NYNilay Çavuşoğlu Yalçın

Nilay Çavuşoğlu Yalçın

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Nilay Çavuşoğlu Yalçın has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Educational quality of YouTube videos on robot-assisted thymectomy: a LAP-VEGaS-based evaluation

    by Okan Karataş, Ayşegül Güler, Nilay Çavuşoğlu Yalçın, Muharrem Özkaya

    Video-based learning has become an integral component of surgical training, especially with the growing implementation of minimally invasive techniques suc

  • Open Access

    Comparative performance analysis of deep learning architectures for pulmonary nodule candidate classification: a computational study using public Benchmark datasets

    by Koray Kaya Kılıç, Nilay Çavuşoğlu Yalçın, Mustafa Yalçın, Nevfel Kahvecioğlu

    Aims: To systematically compare the candidate-level classification performance of four state-of-the-art deep learning architectures—U-Net, ResNet-50, Vision Transformer (ViT-B/16), and YOLOv8—for pulmonary nodule candidate classification using patch-based classification on public benchmark CT datasets, and to evaluate the trade-off between detection accuracy and computational efficiency.Methods: This computational study utilized publicly available, de-identified datasets including LUNA16 (Lung Nodule Analysis 2016) and LIDC-IDRI (Lung Image Database Consortium). Candidate nodule locations were generated using a multi-scale Laplacian of Gaussian (LoG) blob detector applied to full CT volumes. From these candidates, 64×64×64 voxel patches were extracted and classified as true nodules or false positives. The dataset was partitioned at the patient level: 70% training, 15% validation, and 15% held-out test. Stratified 5-fold cross-validation was conducted exclusively within the training set for hyperparameter optimization. Four deep learning architectures were trained under identical protocols: U-Net (encoder decoder), ResNet-50 (residual CNN), ViT-B/16 (self-attention transformer, adapted to 3D patch input via 3D patch embedding), and YOLOv8 (real-time detector, applied slice-by-slice with 3D aggregation). Primary performance metrics included sensitivity, specificity, F1-score, mAP@0.5, and area under the ROC curve (AUC). Free-response ROC (FROC) analysis was performed following LUNA16 challenge standards, reporting sensitivity at 0.125, 0.25, 0.5, 1, 2, 4, and 8 false positives per scan (FP/scan). Statistical comparisons focused on AUC using paired DeLong’s test with Bonferroni correction for multiple comparisons. Bootstrap confidence intervals (n=2,000 resamples) were computed for sensitivity, specificity, and F1-score. Results: Across 888 CT scans (1,186 annotated nodules; LUNA16 test set: 133 scans, 178 nodules), Vision Transformer achieved the highest candidate-level patch classification performance: sensitivity 94.2% (95% CI: 91.8–96.1%), specificity 92.8% (95% CI: 90.3–94.9%), F1-score 0.935, mAP@0.5 0.947, and AUC 0.971 (95% CI: 0.958–0.982). Pairwise AUC comparisons using DeLong’s test confirmed superior discrimination for ViT-B/16 relative to the comparator architectures. FROC analysis demonstrated ViT-B/16 achieved the highest mean sensitivity at 7 operating points (CPM=0.847), outperforming ResNet-50 (CPM=0.798), YOLOv8 (CPM=0.781), and U-Net (CPM=0.762). However, ViT-B/16 required 3.2× longer inference time (8.4 vs 2.6 seconds/scan) and 3.7× more trainable parameters than ResNet-50. YOLOv8 demonstrated superior computational efficiency with the shortest inference time (1.1 seconds/scan). Conclusion: The attention-based Vision Transformer architecture achieved superior candidate-level patch classification performance for pulmonary nodule candidate evaluation; however, this advantage must be weighed against substantial computational costs. Architecture selection should be guided by deployment context, with ResNet-50 offering optimal accuracy efficiency balance for clinical deployment and YOLOv8 for real-time screening applications.

  • Open Access

    Educational quality of YouTube videos on video assisted thoracoscopic segmentectomy

    by Nilay Çavuşoğlu Yalçın, Ayşegül Güler, Muharrem Özkaya

    Video-assisted thoracoscopic segmentectomy (VATS) is increasingly performed as a parenchyma-sparing procedure for early-stage lung cancer, yet standardized educational resources remain limited. YouTube is widely accessed by surgeons and trainees, but the educational quality of its content is largely unregulated. This study systematically evaluated YouTube videos on VATS segmentectomy using the validated LAParoscopic surgery Video Educational GuidelineS (LAP-VEGaS) tool. A structured search was performed on June 12, 2025, and 34 videos with ≥ 2500 views were included. Two experienced thoracic surgeons independently assessed all videos, and inter-rater agreement was measured using Cohen’s kappa. The mean LAP-VEGaS score was 6.6 (range 2–14), with only 23.5% of videos reaching the validated threshold (≥ 11) for adequate educational quality. No significant correlation was observed between LAP-VEGaS scores and popularity metrics such as views, likes, or duration, although narration was strongly associated with higher scores. To our knowledge, this is the first study systematically evaluating VATS segmentectomy videos on YouTube using LAP-VEGaS. These findings demonstrate that most YouTube videos on VATS segmentectomy are educationally inadequate and highlight the need for peer-reviewed, curated repositories to ensure reliable and high-quality training materials for thoracic surgical education.


  • Open Access

    Limited Predictive Utility of Inflammatory Indices for Postoperative Complications in Primary Lung Cancer Surgery

    by Muharrem Özkaya, Nilay Yalçın, Erhan Özyurt, Mehmet Tercan

    Background: Systemic inflammatory indices such as the Pan-Immune Inflammation Value (PIV), Systemic Immune-Inflammation Index (SII), and Systemic Inflammation Response Index (SIRI) are recognized prognostic markers in oncology. Their potential role in predicting early postoperative complications after lung cancer surgery, however, remains uncertain. Methods: We retrospectively analyzed 68 patients who underwent pulmonary resection for primary lung cancer between January 2019 and November 2024. PIV, SII, and SIRI were calculated from preoperative and first postoperative day blood counts. Associations with 30-day complications were assessed using comparative statistics and receiver operating characteristic (ROC) analysis. Results: Complications occurred in 10 patients (14.7%). None of the indices differed significantly between patients with and without complications. ROC analysis demonstrated poor predictive performance across all indices (AUC range: 0.447– 0.612). A significant histology imbalance (p=0.039) suggested that tumor biology may have contributed to complication risk. Conclusion: Despite their established prognostic relevance in oncology, PIV, SII, and SIRI provided limited discrimination for early postoperative complications in lung cancer surgery. These negative findings underscore the importance of cautious interpretation, particularly given the small number of events and low statistical power. They highlight the limited perioperative utility of such indices, helping to prevent their overestimation in clinical practice, and point to the need for prospective studies exploring alternative predictive markers within multimodal models.


  • Open Access

    Predicting the Need for Tube Thoracostomy in Blunt Trauma Patients With Occult Pneumothorax: Observation Versus Intervention

    by Nilay Çavuşoğlu Yalçın, Muharrem Özkaya

    Objectives: Occult pneumothorax is increasingly diagnosed in trauma patients due to widespread use of computed tomography (CT), yet its optimal management remains controversial. This study aimed to identify clinical and radiological predictors of deterioration requiring tube thoracostomy and to develop a predictive model to guide management decisions. Methods: In this retrospective single-centre study, 166 patients with blunt trauma-associated occult pneumothorax were analyzed. Clinical and radiological variables—including subcutaneous emphysema, haemothorax volume, pneumothorax size, mechanical ventilation, and rib fractures—were evaluated for association with delayed tube thoracostomy. A weighted multivariable logistic regression model addressed class imbalance, and model performance was assessed using receiver operating characteristic (ROC) analysis. Results: Of 166 patients, 17 (10.2%) required delayed tube thoracostomy. Subcutaneous emphysema (odds ratio [OR] 20.10, P = .001) and mechanical ventilation (OR 17.30, P = .002) were the strongest independent predictors of deterioration. Haemothorax volume also showed a significant association (OR 1.06, P = .045). Other factors, including pneumothorax size, rib fractures, age, and sex, were not predictive. The predictive model demonstrated excellent discrimination (area under the curve [AUC] = 0.97), suggesting potential for clinical risk stratification. Conclusions: Physiological indicators such as subcutaneous emphysema and mechanical ventilation are superior to anatomical parameters in predicting deterioration among patients with occult pneumothorax. Our findings support a selective management strategy and highlight the utility of predictive modelling to guide tube thoracostomy decisions. Prospective multicentre studies are warranted to validate these results.

  • Open Access

    Global awareness and integration of immunotherapy among thoracic surgeons: a multicenter survey study

    by Muharrem Özkaya, Nilay Cavusoglu Yalcin, Ayşegül Güler, Arif Hakan Önder, Halil Göksel Güzel

    SUMMARY OBJECTIVE: Lung cancer is the leading cause of cancer-related mortality, with non-small cell lung cancer accounting for most cases. Surgery remains the primary treatment for early-stage non-small cell lung cancer, while advanced disease requires multimodal strategies. Immunotherapy, particularly immune checkpoint inhibitors targeting programmed cell death protein-1, programmed death-ligand 1, and cytotoxic T-lymphocyte-associated protein 4, has significantly improved survival and is increasingly incorporated into neoadjuvant and adjuvant settings. The aim of the study was to evaluate thoracic surgeons’ awareness, perceptions, and integration of immunotherapy in surgical practice. METHODS: A cross-sectional survey was conducted among 64 thoracic surgeons from 19 countries to assess their perspectives, challenges, and regional disparities in immunotherapy adoption. Statistical analyses examined associations between perceptions and variables such as specialty, experience, hospital type, and geographic region. RESULTS: Perceptions of immunotherapy did not differ significantly by specialty, experience, hospital type, or geographic location. However, significant associations were observed between years of experience and hospital type, as well as surgical specialty and geographic region. Key barriers included cost, lack of standardized guidelines, and challenges in multidisciplinary coordination. Surgeons in low- and middle-income countries reported greater difficulties in drug access and institutional infrastructure. The majority of participants (85%) expressed a need for further training, highlighting the importance of structured education programs and enhanced collaboration between surgical and medical oncology teams. CONCLUSION: While immunotherapy is widely accepted among thoracic surgeons, challenges related to education, accessibility, and implementation persist. Addressing these barriers through global initiatives, cost-effective policies, and multidisciplinary cooperation is essential for optimizing immunotherapy integration in thoracic surgery and improving outcomes for non-small cell lung cancer patients.

  • Surgical Management of Neurogenic Thoracic Outlet Syndrome: Exploring the Efficacy of the Posterior Intermuscular Approach in Cases Involving Bone Anomalies

    by Gediz Tolga, Yalçın Çavuşoğlu Nilay, Mutlucan Ogün Umut, Türk Cezmi Çağrı

    BACKGROUND AND OBJECTIVES: This article presents a cohort study focusing on neurogenic thoracic outlet syndrome (NTOS) caused by bone anomalies in the cervicothoracic region, specifically the extraforaminal area and the scalene triangle. Our aim was to contribute to understanding NTOS diagnosis and management, particularly in patients with bone anomalies, and to highlight the potential benefits of the posterior intermuscular approach as a surgical option in this particular patient group. METHODS: We retrospectively evaluated the patients who underwent surgery for NTOS with accessory ribs or an elongated cervical vertebrae 7 (C7) transverse process (n = 9). Patients' clinical data, preoperative neurophysiological tests, cervical computed tomography (CT) scans, CT angiography, and postoperative cervical CT scans were reviewed. A single experienced surgeon used the posterior intermuscular approach on all patients. The accessory rib and/or elongated C7 transverse process and fibrous bands were removed; C7, C8, and T1 branches of the plexus were decompressed; and neurolysis was performed. Quality of life, a functional outcome, was measured by using Disabilities of the Arm, Shoulder and Hand (DASH) questionnaire, and pain was measured using visual analog scale scores. RESULTS: The mean follow-up time after surgery was 7 months (range: 4-10 months). Before surgery, the mean DASH score was 55.8 ± 5.6. At the 3- and 6-month postoperative evaluations, the mean DASH scores decreased to 15.7 ± 5.8 and 15.4 ± 5.7, respectively. The mean visual analog scale score was 8.2/10 before surgery and decreased to 2.4/10 and 2.1/10 at the 3- and 6-month postoperative evaluations, respectively. All patients experienced good or excellent recovery at the 3- and 6-month postoperative evaluations. CONCLUSION: Cervicothoracic extraforaminal area may be the primary site of nerve compression in NTOS, and posterior decompression using the posterior intermuscular approach can provide efficient access to extraforaminal nerve roots.

  • Open Access

    Anterior Mediastinal Kitlelere Cerrahi Yaklaşım

    by Muharrem Özkaya, Nilay Çavuşoğlu

    Aim: The aim of this study was to evaluate the clinical progress, type of surgical approach and early results of resection of anterior mediastinal masses. Patients and Methods: We retrospectively reviewed the reports of 25 patients who underwent surgery for an anterior mediastinal mass between 2014 and 2019. Patients’ age, gender, presenting symptoms, preoperative radiological investigations and surgical techniques were recorded. There were eight male and 17 female patients, and their age ranged from 18-89 with a mean of 44.4± 16.9 years. Results: The most frequent presenting symptoms were chest pain (90%) and cough (50%). The most common pathological diagnoses were thymic tumors (n=14, 56%) and lymphoma (n=5, 20%). Surgical approaches applied were median sternotomy in 16 patients, partial sternotomy in five patients and VATS (Video Assisted Thoracic Surgery) in four patients. There were no postoperative deaths or major complications, but eight patients had minor complications. Postoperative stay was 5±5.2 days. Conclusion:Surgery is a safe technique for diagnosis and treatment of anterior mediastinal masses.