Current practices of craniospinal irradiation techniques in Turkey: a comprehensive dosimetric analysis.

OBJECTIVE: This study evaluates various craniospinal irradiation (CSI) techniques used in Turkish centers to understand their advantages, disadvantages and overall effectiveness, with a focus on enhancing dose distribution. METHODS: Anonymized CT scans of adult and pediatric patients, alongside target volumes and organ-at-risk (OAR) structures, were shared with 25 local radiotherapy centers. They were tasked to develop optimal treatment plans delivering 36 Gy in 20 fractions with 95% PTV coverage, while minimizing OAR exposure. The same CT data was sent to a US proton therapy center for comparison. Various planning systems and treatment techniques (3D conformal RT, IMRT, VMAT, tomotherapy) were utilized. Elekta Proknow software was used to analyze parameters, assess dose distributions, mean doses, conformity index (CI), and homogeneity index (HI) for both target volumes and OARs. Comparisons were made against proton therapy. RESULTS: All techniques consistently achieved excellent PTV coverage (V95 > 98%) for both adult and pediatric patients. Tomotherapy closely approached ideal Dmean doses for all PTVs, while 3D-CRT had higher Dmean for PTV_brain. Tomotherapy excelled in CI and HI for PTVs. IMRT resulted in lower pediatric heart, kidney, parotid, and eye doses, while 3D-CRT achieved the lowest adult lung doses. Tomotherapy approached proton therapy doses for adult kidneys and thyroid, while IMRT excelled for adult heart, kidney, parotid, esophagus, and eyes. CONCLUSION: Modern radiotherapy techniques offer improved target coverage and OAR protection. However, 3D techniques are continued to be used for CSI. Notably, proton therapy stands out as the most efficient approach, closely followed by Tomotherapy in terms of achieving superior target coverage and OAR protection.

Two Different Points of View through Artificial Intelligence and Vector Autoregressive Models for Ex Post and Ex Ante Forecasting.

The ANN method has been applied by means of multilayered feedforward neural networks (MLFNs) by using different macroeconomic variables such as the exchange rate of USD/TRY, gold prices, and the Borsa Istanbul (BIST) 100 index based on monthly data over the period of January 2000 and September 2014 for Turkey. Vector autoregressive (VAR) method has also been applied with the same variables for the same period of time. In this study, different from other studies conducted up to the present, ENCOG machine learning framework has been used along with JAVA programming language in order to constitute the ANN. The training of network has been done by resilient propagation method. The ex post and ex ante estimates obtained by the ANN method have been compared with the results obtained by the econometric forecasting method of VAR. Strikingly, our findings based on the ANN method reveal that there is a possibility of financial distress or a financial crisis in Turkey starting from October 2017. The results which were obtained with the method of VAR also support the results of ANN method. Additionally, our results indicate that the ANN approach has more superior prediction performance than the VAR method.