Helium ion beam therapy for the treatment of cancer was one of several developed and studied particle modalities in the 1950's, leading to clinical trials beginning in 1975 at the Lawrence Berkeley National Laboratory. The trial shutdown was followed by decades of research and clinical silence on the topic while proton and carbon ion therapy made debuts at research facilities and academic hospitals worldwide. The lack of progression in understanding of principle facets of helium ion beam therapy in terms of physics, biological and clinical findings persist today, mainly attributable to its highly limited availability. Despite this major setback, there has been an increasing focus on evaluating and establishing clinical and research programs using helium ion beams, with both therapy and imaging initiatives to supplement the clinical palette of radiotherapy in the treatment of aggressive disease and sensitive clinical cases. Moreover, due its intermediate physical and radio-biological properties between proton and carbon ion beams, helium ions may provide a streamlined economic steppingstone towards an era of widespread use of multi-particle approaches to light and heavy ion therapy. This roadmap presents an overview of the current state-of-the-art and future directions of helium ion therapy: understanding physics and improving modeling, understanding biology and improving modeling, imaging techniques using helium ions and refining and establishing clinical approaches and aims from learned experience with protons. These topics are organized and presented into three main sections, outlining current and future tasks in establishing clinical and research programs using helium ion beams — A. Physics B. Biological and C. Clinical Perspectives.

Objective. Magnetic particle imaging (MPI) is a new medical, non-destructive, imaging method for visualizing the spatial distribution of superparamagnetic iron oxide nanoparticles. In MPI, spatial resolution is an important indicator of efficiency; traditional techniques for improving the spatial resolution may result in higher costs, lower sensitivity, or reduced contrast. Approach. Therefore, we propose a deep-learning approach to improve the spatial resolution of MPI by fusing a dual-sampling convolutional neural network (FDS-MPI). An end-to-end model is established to generate high-spatial-resolution images from low-spatial-resolution images, avoiding the aforementioned shortcomings. Main results. We evaluate the performance of the proposed FDS-MPI model through simulation and phantom experiments. The results demonstrate that the FDS-MPI model can improve the spatial resolution by a factor of two. Significance. This significant improvement in MPI could facilitate the preclinical application of medical imaging modalities in the future.

The role of plasticity and epigenetics in shaping cancer evolution and response to therapy has taken center stage with recent technological advances including single cell sequencing. This roadmap article is focused on state-of-the-art mathematical and experimental approaches to interrogate plasticity in cancer, and addresses the following themes and questions: is there a formal overarching framework that encompasses both non-genetic plasticity and mutation-driven somatic evolution? How do we measure and model the role of the microenvironment in influencing/controlling non-genetic plasticity? How can we experimentally study non-genetic plasticity? Which mathematical techniques are required or best suited? What are the clinical and practical applications and implications of these concepts?

Epidermal growth factor (EGF), a potent cytokine, is known to promote tumor invasion both in vivo and in vitro. Previously, we observed that single breast tumor cells (MDA-MB-231 cell line) embedded within a 3D collagen matrix displayed enhanced motility but no discernible chemotaxis in the presence of linear EGF gradients using a microfluidic platform. Inspired by a recent theoretical development that clustered mammalian cells respond differently to chemical gradients than single cells, we studied tumor spheroid invasion within a 3D extracellular matrix (ECM) in the presence of EGF gradients. We found that EGF gradients promoted tumor cell detachment from the spheroid core, and the position of the tumor spheroid core showed a mild chemotactic response towards the EGF gradients. For those tumor cells detached from the spheroids, they showed an enhanced motility response in contrast to previous experimental results using single cells embedded within an ECM. No discernible chemotactic response towards the EGF gradients was found for the cells outside the spheroid core. This work demonstrates that a cluster of tumor cells responds differently than single tumor cells towards EGF gradients and highlights the importance of a tumor spheroid platform for tumor invasion studies.

Objective. Autonomic nervous system function and thereby bodily stress and recovery reactions may be assessed by wearable devices measuring heart rate (HR) and its variability (HRV). So far, the validity of HRV-based stress assessments has been mainly studied in healthy populations. In this study, we determined how psychosocial stress affects physiological and psychological stress responses in both young (18–30 years) and middle-aged (45–64 years) healthy individuals as well as in patients with arterial hypertension and/or either prior evidence of prediabetes or type 2 diabetes. We also studied how an HRV-based stress index (Relax-Stress Intensity, RSI) relates to perceived stress (PS) and cortisol (CRT) responses during psychosocial stress. Approach. A total of 197 participants were divided into three groups: (1) healthy young (HY, N = 63), (2) healthy middle-aged (HM, N = 61) and (3) patients with cardiometabolic risk factors (Pts, N = 73, 32–65 years). The participants underwent a group version of Trier Social Stress Test (TSST-G). HR, HRV (quantified as root mean square of successive differences of Rmdash;R intervals, RMSSD), RSI, PS, and salivary CRT were measured regularly during TSST-G and a subsequent recovery period. Main results. All groups showed significant stress reactions during TSST-G as indicated by significant responses of HR, RMSSD, RSI, PS, and salivary CRT. Between-group differences were also observed in all measures. Correlation and regression analyses implied RSI being the strongest predictor of CRT response, while HR was more closely associated with PS. Significance. The HRV-based stress index mirrors responses of CRT, which is an independent marker for physiological stress, around TSST-G. Thus, the HRV-based stress index may be used to quantify physiological responses to psychosocial stress across various health and age groups.

Modern deep learning holds a great potential to transform clinical studies of human sleep. Teaching a machine to carry out routine tasks would be a tremendous reduction in workload for clinicians. Sleep staging, a fundamental step in sleep practice, is a suitable task for this and will be the focus in this article. Recently, automatic sleep-staging systems have been trained to mimic manual scoring, leading to similar performance to human sleep experts, at least on scoring of healthy subjects. Despite tremendous progress, we have not seen automatic sleep scoring adopted widely in clinical environments. This review aims to provide the shared view of the authors on the most recent state-of-the-art developments in automatic sleep staging, the challenges that still need to be addressed, and the future directions needed for automatic sleep scoring to achieve clinical value.

The purpose of this work was to develop and manufacture a 3D range-modulator (3D RM) for a complex target contour for scanned proton therapy. The 3D RM is considered to be a viable technique for the very fast dose application in patient-specific tumors with only one fixed energy. The RM was developed based on a tumor from a patient CT and manufactured with high-quality 3D printing techniques with both polymer resin and aluminum. Monte Carlo simulations were utilized to investigate its modulating properties and the resulting dose distribution. Additionally, the simulation results were validated with measurements at the Marburg Ion-Beam Therapy Centre. For this purpose, a previously developed water phantom was used to conduct fast, automated high-resolution dose measurements. The results show a very good agreement between simulations and measurements and indicate that highly homogeneous dose distributions are possible. The delivered dose is conformed to the distal as well as to the proximal edge of the target. The 3D range-modulator concept combines a high degree of dose homogeneity and conformity, comparable to standard IMPT with very short irradiation times, promising clinically applicable dose distributions for lung and/or FLASH treatment, comparable and competitive to those from conventional irradiation techniques.

Purpose. To utilize radiomic features extracted from CT images to characterize Human Papilloma Virus (HPV) for patients with oropharyngeal cancer squamous cell carcinoma (OPSCC). Methods. One hundred twenty-eight OPSCC patients with known HPV-status (60-HPV + and 68-HPV-, confirmed by immunohistochemistry-P16-protein testing) were retrospectively studied. Radiomic features (11 feature-categories) were extracted in 3D from contrast-enhanced (CE)-CT images of gross-tumor-volumes using 'in-house' software ('ROdiomiX') developed and validated following the image-biomarker-standardization-initiative (IBSI) guidelines. Six clinical factors were investigated: Age-at-Diagnosis, Gender, Total-Charlson, Alcohol-Use, Smoking-History, and T-Stage. A Least-Absolute-Shrinkage-and-Selection-Operation (Lasso) technique combined with a Generalized-Linear-Model (Lasso-GLM) were applied to perform regularization in the radiomic and clinical feature spaces to identify the ranking of optimal feature subsets with most representative information for prediction of HPV. Lasso-GLM models/classifiers based on clinical factors only, radiomics only, and combined clinical and radiomics (ensemble/integrated) were constructed using random-permutation-sampling. Tests of significance (One-way ANOVA), average Area-Under-Receiver-Operating-Characteristic (AUC), and Positive and Negative Predictive values (PPV and NPV) were computed to estimate the generalization-error and prediction performance of the classifiers. Results. Five clinical factors, including T-stage, smoking status, and age, and 14 radiomic features, including tumor morphology, and intensity contrast were found to be statistically significant discriminators between HPV positive and negative cohorts. Performances for prediction of HPV for the 3 classifiers were: Radiomics-Lasso-GLM: AUC/PPV/NPV = 0.789/0.755/0.805; Clinical-Lasso-GLM: 0.676/0.747/0.672, and Integrated/Ensemble-Lasso-GLM: 0.895/0.874/0.844. Results imply that the radiomics-based classifier enabled better characterization and performance prediction of HPV relative to clinical factors, and that the combination of both radiomics and clinical factors yields even higher accuracy characterization and predictive performance. Conclusion. Albeit subject to confirmation in a larger cohort, this pilot study presents encouraging results in support of the role of radiomic features towards characterization of HPV in patients with OPSCC.

The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.

In this article, we perform a review of the state-of-the-art of hybrid machine learning in medical imaging. We start with a short summary of the general developments of the past in machine learning and how general and specialized approaches have been in competition in the past decades. A particular focus will be the theoretical and experimental evidence pro and contra hybrid modelling. Next, we inspect several new developments regarding hybrid machine learning with a particular focus on so-called known operator learning and how hybrid approaches gain more and more momentum across essentially all applications in medical imaging and medical image analysis. As we will point out by numerous examples, hybrid models are taking over in image reconstruction and analysis. Even domains such as physical simulation and scanner and acquisition design are being addressed using machine learning grey box modelling approaches. Towards the end of the article, we will investigate a few future directions and point out relevant areas in which hybrid modelling, meta learning, and other domains will likely be able to drive the state-of-the-art ahead.

Pollen grains dehydrate during their development and following their departure from the host stigma. Since the size and shape of a pollen grain can be dependent on environmental conditions, being able to predict both of these factors for hydrated pollen grains from their dehydrated state could be beneficial in the fields of climate science, agriculture, and palynology. Here, we use deep learning to transform images of dehydrated Ranunculus pollen grains into images of hydrated Ranunculus pollen grains. We also then use a deep learning neural network that was trained on experimental images of different genera of pollen grains to identify the hydrated pollen grains from the generated transformed images, to test the accuracy of the image generation neural network. This pilot work demonstrates the first steps needed towards creating a general deep learning-based rehydration model that could be useful in understanding and predicting pollen morphology.