Search

Abstract Introduction The delineation of organs-at-risk and lymph node areas is a crucial step in radiotherapy, but it is time-consuming and associated with substantial user-dependent variability in contouring. Artificial intelligence (AI) appears to be the solution to facilitate and standardize this work. The objective of this study is to compare eight available AI software programs in terms of technical aspects and accuracy for contouring organs-at-risk and lymph node areas with current international contouring recommendations. Material and methods From January–July 2023, we performed a blinded study of the contour scoring of the organs-at-risk and lymph node areas by eight self-contouring AI programs by 20 radiation oncologists. It was a single-center study conducted in radiation department at the Lorraine Cancer Institute. A qualitative analysis of technical characteristics of the different AI programs was also performed. Three adults (two women and one man) and three children (one girl and two boys) provided six whole-body anonymized CT scans, along with two other adult brain MRI scans. Using a scoring scale from 1 to 3 (best score), radiation oncologists blindly assessed the quality of contouring of organs-at-risk and lymph node areas of all scans and MRI data by the eight AI programs. We have chosen to define the threshold of an average score equal to or greater than 2 to characterize a high-performing AI software, meaning an AI with minimal to moderate corrections but usable in clinical routine. Results For adults CT scans: There were two AI programs for which the overall average quality score (that is, all areas tested for OARs and lymph nodes) was higher than 2.0: Limbus (overall average score = 2.03 (0.16)) and MVision (overall average score = 2.13 (0.19)). If we only consider OARs for adults, only Limbus, Therapanacea, MVision and Radformation have an average score above 2. For children CT scan, MVision was the only program to have a average score higher than 2 with overall average score = 2.07 (0.19). If we only consider OARs for children, only Limbus and MVision have an average score above 2. For brain MRIs: TheraPanacea was the only program with an average score over 2, for both brain delineation (2.75 (0.35)) and OARs (2.09 (0.19)). The comparative analysis of the technical aspects highlights the similarities and differences between the software. There is no difference in between senior radiation oncologist and residents for OARs contouring. Conclusion For adult CT-scan, two AI programs on the market, MVision and Limbus, delineate most OARs and lymph nodes areas that are useful in clinical routine. For children CT-scan, only one IA, MVision, program is efficient. For adult brain MRI, Therapancea,only one AI program is efficient. Trial registration: CNIL-MR0004 Number HDH434.

Background and purpose: Magnetic resonance imaging (MRI)-to-computed tomography (CT) synthesis is essential in MRI-only radiotherapy workflows, particularly through deep learning techniques known for their accuracy. However, current supervised methods are limited to specific center’s learnings and depend on registration precision. The aim of this study was to evaluate the accuracy of unsupervised and supervised approaches in the context of prostate MRI-to-CT generation for radiotherapy dose calculation. Methods: CT/MRI image pairs from 99 prostate cancer patients across three different centers were used. A comparison between supervised and unsupervised conditional Generative Adversarial Networks (cGAN) was conducted. Unsupervised training incorporates a style transfer method with. Content and Style Representation for Enhanced Perceptual synthesis (CREPs) loss. For dose evaluation, the photon prescription dose was 60 Gy delivered in volumetric modulated arc therapy (VMAT). Imaging endpoint for sCT evaluation was Mean Absolute Error (MAE). Dosimetric endpoints included absolute dose differences and gamma analysis between CT and sCT dose calculations. Results: The unsupervised paired network exhibited the highest accuracy for the body with a MAE at 33.6 HU, the highest MAE was 45.5 HU obtained with unsupervised unpaired learning. All architectures provided clinically acceptable results for dose calculation with gamma pass rates above 94 % (1 % 1 mm 10 %). Conclusions: This study shows that multicenter data can produce accurate sCTs via unsupervised learning, eliminating CT-MRI registration. The sCTs not only matched HU values but also enabled precise dose calculations, suggesting their potential for wider use in MRI-only radiotherapy workflows.

Introduction: The delineation of organs-at-risk and lymph node areas is a crucial step in radiotherapy, but it is time-consuming and associated with substantial user-dependent variability in contouring. Artificial intelligence (AI) appears to be the solution to facilitate and standardize this work. The objective of this study is to compare eight available AI software programs in terms of technical aspects and accuracy for contouring organs-at-risk and lymph node areas with current international contouring recommendations. Material and methods: From January–July 2023, we performed a blinded study of the contour scoring of the organs-at-risk and lymph node areas by eight self-contouring AI programs by 20 radiation oncologists. It was a single-center study conducted in radiation department at the Lorraine Cancer Institute. A qualitative analysis of technical characteristics of the different AI programs was also performed. Three adults (two women and one man) and three children (one girl and two boys) provided six whole-body anonymized CT scans, along with two other adult brain MRI scans. Using a scoring scale from 1 to 3 (best score), radiation oncologists blindly assessed the quality of contouring of organs-at-risk and lymph node areas of all scans and MRI data by the eight AI programs. We have chosen to define the threshold of an average score equal to or greater than 2 to characterize a high-performing AI software, meaning an AI with minimal to moderate corrections but usable in clinical routine. Results: For adults CT scans: There were two AI programs for which the overall average quality score (that is, all areas tested for OARs and lymph nodes) was higher than 2.0: Limbus (overall average score = 2.03 (0.16)) and MVision (overall average score = 2.13 (0.19)). If we only consider OARs for adults, only Limbus, Therapanacea, MVision and Radformation have an average score above 2. For children CT scan, MVision was the only program to have a average score higher than 2 with overall average score = 2.07 (0.19). If we only consider OARs for children, only Limbus and MVision have an average score above 2. For brain MRIs: TheraPanacea was the only program with an average score over 2, for both brain delineation (2.75 (0.35)) and OARs (2.09 (0.19)). The comparative analysis of the technical aspects highlights the similarities and differences between the software. There is no difference in between senior radiation oncologist and residents for OARs contouring. Conclusion: For adult CT-scan, two AI programs on the market, MVision and Limbus, delineate most OARs and lymph nodes areas that are useful in clinical routine. For children CT-scan, only one IA, MVision, program is efficient. For adult brain MRI, Therapancea,only one AI program is efficient. Trial registration: CNIL-MR0004 Number HDH434. [ABSTRACT FROM AUTHOR]

Summary: We aim to identify genetic markers associated with idiopathic hypersomnia, a disabling orphan central nervous system disorder of hypersomnolence that is still poorly understood. In our study, DNA was extracted from 79 unrelated patients diagnosed with idiopathic hypersomnia with long sleep time at the National Reference Center for Narcolepsy‐France according to very stringent diagnostic criteria. Whole exome sequencing on the first 30 patients with idiopathic hypersomnia (25 females and 5 males) allowed the single nucleotide variants to be compared with a control population of 574 healthy subjects from the French Exome project database. We focused on the identification of genetic variants among 182 genes related to the regulation of sleep and circadian rhythm. Candidate variants obtained by exome sequencing analysis were then validated in a second sample of 49 patients with idiopathic hypersomnia (37 females and 12 males). Our study characterised seven variants from six genes significantly associated with idiopathic hypersomnia compared with controls. A targeted sequencing analysis of these seven variants on 49 other patients with idiopathic hypersomnia confirmed the relative over‐representation of the A➔C variant of rs2859390, located in a potential splicing‐site of PER3 gene. Our findings support a genetic predisposition and identify pathways involved in the pathogeny of idiopathic hypersomnia. A variant of the PER3 gene may predispose to idiopathic hypersomnia with long sleep time. [ABSTRACT FROM AUTHOR]

Summary Since the first description of narcolepsy at the end of the 19th Century, great progress has been made. The disease is nowadays distinguished as narcolepsy type 1 and type 2. In the 1960s, the discovery of rapid eye movement sleep at sleep onset led to improved understanding of core sleep‐related disease symptoms of the disease (excessive daytime sleepiness with early occurrence of rapid eye movement sleep, sleep‐related hallucinations, sleep paralysis, rapid eye movement parasomnia), as possible dysregulation of rapid eye movement sleep, and cataplexy resembling an intrusion of rapid eye movement atonia during wake. The relevance of non‐sleep‐related symptoms, such as obesity, precocious puberty, psychiatric and cardiovascular morbidities, has subsequently been recognized. The diagnostic tools have been improved, but sleep‐onset rapid eye movement periods on polysomnography and Multiple Sleep Latency Test remain key criteria. The pathogenic mechanisms of narcolepsy type 1 have been partly elucidated after the discovery of strong HLA class II association and orexin/hypocretin deficiency, a neurotransmitter that is involved in altered rapid eye movement sleep regulation. Conversely, the causes of narcolepsy type 2, where cataplexy and orexin deficiency are absent, remain unknown. Symptomatic medications to treat patients with narcolepsy have been developed, and management has been codified with guidelines, until the recent promising orexin‐receptor agonists. The present review retraces the steps of the research on narcolepsy that linked the features of the disease with rapid eye movement sleep abnormality, and those that do not appear associated with rapid eye movement sleep. [ABSTRACT FROM AUTHOR]

The article discusses the pharmacological management of narcolepsy in children and adolescents. It highlights the need for safe and effective treatments for young people with narcolepsy and mentions the European guidelines on the management of narcolepsy in adults and children. The article focuses on the efficacy and safety of pitolisant, a drug that has been approved by the European Medicine Agency for the treatment of narcolepsy in children and adolescents. It mentions a clinical trial that showed significant improvements in narcolepsy symptoms with pitolisant compared to a placebo. The article concludes by emphasizing the importance of early treatment for narcolepsy to prevent long-term consequences. [Extracted from the article]

Summary: Sleep disturbances after ischaemic stroke include alterations of sleep architecture, obstructive sleep apnea, restless legs syndrome, daytime sleepiness and insomnia. Our aim was to explore their impacts on functional outcomes at month 3 after stroke, and to assess the benefit of continuous positive airway pressure in patients with severe obstructive sleep apnea. Ninety patients with supra‐tentorial ischaemic stroke underwent clinical screening for sleep disorders and polysomnography at day 15 ± 4 after stroke in a multisite study. Patients with severe obstructive apnea (apnea–hypopnea index ≥ 30 per hr) were randomized into two groups: continuous positive airway pressure‐treated and sham (1:1 ratio). Functional independence was assessed with the Barthel Index at month 3 after stroke in function of apnea–hypopnea index severity and treatment group. Secondary objectives were disability (modified Rankin score) and National Institute of Health Stroke Scale according to apnea–hypopnea index. Sixty‐one patients (71.8 years, 42.6% men) completed the study: 51 (83.6%) had obstructive apnea (21.3% severe apnea), 10 (16.7%) daytime sleepiness, 13 (24.1%) insomnia, 3 (5.7%) depression, and 20 (34.5%) restless legs syndrome. Barthel Index, modified Rankin score and Stroke Scale were similar at baseline and 3 months post‐stroke in the different obstructive sleep apnea groups. Changes at 3 months in those three scores were similar in continuous positive airway pressure versus sham‐continuous positive airway pressure patients. In patients with worse clinical outcomes at month 3, mean nocturnal oxygen saturation was lower whereas there was no association with apnea–hypopnea index. Poorer outcomes at 3 months were also associated with insomnia, restless legs syndrome, depressive symptoms, and decreased total sleep time and rapid eye movement sleep. [ABSTRACT FROM AUTHOR]

Summary The aim of the present study was to examine gender and age‐specific effects on subjective daytime sleepiness (as measured by the Epworth Sleepiness Scale), body weight and eating behaviour in patients with central disorders of hypersomnolence. Based on the European Narcolepsy Network database, we compared 1035 patients with narcolepsy type I and 505 patients with other central disorders of hypersomnolence (“narcoleptic borderland”), including narcolepsy type II (N = 308) and idiopathic hypersomnia (N = 174), using logistic regression and general linear models. In the entire study population, the Epworth Sleepiness Scale was higher in women (N = 735, mean age = 30 years, mean Epworth Sleepiness Scale = 16.6 ± SD 3.9) than in men (N = 805, mean age = 32 years, mean Epworth Sleepiness Scale = 15.8 ± SD 4.4). In women with narcolepsy type I (N = 475), both Epworth Sleepiness Scale and body mass index increased in parallel with age. In women of the narcoleptic borderland (N = 260), the Epworth Sleepiness Scale markedly peaked in their early 30s, while body mass index only started to rise at that age. This rise in body mass index following the Epworth Sleepiness Scale peak cannot be explained by sleepiness‐induced uncontrolled eating, as self‐reported uncontrolled eating was negatively associated with the Epworth Sleepiness Scale in this group. We propose that the narcoleptic borderland harbours a unique cluster of women in their fertile years with an unexplored aetiology requiring further investigation towards tailored interventions. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of the study was to evaluate the dosimetric impact of sexual-sparing radiotherapy for prostate cancer, with magnetic resonance-only treatment planning., Material and Methods: Fifteen consecutive patients receiving prostate cancer radiotherapy were selected. A synthetic CT was generated with a deep learning method from each T2-weighted MRI performed at the time of treatment planning. For each patient, two plans were performed: standard treatment planning and sexual-structures sparing treatment planning. The treatment plan was designed to deliver a dose of 78Gy to the prostate and 50Gy to the seminal vesicles in 2Gy daily fractions, using volumetric arc therapy. Dose-volume histograms were computed to compare treatment plans., Results: All plans fulfilled dosimetric objectives and were equivalent regarding planning target volume coverage. The doses delivered to both rectum, bladder, and femoral heads were similar between plans (P=0.20). Sexual-sparing plans enabled to decrease all dosimetric parameters on sexual organs-at-risk. The mean penile bulb dose in sexual-sparing plans was significantly reduced (21.1Gy±20.7 versus 13.4Gy±14.0, P<0.01), however with large variability observed between individuals. The mean dose delivered to the corpora cavernosa was also significantly reduced within sexual-sparing plans (13.1Gy±16.7 versus 8.6Gy±10.4, P<0.01). A significant reduction was also observed in the highest doses delivered to internal pudendal arteries (D10%: 48.4Gy±8.3 versus 33.1Gy±4.6, P<0.05; D5%: 52.0Gy±8.7 versus 36.8Gy±5.5, P<0.05)., Conclusion: Sparing of sexual structures appears feasible, without compromising neither planning target volume coverage nor doses delivered to non-sexual organs at risk. The clinical significance of this dose-reduction requires prospective evaluation., (Copyright © 2024 Société française de radiothérapie oncologique (SFRO). Published by Elsevier Masson SAS. All rights reserved.)