Automated detection and classification of tumor histotypes on dynamic PET imaging data through machine-learning driven voxel classification.

2-deoxy-2-fluorine-(18F)fluoro-d-glucose Positron Emission Tomography/Computed Tomography (18F-FDG-PET/CT) is widely used in oncology mainly for diagnosis and staging of various cancer types, including lung cancer, which is the most common cancer worldwide. Since histopathologic subtypes of lung cancer show different degree of 18F-FDG uptake, to date there are some diagnostic limits and uncertainties, hindering an 18F-FDG-PET-driven classification of histologic subtypes of lung cancers. On the other hand, since activated macrophages, neutrophils, fibroblasts and granulation tissues also show an increased 18F-FDG activity, infectious and/or inflammatory processes and post-surgical and post-radiation changes may cause false-positive results, especially for lymph-nodes assessment. Here we propose a model-free, machine-learning based algorithm for the automated classification of adenocarcinoma, the most common type of lung cancer, and other types of tumors. Input for the algorithm are dynamic acquisitions of PET data (dPET), providing for a spatially and temporally resolved characterization of the uptake kinetic. The algorithm consists in a trained Random Forest classifier which, relying contextually on several spatial and temporal features of 18F-FDG uptake, generates as an outcome probability maps allowing to distinguish adenocarcinoma from other lung histotype and to identify metastatic lymph-nodes, ultimately increasing the specificity of the technique. Its performance, evaluated on a dPET dataset of 19 patients affected by primary lung cancer, provides a probability 0.943 ± 0.090 for the detection of adenocarcinoma. The use of this algorithm will guarantee an automatic and more accurate localization and discrimination of tumors, also providing a powerful tool for detecting at which extent tumor has spread beyond a primary tumor into lymphatic system.

When your MR linac is down: Can an automated pipeline bail you out of trouble?

PURPOSE: The unique treatment delivery technique provided by magnetic resonance guided radiotherapy (MRgRT) can represent a significant drawback when system fail occurs. This retrospective study proposes and evaluates a pipeline to completely automate the workflow necessary to shift a MRgRT treatment to a traditional radiotherapy linac. MATERIAL AND METHODS: Patients undergoing treatment during the last MRgRT system failure were retrospectively included in this study. The core of the proposed pipeline was based on a tool able to mimic the original MR linac dose distribution. The so obtained dose distribution (AUTO) has been compared with the distribution obtained in the conventional radiotherapy linac (MAN). Plan comparison has been performed in terms of time required to obtain the final dose distribution, DVH parameters, dosimetric indices and visual analogue scales scoring by radiation oncologists. RESULTS: AUTO plans generation has been obtained within 10 min for all the considered cases. All AUTO plans were found to be within clinical tolerance, showing a mean target coverage variation of 1.7% with a maximum value of 4.3% and a minimum of 0.6% when compared with MAN plans. The highest OARs mean variation has been found for rectum V60 (6.7%). Dosimetric indices showed no relevant differences, with smaller gradient measure in favour of AUTO plans. Visual analogue scales scoring has confirmed comparable plan quality for AUTO plans. CONCLUSION: The proposed workflow allows a fast and accurate generation of automatic treatment plans. AUTO plans can be considered equivalent to MAN ones, with limited clinical impact in the worst-case scenario.

VMAT-like plans for magnetic resonance guided radiotherapy: Addressing unmet needs.

PURPOSE: VMAT delivery technique is currently not applicable to Magnetic Resonance-guided radiotherapy (MRgRT) hybrid systems. Aim of this study is to evaluate an innovative VMAT-like (VML) delivery technique. MATERIAL AND METHODS: First, planning and dosimetric evaluation of the MRgRT VML treatment have been performed on 10 different disease sites and the results have been compared with the corresponding IMRT plans. Then, in the second phase, 10 of the most dosimetrically challenging locally advanced pancreas treatment plans have been retrospectively re-planned using the VML approach to explore the potentiality of this new delivery technique. Finally, VML robustness was evaluated and compared with the IMRT plans, considering a lateral positioning error of ± 5 mm. RESULTS: In phase one, all VML plans were within constraint for all OARs. When PTV coverage is considered, in the 50% of the cases VML PTV coverage is equal or higher than in IMRT plan. In the remaining 50%, the highest target under coverage difference in comparison with IMRT plan is -1.71%. The mean and maximum treatment time differences (VML-IMRT) is 0.2 min and 3.1 min respectively. In phase two, the treatment time variation (VML-IMRT), shows a mean, maximum and minimum variations of 1.3, 4.6 and -0.6 min respectively. All VML plans have a better target coverage if compared with IMRT plans, keeping in any case the OARs constraints within tolerance. VML doesn't increase plan robustness. CONCLUSION: VMAT-like treatment approach appeared to be an efficient planning solution and it was decided to clinically implement it in daily practice, especially in the frame of hypo fractionated treatments.

Dosimetric accuracy of dual isocenter irradiation in low magnetic field resonance guided radiotherapy system for extended abdominal tumours.

PURPOSE: Due to limited field size of Magnetic Resonance Linear Accelerators (MR-Linac), some treatments could require a dual-isocenter planning approach to achieve a complete target coverage and thus exploit the benefits of the online adaptation. This study evaluates the dosimetric accuracy of the dual-isocenter intensity modulated radiation therapy (IMRT) delivery technique for MR-Linac. MATERIAL AND METHODS: Dual-isocenter multi leaf collimator (MLC) and couch accuracy tests have been performed to evaluate the delivery accuracy of the system. A mono-isocenter plan delivered in clinical practice has then been retrospectively re-planned with dual-isocenter technique. The dual-isocenter plan has been re-calculated and delivered on a 3-dimensional (3D) ArcCHECK phantom and 2-dimensional (2D) films to assess its dosimetric accuracy in terms of gamma analysis. Clinical and planning target volume (CTV and PTV respectively) coverage robustness was then investigated after the introduction of ± 2 mm and ± 5 mm positioning errors by shifting the couch. RESULTS: MLC and couch accuracy tests confirmed the system accuracy in delivering a dual-isocenter irradiation. 2D/3D gamma analysis results occurred always to be above 95% if considered a gamma criteria 1%/2 mm and 1%/1 mm respectively for the 2D and 3D analysis. The mean variations for CTV D98% and PTV V95% were 0.2% and 1.1% respectively when positioning error was introduced separately in each direction, while the maximum observed variations were 0.9% (CTV) and 3.7% (PTV). CONCLUSION: The dosimetric accuracy of dual-isocenter irradiation has been verified for MR-Linac, achieving accurate and robust treatment strategy and improving dose conformality also in presence of targets whose extension exceeds the nominal maximum field size.

Correction to: Comparison of three-parameter kinetic model analysis to standard Patlak's analysis in 18F-FDG PET imaging of lung cancer patients.

Following publication of the original article [1], the authors flagged that the author affiliations detailed in the article are incorrect for the authors M. L. Calcagni and A. Giordano.

Comparison of three-parameter kinetic model analysis to standard Patlak's analysis in 18F-FDG PET imaging of lung cancer patients.

BACKGROUND: Patlak's graphical analysis can provide tracer net influx constant (Ki) with limitation of assuming irreversible tracer trapping, that is, release rate constant (kb) set to zero. We compared linear Patlak's analysis to non-linear three-compartment three-parameter kinetic model analysis (3P-KMA) providing Ki, kb, and fraction of free 18F-FDG in blood and interstitial volume (Vb). METHODS: Dynamic PET data of 21 lung cancer patients were retrospectively analyzed, yielding for each patient an 18F-FDG input function (IF) and a tissue time-activity curve. The former was fitted with a three-exponentially decreasing function, and the latter was fitted with an analytical formula involving the fitted IF data (11 data points, ranging 7.5-57.5 min post-injection). Bland-Altman analysis was used for Ki comparison between Patlak's analysis and 3P-KMA. Additionally, a three-compartment five-parameter KMA (5P-KMA) was implemented for comparison with Patlak's analysis and 3P-KMA. RESULTS: We found that 3P-KMA Ki was significantly greater than Patlak's Ki over the whole patient series, + 6.0% on average, with limits of agreement of ± 17.1% (95% confidence). Excluding 8 out of 21 patients with kb > 0 deleted this difference. A strong correlation was found between Ki ratio (=3P-KMA/Patlak) and kb (R = 0.801; P < 0.001). No significant difference in Ki was found between 3P-KMA versus 5P-KMA, and between 5P-KMA versus Patlak's analysis, with limits of agreement of ± 23.0 and ± 31.7% (95% confidence), respectively. CONCLUSIONS: Comparison between 3P-KMA and Patlak's analysis significantly showed that the latter underestimates Ki because it arbitrarily set kb to zero: the greater the kb value, the greater the Ki underestimation. This underestimation was not revealed when comparing 5P-KMA and Patlak's analysis. We suggest that further studies are warranted to investigate the 3P-KMA efficiency in various tissues showing greater 18F-FDG trapping reversibility than lung cancer lesions.