A guide to artificial intelligence for cancer researchers.

Artificial intelligence (AI) has been commoditized. It has evolved from a specialty resource to a readily accessible tool for cancer researchers. AI-based tools can boost research productivity in daily workflows, but can also extract hidden information from existing data, thereby enabling new scientific discoveries. Building a basic literacy in these tools is useful for every cancer researcher. Researchers with a traditional biological science focus can use AI-based tools through off-the-shelf software, whereas those who are more computationally inclined can develop their own AI-based software pipelines. In this article, we provide a practical guide for non-computational cancer researchers to understand how AI-based tools can benefit them. We convey general principles of AI for applications in image analysis, natural language processing and drug discovery. In addition, we give examples of how non-computational researchers can get started on the journey to productively use AI in their own work.

Analysis of 3D pathology samples using weakly supervised AI.

Human tissue, which is inherently three-dimensional (3D), is traditionally examined through standard-of-care histopathology as limited two-dimensional (2D) cross-sections that can insufficiently represent the tissue due to sampling bias. To holistically characterize histomorphology, 3D imaging modalities have been developed, but clinical translation is hampered by complex manual evaluation and lack of computational platforms to distill clinical insights from large, high-resolution datasets. We present TriPath, a deep-learning platform for processing tissue volumes and efficiently predicting clinical outcomes based on 3D morphological features. Recurrence risk-stratification models were trained on prostate cancer specimens imaged with open-top light-sheet microscopy or microcomputed tomography. By comprehensively capturing 3D morphologies, 3D volume-based prognostication achieves superior performance to traditional 2D slice-based approaches, including clinical/histopathological baselines from six certified genitourinary pathologists. Incorporating greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, further emphasizing the value of capturing larger extents of heterogeneous morphology.

Demographic bias in misdiagnosis by computational pathology models.

Despite increasing numbers of regulatory approvals, deep learning-based computational pathology systems often overlook the impact of demographic factors on performance, potentially leading to biases. This concern is all the more important as computational pathology has leveraged large public datasets that underrepresent certain demographic groups. Using publicly available data from The Cancer Genome Atlas and the EBRAINS brain tumor atlas, as well as internal patient data, we show that whole-slide image classification models display marked performance disparities across different demographic groups when used to subtype breast and lung carcinomas and to predict IDH1 mutations in gliomas. For example, when using common modeling approaches, we observed performance gaps (in area under the receiver operating characteristic curve) between white and Black patients of 3.0% for breast cancer subtyping, 10.9% for lung cancer subtyping and 16.0% for IDH1 mutation prediction in gliomas. We found that richer feature representations obtained from self-supervised vision foundation models reduce performance variations between groups. These representations provide improvements upon weaker models even when those weaker models are combined with state-of-the-art bias mitigation strategies and modeling choices. Nevertheless, self-supervised vision foundation models do not fully eliminate these discrepancies, highlighting the continuing need for bias mitigation efforts in computational pathology. Finally, we demonstrate that our results extend to other demographic factors beyond patient race. Given these findings, we encourage regulatory and policy agencies to integrate demographic-stratified evaluation into their assessment guidelines.

Epstein-Barr Virus Orchestrates Spatial Reorganization and Immunomodulation within the Classic Hodgkin Lymphoma Tumor Microenvironment.

Classic Hodgkin Lymphoma (cHL) is a tumor composed of rare malignant Hodgkin and Reed-Sternberg (HRS) cells nested within a T-cell rich inflammatory immune infiltrate. cHL is associated with Epstein-Barr Virus (EBV) in 25% of cases. The specific contributions of EBV to the pathogenesis of cHL remain largely unknown, in part due to technical barriers in dissecting the tumor microenvironment (TME) in high detail. Herein, we applied multiplexed ion beam imaging (MIBI) spatial pro-teomics on 6 EBV-positive and 14 EBV-negative cHL samples. We identify key TME features that distinguish between EBV-positive and EBV-negative cHL, including the relative predominance of memory CD8 T cells and increased T-cell dysfunction as a function of spatial proximity to HRS cells. Building upon a larger multi-institutional cohort of 22 EBV-positive and 24 EBV-negative cHL samples, we orthogonally validated our findings through a spatial multi-omics approach, coupling whole transcriptome capture with antibody-defined cell types for tu-mor and T-cell populations within the cHL TME. We delineate contrasting transcriptomic immunological signatures between EBV-positive and EBV-negative cases that differently impact HRS cell proliferation, tumor-immune interactions, and mecha-nisms of T-cell dysregulation and dysfunction. Our multi-modal framework enabled a comprehensive dissection of EBV-linked reorganization and immune evasion within the cHL TME, and highlighted the need to elucidate the cellular and molecular fac-tors of virus-associated tumors, with potential for targeted therapeutic strategies.

Towards a general-purpose foundation model for computational pathology.

Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks, requiring the objective characterization of histopathological entities from whole-slide images (WSIs). The high resolution of WSIs and the variability of morphological features present significant challenges, complicating the large-scale annotation of data for high-performance applications. To address this challenge, current efforts have proposed the use of pretrained image encoders through transfer learning from natural image datasets or self-supervised learning on publicly available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using more than 100 million images from over 100,000 diagnostic H&E-stained WSIs (>77 TB of data) across 20 major tissue types. The model was evaluated on 34 representative CPath tasks of varying diagnostic difficulty. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient artificial intelligence models that can generalize and transfer to a wide range of diagnostically challenging tasks and clinical workflows in anatomic pathology.

MAPS: pathologist-level cell type annotation from tissue images through machine learning.

Highly multiplexed protein imaging is emerging as a potent technique for analyzing protein distribution within cells and tissues in their native context. However, existing cell annotation methods utilizing high-plex spatial proteomics data are resource intensive and necessitate iterative expert input, thereby constraining their scalability and practicality for extensive datasets. We introduce MAPS (Machine learning for Analysis of Proteomics in Spatial biology), a machine learning approach facilitating rapid and precise cell type identification with human-level accuracy from spatial proteomics data. Validated on multiple in-house and publicly available MIBI and CODEX datasets, MAPS outperforms current annotation techniques in terms of speed and accuracy, achieving pathologist-level precision even for typically challenging cell types, including tumor cells of immune origin. By democratizing rapidly deployable and scalable machine learning annotation, MAPS holds significant potential to expedite advances in tissue biology and disease comprehension.

Multiple-instance learning of somatic mutations for the classification of tumour type and the prediction of microsatellite status.

Large-scale genomic data are well suited to analysis by deep learning algorithms. However, for many genomic datasets, labels are at the level of the sample rather than for individual genomic measures. Machine learning models leveraging these datasets generate predictions by using statically encoded measures that are then aggregated at the sample level. Here we show that a single weakly supervised end-to-end multiple-instance-learning model with multi-headed attention can be trained to encode and aggregate the local sequence context or genomic position of somatic mutations, hence allowing for the modelling of the importance of individual measures for sample-level classification and thus providing enhanced explainability. The model solves synthetic tasks that conventional models fail at, and achieves best-in-class performance for the classification of tumour type and for predicting microsatellite status. By improving the performance of tasks that require aggregate information from genomic datasets, multiple-instance deep learning may generate biological insight.

HBV Vaccines: Advances and Development.

Hepatitis B virus (HBV) infection is a global public health problem that is closely related to liver cirrhosis and hepatocellular carcinoma (HCC). The prevalence of acute and chronic HBV infection, liver cirrhosis, and HCC has significantly decreased as a result of the introduction of universal HBV vaccination programs. The first hepatitis B vaccine approved was developed by purifying the hepatitis B surface antigen (HBsAg) from the plasma of asymptomatic HBsAg carriers. Subsequently, recombinant DNA technology led to the development of the recombinant hepatitis B vaccine. Although there are already several licensed vaccines available for HBV infection, continuous research is essential to develop even more effective vaccines. Prophylactic hepatitis B vaccination has been important in the prevention of hepatitis B because it has effectively produced protective immunity against hepatitis B viral infection. Prophylactic vaccines only need to provoke neutralizing antibodies directed against the HBV envelop proteins, whereas therapeutic vaccines are most likely needed to induce a comprehensive T cell response and thus, should include other HBV antigens, such as HBV core and polymerase. The existing vaccines have proven to be highly effective in preventing HBV infection, but ongoing research aims to improve their efficacy, duration of protection, and accessibility. The routine administration of the HBV vaccine is safe and well-tolerated worldwide. The purpose of this type of immunization is to trigger an immunological response in the host, which will halt HBV replication. The clinical efficacy and safety of the HBV vaccine are affected by a number of immunological and clinical factors. However, this success is now in jeopardy due to the breakthrough infections caused by HBV variants with mutations in the S gene, high viral loads, and virus-induced immunosuppression. In this review, we describe various types of available HBV vaccines, along with the recent progress in the ongoing battle to develop new vaccines against HBV.

An open-source nnU-net algorithm for automatic segmentation of MRI scans in the male pelvis for adaptive radiotherapy.

Background: Adaptive MRI-guided radiotherapy (MRIgRT) requires accurate and efficient segmentation of organs and targets on MRI scans. Manual segmentation is time-consuming and variable, while deformable image registration (DIR)-based contour propagation may not account for large anatomical changes. Therefore, we developed and evaluated an automatic segmentation method using the nnU-net framework. Methods: The network was trained on 38 patients (76 scans) with localized prostate cancer and tested on 30 patients (60 scans) with localized prostate, metastatic prostate, or bladder cancer treated at a 1.5 T MRI-linac at our institution. The performance of the network was compared with the current clinical workflow based on DIR. The segmentation accuracy was evaluated using the Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff distance (HD) metrics. Results: The trained network successfully segmented all 600 structures in the test set. High similarity was obtained for most structures, with 90% of the contours having a DSC above 0.9 and 86% having an MSD below 1 mm. The largest discrepancies were found in the sigmoid and colon structures. Stratified analysis on cancer type showed that the best performance was seen in the same type of patients that the model was trained on (localized prostate). Especially in patients with bladder cancer, the performance was lower for the bladder and the surrounding organs. A complete automatic delineation workflow took approximately 1 minute. Compared with contour transfer based on the clinically used DIR algorithm, the nnU-net performed statistically better across all organs, with the most significant gain in using the nnU-net seen for organs subject to more considerable volumetric changes due to variation in the filling of the rectum, bladder, bowel, and sigmoid. Conclusion: We successfully trained and tested a network for automatically segmenting organs and targets for MRIgRT in the male pelvis region. Good test results were seen for the trained nnU-net, with test results outperforming the current clinical practice using DIR-based contour propagation at the 1.5 T MRI-linac. The trained network is sufficiently fast and accurate for clinical use in an online setting for MRIgRT. The model is provided as open-source.

Geometric distortions in clinical MRI sequences for radiotherapy: insights gained from a multicenter investigation.

BACKGROUND: As magnetic resonance imaging (MRI) becomes increasingly integrated into radiotherapy (RT) for enhanced treatment planning and adaptation, the inherent geometric distortion in acquired MR images pose a potential challenge to treatment accuracy. This study aimed to evaluate the geometric distortion levels in the clinical MRI protocols used across Danish RT centers and discuss influence of specific sequence parameters. Based on the variety in geometric performance across centers, we assess if harmonization of MRI sequences is a relevant measure. MATERIALS AND METHODS: Nine centers participated with 12 MRI scanners and MRI-Linacs (MRL). Using a travelling phantom approach, a reference MRI sequence was used to assess variation in baseline distortion level between scanners. The phantom was also scanned with local clinical MRI sequences for brain, head/neck (H/N), abdomen, and pelvis. The influence of echo time, receiver bandwidth, image weighting, and 2D/3D acquisition was investigated. RESULTS: We found a large variation in geometric accuracy across 93 clinical sequences examined, exceeding the baseline variation found between MRI scanners (σ = 0.22 mm), except for abdominal sequences where the variation was lower. Brain and abdominal sequences showed lowest distortion levels ([0.22, 2.26] mm), and a large variation in performance was found for H/N and pelvic sequences ([0.19, 4.07] mm). Post hoc analyses revealed that distortion levels decreased with increasing bandwidth and a less clear increase in distortion levels with increasing echo time. 3D MRI sequences had lower distortion levels than 2D (median of 1.10 and 2.10 mm, respectively), and in DWI sequences, the echo-planar imaging read-out resulted in highest distortion levels. CONCLUSION: There is a large variation in the geometric distortion levels of clinical MRI sequences across Danish RT centers, and between anatomical sites. The large variation observed makes harmonization of MRI sequences across institutions and adoption of practices from well-performing anatomical sites, a relevant measure within RT.

A General-Purpose Self-Supervised Model for Computational Pathology.

Tissue phenotyping is a fundamental computational pathology (CPath) task in learning objective characterizations of histopathologic biomarkers in anatomic pathology. However, whole-slide imaging (WSI) poses a complex computer vision problem in which the large-scale image resolutions of WSIs and the enormous diversity of morphological phenotypes preclude large-scale data annotation. Current efforts have proposed using pretrained image encoders with either transfer learning from natural image datasets or self-supervised pretraining on publicly-available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using over 100 million tissue patches from over 100,000 diagnostic haematoxylin and eosin-stained WSIs across 20 major tissue types, and evaluated on 33 representative CPath clinical tasks in CPath of varying diagnostic difficulties. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree code classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient AI models that can generalize and transfer to a gamut of diagnostically-challenging tasks and clinical workflows in anatomic pathology.

Impact of abdominal compression on intra-fractional motion and delivered dose in magnetic resonance image-guided adaptive radiation ablation of adrenal gland metastases.

PURPOSE: The current study investigated the impact of abdominal compression on motion and the delivered dose during non-gated, magnetic resonance image (MRI)-guided radiation ablation of adrenal gland metastases. METHODS: Thirty-one patients with adrenal gland metastases treated to 45-60 Gy in 3-8 fractions on a 1.5 T MRI-linac were included in the study. The patients were breathing freely (n = 14) or with motion restricted by using an abdominal compression belt (n = 17). The time-resolved position of the target in online 2D cine MR images acquired during treatment was assessed and used to estimate the dose delivered to the GTV and abutting luminal organs at risk (OAR). RESULTS: The median (range) 3D root-mean-square target position error was significantly higher in patients treated without a compression belt [2.9 (1.9-5.6) mm] compared to patients using the belt [2.1 (1.2-3.5) mm] (P < 0.01). The median (range) GTV V95% was significantly reduced from planned 98.6 (65.9-100) % to delivered 96.5 (64.5-99.9) % due to motion (P < 0.01). Most prominent dose reductions were found in patients showing either large target drift or respiration motion and were mainly treated without abdominal compression. Motion did not lead to an increased number of constraint violations for luminal OAR. CONCLUSIONS: Acceptable target coverage and dose to OAR was observed in the vast majority of patients despite intra-fractional motion during adaptive MRI-guided radiation ablation. The use of abdominal compression significantly reduced the target position error and prevented the most prominent target coverage degradations and is, therefore, recommended as motion management at MRI-linacs.

Artificial Intelligence-Triaged 3-Dimensional Pathology to Improve Detection of Esophageal Neoplasia While Reducing Pathologist Workloads.

Early detection of esophageal neoplasia via evaluation of endoscopic surveillance biopsies is the key to maximizing survival for patients with Barrett's esophagus, but it is hampered by the sampling limitations of conventional slide-based histopathology. Comprehensive evaluation of whole biopsies with 3-dimensional (3D) pathology may improve early detection of malignancies, but large 3D pathology data sets are tedious for pathologists to analyze. Here, we present a deep learning-based method to automatically identify the most critical 2-dimensional (2D) image sections within 3D pathology data sets for pathologists to review. Our method first generates a 3D heatmap of neoplastic risk for each biopsy, then classifies all 2D image sections within the 3D data set in order of neoplastic risk. In a clinical validation study, we diagnose esophageal biopsies with artificial intelligence-triaged 3D pathology (3 images per biopsy) vs standard slide-based histopathology (16 images per biopsy) and show that our method improves detection sensitivity while reducing pathologist workloads.

Weakly Supervised AI for Efficient Analysis of 3D Pathology Samples.

Human tissue consists of complex structures that display a diversity of morphologies, forming a tissue microenvironment that is, by nature, three-dimensional (3D). However, the current standard-of-care involves slicing 3D tissue specimens into two-dimensional (2D) sections and selecting a few for microscopic evaluation1,2, with concomitant risks of sampling bias and misdiagnosis3-6. To this end, there have been intense efforts to capture 3D tissue morphology and transition to 3D pathology, with the development of multiple high-resolution 3D imaging modalities7-18. However, these tools have had little translation to clinical practice as manual evaluation of such large data by pathologists is impractical and there is a lack of computational platforms that can efficiently process the 3D images and provide patient-level clinical insights. Here we present Modality-Agnostic Multiple instance learning for volumetric Block Analysis (MAMBA), a deep-learning-based platform for processing 3D tissue images from diverse imaging modalities and predicting patient outcomes. Archived prostate cancer specimens were imaged with open-top light-sheet microscopy12-14 or microcomputed tomography15,16 and the resulting 3D datasets were used to train risk-stratification networks based on 5-year biochemical recurrence outcomes via MAMBA. With the 3D block-based approach, MAMBA achieves an area under the receiver operating characteristic curve (AUC) of 0.86 and 0.74, superior to 2D traditional single-slice-based prognostication (AUC of 0.79 and 0.57), suggesting superior prognostication with 3D morphological features. Further analyses reveal that the incorporation of greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, suggesting that there is value in capturing larger extents of spatially heterogeneous 3D morphology. With the rapid growth and adoption of 3D spatial biology and pathology techniques by researchers and clinicians, MAMBA provides a general and efficient framework for 3D weakly supervised learning for clinical decision support and can help to reveal novel 3D morphological biomarkers for prognosis and therapeutic response.

MAPS: Pathologist-level cell type annotation from tissue images through machine learning.

Highly multiplexed protein imaging is emerging as a potent technique for analyzing protein distribution within cells and tissues in their native context. However, existing cell annotation methods utilizing high-plex spatial proteomics data are resource intensive and necessitate iterative expert input, thereby constraining their scalability and practicality for extensive datasets. We introduce MAPS (Machine learning for Analysis of Proteomics in Spatial biology), a machine learning approach facilitating rapid and precise cell type identification with human-level accuracy from spatial proteomics data. Validated on multiple in-house and publicly available MIBI and CODEX datasets, MAPS outperforms current annotation techniques in terms of speed and accuracy, achieving pathologist-level precision even for challenging cell types, including tumor cells of immune origin. By democratizing rapidly deployable and scalable machine learning annotation, MAPS holds significant potential to expedite advances in tissue biology and disease comprehension.

Recommendations for improved reproducibility of ADC derivation on behalf of the Elekta MRI-linac consortium image analysis working group.

BACKGROUND AND PURPOSE: The apparent diffusion coefficient (ADC), a potential imaging biomarker for radiotherapy response, needs to be reproducible before translation into clinical use. The aim of this study was to evaluate the multi-centre delineation- and calculation-related ADC variation and give recommendations to minimize it. MATERIALS AND METHODS: Nine centres received identical diffusion-weighted and anatomical magnetic resonance images of different cancerous tumours (adrenal gland, pelvic oligo metastasis, pancreas, and prostate). All centres delineated the gross tumour volume (GTV), clinical target volume (CTV), and viable tumour volume (VTV), and calculated ADCs using both their local calculation methods and each of the following calculation conditions: b-values 0-500 vs. 150-500 s/mm2, region-of-interest (ROI)-based vs. voxel-based calculation, and mean vs. median. ADC variation was assessed using the mean coefficient of variation across delineations (CVD) and calculation methods (CVC). Absolute ADC differences between calculation conditions were evaluated using Friedman's test. Recommendations for ADC calculation were formulated based on observations and discussions within the Elekta MRI-linac consortium image analysis working group. RESULTS: The median (range) CVD and CVC were 0.06 (0.02-0.32) and 0.17 (0.08-0.26), respectively. The ADC estimates differed 18% between b-value sets and 4% between ROI/voxel-based calculation (p-values < 0.01). No significant difference was observed between mean and median (p = 0.64). Aligning calculation conditions between centres reduced CVC to 0.04 (0.01-0.16). CVD was comparable between ROI types. CONCLUSION: Overall, calculation methods had a larger impact on ADC reproducibility compared to delineation. Based on the results, significant sources of variation were identified, which should be considered when initiating new studies, in particular multi-centre investigations.

Transcriptomics based identification of S100A3 as the key anti-hepatitis B virus factor of 16F16.

More than 250 million people worldwide have chronic hepatitis B virus (HBV) infections, resulting in over 1 million annual fatalities because HBV cannot be adequately treated with current antivirals. Hepatocellular carcinoma (HCC) risk is elevated in the presence of the HBV. Novel and powerful medications that specifically target the persistent viral components are needed to remove infection. This study aimed to use HepG2.2.15 cells and the rAAV-HBV1.3 C57BL/6 mouse model established in our laboratory to examine the effects of 16F16 on HBV. The transcriptome analysis of the samples was performed to examine the impact of 16F16 therapy on host factors. We found that the HBsAg and HBeAg levels significantly decreased in a dose-dependent manner following the 16F16 treatment. 16F16 also showed significant anti-hepatitis B effects in vivo. The transcriptome analysis showed that 16F16 regulated the expression of several proteins in HBV-producing HepG2.2.15 cells. As one of the differentially expressed genes, the role of S100A3 in the anti-hepatitis B process of 16F16 was further investigated. The expression of the S100A3 protein significantly decreased following the 16F16 therapy. And upregulation of S100A3 caused an upregulation of HBV DNA, HBsAg, and HBeAg in HepG2.2.15 cells. Similarly, knockdown of S100A3 significantly reduced the levels of HBsAg, HBeAg, and HBV DNA. Our findings proved that S100A3 might be a new target for combating HBV pathogenesis. 16F16 can target several proteins involved in HBV pathogenesis, and may be a promising drug precursor molecule for the treatment of HBV.

Effect of melatonin cream on acute radiation dermatitis in patients with primary breast cancer: A double-blind, randomized, placebo-controlled trial.

AIM: This was a double-blind, placebo-controlled randomized study investigating whether melatonin can protect against radiation dermatitis in women receiving radiation therapy for primary breast cancer. METHODS: Patients were included before radiation therapy and followed once weekly throughout treatment with a 3-week follow-up. Patients applied 1 g of cream to the irradiated skin twice daily, consisting of either 25 mg/g melatonin and 150 mg/g dimethyl sulfoxide, or placebo. Our outcomes were the Radiation Therapy Oncology Group's (RTOG) acute radiation morbidity scoring criteria for skin, a pixel analysis of erythema in clinical photographs, and patients' use of corticosteroid cream. Outcomes were evaluated once weekly throughout the trial. The primary outcomes were RTOG-score and pixel analysis at 2 weeks follow-up. Secondary outcomes were the use of corticosteroid cream and analyses of RTOG-scores and pixel analyses throughout the trial. RESULTS: Sixty-five patients were included, 17 dropped out, totaling 26 and 22 patients randomized to melatonin and placebo, respectively. RTOG-scores and pixel analyses at 2 weeks follow-up showed no difference p = .441 and p = .890, respectively). There was no difference in the use of corticosteroid cream (p = .055). Using logistic regression, the melatonin group had a higher likelihood of having a low RTOG-score (p = .0016). The logistic regression showed no difference between the groups for the pixel analyses. CONCLUSION: Our primary outcome showed no difference in RTOG-scores at 2 weeks follow-up, however, the RTOG-score over the entire duration of the study demonstrated a protective effect of melatonin. Further studies are warranted investigating higher doses of melatonin, and whether corticosteroids may influence the effect of melatonin cream against radiation dermatitis.

An ESTRO-ACROP guideline on quality assurance and medical physics commissioning of online MRI guided radiotherapy systems based on a consensus expert opinion.

OBJECTIVE: The goal of this consensus expert opinion was to define quality assurance (QA) tests for online magnetic resonance image (MRI) guided radiotherapy (oMRgRT) systems and to define the important medical physics aspects for installation and commissioning of an oMRgRT system. MATERIALS AND METHODS: Ten medical physicists and two radiation oncologists experienced in oMRgRT participated in the survey. In the first round of the consensus expert opinion, ideas on QA and commissioning were collected. Only tests and aspects different from commissioning of a CT guided radiotherapy (RT) system were considered. In the following two rounds all twelve participants voted on the importance of the QA tests, their recommended frequency and their suitability for the two oMRgRT systems approved for clinical use as well as on the importance of the aspects to consider during medical physics commissioning. RESULTS: Twenty-four QA tests were identified which are potentially important during commissioning and routine QA on oMRgRT systems compared to online CT guided RT systems. An additional eleven tasks and aspects related to construction, workflow development and training were collected. Consensus was found for most tests on their importance, their recommended frequency and their suitability for the two approved systems. In addition, eight aspects mostly related to the definition of workflows were also found to be important during commissioning. CONCLUSIONS: A program for QA and commissioning of oMRgRT systems was developed to support medical physicists to prepare for safe handling of such systems.

Decomposition-based framework for tumor classification and prediction of treatment response from longitudinal MRI.

Objective.In the field of radiation oncology, the benefit of MRI goes beyond that of providing high soft-tissue contrast images for staging and treatment planning. With the recent clinical introduction of hybrid MRI linear accelerators it has become feasible to map physiological parameters describing diffusion, perfusion, and relaxation during the entire course of radiotherapy, for example. However, advanced data analysis tools are required for extracting qualified prognostic and predictive imaging biomarkers from longitudinal MRI data. In this study, we propose a new prediction framework tailored to exploit temporal dynamics of tissue features from repeated measurements. We demonstrate the framework using a newly developed decomposition method for tumor characterization.Approach.Two previously published MRI datasets with multiple measurements during and after radiotherapy, were used for development and testing:T2-weighted multi-echo images obtained for two mouse models of pancreatic cancer, and diffusion-weighted images for patients with brain metastases. Initially, the data was decomposed using the novel monotonous slope non-negative matrix factorization (msNMF) tailored for MR data. The following processing consisted of a tumor heterogeneity assessment using descriptive statistical measures, robust linear modelling to capture temporal changes of these, and finally logistic regression analysis for stratification of tumors and volumetric outcome.Main Results.The framework was able to classify the two pancreatic tumor types with an area under curve (AUC) of 0.999,P< 0.001 and predict the tumor volume change with a correlation coefficient of 0.513,P= 0.034. A classification of the human brain metastases into responders and non-responders resulted in an AUC of 0.74,P= 0.065.Significance.A general data processing framework for analyses of longitudinal MRI data has been developed and applications were demonstrated by classification of tumor type and prediction of radiotherapy response. Further, as part of the assessment, the merits of msNMF for tumor tissue decomposition were demonstrated.