Alper Akın

Dr. Alper Akın

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 April 2026 in Liver Transplantation
Verified
Journal Article
Closed access
KMKenan Moral
Kenan Moral
MHMURAT HARPUTLUOGLU
MURAT HARPUTLUOGLU
GÖGülşah Fidan Özkumur
Gülşah Fidan Özkumur
DGDOĞAN CAN GAVCAR
DOĞAN CAN GAVCAR
EEEfe Erbay
Efe Erbay
GKGökhan Kabacam
Gökhan Kabacam
The Model for End-stage Liver Disease Sodium (MELD-Na) score predicts mortality in liver transplant candidates. MELD 3.0 has been proposed as an improved model for estimating mortality risk. This study evaluated MELD 3.0’s predictive accuracy for short-term mortality among Turkish liver transplant candidates and compared its performance with MELD and MELD-Na scores. Patients listed both for deceased donor transplants and living donor transplants were analyzed in the study. The discriminative abilities of MELD, MELD-Na, and MELD 3.0 scores were assessed using the area under the receiver operating characteristic curve (AUROC). Comparisons between AUROC values used the DeLong test. The most predictive cutoff for MELD 3.0 was determined using the Youden index. Transplant-free survival was analyzed using the Kaplan–Meier method, with survival curves compared using the log-rank test. A total of 1689 patients were included in this nationwide, multicenter study. Hepatitis B was the leading cause of cirrhosis (29%, n=491), followed by metabolic dysfunction–associated steatohepatitis (20%, n=335). For 3-month mortality, MELD 3.0 had the highest AUROC (0.753), followed by MELD-Na (0.747) and MELD (0.725). The most predictive cutoff values were 18 for MELD and 21 for MELD-Na and MELD 3.0. Both MELD-Na and MELD 3.0 outperformed MELD ( p <0.001), but showed no significant difference between them ( p =0.17). MELD 3.0 and MELD-Na demonstrated superior performance to MELD in predicting 3-month mortality among Turkish liver transplant candidates, though their predictive accuracy was comparable. Further refinements are needed to enhance MELD 3.0’s clinical utility.

1 January 2025 in Journal of Enterocolitis
Verified
Journal Article
Open access
PDF file
ASAdem Sarıca
Adem Sarıca
AAAlper Akın
Alper Akın
GDGİZEM DAĞCI
GİZEM DAĞCI
The term inflammatory bowel disease (IBD) typically refers to a group of inflammatory gastrointestinal conditions, primarily Crohn’s disease and ulcerative colitis. Colonoscopy remains the gold standard for diagnosing and managing IBD by evaluating mucosal healing. However, instead of relying solely on invasive endoscopy to confirm mucosal healing, biomarkers are frequently used to indicate inflammation in patients with IBD. In recent decades, fecal calprotectin and fecal lactoferrin have received considerable attention for the diagnosis and non-invasive management of IBD. Numerous studies have investigated fecal biomarkers for predicting the endoscopic and histologic activity of IBD, as well as the likelihood of disease recurrence. In this paper, we reviewed original articles and literature reviews on inflammatory markers in adults, published primarily between 2019 and 2024, along with select older studies. Although fecal calprotectin is the most commonly used fecal biomarker in clinical practice, several other potential fecal biomarkers have been described in the literature. After a brief introduction to these biomarkers, we aim to answer the question of which is the most sensitive biomarker of mucosal healing and whether alternatives to fecal calprotectin could be utilized.

25 August 2022 in Turkish Journal of Hematology
Verified
Journal Article
Open access
ÜGÜbeyde Ayşe Gülseren
Übeyde Ayşe Gülseren
EÜEce Ük
Ece Ük
AAAlper Akın
Alper Akın
AMAlpay Medetalibeyoglu
Alpay Medetalibeyoglu
SESimge Erdem
Simge Erdem

1 September 2026 in Cancers
Verified
Journal Article
Open access
PDF file
HAHalil Ertugrul Aktas
Halil Ertugrul Aktas
ETEminenur Sen Tasci
Eminenur Sen Tasci
LPLinkai Peng
Linkai Peng
MTMuhammed Enes Tasci
Muhammed Enes Tasci
YTYavuz B. Taktak
Yavuz B. Taktak
UBUlas Bagci
Ulas Bagci
Background: Accurate pancreatic tumor segmentation on contrast-enhanced computed tomography (CECT) is important for staging, treatment planning, and response assessment in pancreatic ductal adenocarcinoma (PDAC). Although foundation models have shown promise for medical image segmentation, their effectiveness for disease-specific tumor delineation remains uncertain. This study evaluated whether fine-tuning a Segment Anything Model (SAM)-based framework on the target cohorts improves pancreatic tumor segmentation compared with directly applied foundation models. Methods: In this retrospective multicenter study, CECT examinations from patients with pathologically confirmed PDAC acquired between 2015 and 2025 were included. Two foundation model baselines, nnInteractive and MedSAM2, were compared with three TAGS-based configurations representing increasing levels of adaptation: TAGS (Zero-Shot), SAM-TAGS (fine-tuned from SAM weights), and MSD-TAGS (fine-tuned from a pancreas-specific checkpoint). Performance was assessed using patient-level five-fold cross-validation with the Dice Similarity Coefficient (DSC) and Normalized Surface Dice (NSD). A leave-one-center-out analysis was additionally performed to evaluate generalization to institutions absent from training. Results: A total of 500 patients with PDAC from four independent centers were included. MSD-TAGS achieved the highest overall segmentation performance, with a mean DSC of 0.703 and a mean NSD of 0.835. SAM-TAGS achieved a mean DSC of 0.691 and a mean NSD of 0.822. In comparison, nnInteractive achieved a mean DSC of 0.632 and a mean NSD of 0.782; MedSAM2, 0.585 and 0.792; and TAGS (Zero-Shot), 0.496 and 0.639, respectively. Compared with each competing method, MSD-TAGS achieved significantly higher DSC and NSD values (all Holm-adjusted p < 0.001). It also achieved the highest DSC across all four centers and the highest NSD in three of the four centers. Under leave-one-center-out evaluation, MSD-TAGS declined by 0.025 DSC and SAM-TAGS by 0.089. Conclusions: Task-specific adaptation improved pancreatic tumor segmentation with foundation models, and fine-tuned TAGS outperformed two publicly released promptable models applied without adaptation. Models initialized from a pancreas-specific checkpoint showed greater robustness under center-held-out evaluation. These findings support the importance of organ-specific initialization and target-cohort fine-tuning for disease-specific segmentation and warrant further validation before clinical translation. The multicenter pancreatic tumor CT segmentation dataset, including de-identified images and expert segmentation annotations, is publicly available to facilitate future research.

31 July 2026 in Abdominal Radiology
Verified
Journal Article
Open access
PDF file
AKAHMET YASIN KARKAS
AHMET YASIN KARKAS
YTYavuz B. Taktak
Yavuz B. Taktak
BGBurak Gultekin
Burak Gultekin
ZHZiliang Hong
Ziliang Hong
HAHalil Ertugrul Aktas
Halil Ertugrul Aktas
SESukru Mehmet Erturk
Sukru Mehmet Erturk