Search

This review presents and discusses the ways in which artificial intelligence (AI) tools currently intervene, or could potentially intervene in the future, to enhance the diverse tasks involved in the radiotherapy workflow. The radiotherapy framework is presented on 2 different levels for the personalization of the treatment, distinct in tasks and methodologies. The first level is the clinically well-established anatomy-based workflow, known as adaptive radiation therapy. The second level is referred to as biology-driven workflow, explored in the research literature and recently appearing in some preliminary clinical trials for personalized radiation treatments. A 2-fold role for AI is defined according to these 2 different levels. In the anatomy-based workflow, the role of AI is to streamline and improve the tasks in terms of time and variability reductions compared to conventional methodologies. The biology-driven workflow instead fully relies on AI, which introduces decision-making tools opening uncharted frontiers that were in the past deemed challenging to explore. These methodologies are referred to as radiomics and dosiomics, handling imaging and dosimetric information, or multiomics, when complemented by clinical and biological parameters (ie, biomarkers). The review explicitly highlights the methodologies that are currently incorporated into clinical practice or still in research, with the aim of presenting the AI’s growing role in personalized radiotherapy.

A dedicated tomographic image reconstruction algorithm for integration-mode detector configuration is proposed and investigated. The algorithm makes use of the stopping power and the model of the scattering power for the entire histogram of Water Equivalent Thickness (WET) components. Therefore, compared to conventional tomographic image reconstruction of the WET component with maximum occurrence along straight trajectories, this algorithm is expected to provide better image quality. An anthropomorphic phantom, adopted as ground truth, is used to simulate the proton trajectories. The system matrix of the proposed algorithm is based on the statistical estimation of the integral scattering power for each WET as a 2D Gaussian distribution according to a multiple Coulomb scattering model. The 2D Gaussian distributions are normalized to the unit, thus forming a 3D distribution, namely the "cone", for each WET. The cones are interpolated to each integration line, thus matching the image. The updating formula of the simultaneous algebraic reconstruction technique is modified to account for the entire histogram of the WET components. For computational reasons, the tomographic image reconstruction is implemented relying on ordered subsets of projection angles. In general, better convergence is obtained for the dedicated algorithm, thus showing extremely reduced noise break-up. The results indicate the potential of the proposed algorithm to provide better image quality than conventional tomographic image reconstruction. Future studies will include the application of the proposed algorithm to Monte Carlo simulations of clinical ion imaging and a deeper image quality assessment.

Purpose: An innovative strategy to improve the sensitivity of positron emission tomography (PET)- based treatment verification in ion beam radiotherapy is proposed. Methods: Low counting statistics PET images acquired during or shortly after the treatment (Measured PET) and a Monte Carlo estimate of the same PET images derived from the treatment plan (Expected PET) are considered as two frames of a 4D dataset. A 4D maximum likelihood reconstruction strategy was adapted to iteratively estimate the annihilation events distribution in a reference frame and the deformation motion fields that map it in the Expected PET and Measured PET frames. The outputs generated by the proposed strategy are as follows: (1) an estimate of the Measured PET with an image quality comparable to the Expected PET and (2) an estimate of the motion field mapping Expected PET to Measured PET. The details of the algorithm are presented and the strategy is preliminarily tested on analytically simulated datasets. Results: The algorithm demonstrates (1) robustness against noise, even in the worst conditions where 1.5-104 true coincidences and a random fraction of 73% are simulated; (2) a proper sensitivity to different kind and grade of mismatches ranging between 1 and 10 mm; (3) robustness against bias due to incorrect washout modeling in the Monte Carlo simulation up to 1/3 of the original signal amplitude; and (4) an ability to describe the mismatch even in presence of complex annihilation distributions such as those induced by two perpendicular superimposed ion fields. Conclusions: The promising results obtained in this work suggest the applicability of the method as a quantification tool for PET-based treatment verification in ion beam radiotherapy. An extensive assessment of the proposed strategy on real treatment verification data is planned.

Background and purpose In clinical applications of Positron Emission Tomography (PET)-based treatment verification in ion beam therapy (PT-PET), detection and interpretation of inconsistencies between Measured PET and Expected PET are mostly limited by Measured PET noise, due to low count statistics, and by Expected PET bias, especially due to inaccurate washout modelling in off-line implementations. In this work, a recently proposed 4D Maximum Likelihood (ML) reconstruction algorithm which considers Measured PET and Expected PET as two different motion phases of a 4D dataset is assessed on clinical 4D PET-CT datasets acquired after carbon ion therapy. Material and methods The 4D ML reconstruction algorithm estimates: (1) Measured PET of enhanced image quality with respect to the conventional Measured PET, thanks to the exploitation of Expected PET; (2) the deformation field mapping the Expected PET onto the Measured PET as a measure of the occurred displacements. Results Results demonstrate the desired sensitivity to inconsistencies due to breathing motion and/or setup modification, robustness to noise in different count statistics scenarios, but a limited sensitivity to Expected PET washout inaccuracy. Conclusions The 4D ML reconstruction algorithm supports clinical 4D PT-PET in ion beam therapy. The limited sensitivity to washout inaccuracy can be detected and potentially overcome.

A review of recent works by our group in the segmentation and quantification of oncological lesions in 18-fluoro-deoxy-glucose (FDG) positron emission tomography (PET) images is given, stressing the underlying model assumption. In a first approach, a targeted reconstruction strategy was set in the framework of linear space variant (LSV) reconstruction from projections. Resolution recovery by ordered subset expectation maximization (OSEM) from raw emission data was based on the Poissonian description of errors and on a parametric model of PET scanner space variant blurring. The targeted strategy estimates and refines lesion basis functions while freezing the rest of background in a single one, thus providing an estimate of lesion borders and uptake. In a second approach lesions are segmented on standard clinical images. Reconstructed images lose the original Poissonian features and are well fitted by Gaussian mixture models (GMM). However, this popular clustering method required a specific adaptation to lesion segmentation: constraint of the warm background based on GMM modeling of healthy tissue; proximity priors in the voxel-wise classification to extract connected object and increase noise robustness. In both approaches, the spill-out of high uptake organs in the lesion area was removed by means of appropriate models relying on the CT anatomy. Results obtained on digital and physical phantoms and on clinical datasets will be recalled.

The aim of this work is to propose an adaptation of a 4D Maximum Likelihood (ML) reconstruction strategy as a tool to improve the sensitivity of PET-based treatment verification in ion beam radiotherapy. PET images acquired during/shortly after the treatment (Measured PET) and an estimate of the same PET images derived from the treatment plan (Estimated PET) are considered as two frames of a 4D dataset. The algorithm iteratively estimates the annihilation events distribution in a reference frame and the deformation motion fields that map it in the Expected and Measured PET frames. Expected PET images can be then mapped into the Measured PET frame to verify the treatment. The details of the algorithm are presented and the strategy is preliminarily tested on an analytically simulated dataset. Convergence at different count statistics and ability to detect mismatches are assessed.

In ion beam therapy, Positron Emission Tomography (PET) imaging can be applied to provide a consistency check of the delivered treatment with respect to the treatment plan. Treatment verification relies on the comparison between a PET distribution measured during or after treatment delivery (measured PET) and a PET simulation calculated on the basis of the treatment plan (expected PET). The method is challenged by the poor image quality of the measured PET, which may result in a low sensitivity to detectable mismatches between planned and applied treatment. In this work we propose the application of a motion-aware 4D Maximum Likelihood (ML) reconstruction strategy for PET-based treatment verification in ion beam therapy. This approach is specifically tested on simulated clinical-like scenarios, as well as on a real clinical dataset. The measured PET and the expected PET are interpreted as two different motion states of a 4D PET dataset. The idea is to estimate the deformation field mapping the expected PET onto the measured PET as a measure of mismatches. An enhanced measured PET is therefore obtained by warping the expected PET according to the estimated motion field. Clinical-like scenarios were reproduced by means of Monte Carlo simulations corresponding to a hypo-fractionated carbon ion treatment of liver tumour. The measured PET was attributed to different simulations introducing positioning mismatches by means of rigid translations, to be compared to the reference expected PET simulation without mismatch. Real clinical dataset include PET data acquired shortly after treatment at a dedicated PET-CT scanner installed at HIT (Heidelberg Ion beam Therapy Center, Germany), in comparison to the corresponding expected PET coming from Monte Carlo simulations. The accuracy of mismatch estimation and the robustness to noise are shown.

The purpose of this paper is to describe the experiments and methods that led to the geometrical interpretation of new-generation commercial PET-CT scanners, finalized to off-line PET-based treatment verification in ion beam therapy. Typically, the geometrical correspondence between the image domain (i.e., the dicom PET) and the sinogram domain (i.e., the PET raw data) is not explicitly described by scanner vendors. Hence, the proposed characterization can be applied to commercial PET-CT scanners used in biomedical research, for the development of technologies and methods requiring the use of PET raw data, without having access to confidential information from the vendors.

Background: Quantification of lesion activity by FDG uptake in oncological PET is severely limited by partial volume effects. A maximum likelihood (ML) expectation maximization (EM) algorithm considering regional basis functions (AWOSEM-region) had been previously developed. Regional basis functions are iteratively segmented and quantified, thus identifying the volume and the activity of the lesion. Objectives: Improvement of AWOSEM-region when analyzing proximal interfering hot objects is addressed by proper segmentation initialization steps and models of spill-out and partial volume effects. Conditions relevant to lung PET-CT studies are considered: 1) lesion close to hot organ (e.g. chest wall, heart and mediastinum), 2) two close lesions. Methods: CT image was considered for presegmenting hot anatomical structures, never for lesion identification, solely defined by iterations on PET data. Further resolution recovery beyond the smooth standard clinical image was necessary to start lesion segmentation. A watershed algorithm was used to separate two close lesions. A subtraction of the spill-out from a nearby hot organ was introduced to enhance a lesion for the initial segmentation and start the further quantification steps. Biograph scanner blurring was modeled from phantom data in order to implement the procedure for 3D clinical lung studies. Results: In simulations, the procedure was able to separate structures as close as one pixel-size (2.25 mm). Robustness against the input segmentation errors defining the addressed objects was tested showing that convergence was not sensitive to initial volume overestimates up to 130%. Poor robustness was found against underestimates. A clinical study of a small lung lesion close to chest wall displayed a good recovery of both lesion activity and volume. Conclusions: With proper initialization and models of spill-out from hot organs, AWOSEMregion can be successfully applied to lung oncological studies.