Browsing by Author "Koska, Ilker Ozgur"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Article
    Citation - WoS: 11
    Citation - Scopus: 11
    Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach
    (NATURE PORTFOLIO, 2025) Ilker Ozgur Koska; Cagan Koska; Koska, Cagan; Koska, Ilker Ozgur
    We aimed to build a robust classifier for the MGMT methylation status of glioblastoma in multiparametric MRI. We focused on multi-habitat deep image descriptors as our basic focus. A subset of the BRATS 2021 MGMT methylation dataset containing both MGMT class labels and segmentation masks was used. A comprehensive mask fusion approach was developed to select relevant image crops of diseased tissue. These fusion masks which were guided by multiple sequences helped collect information from the regions that seem disease-free to radiologists in standard MRI sequences while harboring pathology. Integrating the information in different MRI sequences and leveraging the high entropic capacity of deep neural networks we built a 3D ROI-based custom CNN classifier for the automatic prediction of MGMT methylation status of glioblastoma in multi-parametric MRI. Single sequence-based classifiers reached intermediate predictive performance with 0.65 0.71 0.77 and 0.82 accuracy for T1W T2W T1 contrast-enhanced and FLAIR sequences respectively. The multiparametric classifier using T1 contrast-enhanced and FLAIR images reached 0.88 accuracy. The accuracy of the four-input model that used all sequences was 0.81. The best model reached 0.90 ROC AUC value. Integrating human knowledge in the form of relevant target selection was a useful approach in MGMT methylation status prediction in MRI. Exploration of means to integrate radiology knowledge into the models and achieve human-machine collaboration may help to develop better models. MGMT methylation status of glioblastoma is an important prognostic marker and is also important for treatment decisions. The preoperative non-invasive predictive ability and the explanation tools of the developed model may help clinicians to better understand imaging phenotypes of MGMT methylation status of glial tumors.
  • Thumbnail Image
    Article
    Citation - WoS: 4
    Citation - Scopus: 3
    Deep learning-based classification of parotid gland tumors: integrating dynamic contrast-enhanced MRI for enhanced diagnostic accuracy
    (BMC, 2025) Kazim Ayberk Sinci; Ilker Ozgur Koska; Yusuf Kenan Cetinoglu; Nezahat Erdogan; Ali Murat Koc; Nuket Ozkavruk Eliyatkin; Cagan Koska; Barkan Candan; Erdogan, Nezahat; Sinci, Kazim Ayberk; Koska, Ilker Ozgur; Koc, Ali Murat; Cetinoglu, Yusuf Kenan; Eliyatkin, Nuket Ozkavruk; Candan, Barkan
    BackgroundTo evaluate the performance of deep learning models in classifying parotid gland tumors using T2-weighted diffusion-weighted and contrast-enhanced T1-weighted MR images along with DCE data derived from time-intensity curves.MethodsIn this retrospective single-center study including a total of 164 participants 124 patients with surgically confirmed parotid gland tumors and 40 individuals with normal parotid glands underwent multiparametric MRI including DCE sequences. Data partitions were performed at the patient level (80% training 10% validation 10% testing). Two deep learning architectures (MobileNetV2 and EfficientNetB0) as well as a combined approach integrating predictions from both models were fine-tuned using transfer learning to classify (i) normal versus tumor (Task 1) (ii) benign versus malignant tumors (Task 2) and (iii) benign subtypes (Warthin tumor vs. pleomorphic adenoma) (Task 3). For Tasks 2 and 3 DCE-derived metrics were integrated via a support vector machine. Classification performance was assessed using accuracy precision recall and F1-score with 95% confidence intervals derived via bootstrap resampling.ResultsIn Task 1 EfficientNetB0 achieved the highest accuracy (85%). In Task 2 the combined approach reached an accuracy of 65% while adding DCE data significantly improved performance with MobileNetV2 achieving an accuracy of 96%. In Task 3 EfficientNetB0 demonstrated the highest accuracy without DCE data (75%) while including DCE data boosted the combined approach to an accuracy of 89%.ConclusionsAdding DCE-MRI data to deep learning models substantially enhances parotid gland tumor classification accuracy highlighting the value of functional imaging biomarkers in improving noninvasive diagnostic workflows.