Comparing the effects of irradiation with protons or photons on neonatal mouse brain: Apoptosis, oncogenesis and hippocampal alterations.

BACKGROUND AND PURPOSE: Medulloblastoma (MB) is a common primary brain cancer in children. Proton therapy in pediatric MB is intensively studied and widely adopted. Compared to photon, proton radiations offer potential for reduced toxicity due to the characteristic Bragg Peak at the end of their path in tissue. The aim of this study was to compare the effects of irradiation with the same dose of protons or photons in Patched1 heterozygous knockout mice, a murine model predisposed to cancer and non-cancer radiogenic pathologies, including MB and lens opacity. MATERIALS AND METHODS: TOP-IMPLART is a pulsed linear proton accelerator for proton therapy applications. We compared the long-term health effects of 3 Gy of protons or photons in neonatal mice exposed at postnatal day 2, during a peculiarly susceptible developmental phase of the cerebellum, lens, and hippocampus, to genotoxic stress. RESULTS: Experimental testing of the 5 mm Spread-Out Bragg Peak (SOBP) proton beam, through evaluation of apoptotic response, confirmed that both cerebellum and hippocampus were within the SOBP irradiation field. While no differences in MB induction were observed after irradiation with protons or photons, lens opacity examination confirmed sparing of the lens after proton exposure. Marked differences in expression of neurogenesis-related genes and in neuroinflammation, but not in hippocampal neurogenesis, were observed after irradiation of wild-type mice with both radiation types. CONCLUSION: In-vivo experiments with radiosensitive mouse models improve our mechanistic understanding of the dependence of brain damage on radiation quality, thus having important implications in translational research.

In Vivo Radiobiological Investigations with the TOP-IMPLART Proton Beam on a Medulloblastoma Mouse Model.

Protons are now increasingly used to treat pediatric medulloblastoma (MB) patients. We designed and characterized a setup to deliver proton beams for in vivo radiobiology experiments at a TOP-IMPLART facility, a prototype of a proton-therapy linear accelerator developed at the ENEA Frascati Research Center, with the goal of assessing the feasibility of TOP-IMPLART for small animal proton therapy research. Mice bearing Sonic-Hedgehog (Shh)-dependent MB in the flank were irradiated with protons to test whether irradiation could be restricted to a specific depth in the tumor tissue and to compare apoptosis induced by the same dose of protons or photons. In addition, the brains of neonatal mice at postnatal day 5 (P5), representing a very small target, were irradiated with 6 Gy of protons with two different collimated Spread-Out Bragg Peaks (SOBPs). Apoptosis was visualized by immunohistochemistry for the apoptotic marker caspase-3-activated, and quantified by Western blot. Our findings proved that protons could be delivered to the upper part while sparing the deepest part of MB. In addition, a comparison of the effectiveness of protons and photons revealed a very similar increase in the expression of cleaved caspase-3. Finally, by using a very small target, the brain of P5-neonatal mice, we demonstrated that the proton irradiation field reached the desired depth in brain tissue. Using the TOP-IMPLART accelerator we established setup and procedures for proton irradiation, suitable for translational preclinical studies. This is the first example of in vivo experiments performed with a "full-linac" proton-therapy accelerator.

UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images.

Purpose: The aim of this work is the development and characterization of a model observer (MO) based on convolutional neural networks (CNNs), trained to mimic human observers in image evaluation in terms of detection and localization of low-contrast objects in CT scans acquired on a reference phantom. The final goal is automatic image quality evaluation and CT protocol optimization to fulfill the ALARA principle. Approach: Preliminary work was carried out to collect localization confidence ratings of human observers for signal presence/absence from a dataset of 30,000 CT images acquired on a PolyMethyl MethAcrylate phantom containing inserts filled with iodinated contrast media at different concentrations. The collected data were used to generate the labels for the training of the artificial neural networks. We developed and compared two CNN architectures based respectively on Unet and MobileNetV2, specifically adapted to achieve the double tasks of classification and localization. The CNN evaluation was performed by computing the area under localization-ROC curve (LAUC) and accuracy metrics on the test dataset. Results: The mean of absolute percentage error between the LAUC of the human observer and MO was found to be below 5% for the most significative test data subsets. An elevated inter-rater agreement was achieved in terms of S-statistics and other common statistical indices. Conclusions: Very good agreement was measured between the human observer and MO, as well as between the performance of the two algorithms. Therefore, this work is highly supportive of the feasibility of employing CNN-MO combined with a specifically designed phantom for CT protocol optimization programs.

Argument mining as rapid screening tool of COVID-19 literature quality: Preliminary evidence.

Background: The COVID-19 pandemic prompted the scientific community to share timely evidence, also in the form of pre-printed papers, not peer reviewed yet. Purpose: To develop an artificial intelligence system for the analysis of the scientific literature by leveraging on recent developments in the field of Argument Mining. Methodology: Scientific quality criteria were borrowed from two selected Cochrane systematic reviews. Four independent reviewers gave a blind evaluation on a 1-5 scale to 40 papers for each review. These scores were matched with the automatic analysis performed by an AM system named MARGOT, which detected claims and supporting evidence for the cited papers. Outcomes were evaluated with inter-rater indices (Cohen's Kappa, Krippendorff's Alpha, s* statistics). Results: MARGOT performs differently on the two selected Cochrane reviews: the inter-rater indices show a fair-to-moderate agreement of the most relevant MARGOT metrics both with Cochrane and the skilled interval scores, with larger values for one of the two reviews. Discussion and conclusions: The noted discrepancy could rely on a limitation of the MARGOT system that can be improved; yet, the level of agreement between human reviewers also suggests a different complexity between the two reviews in debating controversial arguments. These preliminary results encourage to expand and deepen the investigation to other topics and a larger number of highly specialized reviewers, to reduce uncertainty in the evaluation process, thus supporting the retraining of AM systems.

Addressing signal alterations induced in CT images by deep learning processing: A preliminary phantom study.

PURPOSE: We investigate, by an extensive quality evaluation approach, performances and potential side effects introduced in Computed Tomography (CT) images by Deep Learning (DL) processing. METHOD: We selected two relevant processing steps, denoise and segmentation, implemented by two Convolutional Neural Networks (CNNs) models based on autoencoder architecture (encoder-decoder and UNet) and trained for the two tasks. In order to limit the number of uncontrolled variables, we designed a phantom containing cylindrical inserts of different sizes, filled with iodinated contrast media. A large CT image dataset was collected at different acquisition settings and two reconstruction algorithms. We characterized the CNNs behavior using metrics from the signal detection theory, radiological and conventional image quality parameters, and finally unconventional radiomic features analysis. RESULTS: The UNet, due to the deeper architecture complexity, outperformed the shallower encoder-decoder in terms of conventional quality parameters and preserved spatial resolution. We also studied how the CNNs modify the noise texture by using radiomic analysis, identifying sensitive and insensitive features to the denoise processing. CONCLUSIONS: The proposed evaluation approach proved effective to accurately analyze and quantify the differences in CNNs behavior, in particular with regard to the alterations introduced in the processed images. Our results suggest that even a deeper and more complex network, which achieves good performances, is not necessarily a better network because it can modify texture features in an unwanted way.