Şahin, Sevim
Loading...
Profile URL
Name Variants
Şahin, S. Sahin, S. Sahin, Sevim
Job Title
Doktor Öğretim
Email Address
sevim.sahin@fbu.edu.tr
Main Affiliation
Elektrik-elektronik Mühendisliği Bölümü
Status
Website
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
Research Topics
Domains
Physical SciencesHealth Sciences
Fields
Physics and AstronomyMedicineComputer Science
Subfields
RadiationPathology and Forensic MedicineArtificial IntelligenceRadiology, Nuclear Medicine and ImagingPulmonary and Respiratory Medicine
Specific Research Areas
Advanced Radiotherapy Techniques
Multiple Sclerosis Research Studies
AI in cancer detection
Effects of Radiation Exposure
Radiation Therapy and Dosimetry
Sustainable Development Goals
1NO POVERTY
0
Research Products
2ZERO HUNGER
0
Research Products
3GOOD HEALTH AND WELL-BEING
2
Research Products
4QUALITY EDUCATION
0
Research Products
5GENDER EQUALITY
0
Research Products
6CLEAN WATER AND SANITATION
0
Research Products
7AFFORDABLE AND CLEAN ENERGY
0
Research Products
8DECENT WORK AND ECONOMIC GROWTH
0
Research Products
9INDUSTRY, INNOVATION AND INFRASTRUCTURE
0
Research Products
10REDUCED INEQUALITIES
0
Research Products
11SUSTAINABLE CITIES AND COMMUNITIES
0
Research Products
12RESPONSIBLE CONSUMPTION AND PRODUCTION
0
Research Products
13CLIMATE ACTION
0
Research Products
14LIFE BELOW WATER
0
Research Products
15LIFE ON LAND
0
Research Products
16PEACE, JUSTICE AND STRONG INSTITUTIONS
0
Research Products
17PARTNERSHIPS FOR THE GOALS
0
Research Products
Publication Collaboration
| Affiliation Name | Count |
|---|---|
| Fenerbahçe University | 9 |
| Kocaeli Üniversitesi | 4 |
| Yeditepe University | 3 |
| Istanbul Eye Hospital | 3 |
| Acıbadem University | 2 |
1 / 3
Data obtained from OpenAlex
Scholarly Output
9
Articles
9
WoS Citation Count
8
Scopus Citation Count
4
9 results
Scholarly Output Search Results
Now showing 1 - 9 of 9
Article Sekonder Progresif Multipl Sklerozun Tedavisinde Olası Biyomedikal Çözüm Önerileri(2022) Gündoğdu, Ö.; Çelik, Halenur; Sahin, SevimMultipl Skleroz (MS), vücudun bağışıklık sistemi hücreleri tarafından beyindeki sinir hücrelerinin dış kısmında bulunan miyelin kılıfların zarar görmesi sonucu lezyon veya plak oluşmasına bağlı nörolojik bir hastalıktır. Bu makalenin amacı Sekonder Progresif MS (SPMS) için tıp ve biyomedikal mühendisliği alanında çözüm önerileri üreterek yapılan çalışmaların anlatılmasıdır. Hastalığın tıp alanında çeşitli tedavi yöntemleri vardır. MS tedavisi kişiye özel olarak yapılmaktadır. Tıp alanında yapılan en temel tedavi yöntemi ilaç ile tedavidir. Son yapılan çalışmalar sonucunda nanoparçacıkların polimerik yapısının içerisine konulan miyelin antijenleri sayesinde bağışıklık sistemi hücrelerinin miyelinli hücrelere saldırması engellenerek hastalığın yavaşlatılması sağlanmıştır. Zarar gören miyelin kılıfların onarımı ise kolesterolün düşürülmesinde kullanılan bir molekül sayesinde yapılmıştır. MS tam olarak nedeni bilinmeyen otoimmün ve nörolojik bir hastalıktır. Bu makale çalışmasında ise yapılmış olan deneysel çalışmalara göre üretilen tüm çözüm önerilerinin derlenmesi amaçlanmıştır.Article Citation - Scopus: 1The Therapeutic Role of Ginseng in Promoting Hippocampal Neurogenesis and Ameliorating Cognitive Function Following Whole Brain Radiotherapy in Rats(Springer/Plenum Publishers, 2025) Sahin, Sevim; Bayindir, Nihan; Ertas, Busra; Ceylan, Cemile; Elibol, Birsen; Ozkan, Alper; Sener, GokselWhole-brain radiotherapy (WBRT) is a prevalent technique for managing multiple intracranial metastases, however, the cognitive damage in long-term survivors due to WBTR is a critical concern that impacts patients' quality of life. Panax ginseng, a bioactive compound recognized for its neuroprotective benefits, also enhances cognitive functions, including memory and learning. This study aims to examine the potential protective effects of Panax ginseng supplementation on cognitive dysfunction and the levels of neurogenesis-related proteins in the hippocampus of rats that underwent WBRT, which was delivered as 3 fractions of 6 Gy (total dose 18 Gy) using a linear accelerator. Thirty-six male Sprague-Dawley rats were divided into three groups: radiation, ginseng treatment, and control. After 60 days of Panax ginseng administration (100 mg/kg), behavior tests (Morris water maze and novel object recognition) were performed, followed by western blot analysis of the hippocampus. Results indicated that Panax ginseng supplementation ameliorated radiation-induced cognitive impairments. Additionally, western blot analyses revealed that Panax ginseng promoted neuronal recovery and neuroplasticity processes in the hippocampus, simultaneously exhibiting a neuroprotective mechanism by reducing apoptosis and neurotoxicity markers. Panax ginseng ameliorates cognitive dysfunction after WBRT by enhancing neurogenesis and diminishing cell death in the hippocampus.Article Citation - WoS: 2Efficiency of Modulated and Dose Rate Altered Flattening Filter Free Beams in High Dose Per Fraction Radiotherapy Applications on the Survival of Prostate Cancer Cell Lines(Ijrr-iranian Journal Radiation Res, 2021) Ceylan, C.; Ozturk, A.; Gungor, G.; Karabey, A. U.; Sahin, S.; Duruksu, G.; Gundogdu, O.Background: The radiobiological effect of high dose rate FFF beams on the DU-145 cells was investigated with SBRT plans which have >10 Gy. Methods and Materials: To compare the radiobiological effect on DU-145 cell line four experiments designed: (1) the constant dose rate of 6 MV and 6 MV FFF with increased dose per pulse (2) the effect of dose per pulse while increasing instantaneous dose rate for 6 MV and 6 MV FFF, (3) the effect of increased average dose rate for 6 MV FFF and (4) the effect of protracted treatment time and modulation of 6 MV FFF beams. The survival fraction was counted with WST. Results: FF and FFF for 6 MV with same dose rate and treatment time has no effect on cell survival. Significant differences was observed on survival which were irradiated with 6 MV 600 MU/min and 6 MV FFF 1400 MU/min (p=0.024). There was no difference between 6 MV FFF 600 MU/min and 6 MV FFF 1400 MU/min for 10 Gy. The significant survival difference obtained for 20 Gy. The survival percentages for both 10 Gy and 20 Gy with Cyberknife were obtained higher than FFF. Conclusion: Our in-vitro study presented here show that higher dose rate and reduced treatment time might become a crucial factor for SBRT especially which has >10 Gy fraction dose.Article Data-Efficient and Explainable Multimodal Survival Prediction in NSCLC Using Deep Image Embeddings, Clinical Variables, and Gradient-Boosted Trees(MDPI, 2026) Sahin, Sevim; Karaçor, Adil GürselBackground/Objectives: Survival prediction in non-small cell lung cancer (NSCLC) remains challenging, particularly in limited-sample settings where end-to-end deep learning models may suffer from limited generalization. This study aimed to develop a data-efficient, multimodal, and explainable framework integrating computed tomography (CT)-derived imaging information with clinical variables for NSCLC survival prediction. Methods: CT images, tumor segmentations, and clinical data from the publicly available NSCLC Radiomics (LUNG1) dataset (377 patients) were used. Tumor-focused regions were extracted using segmentation masks, and pretrained RadImageNet-InceptionV3 embeddings were obtained from the largest tumor-containing slice and neighboring-slice summaries. Deep imaging embeddings, engineered imaging features, and clinical variables were fused into a unified tabular representation. To improve robustness under limited-sample conditions, feature blocks were compressed using principal component analysis. CatBoost, XGBoost, and LightGBM models were trained on a development set and evaluated on a strictly held-out final validation set. Results: In three-class survival stratification, assigning censored/non-event patients to the upper survival group produced the strongest ordinal prognostic performance. Under the EX_PLUS_NON_EX_TOP setting, CatBoost achieved the best holdout score-based class C-index of 0.655. In continuous survival regression, LightGBM achieved the best holdout event-patient C-index of 0.576. Clinical variables provided the dominant prognostic signal, while compact deep image embeddings contributed complementary information, particularly in separating short- and long-survival groups. SHAP analysis confirmed contributions from both clinical and image-derived features. Conclusions: The proposed framework provides a proof-of-concept demonstration of a data-efficient and explainable image-to-tabular approach for NSCLC survival prediction under strict internal holdout validation. The results suggest that pretrained CT embeddings, clinical variables, gradient-boosted trees, and SHAP-based interpretation can be combined in a feasible, limited-sample survival modeling pipeline, while external validation remains necessary before clinical translation.Article Evaluation of Patient-Specific Quality Assurance Results to Optimise Automatic Flash Margin in Monte Carlo Algorithm for VMAT of the Breast and Chest Wall Irradiation(MDPI, 2026) Ceylan, Cemile; Sahin, SevimBackground/Objectives: To evaluate the impact of automatic flash (AF) margin thickness on plan complexity and patient-specific quality assurance (PSQA) outcomes in 4-partial-arc VMAT (4pVMAT) for breast and chest wall irradiation using the Monaco Monte Carlo treatment planning system. Methods: Twenty patients (11 left-sided, 9 right-sided) previously treated with 4pVMAT were retrospectively replanned with five AF thicknesses (AF0, AF3, AF5, AF10, AF15), yielding 100 plans on Elekta Versa HD/Agility MLC. Plan complexity was assessed via modulation factor (MF), total monitor units (MU), segment number, MU efficiency, and normalisation ratio. PSQA was performed using the IBA Matrixx Resolution detector, with gamma passing rates (GPRs) evaluated under 3%/3 mm, 3%/2 mm, and 2%/2 mm criteria. Friedman and Wilcoxon signed-rank tests were used with Bonferroni correction. Results: All five complexity metrics were statistically invariant across AF0–AF15 (Friedman p > 0.05; no pairwise comparison against AF10 reached significance). Mean GPR increased monotonically up to AF10—92.28 ± 4.83% (AF0) to 93.73 ± 4.55% (AF10) at 3%/3 mm—and plateaued at AF15. After Bonferroni correction, AF0 vs. AF10 (p = 0.0003) and AF3 vs. AF10 (p = 0.005) remained significant under the 3%/3 mm criterion. The proportion of plans meeting GPR ≥ 95% at 3%/3 mm rose from 25% (AF0) to 45% (AF10). Conclusions: AF thickness has no clinically meaningful effect on plan complexity but significantly affects delivery accuracy in 4pVMAT breast and chest wall irradiation. AF10 emerges as the optimal margin—maximising delivery accuracy at a plateau without increasing plan complexity—with AF5 as the practical lower bound and AF15 as the upper bound.Article Paired Dosimetric Comparison of VMAT-Based Total Body and Total Marrow Irradiation in Adult Leukemia Patients: Enhanced Organ Sparing with Consistent Plan Complexity(Frontiers Media SA, 2026) Yesil, Abdullah; Sahin, SevimBackground/objectives: Total body irradiation (TBI) is widely used in conditioning regimens prior to hematopoietic stem cell transplantation, but it is associated with significant radiation exposure to normal tissues. Total marrow irradiation (TMI) has emerged as a more targeted alternative, aiming to reduce organ-at-risk doses while maintaining target coverage. This study aimed to evaluate whether TMI can provide clinically meaningful organ sparing while maintaining acceptable treatment complexity using a paired dosimetric approach. Methods: Thirty adult patients with acute leukemia who previously received VMAT-based TBI were retrospectively included. For each patient, a corresponding VMAT-based TMI plan was generated using the same CT datasets. To ensure planning efficiency and standardization, target delineation for TMI was facilitated by AI-based auto-segmentation. Plan quality was assessed using the homogeneity index, and complexity was analyzed based on monitor units, segment number, and modulation factor. Paired comparisons were performed using the Wilcoxon signed-rank test. Results: TMI plans demonstrated a consistent and statistically significant reduction in dose to all evaluated organs at risk compared with TBI (p < 0.001). Mean doses to the heart, kidneys, and liver were reduced by approximately 5-6 Gy, and the lung dose was also significantly decreased. TMI provided improved dose homogeneity and showed significantly lower monitor units, segment number, and modulation factor compared with TBI. Conclusions: VMAT-based TMI reduced organ-at-risk doses while preserving target coverage and showing favorable plan quality and complexity metrics. AI-based auto-segmentation may reduce the workload of skeletal target delineation; however, treatment uncertainties related to patient positioning, respiratory motion, and field-junction dose matching should be carefully managed during clinical implementation.Article Citation - WoS: 1Citation - Scopus: 1A Data-Efficient Machine Learning Approach for Breast Ultrasound Lesion Classification Integrating Image-Derived Features and Sonographic Descriptors(MDPI, 2026) Karacor, Adil Gursel; Sahin, SevimBackground/Objectives: Breast ultrasound is widely used for the diagnostic evaluation of breast lesions; however, reliable lesion characterization remains challenging due to substantial image heterogeneity and the limited size of most clinically available datasets. These constraints reduce the generalizability of end-to-end deep learning approaches in routine practice. The objective of this study was to evaluate a data-efficient diagnostic framework that integrates image-derived features with clinical sonographic descriptors to improve breast ultrasound lesion classification in small cohorts. Methods: Ultrasound images from the publicly available BrEaST-Lesions dataset were processed using a pretrained convolutional neural network to extract compact image feature representations from full images, lesion masks, and cropped tumor regions. These features were combined with manually recorded sonographic descriptors after label encoding to form a unified tabular dataset. Gradient-boosted tree models were trained using descriptor-only and fused feature sets with fivefold stratified cross-validation and evaluated on an independent external hold-out test set. Results: Using sonographic descriptors alone, the best-performing model (LightGBM) achieved an external validation accuracy of 0.88, with an area under the receiver operating characteristic curve (AUC) of 0.95. Incorporation of image-derived features improved diagnostic performance on the external test set, yielding an accuracy of 0.88, an AUC of 0.96, and a sensitivity of 1.00 for malignant lesion detection. The fused framework demonstrated more stable generalization than descriptor-only models, particularly for malignant cases. Conclusions: Combining image-derived features with clinical sonographic descriptors within a tabular learning framework provides a robust and data-efficient approach for breast ultrasound-based lesion classification. This strategy supports diagnostic decision-making in small ultrasound datasets and represents a clinically realistic alternative when large-scale deep learning models are impractical.Article Citation - Scopus: 2Efficiency of Modulated and Dose Rate Altered Flattening Filter Free Beams in High Dose Per Fraction Radiotherapy Applications on the Survival of Prostate Cancer Cell Lines(Novin Medical Radiation Institute, 2021) Ceylan, C.; Öztürk, A.; Güngör, G.; Karabey, A.U.; Şahin, S.; Duruksu, G.; Gündoğdu, Ö.; Deparment Of Biomedical Engineering, Kocaeli Univetsity, Kocaeli, TurkeyBackground: The radiobiological effect of high dose rate FFF beams on the DU-145 cells was investigated with SBRT plans which have >10 Gy. Methods and Materials: To compare the radiobiological effect on DU-145 cell line four experiments designed: (1) the constant dose rate of 6 MV and 6 MV FFF with increased dose per pulse (2) the effect of dose per pulse while increasing instantaneous dose rate for 6 MV and 6 MV FFF, (3) the effect of increased average dose rate for 6 MV FFF and (4) the effect of protracted treatment time and modulation of 6 MV FFF beams. The survival fraction was counted with WST. Results: FF and FFF for 6 MV with same dose rate and treatment time has no effect on cell survival. Significant differences was observed on survival which were irradiated with 6 MV 600 MU/min and 6 MV FFF 1400 MU/min (p=0.024). There was no difference between 6 MV FFF 600 MU/min and 6 MV FFF 1400 MU/min for 10 Gy. The significant survival difference obtained for 20 Gy. The survival percentages for both 10 Gy and 20 Gy with Cyberknife were obtained higher than FFF. Conclusion: Our in-vitro study presented here show that higher dose rate and reduced treatment time might become a crucial factor for SBRT especially which has >10 Gy fraction dose. © 2021 Novin Medical Radiation Institute. All rights reserved.Article Citation - WoS: 5Effect of Multileaf Collimator Leaf Position Error Determined by Picket Fence Test on Gamma Index Value in Patient-Specific Quality Assurance of Volumetric-Modulated Arc Therapy Plans(Springernature, 2021) Ceylan, Cemile; Inal, Serpil Yondem; Senol, Elif; Yilmaz, Berrin; Sahin, SevimAim The correlation between the MLC QA (IBA Dosimetry, Germany) results of the picket fence test created with intentional errors and the patient's quality assurance (QA) evaluation was investigated to assess the impact of multileaf collimator (MLC) positioning error on patient QA. Materials and methods The picket fence, including error-free and intentional MLC errors, defined in Bank In, Bank Out, and Bank Both were analyzed using MLC QA. The QA of 15 plans consisting of stereotactic radiosurgery (SRS), stereotactic body radiotherapy (SBRT), and conventionally fractionated volumetric-modulated arc therapy (VMAT) acquired with electronic portal imaging devices (EPID) was evaluated in the presence of error-free and MLC errors. The QA of plans were analyzed with 2%/2 mm and 3%/3 mm criteria. Results The passing rates of the picket fence test were 97%, 92%, 91%, and 87% for error-free and intentional errors. The criterion of 3%/3 mm wasn't able to detect an MLC error for either SRS/SBRT or conventionally fractionated VMAT. The criterion of 2%/2mm was more sensitive to detect MLC error for the conventionally fractionated VMAT than SRS/SBRT. While only two of SBRT plans had <90%, four of conventionally fractionated VMAT plans had a <90% passing rate. Conclusion We found that the systematic MLC positioning errors defined with picket fence have a smaller but measurable impact on SRS/SBRT than the VMAT plan for a conventionally fractionated and relatively complex plan such as head and neck and endometrium cases.