Search

Background: To address the numerous unmeet clinical needs, in recent years several Machine Learning models applied to medical images and clinical data have been introduced and developed. Even when they achieve encouraging results, they lack evolutionary progression, thus perpetuating their status as autonomous entities. We postulated that different algorithms which have been proposed in the literature to address the same diagnostic task, can be aggregated to enhance classification performance. We suggested a proof of concept to define an ensemble approach useful for integrating different algorithms proposed to solve the same clinical task. Methods: The proposed approach was developed starting from a public database consisting of radiomic features extracted from CT images relating to 535 patients suffering from lung cancer. Seven algorithms were trained independently by participants in the AI4MP working group on Artificial Intelligence of the Italian Association of Physics in Medicine to discriminate metastatic from non-metastatic patients. The classification scores generated by these algorithms are used to train SVM classifier. The Explainable Artificial Intelligence approach is applied to the final model. The ensemble model was validated following an 80–20 hold-out and leave-one-out scheme on the training set. Results: Compared to individual algorithms, a more accurate result was achieved. On the independent test the ensemble model achieved an accuracy of 0.78, a F1-score of 0.57 and a log-loss of 0.49. Shapley values representing the contribution of each algorithm to the final classification result of the ensemble model were calculated. This information represents an added value for the end user useful for evaluating the appropriateness of the classification result on a particular case. It also allows us to evaluate on a global level which methodological approaches of the individual algorithms are likely to have the most impact. Conclusion: Our proposal represents an innovative approach useful for integrating different algorithms that populate the literature and which lays the foundations for future evaluations in broader application scenarios. [ABSTRACT FROM AUTHOR]

The increasing use of 177Lu-labelled agents for targeted radionuclide cancer therapy highlights the radiation protection challenges in the management of radioactive waste due to 177mLu impurities. To ensure safe disposal, compliance with clearance criteria must be verified using calibrated systems, such as Hyper Pure Germanium (HPGe) spectrometers. This work aims to validate a customized GEANT4 model of our HPGe system in Marinelli beaker geometry to propose an operational approach properly quantifying 177Lu and 177mLu in waste samples. The system's efficiency curve was calculated by modelling gamma sources in the energy range of interest and validated by spectra measurements of 177Lu and 99mTc sources. Correction factors accounting for true coincidence summing (TCS) effect were simulated for 177Lu, 177mLu and 99mTc and they were applied to the spectrum measurement of a waste sample model with known activities of 177Lu and 177mLu. Thus, an operational approach for activities quantification was tested comparing the results with the nominal values. No significant differences were observed between simulated and measured efficiency values. TCS correction factors are significant only for 177mLu (1.6 at 112.95 keV and 204.11 keV). Eventually, the proposed framework to quantify 177Lu in a waste sample allowed to estimate the 177Lu and 177mLu component activities within a maximum 16% uncertainty. Results show that the HPGe model could be a powerful resource for a wide range of applications in daily clinical routine and it could be used to build a simple quality assurance program to monitor the detector response constancy in time. [ABSTRACT FROM AUTHOR]

Featured Application: The results of this work may promote the clinical application of the DirectDensity® CT reconstruction algorithm as a basis for radiation therapy dose calculations in different clinical situations (e.g., metal implants artifacts), allowing for a more personalized workflow while ensuring simplicity and solidity. The DirectDensity® CT reconstruction algorithm provides a reconstruction approach independent of the tube voltage, directly reconstructing the CT projection data into CT numbers related to the electron densities of the materials. This work examines the efficacy of DirectDensity® in the treatment planning process with both tissues and metallic materials. CT scans of a Cheese phantom were acquired at 80, 100, 120 and 140 kVp and reconstructed with different algorithms. Calibration curves were built for each kVp and reconstruction technique. To evaluate the flexibility of the DirectDensity® in dose calculations, a prostate cancer treatment plan was simulated on phantom images with and without metal inserts. Moreover, the robustness of the algorithm was tested by simulating a possible error in the selection of the calibration curve. As expected, the calibration curves related to DirectDensity® showed a tube voltage dependence only for densities above 1.82 g/cm3. The maximum percentage differences in dose distributions comparations never exceeded the 3% of tolerance and the 3D gamma analysis always returned indices greater than 90%. The results suggest that the DD reconstruction algorithm can be employed in most clinical cases and allows for a personalized radiotherapy cancer treatment workflow, maintaining its robustness and simplicity. [ABSTRACT FROM AUTHOR]

In a clinical contest, it is common to use dedicated phantoms to perform quality assurance test to check the performance of a SPECT system. Some of these phantoms are also used to calibrate the system for dosimetric evaluation of patients undergoing radiometabolic cancer therapy. In this work, a 3D-OSEM reconstructed 177Lu SPECT dataset of a homogeneous cylindrical phantom is described. This dataset was acquired to investigate the variation of the SPECT calibration factor, counts convergence, noise and uniformity by varying the number of subsets and iterations. In particular, the dataset is composed of images reconstructed using five different numbers of subsets and sixteen different numbers of iterations, for a total of 80 different configurations. The dataset is suitable for comparison with other reconstruction algorithms (e.g. FBP, MLEM, etc.) and radionuclides (e.g. technetium, yttrium). In regards to the uniformity issue, the same dataset allows the user to perform radiomic investigations on the influence of the border effect on the reconstructed images. Measurement(s) Calibration Factor • coefficient of variation • Texture Descriptor Technology Type(s) Single Photon Emission Computed Tomography • Image Feature [ABSTRACT FROM AUTHOR]