An integrated model combined intra- and peritumoral regions for predicting chemoradiation response of non small cell lung cancers based on radiomics and deep learning.

PURPOSE: The purpose of this study was to develop a model for predicting chemoradiation response in non-small cell lung cancer (NSCLC) patients by integrating radiomics and deep-learning features and combined intra- and peritumoral regions with pre-treated CT images. MATERIALS AND METHODS: This study enrolled 462 patients with NSCLC who received chemoradiation. On the basis of pretreated CT images, we developed three models to compare the prediction of chemoradiation: intratumoral, peritumoral and combined regions. To further illustrate each model, we established different feature integration methods: a) radiomics model with 1500 features; b) deep learning model with a multiple instance learning algorithm; c) integrated model by integrating radiomic and deep learning features. For radiomics and integrated models, support vector machine and the least absolute shrinkage and selection operator were used to extract and select features. Transfer learning and max pooling algorithms were used to identify high informative features in deep learning models. We applied ten-fold cross validation in model training and testing. RESULTS: The best area under the curve (AUC) of intratumoral, peritumoral and combined models were 0.89 (95% CI, 0.74-0.93), 0.86 (95% CI, 0.75-0.92) and 0.92 (95% CI, 0.81-0.95), respectively. It indicated the importance of the peritumoral region for treatment response prediction and should be used in combination with the intratumoral region. Integrated models gave better results than models with radiomics and deep learning features alone in all regions of interest and radiomics models outperformed deep learning models in any comparative models. CONCLUSIONS: The model that integrate radiomic and deep learning features and combined intra- and peritumoral regions provide valuable information in predicting treatment response of chemoradiation. It can help oncologists customize personalized clinical treatment plans for NSCLC patients.

RadioTransNet, Radiotherapy Translational and Preclinical Research Network: Results from the dedicated French cancer institute (INCa) call for projects.

PURPOSE: The RadioTransNet project is a French initiative structuring preclinical and translational research in radiation therapy for cancer at national level. The network's activities are organized around four chosen priorities, which are: target definition, normal tissue, combined treatments and dose modelling. The subtargets linked to these four major priorities are unlimited. They include all aspects associated with fundamental radiobiology, preclinical studies, imaging, medical physics research and transversal components clearly related to these scientific areas, such as medical oncology, radio-diagnostics, nuclear medicine and cost-effectiveness considerations. METHOD: During its first phase of activity, four workshops following the consensus conference model and based on scientific and medical state of the art in radiotherapy and radiobiology were organized on the four above-mentioned objectives to identify key points. Then a road map has been defined and served as the basis for the opening in 2022 of a dedicated call, SEQ-RTH22, proposed by the French cancer national institute (INCa). RESULTS: Four research projects submitted by RadioTransNet partners have been selected to be supported by INCa: the first by Professor Anne Laprie from Oncopole Claudius-Regaud and Inserm ToNic in Toulouse on neurocognition and health after pediatric irradiation, the second submitted by Fabien Milliat from IRSN aims to study decryption and targeting of endothelial cell-immune cells interactions to limit radiation-induced intestinal toxicity, the third project, submitted by Yolanda Prezado from institut Curie-CNRS on proton minibeam radiotherapy as a new approach to reduce toxicity, and the latest project proposed by R. de Crevoisier from centre Eugène-Marquis in Rennes on predictive multiscale models of head and neck radiotoxicity induced for optimized personalized radiation therapy. Topics of each of these projects are presented here. CONCLUSION: RadioTransNet project has been launched in 2018, supported by INCa, in order to structure and promote preclinical research in oncology radiotherapy and to favor collaboration between the actors of this research. INCa relied on RadioTransNet initiatives and activities, resulting in the opening of dedicated call for projects. Beyond its first main goals, RadioTransNet network is able to help to fund the human and technical resources necessary to conduct optimal translational and preclinical research in radiation oncology.

Radiotherapy modification based on artificial intelligence and radiomics applied to (18F)-fluorodeoxyglucose positron emission tomography/computed tomography.

Over the last decades, the refinement of radiation therapy techniques has been associated with an increasing interest for individualized radiation therapy with the aim of increasing or maintaining tumor control and reducing radiation toxicity. Developments in artificial intelligence (AI), particularly machine learning and deep learning, in imaging sciences, including nuclear medecine, have led to significant enthusiasm for the concept of "rapid learning health system". AI combined with radiomics applied to (18F)-fluorodeoxyglucose positron emission tomography/computed tomography ([18F]-FDG PET/CT) offers a unique opportunity for the development of predictive models that can help stratify each patient's risk and guide treatment decisions for optimal outcomes and quality of life of patients treated with radiation therapy. Here we present an overview of the current contribution of AI and radiomics-based machine learning models applied to (18F)-FDG PET/CT in the management of cancer treated by radiation therapy.

News in magnetic resonance imaging use for radiation oncology.

The purpose of this article is to give a summary of the progress of magnetic resonance imaging (MRI) in radiotherapy. MRI is an important imaging modality for treatment planning in radiotherapy. However, the registration step with the simulation scanner can be a source of errors, motivating the implementation of all-MRI simulation methods and new accelerators coupled with on-board MRI. First, practical MRI imaging for radiotherapy is detailed, but also the importance of a coherent imaging workflow incorporating all imaging modalities. Second, future evolutions and research domains such as quantitative imaging biomarkers, MRI-only pseudo computed tomography and radiomics are discussed. Finally, the application of MRI during radiotherapy treatment is reviewed: the use of MR-linear accelerators. MRI is increasingly integrated into radiotherapy. Advances in diagnostic imaging can thus benefit radiotherapy, but specific radiotherapy constraints lead to additional challenges and require close collaboration between radiologists, radiation oncologists, technologists and physicists. The integration of quantitative imaging biomarkers in the radiotherapy process will result in mutual benefit for diagnostic imaging and radiotherapy. MRI-guided radiotherapy has already been used for several years in clinical routine. Abdominopelvic neoplasias (pancreas, liver, prostate) are the preferred locations for treatment because of their favourable contrast in MRI, their movement during irradiation and their proximity to organs at risk of radiation exposure, making the tracking and daily adaptation of the plan essential. MRI has emerged as an increasingly necessary imaging modality for radiotherapy planning. Inclusion of patients in clinical trials evaluating new MRI-guided radiotherapy techniques and associated quantitative imaging biomarkers will be necessary to assess the benefits.

[Artificial intelligence and medical imaging]. / Intelligence artificielle et imagerie médicale.

The use of artificial intelligence methods for image recognition is one of the most developed branches of the AI field and these technologies are now commonly used in our daily lives. In the field of medical imaging, approaches based on artificial intelligence are particularly promising, with numerous applications and a strong interest in the search for new biomarkers. Here, we will present the general methods used in these approaches as well as the potential areas of application.

[Artificial intelligence, radiomics and pathomics to predict response and survival of patients treated with radiations]. / Intelligence artificielle en radiothérapie : radiomique, pathomique, et prédiction de la survie et de la réponse aux traitements.

Artificial intelligence approaches in medicine are more and more used and are extremely promising due to the growing number of data produced and the variety of data they allow to exploit. Thus, the computational analysis of medical images in particular, radiological (radiomics), or anatomopathological (pathomics), has shown many very interesting results for the prediction of the prognosis and the response of cancer patients. Radiotherapy is a discipline that particularly benefits from these new approaches based on computer science and imaging. This review will present the main principles of an artificial intelligence approach and in particular machine learning, the principles of a radiomic and pathomic approach and the potential of their use for the prediction of the prognosis of patients treated with radiotherapy.

Use of radiomics in the radiation oncology setting: Where do we stand and what do we need?

Radiomics is a field that has been growing rapidly for the past ten years in medical imaging and more particularly in oncology where the primary objective is to contribute to personalised and predictive medicine. This short review aimed at providing some insights regarding the potential value of radiomics for cancer patients treated with radiotherapy. Radiomics may contribute to each stage of the patients' management: diagnosis, planning, treatment monitoring and post-treatment follow-up (toxicity and response). However, its applicability in clinical routine is currently hindered by several factors, including lack of automation, standardisation and harmonisation. A major effort must be carried out to automate the workflow, standardise radiomics good practices and carry out large-scale studies before any transfer to daily clinical practice.

[Radiation-oncology horizon 2030: From microbiota to plasma laser]. / Oncologie-radiothérapie horizon 2030 : du microbiote au laser plasma.

Advances in physical, technological and biological fields have made radiation oncology a discipline in continual evolution. New current research areas could be implemented in the clinic in the near future. In this review in the form of several interviews, various promising themes for our specialty are described such as the gut microbiota, tumor organoids (or avatar), artificial intelligence, connected therapies, nanotechnologies and plasma laser. The individual prediction of the best therapeutic index combined with the integration of new technologies will ideally allow highly personalized treatment of patients receiving radiation therapy.

Anatomical and functional MR imaging to define tumoral boundaries and characterize lesions in neuro-oncology.

Neuroimaging and especially MRI has emerged as a necessary imaging modality to detect, measure, characterize and monitor brain tumours. Advanced MRI sequences such as perfusion MRI, diffusion MRI and spectroscopy as well as new post-processing techniques such as automatic segmentation of tumours and radiomics play a crucial role in characterization and follow up of brain tumours. The purpose of this review is to provide an overview on anatomical and functional MRI use for brain tumours boundaries determination and tumour characterization in the specific context of radiotherapy. The usefulness of anatomical and functional MRI on particular challenges posed by radiotherapy such as pseudo progression and pseudo esponse and new treatment strategies such as dose painting is also described.

Radiomics: A primer for the radiation oncologist.

PURPOSE: Radiomics are a set of methods used to leverage medical imaging and extract quantitative features that can characterize a patient's phenotype. All modalities can be used with several different software packages. Specific informatics methods can then be used to create meaningful predictive models. In this review, we will explain the major steps of a radiomics analysis pipeline and then present the studies published in the context of radiation therapy. METHODS: A literature review was performed on Medline using the search engine PubMed. The search strategy included the search terms "radiotherapy", "radiation oncology" and "radiomics". The search was conducted in July 2019 and reference lists of selected articles were hand searched for relevance to this review. RESULTS: A typical radiomics workflow always includes five steps: imaging and segmenting, data curation and preparation, feature extraction, exploration and selection and finally modeling. In radiation oncology, radiomics studies have been published to explore different clinical outcome in lung (n=5), head and neck (n=5), esophageal (n=3), rectal (n=3), pancreatic (n=2) cancer and brain metastases (n=2). The quality of these retrospective studies is heterogeneous and their results have not been translated to the clinic. CONCLUSION: Radiomics has a great potential to predict clinical outcome and better personalize treatment. But the field is still young and constantly evolving. Improvement in bias reduction techniques and multicenter studies will hopefully allow more robust and generalizable models.

[Prediction of chemotherapy response in primary osteosarcoma using the machine learning technique on radiomic data]. / Prédiction de la réponse à la chimiothérapie des ostéosarcomes à partir des données radiomiques issues des IRM diagnostiques.

INTRODUCTION: Osteosarcoma is the most common malignant bone tumor before 25 years of age. Response to neoadjuvant chemotherapy determines continuation of treatment and is also a powerful prognostic factor. There are currently no reliable ways to evaluate it early. The aim is to develop a method to predict the chemotherapy response using radiomics from pre-treatment MRI. METHODS: Clinical characteristics and MRI of patients treated for local or metastatic osteosarcoma were collected retrospectively in the Rhône-Alpes region, from 2007 to 2016. On initial MRI exams, each tumor was segmented by expert radiologist and 87 radiomic features were extracted automatically. Univariate analysis was performed to assess each feature's association with histological response following neoadjuvante chemotherapy. To distinguish good histological responder from poor, we built predictive models based on support vector machines. Their classification performance was assessed with the area under operating characteristic curve receiver (AUROC) from test data. RESULTS: The analysis focused on the MRIs of 69 patients, 55.1% (38/69) of whom were good histological responders. The model obtained by support vector machines from initial MRI radiomic data had an AUROC of 0.98, a sensitivity of 100% (IC 95% [100%-100%]) and specificity of 86% (IC 95% [59.7%-111%]). DISCUSSION: Radiomic based on MRI data would predict the chemotherapy response before treatment initiation, in patients treated for osteosarcoma.

Adaptive radiotherapy for head and neck cancers: Fact or fallacy to improve therapeutic ratio?

Modern standards of precision radiotherapy, primarily driven by the technological advances of intensity modulation and image guidance, have led to increased versatility in radiotherapy planning and delivery. The ability to shape doses around critical normal organs, while simultaneously "painting" boost doses to the tumor have translated to substantial therapeutic gains in head and neck cancer patients. Recently, dose adaptation (or adaptive radiotherapy) has been proposed as a novel concept to enhance the therapeutic ratio of head and neck radiotherapy, facilitated in part by the onset of molecular and functional imaging. These contemporary imaging techniques have enabled visualisation of the spatial molecular architecture of the tumor. Daily cone-beam imaging, besides improving treatment accuracy, offers another unique angle to explore radiomics - a novel high throughput feature extraction and selection workflow, for adapting radiotherapy based on real-time tumor changes. Here, we review the existing evidence of molecular and functional imaging in head and neck cancers, as well as the current application of adaptive radiotherapy in the treatment of this tumor type. We propose that adaptive radiotherapy can be further exploited through a systematic application of molecular and functional imaging, including radiomics, at the different phases of planning and treatment.

[Computational medical imaging (radiomics) and potential for immuno-oncology]. / Imagerie médicale computationnelle (radiomique) et potentiel en immuno-oncologie.

The arrival of immunotherapy has profoundly changed the management of multiple cancers, obtaining unexpected tumour responses. However, until now, the majority of patients do not respond to these new treatments. The identification of biomarkers to determine precociously responding patients is a major challenge. Computational medical imaging (also known as radiomics) is a promising and rapidly growing discipline. This new approach consists in the analysis of high-dimensional data extracted from medical imaging, to further describe tumour phenotypes. This approach has the advantages of being non-invasive, capable of evaluating the tumour and its microenvironment in their entirety, thus characterising spatial heterogeneity, and being easily repeatable over time. The end goal of radiomics is to determine imaging biomarkers as decision support tools for clinical practice and to facilitate better understanding of cancer biology, allowing the assessment of the changes throughout the evolution of the disease and the therapeutic sequence. This review will develop the process of computational imaging analysis and present its potential in immuno-oncology.