Training and assessing convolutional neural network performance in automatic vascular segmentation using Ga-68 DOTATATE PET/CT.

To evaluate a convolutional neural network's performance (nnU-Net) in the assessment of vascular contours, calcification and PET tracer activity using Ga-68 DOTATATE PET/CT. Patients who underwent Ga-68 DOTATATE PET/CT imaging over a 12-month period for neuroendocrine investigation were included. Manual cardiac and aortic segmentations were performed by an experienced observer. Scans were randomly allocated in ratio 64:16:20 for training, validation and testing of the nnU-Net model. PET tracer uptake and calcium scoring were compared between segmentation methods and different observers. 116 patients (53.5% female) with a median age of 64.5 years (range 23-79) were included. There were strong, positive correlations between all segmentations (mostly r > 0.98). There were no significant differences between manual and AI segmentation of SUVmean for global cardiac (mean ± SD 0.71 ± 0.22 vs. 0.71 ± 0.22; mean diff 0.001 ± 0.008, p > 0.05), ascending aorta (mean ± SD 0.44 ± 0.14 vs. 0.44 ± 0.14; mean diff 0.002 ± 0.01, p > 0.05), aortic arch (mean ± SD 0.44 ± 0.10 vs. 0.43 ± 0.10; mean diff 0.008 ± 0.16, p > 0.05) and descending aorta (mean ± SD < 0.001; 0.58 ± 0.12 vs. 0.57 ± 0.12; mean diff 0.01 ± 0.03, p > 0.05) contours. There was excellent agreement between the majority of manual and AI segmentation measures (r ≥ 0.80) and in all vascular contour calcium scores. Compared with the manual segmentation approach, the CNN required a significantly lower workflow time. AI segmentation of vascular contours using nnU-Net resulted in very similar measures of PET tracer uptake and vascular calcification when compared to an experienced observer and significantly reduced workflow time.

A comprehensive study of the mechanical performance of gantry, EPID and the MLC assembly in Elekta linacs during gantry rotation.

OBJECTIVE: In radiotherapy treatments, it is crucial to monitor the performance of linear accelerator (linac) components, including gantry, collimation system and electronic portal imaging device (EPID) during arc deliveries. In this study, a simple EPID-based measurement method is suggested in conjunction with an algorithm to investigate the stability of these systems at various gantry angles with the aim of evaluating machine-related errors in treatments. METHODS: The EPID sag, gantry sag, changes in source-to-detector distance (SDD), EPID and collimator skewness, EPID tilt and the sag in leaf bank assembly owing to linac rotation were separately investigated by acquisition of 37 EPID images of a simple phantom with 5 ball bearings at various gantry angles. A fast and robust software package was developed for automated analysis of the image data. Nine Elekta AB (Stockholm, Sweden) linacs of different models and number of years in service were investigated. RESULTS: The average EPID sag was within 2 mm for all tested linacs. Some machines showed >1-mm gantry sag. Changes in the SDD values were within 1.3 cm. EPID skewness and tilt values were <1° in all machines. The maximum sag in multileaf collimator leaf bank assemblies was around 1 mm. A meaningful correlation was found between the age of the linacs and their mechanical performance. Conclusions and Advances in knowledge: The method and software developed in this study provide a simple tool for effective investigation of the behaviour of Elekta linac components with gantry rotation. Such a comprehensive study has been performed for the first time on Elekta machines.

Preparation of [61Cu]-2-acetylpyridine thiosemicarbazone complex as a possible PET tracer for malignancies.

Due to the interesting anti-proliferative properties of copper-thiosemicarbazone complexes, the production of a (61)Cu-labeled thiosemicarbazone, i.e. 2-acetylpyridine thiosemicarbazone (APTS) was investigated. Copper-61 (T(1/2)=3.33 h) was produced via the (64)Zn(p,alpha)(61)Cu nuclear reaction using a natural zinc target irradiated with 22 MeV protons for 500 microAh. The (61)Cu was separated from the irradiated target material by a two-step method and converted to acetate; this yielded a final activity of 222 GBq (6.0 Ci), with a radiochemical yield of >95%. The (61)Cu-acetate was mixed with 2-acetylpyridine thiosemicarbazone for 30 min at room temperature to yield [(61)Cu]APTS with a radiochemical yield of more than 80%. Colorimetric methods showed that residual chemical impurities in the product were below the accepted limits. Radio thin layer chromatography (RTLC) showed a radiochemical purity of more than 99% after C(18) column chromatography. A specific activity of about 370-740 MBq/mmol (10-20 Ci/mmol) was obtained. The stability of the final product was checked in the absence and presence of human serum at 37 degrees C for up to 3 h. The partition coefficient of the final complex was also determined.

Synthesis of [75Se]5-ethoxycarbonyl-4-methyl-1,2,3-selenadiazole.

Selenium-75 (t1/2 = 120.4d; 100% EC) was prepared in no-carrier-added form by 22MeV proton-bombardment of natural arsenic(III) oxide powder held in a copper-aluminum drawer target (highest yield, 35 microCi/microAh; maximum current, 6 microA), followed by oxidation to [75Se]selenium(IV) oxide. No-carrier-added [75Se]5-ethoxycarbonyl-4-methyl-1,2,3-selenadiazole was prepared in one step from ethylacetoacetate semicarbazone with [75Se]selenium(IV) oxide in glacial acetic acid at 50 degrees C. Column chromatography of the final solution afforded the desired labeled compound in 30% yield and greater than 98% radiochemical purity.