18-Month Performance Assessment of Gemini TF 16 PET/CT System in a High-Volume Department

Development and validation of radiomic signature for predicting overall survival in advanced-stage cervical cancer

Background

The role of artificial intelligence and radiomics in prediction model development in cancer has been increasing every passing day. Cervical cancer is the 4th most common cancer in women worldwide, contributing to 6.5% of all cancer types. The treatment outcome of cervical cancer patients varies and individualized prediction of disease outcome is of paramount importance.

Purpose

The purpose of this study is to develop and validate the digital signature for 5-year overall survival prediction in cervical cancer using robust CT radiomic and clinical features.

Materials and Methods

Pretreatment clinical features and CT radiomic features of 68 patients, who were treated with chemoradiation therapy in our hospital, were used in this study. Radiomic features were extracted using an in-house developed python script and pyradiomic package. Clinical features were selected by the recursive feature elimination technique. Whereas radiomic feature selection was performed using a multi-step process i.e., step-1: only robust radiomic features were selected based on our previous study, step-2: a hierarchical clustering was performed to eliminate feature redundancy, and step-3: recursive feature elimination was performed to select the best features for prediction model development. Four machine algorithms i.e., Logistic regression (LR), Random Forest (RF), Support vector classifier (SVC), and Gradient boosting classifier (GBC), were used to develop 24 models (six models using each algorithm) using clinical, radiomic and combined features. Models were compared based on the prediction score in the internal validation.

Results

The average prediction accuracy was found to be 0.65 (95% CI: 0.60-0.70), 0.72 (95% CI: 0.63-0.81), and 0.77 (95% CI: 0.72-0.82) for clinical, radiomic, and combined models developed using four prediction algorithms respectively. The average prediction accuracy was found to be 0.69 (95% CI: 0.62-0.76), 0.79 (95% CI: 0.72-0.86), 0.71 (95% CI: 0.62-0.80), and 0.72 (95% CI: 0.66-0.78) for LR, RF, SVC and GBC models developed on three datasets respectively.

Conclusion

Our study shows the promising predictive performance of a robust radiomic signature to predict 5-year overall survival in cervical cancer patients.

Importance of Understanding and Analyzing Daily Quality Assurance Test of Positron Emission Tomography/Computed Tomography Equipment in Minimizing the Downtime of Equipment in Remote Places

This article briefly describes the event of a defective detector block in a daily quality assurance scan/blank scan and insists on implementing guidelines to scan or not to scan in such a scenario. The nuclear medicine physicist should have a clear understanding of the blank scan graph, which shall help rectify the right cause of problem and give confidence to the physician in reporting the acquired study. A routine blank scan in positron emission tomography signifies various parameters of the crystal (coincidence count rate, single count rate, dead time, and coincidence time along with energy response) and in some respect is analogous to the daily uniformity flood image for gamma cameras, providing an overall assessment of detector response. We encountered a bad detector block in our routine quality assurance scan/blank scan and analyzed the root cause behind such an error which was finally restored to normalcy by replacing the defected part with a new one and an error-free blank scan was established. The analysis was carried out by performing various possible checks and discussing the issue with service engineer to help identify the defects much before service engineer actually arrived in our department. This allowed us to take the correct decision and enabled us to get the scanner repaired faster. Hence, a good understanding of the daily quality control test and proper analysis of the same may result in swift decision-making and faster repair of equipment leading to minimal disruption in the clinical workflow as well as avoidance of suboptimal scanning leading to the wrong diagnosis.

Impact of High Temperature and Humidity on the Performance of Positron Emission Tomography Scanner

Positron emission tomography/computed tomography (PET/CT) scanner is a state-of-art imaging device. Susceptibility of PET scanner in fluctuation environmental condition is known. Hence, every vendor prescribes the optimal conditions such as temperature and humidity to maintain the equipment in its best condition. In a hot summer day, we faced an unexpected long duration power failure in our department after administration of F-18 fluorodeoxyglucose to one of our patients. As air condition was not working in our department, temperature in the machine room went far beyond the prescribed level. As we had already injected the patient, we decided to perform PET scan of that patient in the existing condition in the machine room. When we reviewed the scan, we identified significant count loss in the image, which raised doubt in our mind. We discussed with our colleague and decided to perform a daily quality assurance (DQA) test to assess the condition of the equipment in high temperature. On DQA scan, we spotted several changes in the uniformity plot as well as energy plot. Following to that, the system was shut down completely till the main supply was restored successfully, and room temperature and humidity was restored to normal in machine room and console room. After several hours of restoration of normal condition in console and machine room, PET/CT equipment was restarted, and the DQA was repeated. On review, we found the restoration of normal DQA graph. We conclude that the sudden increase in temperature and humidity in PET/CT equipment room affects the performance of scanner which reflects as count deficit in the image. This impairment in the image quality may be because of bismuth germanate crystal, photomultiplier tubes, and associated electronics.

Performance characteristic evaluation of a bismuth germanate-based high-sensitivity 5-ring discovery image quality positron emission tomography/computed tomography system as per National Electrical Manufacturers Association NU 2-2012

National Electrical Manufacturers Association (NEMA) provides guidelines to assess the performance of Positron Emission Tomography (PET). A PET/CT scanner, Discovery IQ, GE Medical systems, Milwaukee, USA was installed in our department which has high a sensitivity PET component. We have performed the NEMA NU-2 2012 quality control tests to evaluate this system on site before clinical use. Performance measurements of the PET scanner were made using the NEMA NU2-2012 procedures for spatial resolution, scatter fraction, sensitivity, count rate loss and random coincidence estimation, Noise Equivalent Count Rate (NECR) and image quality. As per NU2 2012, spatial resolution was measured at 1 cm, 10 cm and 20 cm vertically from the centre and at each of these points resolution was measured at tangential, radial and axial directions. Sensitivity was measured at centre and 10 cm off center vertically from the center. The system sensitivity is reported as an average of the two measured values. Scatter fraction and NECR measurements, Image quality test was also performed. The tangential, radial and axial FWHM were 4.99 mm, 4.20 mm and 4.79 mm at 1 cm off centre, 5.49 mm, 4.69 mm and 4.81 mm at 10 cm off centre and 7.99 mm, 5.07 mm and 4.95 mm at 20 cm off centre respectively. The absolute sensitivity of this scanner was found to be 20.1 cps/kBq. The scatter fraction calculated from the decay method was 37.94% and NECR was 125 kcps. The peak NECR was achieved at activity concentration of 8.7 KBq/ml and the count loss below the peak NECR was found to be 0.68%. Image quality test for, contrast recovery, background variability and lung error residual mean met all specifications. Overall PET performance of Discovery IQ whole-body scanner was satisfactory and the scanner met all the performance specifications required by NEMA 2012.

NEMA Performance Evaluation of CareMiBrain dedicated brain PET and Comparison with the whole-body and dedicated brain PET systems

This article presents system performance studies of the CareMiBrain dedicated brain PET according to NEMA NU 2-2012 (for whole-body PETs) and NU 4-2008 (for preclinical PETs). This scanner is based on monolithic LYSO crystals coupled to silicon photomultipliers. The results obtained for both protocols are compared with current commercial whole body PETs and dedicated brain PETs found in the literature. Spatial resolution, sensitivity, NECR and scatter-fraction are characterized with NEMA standards, as well as an image quality study. A customized image quality phantom is proposed as NEMA phantoms do not fulfil the necessities of dedicated brain PETs. The full-width half maximum of the radial/tangential/axial spatial resolution of CareMiBrain reconstructed with FBP at 10 and 100 mm from the system center were, respectively, 1.87/1.68/1.39 mm and 1.86/1.91/1.40 mm (NU 2-2012) and 1.58/1.45/1.40 mm and 1.64/1.66/1.44 mm (NU 4-2008). Peak NECR was 49 kcps@287 MBq with a scatter fraction of 48% using NU 2-2012 phantom. The sensitivity was 13.82 cps/kBq at the center of the FOV (NU 2-2012) and 10% (NU 4-2008). Contrast recovery coefficients for customizing image quality phantom were 0.73/0.78/1.14/1.01 for the 4.5/6/9/12 mm diameter rods. The performance characteristics of CareMiBrain are at the top of the current technologies for PET systems. Dedicated brain PET systems significantly improve spatial resolution and sensitivity, but present worse results in count rate measurements and scatter-fraction tests. As for the comparison of preclinical and clinical standards, the results obtained for solid and liquid sources were similar.