. The most common comorbidities were hypertension (HT, 42.1%) and diabetes mellitus (DM, 30.8%). At the time of diagnosis, macroadenomas were present in 153 of 193 patients (79.3%), and, according to the Knosp classification, 28.6% of tumors were grade 4. A total of 218 patients underwent surgical intervention; 86 (39.4%) achieved postoperative cure without the need for adjuvant medical therapy or radiotherapy. Postoperatively, one or more anterior pituitary hormone deficiencies were found in 34 patients (22.8%), with central hypothyroidism being the most common (52.9%). Patients who achieved biochemical remission were significantly older (p = 0.003), had a higher prevalence of HT and DM (both p < 0.05), and were more likely to exhibit positive growth hormone (GH) immunostaining (p = 0.017). In contrast, those who did not achieve remission were more likely to have higher Knosp grades (3–4) (p = 0.002). Conclusions: In this study, a favorable prognosis was associated with older age at diagnosis, lower baseline GH levels, positive GH immunostaining, smaller tumor size, and lower Knosp grade, underscoring the prognostic value of both biochemical and anatomical parameters. Further studies are warranted to refine prognostic markers and establish standardized treatment algorithms to improve long-term outcomes in acromegaly.
- Open Access
- 4 July 2025
- Published by Galenos Yayinevi in Turkish Journal of Anaesthesiology and Reanimation
- Vol. 53 (4) , 177-182
Stereotactic Brain Biopsy with Awake Craniotomy: Our Awake Craniotomy Experience on a Complicated Case and Mini Review
Stereotactic Brain Biopsy with Awake Craniotomy: Our Awake Craniotomy Experience on a Complicated Case and Mini Review - Turkish Journal of Anaesthesiology and Reanimation
- 4 July 2025
- Published by Galenos Yayinevi in Turkish Journal of Anaesthesiology and Reanimation
- Vol. 53 (4) , 177-182
Open AccessStereotactic Brain Biopsy with Awake Craniotomy: Our Awake Craniotomy Experience on a Complicated Case and Mini Review
Stereotactic Brain Biopsy with Awake Craniotomy: Our Awake Craniotomy Experience on a Complicated Case and Mini Review - Turkish Journal of Anaesthesiology and Reanimation
- 27 April 2024
- Published by Elsevier in World Neurosurgery
- Vol. 188, e25-e33
Neuroprotective Effects of Coenzyme Q10 and Ozone Therapy on Experimental Traumatic Spinal Cord Injuries in Rats
- 27 April 2024
- Published by Elsevier in World Neurosurgery
- Vol. 188, e25-e33
Neuroprotective Effects of Coenzyme Q10 and Ozone Therapy on Experimental Traumatic Spinal Cord Injuries in Rats
- 29 September 2023
- Published by Galenos Yayinevi in Medical Journal of Bakırkoy
- Vol. 19 (3) , 263-268
Microendoscopic Discectomy for Lumbar Disc Herniations: A Series of 389 Cases
- 29 September 2023
- Published by Galenos Yayinevi in Medical Journal of Bakırkoy
- Vol. 19 (3) , 263-268
Microendoscopic Discectomy for Lumbar Disc Herniations: A Series of 389 Cases