Bilgi Tabanlı Planlama (“Knowledge Based Planningˮ-KBP), klinik olarak kabul edilebilir Yoğunluk Ayarlı Radyoterapi (“Intensity Modulated Radiotherapy”-IMRT) ve Hacimsel Modülasyonlu Ark Tedavisi (“Volumetric Modulated Arc Therapy”-VMAT) planlarını minimum iş akışıyla optimize etmek için bilgi tabanlı modeller (“Knowledge Based Model”–KBM) kullanarak plan kalitesini standart hale getirmeyi amaçlar. KBP, Risk Altındaki Organlar (‟Organ at Risk”-OAR) için ulaşılabilir Doz-Volüm Histogramı (DVH)’nı tahmin eder ve her bir yeni hasta için ideal optimizasyon hedefleri sağlar. KBP modeli, plan kalitesini iyileştirir, plan tutarlılığını koruyarak planlayıcılar arası değişkenliği azaltır ve simülasyondan tedavi başlangıcına dek geçen süreyi kısaltır. Bu derlemede prostat kanserinin VMAT tekniği ile tedavisinde KBP tabanlı yöntemlerin kullanıldığı klinik çalışmaların sonuçları incelendi. “Knowledge-based treatment planning”, “prostate cancer”, “VMAT” anahtar kelimeleri kullanılarak “PubMed” tarama motorunda “Clinical Trial” kategorisindeki İngilizce olarak yayınlanmış makalelerin taranması sonucu ulaşılan beş adet çalışma derleme kapsamına alındı. Bu klinik çalışmaların tümünde temelde KBP modelinin dozimetrik ve mekanik performansını değerlendirmek ve optimize etmek istenmiştir. Bu nedenle her bir kliniğin deneyimine göre hazırlanan manuel planlar, KBP ile oluşturulan otomatik planlar ile karşılaştırılmıştır. Prostat kanserinin VMAT planlamasında KBP kullanımı, doğrulama çalışmalarında, güçlü bir şekilde performans göstermiştir. KBP yöntemleri, plan kalitesi açısından genellikle uzman seviyesindeki planlayıcılara eşdeğerdir ancak ön sonuçlar, önemli ölçüde daha gelişmiş olduklarını göstermektedir. Hedef volüm ile örtüşen OAR volümlerinin dikkate alındığı KBP modellerinin örtüşme volüm histogramı (“overlap volüme histogram”-OVH) rehberliğinde daha hassas ve doğru doz tahminleri yapabileceği düşünülmektedir. KBP yöntemlerinin uygulaması sırasında dozimetrik ve mekanik performansın yanı sıra hastaya özgü kalite güvenirliğini (“Quality Assurance” –QA) doğrulamak da çok önemlidir.
Purpose: Molecular subtyping guides diagnosis and targeted therapy for gliomas. Although MRI—the current imaging standard—can be time-consuming and is sometimes contraindicated, computed tomography (CT) is faster, more widely available, and often preferable in emergency and resource-limited settings. We evaluated whether CT-based radiogenomic signatures combined with machine learning could accurately predict clinically relevant glioma molecular markers. Methods: In this retrospective study, we characterised non-contrast CT (NCCT) scans from 197 adults with histologically confirmed gliomas. Models were developed to predict mutations in four molecular markers: ATRX ( n =81), EGFR ( n =17), TP53 ( n =71), and IDH ( n =183). We extracted 208 quantitative radiomic features and added basic demographic variables. Feature selection used LASSO-RFE and Gradient Boosting–RFE with cross-validation. Six classical machine-learning classifiers and deep-learning approaches — including custom fully connected neural networks (FCNN) and TabNet — were trained and compared using ROC–AUC as the primary performance metric. Results: Deep-learning methods outperformed conventional classifiers for all targets. TabNet achieved ROC–AUCs of 0.900 (95% CI: 0.717–0.989; ATRX), 0.955 (95% CI: 0.661–0.978; TP53), and 0.917 (95% CI: 0.858–0.975; EGFR). A custom FCNN obtained a ROC–AUC of 0.971 (95% CI: 0.876–0.995) for IDH. Cross-validation coefficients of variation were 2.0% for ATRX and 3.0% for TP53 and EGFR, and 16.0% for IDH. Deep-learning approaches yielded statistically significant improvements over conventional methods ( p -values ranging from <0.05 to <0.001). Conclusion: NCCT-based analytical methods were able to predict clinically relevant genetic mutations in gliomas and demonstrated performance comparable to established techniques. These findings suggest that CT may serve as a practical option for molecular profiling in urgent or resource-limited settings. Nonetheless, external validation is necessary prior to clinical translation. The EGFR findings, arising from a small EGFR-tested subgroup (n = 17), remain preliminary; the observed performance may not reflect generalisable accuracy, and independent validation in larger cohorts is required.
10 April 2023 in Journal of Basic and Clinical Health Sciences
Purpose: It’s postulated that hybrid techniques (HT) with lower weighting of IMRT/VMAT component would improve lung dose-volume parameters despite some disadvantage in PTV homogeneity index (HI) and target coverage (TC). Material and Methods: Conformal plans were prepared using 6-10-15 MV-X photon energies while IMRT/VMAT plans of HTs were prepared using 6MV-X. Four HTs were developed having two different ratios (10% and 50%) of IMRT/VMAT component (h-IMRT1, h-IMRT2 and h-VMAT1, h-VMAT2, respectively). HTs were compared with 3D-CRT in terms of HI and TC for PTV, and total lung (TL) and contralateral lung (CL) V5Gy, V10Gy, V20Gy and mean lung dose (MLD). Results: All HTs were advantageous for HI and TC, while disadvantageous for TL and CL-V5Gy. H-IMRT2 provided better TC than h-IMRT1, and so did h-VMAT2 compared to h-VMAT1. Lower weighting of IMRT/VMAT decreased TL and CL-V5Gy in HTs. In addition, h-IMRT1 decreased TL and CL-MLD and CL-V20Gy compared to h-IMRT2, while h-VMAT2 decreased TL-V20Gy and CL-MLD compared to h-VMAT2. Conclusion: In the RT of lung tumors close to vertebra, it may be appropriate to suggest a ratio of IMRT/VMAT component about 10% in order to decrease the low and intermediate dose-wash lung volume, if HI and TC values are acceptable.
1 March 2023 in Polish Journal of Medical Physics And Engineering
Introduction: It is necessary to have special experience to perform the Monte Carlo calculation, commonly used in medical physics and accepted as the gold standard. In this study, we developed software to teach basic steps to medical physicists who were inexperienced in the medical linear accelerator Monte Carlo simulation. Material and methods: For the design interface, a software called GamosLinacGUI was developed using Gnome Builder, Python, and GTK. The user, who wants to learn the basics of GAMOS and simulate a linear accelerator, can enter the values in the software, select some options and quickly create geometry and physics files. Results: For proof that the software generates the correct inputs for GAMOS simulation in the same conditions for the measurements and calculations. Required files for GAMOS have been created and tested and run the simulation accordingly. This software was tested with Centos Linux. Conclusions: GamosLinacGUI has been successfully developed, which creates the geometry and physics files required for the simulation with GAMOS as a training and learning tool.
29 September 2025 in Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi
Bismuth and Lead are commonly used for radiation shielding to mitigate risks such as radiation damage and cancer. However, these materials are costly and impractical for certain applications. This study aims to explore the attenuation properties of various elements and composites using Monte Carlo simulations to develop improved radiation shielding materials. GAMOS software was employed to simulate materials with thicknesses ranging from 0.1 to 2.0 mm and x-ray energies between 10 and 150 keV. Initial simulations focused on validating bismuth and lead by calculating their mass attenuation coefficients, which matched NIST (National Institute of Standards and Technology) values within a 2% margin of difference. After verification, the study simulated various shielding materials incorporating metals and rare earth elements. Among these, four composites with rare earth elements demonstrating the highest mass attenuation coefficients were selected. These composites exhibited superior absorption in the 50–80 keV energy range compared to bismuth and lead.
13 April 2026 in Journal of Imaging Informatics in Medicine
Accurate and rapid delineation of diffuse gliomas is essential in emergency neuro-oncology, yet MRI is often unavailable. We present a deep-learning segmentation approach for routine non-contrast CT and evaluate its technical feasibility and WHO grade–stratified performance, demonstrating its potential as a decision-support tool in time-sensitive, resource-limited clinical settings. CT scans from 206 adults with histopathologically confirmed diffuse gliomas were retrospectively collected from a single center and were divided into a development cohort ( n = 177) and an independent validation cohort ( n = 29). The glioma segmentation network (GSN) consists of a ResNet-18 encoder and five-stage U-Net decoder, trained with inverse-frequency weighted cross-entropy to address class imbalance. Model development involved five-fold cross-validation on the development cohort (results reported in the main text). Primary outcome measures were Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD95). Reference segmentations were generated by a board-certified neuroradiologist with over a decade of clinical experience using MITK. In the independent validation cohort, DSCs were 0.846 for grade 2 (95% CI 0.835–0.856), 0.806 for grade 3 (95% CI 0.800–0.811), and 0.802 for grade 4 (95% CI 0.796–0.809). Corresponding HD95 values were 13.677 mm (95% CI 12.70–14.65), 16.193 mm (95% CI 14.73–17.65), and 18.776 mm (95% CI 17.95–19.90). Inference throughput was 20 slices per second (95% CI 16.1–26.3). The proposed GSN demonstrates robust internal performance and clinically meaningful segmentation accuracy on independent CT data, supporting the technical feasibility of CT-based automated glioma delineation for emergency and resource-constrained settings. Evaluation was performed at the 2D slice level. Limitations include the single-center design and reliance on reference segmentations performed by a single neuroradiologist. Prospective multi-center validation is warranted before routine clinical implementation.