Search

Background: We recently developed a gene-expression-based HOT score to identify the hot/cold phenotype of head and neck squamous cell carcinomas (HNSCCs), which is associated with the response to immunotherapy. Our goal was to determine whether radiomic profiling from computed tomography (CT) scans can distinguish hot and cold HNSCC. Method: We included 113 patients from The Cancer Genome Atlas (TCGA) and 20 patients from the Groupe Hospitalier Pitié-Salpêtrière (GHPS) with HNSCC, all with available pre-treatment CT scans. The hot/cold phenotype was computed for all patients using the HOT score. The IBEX software (version 4.11.9, accessed on 30 march 2020) was used to extract radiomic features from the delineated tumor region in both datasets, and the intraclass correlation coefficient (ICC) was computed to select robust features. Machine learning classifier models were trained and tested in the TCGA dataset and validated using the area under the receiver operator characteristic curve (AUC) in the GHPS cohort. Results: A total of 144 radiomic features with an ICC >0.9 was selected. An XGBoost model including these selected features showed the best performance prediction of the hot/cold phenotype with AUC = 0.86 in the GHPS validation dataset. Conclusions and Relevance: We identified a relevant radiomic model to capture the overall hot/cold phenotype of HNSCC. This non-invasive approach could help with the identification of patients with HNSCC who may benefit from immunotherapy.

Background There are many scales for screening the impact of a disease. These scales are generally used to diagnose or assess the type and severity of a disease and are carried out by doctors. The chatbot helps patients suffering from primary headache disorders through personalized text messages. It could be used to collect patient-reported outcomes. Objective The aims of this study were (1) to study whether the collection and analysis of remote scores, without prior medical intervention, are possible by a chatbot, (2) to perform suggested diagnosis and define the type of headaches, and (3) to assess the patient satisfaction and engagement with the chatbot. Method Voluntary users of the chatbot were recruited online. They had to be over 18 and have a personal history of headaches. A questionnaire was presented (1) by text messages to the participants to evaluate migraines (2) based on the criteria of the International Headache Society. Then, the Likert scale (3) was used to assess overall satisfaction with the use of the chatbot. Results We included 610 participants with primary headache disorders. A total of 89.94% (572/610) participants had fully completed the questionnaire (eight items), 4.72% (30/610) had partially completed it, and 5.41% (33) had refused to complete it. Statistical analysis was performed on 86.01% (547/610) of participants. Auto diagnostic showed that 14.26% (78/547) participants had a tension headache, and 85.74% (469/547) had a probable migraine. In this population, 15.78% (74/469) suffered from migraine without probable aura, and 84.22% (395/469) had migraine without aura. The patient’s age had a significant incidence regarding the auto diagnosis ( P = .008

Background and purpose: Physical and mental well-being are crucial for oncology professionals as they affect performance at work. Personality traits, as alexithymia and empathy, may influence professional quality of life. Alexithymia involves diminished skills in emotion processing and awareness. Empathy is pertinent to the ability to understand another’s ‘state of mind/emotion’. The PROject on Burn-Out in RadiatioN Oncology (PRO BONO) investigates professional quality of life amongst radiation oncology professionals, exploring the role of alexithymia and empathy. The present study reports on data pertinent to radiation therapists (RTTs). Material and methods: An online survey targeted ESTRO members. Participants were asked to fill out 3 questionnaires for alexithymia, empathy and professional quality of life: (a) Toronto Alexithymia Scale (TAS-20); (b) Interpersonal Reactivity Index (IRI); (c) Professional Quality of Life Scale (ProQoL). The present analysis focuses on RTTS to evaluate compassion satisfaction (CS), secondary traumatic stress (STS) and Burnout and their correlation with alexithymia and empathy, using generalized linear modeling. Covariates found significant at univariate linear regression analysis were included in the multivariate linear regression model. Results: A total of 399 RTTs completed all questionnaires. The final model for the burnout scale of ProQoL found, as significal predictors, the TAS-20 total score (β = 0.46, p

Background and purpose: The professional quality of life of radiation oncology professionals can be influenced by different contributing factors, including personality traits. Alexithymia involves deficits in emotion processing and awareness. Empathy is the ability to understand another’s ‘state of mind/emotion’. We investigated professional quality of life, including burnout, in radiation oncology, exploring the role of alexithymia and empathy and targeting the population of medical physicists (MPs), since this professional category is usually underrepresented in surveys exploring professional well-being in radiation oncology and MPs may experience professional distress given the increasing complexity of multimodal cancer care. Material and methods: An online survey was addressed to ESTRO members. Participants filled out three questionnaires to evaluate alexithymia, empathy and professional quality of life: a) Toronto Alexithymia Scale (TAS-20); b) Interpersonal Reactivity Index (IRI); c) Professional Quality of Life Scale (ProQoL). Professional quality of life as per ProQoL was considered as dependent variable. The three domains of the ProQoL, namely compassion satisfaction (CS), secondary traumatic stress (STS) and burnout were correlated with alexithymia (as per TAS-20) and empathy (as per IRI with three subcategories: empathic concern, perspective taking and personal distress) and demographic/professional characteristics as independent variables. Generalized linear modeling was used. Significant covariates on univariate linear regression analysis were included in the multivariate linear regression model. Results: A total of 308 medical physicists completed all questionnaires. Alexithymia as per TAS-20 was correlated to decreased CS (β = −0.25, p

This study aimed to describe patient characteristics, treatment efficacy, and safety in patients with hepatocellular carcinoma (HCC) undergoing stereotactic body radiation therapy (SBRT). We retrospectively analyzed data of 318 patients with 375 HCC treated between June 2007 and December 2018. Efficacy (overall survival [OS], relapse-free survival, and local control) and acute and late toxicities were described. The median follow-up period was 70.2 months. Most patients were treated with 45 Gy in three fractions. The median (range) PTV volume was 90.7 (2.6–1067.6) cc. The local control rate at 24 and 60 months was 94% (91–97%) and 94% (91–97%), respectively. Relapse-free survival at 12, 24, and 60 months was 62% (55–67%), 29% (23–36%), and 13% (8–19%), respectively. OS at 12, 24, and 60 months was 72% (95%CI 67–77%), 44% (38–50%), and 11% (7–15%), respectively. Approximately 51% and 38% experienced acute and late toxicity, respectively. Child-Pugh score B-C, high BCLC score, portal thrombosis, high GTV volume, and higher PTV volume reported on total hepatic volume ratio were significantly associated with OS. SBRT is efficient for the management of HCC with a favorable toxicity profile. The outcome is highly related to the natural evolution of the underlying cirrhosis.

Chatbots, also known as conversational agents or digital assistants, are artificial intelligence–driven software programs designed to interact with people in a conversational manner. They are often used for user-friendly customer-service triaging. In healthcare, chatbots can create bidirectional information exchange with patients, which could be leveraged for follow-up, screening, treatment adherence or data-collection. They can be deployed over various modalities, such as text-based services (text messaging, mobile applications, chat rooms) on any website or mobile applications, or audio services, such as Siri, Alexa, Cortana or Google Assistant. Potential applications are very promising, particularly in the field of oncology. In this review, we discuss the available publications and applications and the ongoing trials in that setting. Keywords: Conversational agent, Digital assistant, Chatbot, Oncology, Cancer

Background Lockdowns were implemented to limit the spread of COVID-19. Peritraumatic distress (PD) and post-traumatic stress disorder have been reported after traumatic events, but the specific effect of the pandemic is not well known.Aim The aim of this study was to assess PD in France, a country where COVID-19 had such a dramatic impact that it required a country-wide lockdown.Methods We recruited patients in four groups of chatbot users followed for breast cancer, asthma, depression and migraine. We used the Psychological Distress Inventory (PDI), a validated scale to measure PD during traumatic events, and correlated PD risk with patients’ characteristics in order to better identify the ones who were the most at risk.Results The study included 1771 participants. 91.25% (n=1616) were female with a mean age of 32.8 (13.71) years and 7.96% (n=141) were male with a mean age of 28.0 (8.14) years. In total, 38.06% (n=674) of the respondents had psychological distress (PDI ≥14). An analysis of variance showed that unemployment and depression were significantly associated with a higher PDI score. Patients using their smartphones or computers for more than 1 hour a day also had a higher PDI score (p=0.026).Conclusion Prevalence of PD in at-risk patients is high. These patients are also at an increased risk of developing post-traumatic stress disorder. Specific steps should be implemented to monitor and prevent PD through dedicated mental health policies if we want to limit the public health impact of COVID-19 in time.Trial registration number NCT04337047.

Introduction: Deep Learning (DL) is a machine learning technique that uses deep neural networks to create a model. The application areas of deep learning in radiation oncology include image segmentation and detection, image phenotyping, and radiomic signature discovery, clinical outcome prediction, image dose quantification, dose-response modeling, radiation adaptation, and image generation. In this review, we explain the methods used in DL and perform a literature review using the Medline database to identify studies using deep learning in radiation oncology. The search was conducted in April 2018, and identified studies published between 1997 and 2018, strongly skewed toward 2015 and later.Methods: A literature review was performed using PubMed/Medline in order to identify important recent publications to be synthesized into a review of the current status of Deep Learning in radiation oncology, directed at a clinically-oriented reader. The search strategy included the search terms “radiotherapy” and “deep learning.” In addition, reference lists of selected articles were hand searched for further potential hits of relevance to this review. The search was conducted in April 2018, and identified studies published between 1997 and 2018, strongly skewed toward 2015 and later.Results: Studies using DL for image segmentation were identified in Brain (n = 2), Head and Neck (n = 3), Lung (n = 6), Abdominal (n = 2), and Pelvic (n = 6) cancers. Use of Deep Learning has also been reported for outcome prediction, such as toxicity modeling (n = 3), treatment response and survival (n = 2), or treatment planning (n = 5).Conclusion: Over the past few years, there has been a significant number of studies assessing the performance of DL techniques in radiation oncology. They demonstrate how DL-based systems can aid clinicians in their daily work, be it by reducing the time required for or the variability in segmentation, or by helping to predict treatment outcomes and toxicities. It still remains to be seen when these techniques will be employed in routine clinical practice.

Introduction: Radiotherapy education can be very different across Europe, despite the publication of the ESTRO core curricula in 2011. The purpose of the current study is to map the different RO European education systems, to report their perceived quality and to understand what could be improved to better teach RO. Methods: An online survey consisting of 30 questions was sent to RO professionals under 40 years of age via email and social media. Clinicians, radiobiologists, physicists and radiation therapists (RTTs) were invited to answer questions regarding (1) demographics data, (2) duration, (3) organization, (4) content, (5) quality and potential improvements of national education programs. Results: Four hundred and sixty three questionnaires were received from 34 European countries. All disciplines were represented: 45% clinicians (n = 210), 29% physicists (n = 135), 24% RTTs (n = 108) and 2% radiobiologists (n = 10). Male and female participants were well-balanced in each speciality, except for radiobiologists (80% males). Median age was 31.5 years old (range 21–40). A large range of the duration of the National RO education programs was observed: median = 9 years (range: 3–15). In half of the surveyed countries the European Credit Transfer System (ECTS), that facilitates mobility for trainees, has been implemented. Participants declared only a minority of countries have implemented the ESTRO Core Curriculum (n = 5). A quarter of participants indicated that their national education program is insufficient. Conclusion: This is the first study to examine the different RO education systems in Europe. Large differences in organization and duration of national education programs have been found, along with perceived quality across Europe within each speciality. These results show the necessity of a discussion on how to move forward in this diversity of education programs and the potential contribution that the ESTRO may fulfil.

Prostate cancer treatment strategies are guided by risk-stratification. This stratification can be difficult in some patients with known comorbidities. New models are needed to guide strategies and determine which patients are at risk of prostate cancer mortality. This article presents a gradient-boosting model to predict the risk of prostate cancer mortality within 10 years after a cancer diagnosis, and to provide an interpretable prediction. This work uses prospective data from the PLCO Cancer Screening and selected patients who were diagnosed with prostate cancer. During follow-up, 8776 patients were diagnosed with prostate cancer. The dataset was randomly split into a training (n = 7021) and testing (n = 1755) dataset. Accuracy was 0.98 (±0.01), and the area under the receiver operating characteristic was 0.80 (±0.04). This model can be used to support informed decision-making in prostate cancer treatment. AI interpretability provides a novel understanding of the predictions to the users.

Technological advances have led to more precise radiation delivery, which has resulted in significant clinical gains. A better understanding of tumoral radiosensitivity is still needed to develop strategies and further personalize radiation treatments. Next-Generation Sequencing (NGS) and system biology have significantly transformed the field of oncology in the last two decades, but have only a few clinical applications in radiation oncology. This review describes the technical aspects and evolutions of NGS and discusses the latest clinical applications of genomics to predict tumoral radiosensitivity.

Introduction: An increasing number of parameters can be considered when making decisions in oncology. Tumor characteristics can also be extracted from imaging through the use of radiomics and add to this wealth of clinical data. Machine learning can encompass these parameters and thus enhance clinical decision as well as radiotherapy workflow.Methods: We performed a description of machine learning applications at each step of treatment by radiotherapy in head and neck cancers. We then performed a systematic review on radiomics and machine learning outcome prediction models in head and neck cancers.Results: Machine Learning has several promising applications in treatment planning with automatic organ at risk delineation improvements and adaptative radiotherapy workflow automation. It may also provide new approaches for Normal Tissue Complication Probability models. Radiomics may provide additional data on tumors for improved machine learning powered predictive models, not only on survival, but also on risk of distant metastasis, in field recurrence, HPV status and extra nodal spread. However, most studies provide preliminary data requiring further validation.Conclusion: Promising perspectives arise from machine learning applications and radiomics based models, yet further data are necessary for their implementation in daily care.

Background The recent development of endoscopic resection for superficial gastrointestinal cancers could justify the need for a dedicated oncological multidisciplinary meeting (MDM). The aim of our study was to evaluate the impact of the dedicated MDM on the management of superficial cancers of the digestive tract. Methods A dedicated MDM was developed at our tertiary referral center. A retrospective review of the MDM conclusions for all patients referred from March 2015 to March 2017 was performed. Outcomes measurements were the outcomes of endoscopic resection, and the concordance rate between the MDM recommendations, European Society of Gastrointestinal Endoscopy (ESGE) guidelines, and final patient management. Results In total, 153 patients with a median age of 69 years were included. Half of the patients had major comorbidities. The mean lesion size was 25 mm, and R0 and curative resection rate were 73.9 % and 56.9 %, respectively. Forty-three patients had an indication for surgery after endoscopic resection. The concordance rate between ESGE guidelines and MDM recommendation was 92.2 %, and 12 patients did not receive the treatment recommended due to comorbidities. Conclusion A MDM dedicated to superficial tumors helped tailor the ESGE guidelines to each patient in order to avoid unnecessary surgery.

The immunogenic cell death (ICD) is defined as a regulated cell death able to induce an adaptive immunity. It depends on different parameters including sufficient antigenicity, adjuvanticity and favorable microenvironment conditions. Radiation therapy (RT), a pillar of modern cancer treatment, is being used in many tumor types in curative, (neo) adjuvant, as well as metastatic settings. The anti-tumor effects of RT have been traditionally attributed to the mitotic cell death resulting from the DNA damages triggered by the release of reactive oxygen species. Recent evidence suggests that RT may also exert its anti-tumor effect by recruiting tumor-specific immunity. RT is able to induce the release of tumor antigens, to act as an immune adjuvant and thus to synergize with the anti-tumor immunity. The advent of new efficient immunotherapeutic agents, such as immune checkpoint inhibitors (ICI), in multiple tumor types sheds new light on the opportunity of combining RT and ICI. Here, we will describe the biological and radiobiological rationale of the RT-induced ICD. We will then focus on the interest to combine RT and ICI, from bench to bedside, and summarize the clinical data existing with this combination. Finally, RT technical adaptations to optimize the ICD induction will be discussed.

Background: Esophagectomy is recommended after endoscopic resection of an early esophageal cancer when pejorative histoprognostic criteria indicate a high risk of lymph node involvement. Our aim was to analyze the clinical outcomes of a non-surgical, organ preserving management in this clinical setting. Patients and Methods: This retrospective study was performed in two tertiary centers from 2015 to 2020. Patients were included if they had histologically complete resection of an early esophageal cancer, with poor differentiation, lymphovascular invasion or deep submucosal invasion. Endoscopic resection was followed by chemoradiotherapy or follow-up in case of surgical contraindications or patient refusal. Outcome measures were disease-free survival (DFS), overall survival (OS), cancer specific survival (CSS) and toxicity of chemoradiotherapy. Results: Forty-one patients (36 with squamous cell carcinoma and 5 with adenocarcinomas) were included. The estimated high risk of lymph node involvement was based on poor differentiation (10/41; 24%), lympho-vascular invasion (11/41; 27%), muscularis mucosa invasion or deep sub-mucosal invasion (38/41; 93%). Thirteen patients (13/41; 32%) were closely monitored, and 28 (28/41; 68%) were treated by chemoradiotherapy or radiotherapy alone. In the close follow-up group, DFS, OS and CSS were 92%, 92% and 100%, respectively vs. 75%, 79% and 96%, respectively in the chemoradiotherapy group at the end of the follow-up. Serious adverse events related to chemoradiotherapy occurred in 10% of the patients. There were no treatment-related deaths. Conclusions: Our study shows that close follow-up may be an alternative to systematic esophagectomy after endoscopic resection of early esophageal cancer with a predicted high risk of lymph node involvement.

The worldwide growth of cancer incidence can be explained in part by changes in the prevalence and distribution of risk factors. There are geographical gaps in the estimates of cancer prevalence, which could be filled with innovative methods. We used deep learning (DL) features extracted from satellite images to predict cancer prevalence at the census tract level in seven cities in the United States. We trained the model using detailed cancer prevalence estimates from 2018 available in the CDC (Center for Disease Control) 500 Cities project. Data from 3500 census tracts covering 14,483,366 inhabitants were included. Features were extracted from 170,210 satellite images with deep learning. This method explained up to 64.37% (median = 43.53%) of the variation of cancer prevalence. Satellite features are highly correlated with individual socioeconomic and health measures that are linked to cancer prevalence (age, smoking and drinking status, and obesity). A higher similarity between two environments is associated with better generalization of the model (p = 1.10–6). This method can be used to accurately estimate cancer prevalence at a high spatial resolution without using surveys at a fraction of the cost.

Leveraging Electronic Health Records (EHR) and Oncology Information Systems (OIS) has great potential to generate hypotheses for cancer treatment, since they directly provide medical data on a large scale. In order to gather a significant amount of patients with a high level of clinical details, multicenter studies are necessary. A challenge in creating high quality Big Data studies involving several treatment centers is the lack of semantic interoperability between data sources. We present the ontology we developed to address this issue.Radiation Oncology anatomical and target volumes were categorized in anatomical and treatment planning classes. International delineation guidelines specific to radiation oncology were used for lymph nodes areas and target volumes. Hierarchical classes were created to generate The Radiation Oncology Structures (ROS) Ontology. The ROS was then applied to the data from our institution.Four hundred and seventeen classes were created with a maximum of 14 children classes (average = 5). The ontology was then converted into a Web Ontology Language (.owl) format and made available online on Bioportal and GitHub under an Apache 2.0 License. We extracted all structures delineated in our department since the opening in 2001. 20,758 structures were exported from our "record-and-verify" system, demonstrating a significant heterogeneity within a single center. All structures were matched to the ROS ontology before integration into our clinical data warehouse (CDW).In this study we describe a new ontology, specific to radiation oncology, that reports all anatomical and treatment planning structures that can be delineated. This ontology will be used to integrate dosimetric data in the Assistance Publique-Hôpitaux de Paris CDW that stores data from 6.5 million patients (as of February 2017).

SBRT is the standard of care for inoperable patients with early-stage lung cancer without lymph node involvement. Excellent local control rates have been reported in a large number of series. However, prescription doses and calculation algorithms vary to a great extent between studies, even if most teams prescribe to the D95 of the PTV. Type A algorithms are known to produce dosimetric discrepancies in heterogeneous tissues such as lungs. This study was performed to present a Monte Carlo (MC) prescription dose for NSCLC adapted to lesion size and location and compare the clinical outcomes of two cohorts of patients treated with a standard prescription dose calculated by a type A algorithm or the proposed MC protocol.Patients were treated from January 2011 to April 2013 with a type B algorithm (MC) prescription with 54 Gy in three fractions for peripheral lesions with a diameter under 30 mm, 60 Gy in 3 fractions for lesions with a diameter over 30 mm, and 55 Gy in five fractions for central lesions. Clinical outcome was compared to a series of 121 patients treated with a type A algorithm (TA) with three fractions of 20 Gy for peripheral lesions and 60 Gy in five fractions for central lesions prescribed to the PTV D95 until January 2011. All treatment plans were recalculated with both algorithms for this study. Spearman's rank correlation coefficient was calculated for GTV and PTV. Local control, overall survival and toxicity were compared between the two groups.205 patients with 214 lesions were included in the study. Among these, 93 lesions were treated with MC and 121 were treated with TA. Overall survival rates were 86% and 94% at one and two years, respectively. Local control rates were 79% and 93% at one and two years respectively. There was no significant difference between the two groups for overall survival (p = 0.785) or local control (p = 0.934). Fifty-six patients (27%) developed grade I lung fibrosis without clinical consequences. GTV size was a prognostic factor for overall survival (HR = 1.026, IC95% [1.01-1.041], p

PURPOSE:Standard treatment for early-stage endometrial cancer involves surgery (when possible) followed by brachytherapy or external-beam radiotherapy (EBRT) for high-risk tumors. EBRT is not without toxicity, meaning that it could be difficult to complete for elderly patients, who typically have decreased reserve and resistance to stressors. PATIENTS AND METHODS:Patients aged 70 and over treated between April 2009 and May 2013 for endometrial cancer and received IMRT (Intensity-Modulated Radiation Therapy) were included in this observational study. IMRT could be performed as adjuvant treatment or as an exclusive treatment for patients not amenable to surgery. The primary endpoints of this study were to assess the feasibility and toxicity of pelvic IMRT in this population. Secondary endpoints were to assess disease-specific survival, overall survival, and local control. Predictors of toxicity were also explored. RESULTS:Forty seven consecutive patients were included in the analysis. Median age at diagnosis was 75 years (range, 70-89 years). Eleven patients were aged 80 years and older. Toxicities were found in thirty four patients (72%) during treatment. Among these, toxicity did not exceed grade 2 for 32 patients (68%). Two patients had a grade 3 toxicity (4%). Overall survival rates were 87% and 83% at 1 and 2 years, respectively. Six patients (12.8%) had a local relapse and nine others (19.1%) had distant relapse. CONCLUSIONS:Pelvic helical IMRT for patients aged 70 and older is feasible with full standard radiation doses, showing that age greater than 70 should not be considered as a reason not to perform optimal treatment.

PURPOSE:Stereotactic body radiation therapy (SBRT) for hepatocellular carcinoma (HCC) has been evaluated in several recent studies. The CyberKnife(®) is an SBRT system that allows for real-time tracking of the tumor. The purpose of this study was to evaluate the prognostic factors for local control and overall survival following this treatment. PATIENTS AND METHODS:75 patients with 96 liver-confined HCC were treated with SBRT at the Oscar Lambret Comprehensive Cancer Center. Fiducials were implanted in the liver before treatment and were used as markers to track the lesion's movement. Treatment response was scored according to RECIST v1.1. Local control and overall survival were calculated using the Kaplan and Meier method. A stepwise multivariate analysis (Cox regression) of prognostic factors was performed for local control and overall survival. RESULTS:There were 67 patients with Child-Turcotte-Pugh (CTP) Class A and eight patients with CTP Class B. Treatment was administered in three sessions. A total dose of 40-45 Gy to the 80% isodose line was delivered. The median follow-up was 10 months (range, 3-49 months). The local control rate was 89.8% at 1 and 2 years. Overall survival was 78.5% and 50.4% at 1 and 2 years, respectively. Toxicity mainly consisted of grade 1 and grade 2 events. Higher alpha-fetoprotein (aFP) levels were associated with less favorable local control (HR=1.001; 95% CI [1.000, 1.002]; p=0.0063). A higher dose was associated with better local control (HR=0.866; 95% CI [0.753, 0.996]; p=0.0441). A Child-Pugh score higher than 5 was associated with worse overall survival (HR= 3.413; 95% CI [1.235, 9.435]; p=0.018). CONCLUSION:SBRT affords good local tumor control and higher overall survival rates than other historical controls (best supportive care or sorafenib). High aFP levels were associated with lesser local control, but a higher treatment dose improved local control.