Cardiac stereotactic radiation therapy for refractory ventricular arrhythmias in patients with left ventricular assist devices.

Left ventricular assist device (LVAD) implantation is an established treatment for patients with advanced heart failure refractory to medical therapy. However, the incidence of ventricular arrhythmias (VAs) is high in this population, both in the acute and delayed phases after implantation. About one-third of patients implanted with an LVAD will experience sustained VAs, predisposing these patients to worse outcomes and complicating patient management. The combination of pre-existing myocardial substrate and complex electrical remodeling after LVAD implantation account for the high incidence of VAs observed in this population. LVAD patients presenting VAs refractory to antiarrhythmic therapy and catheter ablation procedures are not rare. In such patients, treatment options are extremely limited. Stereotactic body radiation therapy (SBRT) is a technique that delivers precise and high doses of radiation to highly defined targets, reducing exposure to adjacent normal tissue. Cardiac SBRT has recently emerged as a promising alternative with a growing number of case series reporting the effectiveness of the technique in reducing the VA burden in patients with arrhythmias refractory to conventional therapies. The safety profile of cardiac SBRT also appears favorable, even though the current clinical experience remains limited. The use of cardiac SBRT for the treatment of refractory VAs in patients implanted with an LVAD are even more scarce. This review summarizes the clinical experience of cardiac SBRT in LVAD patients and describes technical considerations related to the implementation of the SBRT procedure in the presence of an LVAD.

Contour-guided deep learning based deformable image registration for dose monitoring during CBCT-guided radiotherapy of prostate cancer.

PURPOSE: To evaluate deep learning (DL)-based deformable image registration (DIR) for dose accumulation during radiotherapy of prostate cancer patients. METHODS AND MATERIALS: Data including 341 CBCTs (209 daily, 132 weekly) and 23 planning CTs from 23 patients was retrospectively analyzed. Anatomical deformation during treatment was estimated using free-form deformation (FFD) method from Elastix and DL-based VoxelMorph approaches. The VoxelMorph method was investigated using anatomical scans (VMorph_Sc) or label images (VMorph_Msk), or the combination of both (VMorph_Sc_Msk). Accumulated doses were compared with the planning dose. RESULTS: The DSC ranges, averaged for prostate, rectum and bladder, were 0.60-0.71, 0.67-0.79, 0.93-0.98, and 0.89-0.96 for the FFD, VMorph_Sc, VMorph_Msk, and VMorph_Sc_Msk methods, respectively. When including both anatomical and label images, VoxelMorph estimated more complex deformations resulting in heterogeneous determinant of Jacobian and higher percentage of deformation vector field (DVF) folding (up to a mean value of 1.90% in the prostate). Large differences were observed between DL-based methods regarding estimation of the accumulated dose, showing systematic overdosage and underdosage of the bladder and rectum, respectively. The difference between planned mean dose and accumulated mean dose with VMorph_Sc_Msk reached a median value of +6.3 Gy for the bladder and -5.1 Gy for the rectum. CONCLUSION: The estimation of the deformations using DL-based approach is feasible for male pelvic anatomy but requires the inclusion of anatomical contours to improve organ correspondence. High variability in the estimation of the accumulated dose depending on the deformable strategy suggests further investigation of DL-based techniques before clinical deployment.

Extraction of Premature Newborns' Spontaneous Cries in the Real Context of Neonatal Intensive Care Units.

Cry analysis is an important tool to evaluate the development of preterm infants. However, the context of Neonatal Intensive Care Units is challenging, since a wide variety of sounds can occur (e.g., alarms and adult voices). In this paper, a method to extract cries is proposed. It is based on an initial segmentation between silence and sound events, followed by feature extraction on the resulting audio segments and a cry and non-cry classification. A database of 198 cry events coming from 21 newborns and 439 non-cry events was created. Then, a set of features-including Mel-Frequency Cepstral Coefficients-issued from principal component analysis, was computed to describe each audio segment. For the first time in cry analysis, noise was handled using harmonic plus noise analysis. Several machine learning models have been compared. The K-Nearest Neighbours approach showed the best results with a precision of 92.9%. To test the approach in a monitoring application, 412 h of recordings were automatically processed. The cries automatically selected were replayed and a precision of 92.2% was obtained. The impact of errors on the fundamental frequency characterisation was also studied. Results show that despite a difficult context, automatic cry extraction for non-invasive monitoring of vocal development of preterm infants is achievable.

Deep Learning-Based Segmentation of Head and Neck Organs-at-Risk with Clinical Partially Labeled Data.

Radiotherapy is one of the main treatments for localized head and neck (HN) cancer. To design a personalized treatment with reduced radio-induced toxicity, accurate delineation of organs at risk (OAR) is a crucial step. Manual delineation is time- and labor-consuming, as well as observer-dependent. Deep learning (DL) based segmentation has proven to overcome some of these limitations, but requires large databases of homogeneously contoured image sets for robust training. However, these are not easily obtained from the standard clinical protocols as the OARs delineated may vary depending on the patient's tumor site and specific treatment plan. This results in incomplete or partially labeled data. This paper presents a solution to train a robust DL-based automated segmentation tool exploiting a clinical partially labeled dataset. We propose a two-step workflow for OAR segmentation: first, we developed longitudinal OAR-specific 3D segmentation models for pseudo-contour generation, completing the missing contours for some patients; with all OAR available, we trained a multi-class 3D convolutional neural network (nnU-Net) for final OAR segmentation. Results obtained in 44 independent datasets showed superior performance of the proposed methodology for the segmentation of fifteen OARs, with an average Dice score coefficient and surface Dice similarity coefficient of 80.59% and 88.74%. We demonstrated that the model can be straightforwardly integrated into the clinical workflow for standard and adaptive radiotherapy.

Cophylogenetic patterns in algal symbionts correlate with repeated symbiont switches during diversification and geographic expansion of lichen-forming fungi in the genus Sticta (Ascomycota, Peltigeraceae).

Species in the fungal genus Sticta form symbiotic associations primarily with either green algae or cyanobacteria, but tripartite associations or photosymbiodemes involving both types of photobionts occur in some species. Sticta is known to associate with green algae in the genus Symbiochloris. However, previous studies have shown that algae from other genera, such as Heveochlorella, may also be suitable partners for Sticta. We examined the diversity of green algal partners in the genus Sticta and assessed the patterns of association between the host fungus and its algal symbiont. We used multi-locus sequence data from multiple individuals collected in Australia, Cuba, Madagascar, Mauritius, New Zealand, Reunion and South America to infer phylogenies for fungal and algal partners and performed tests of congruence to assess coevolution between the partners. In addition, event-based methods were implemented to examine which cophylogenetic processes have led to the observed association patterns in Sticta and its green algal symbionts. Our results show that in addition to Symbiochloris, Sticta associates with green algae from the genera Chloroidium, Coccomyxa, Elliptochloris and Heveochlorella, the latter being the most common algal symbiont associated with Sticta in this study. Geography plays a strong role in shaping fungal-algal association patterns in Sticta as mycobionts associate with different algal lineages in different geographic locations. While fungal and algal phylogenies were mostly congruent, event-based methods did not find any evidence for cospeciation between the partners. Instead, the association patterns observed in Sticta and associated algae, were largely explained by other cophylogenetic events such as host-switches, losses of symbiont and failure of the symbiont to diverge with its host. Our results also show that tripartite associations with green algae evolved multiple times in Sticta.

Les enjeux de l'autotest VIH en officine perçus par des pharmaciens et des populations concernées en France.

OBJECTIVE: The HIV self-test has been on sale in France since September 2015. What is the point of view of pharmacists and key populations with regard to accessing self-tests in community pharmacies ? METHOD: One year after the HIV self-test came onto the market, the points of view of pharmacists and key populations with regard to HIV were collected during six focus groups: the pharmacists themselves; people who had already used HIV self-tests; potential users from two key populations with regard to HIV: migrants from sub-Saharan Africa and men who have sex with men; potential users from populations with active sex lives but not particularly vulnerable with regard to HIV: young adults (<25 years of age), multi-partner heterosexual adults. RESULTS: The HIV self-test in community pharmacies is perceived by all participants as a significant step forward for accessing screening for HIV. However, issues around discretion and anonymity were seen to create significant tensions with regard to accessing the test itself, but also the information necessary to use it correctly both at a technical level and above all concerning how to interpret test results. CONCLUSION: Although the present study underlines the role of the pharmacist as a significant public health actor in the dispensation of the self-test, the sales price and questions of anonymity are seen as major obstacles. Priority actions include renewing communication campaigns concerning the existence and the use of the product for the upcoming generations of young people but also specific campaigns targeting more vulnerable populations.

[Pharmacists' and key populations' points of view on HIV self-test dispensation in pharmacies in France] / Les enjeux de l'autotest VIH en officine perçus par des pharmaciens et des populations concernées en France.

OBJECTIVE: The HIV self-test has been on sale in France since September 2015. What is the point of view of pharmacists and key populations with regard to accessing self-tests in community pharmacies ? METHOD: One year after the HIV self-test came onto the market, the points of view of pharmacists and key populations with regard to HIV were collected during six focus groups: the pharmacists themselves; people who had already used HIV self-tests; potential users from two key populations with regard to HIV: migrants from sub-Saharan Africa and men who have sex with men; potential users from populations with active sex lives but not particularly vulnerable with regard to HIV: young adults (<25 years of age), multi-partner heterosexual adults. RESULTS: The HIV self-test in community pharmacies is perceived by all participants as a significant step forward for accessing screening for HIV. However, issues around discretion and anonymity were seen to create significant tensions with regard to accessing the test itself, but also the information necessary to use it correctly both at a technical level and above all concerning how to interpret test results. CONCLUSION: Although the present study underlines the role of the pharmacist as a significant public health actor in the dispensation of the self-test, the sales price and questions of anonymity are seen as major obstacles. Priority actions include renewing communication campaigns concerning the existence and the use of the product for the upcoming generations of young people but also specific campaigns targeting more vulnerable populations.

[Pharmacists' and key populations' points of view on HIV self-test dispensation in pharmacies in France]. / Les enjeux de l'autotest VIH en officine perçus par des pharmaciens et des populations concernées en France.

OBJECTIVE: The HIV self-test has been on sale in France since September 2015. What is the point of view of pharmacists and key populations with regard to accessing self-tests in community pharmacies ? METHOD: One year after the HIV self-test came onto the market, the points of view of pharmacists and key populations with regard to HIV were collected during six focus groups: the pharmacists themselves; people who had already used HIV self-tests; potential users from two key populations with regard to HIV: migrants from sub-Saharan Africa and men who have sex with men; potential users from populations with active sex lives but not particularly vulnerable with regard to HIV: young adults (<25 years of age), multi-partner heterosexual adults. RESULTS: The HIV self-test in community pharmacies is perceived by all participants as a significant step forward for accessing screening for HIV. However, issues around discretion and anonymity were seen to create significant tensions with regard to accessing the test itself, but also the information necessary to use it correctly both at a technical level and above all concerning how to interpret test results. CONCLUSION: Although the present study underlines the role of the pharmacist as a significant public health actor in the dispensation of the self-test, the sales price and questions of anonymity are seen as major obstacles. Priority actions include renewing communication campaigns concerning the existence and the use of the product for the upcoming generations of young people but also specific campaigns targeting more vulnerable populations.

Deformable image registration for radiation therapy: principle, methods, applications and evaluation.

Background: Deformable image registration (DIR) is increasingly used in the field of radiation therapy (RT) to account for anatomical deformations. The aims of this paper are to describe the main applications of DIR in RT and discuss current DIR evaluation methods. Methods: Articles on DIR published from January 2000 to October 2018 were extracted from PubMed and Science Direct. Our search was restricted to articles that report data obtained from humans, were written in English, and address DIR methods for RT. A total of 207 articles were selected from among 2506 identified in the search process. Results: At planning, DIR is used for organ delineation using atlas-based segmentation, deformation-based planning target volume definition, functional planning and magnetic resonance imaging-based dose calculation. In image-guided RT, DIR is used for contour propagation and dose calculation on per-treatment imaging. DIR is also used to determine the accumulated dose from fraction to fraction in external beam RT and brachytherapy, both for dose reporting and adaptive RT. In the case of re-irradiation, DIR can be used to estimate the cumulated dose of the two irradiations. Finally, DIR can be used to predict toxicity in voxel-wise population analysis. However, the evaluation of DIR remains an open issue, especially when dealing with complex cases such as the disappearance of matter. To quantify DIR uncertainties, most evaluation methods are limited to geometry-based metrics. Software companies have now integrated DIR tools into treatment planning systems for clinical use, such as contour propagation and fraction dose accumulation. Conclusions: DIR is increasingly important in RT applications, from planning to toxicity prediction. DIR is routinely used to reduce the workload of contour propagation. However, its use for complex dosimetric applications must be carefully evaluated by combining quantitative and qualitative analyses.

Cardiac pacing challenge in Sub-Saharan Africa environnement: experience of the Cardiology Department of Teaching Hospital Aristide Le Dantec in Dakar.

BACKGROUND: Cardiac pacing is a growing activity in Sub-Saharan Africa. There is little data on the characteristics of this interventional treatment in our regions. The goal was to evaluate the results of cardiac pacing in a referral service in sub-Saharan Africa. METHODS: We carried out a twelve-year retrospective study (from January 1st, 2004 to December 31st, 2015) in the Cardiology Department of Aristide Le Dantec University Hospital. This work included all patients who received definitive cardiac pacing during the study period and followed up in the service. RESULTS: In total we included 606 patients. There was a growing trend in activity with a peak in 2015 (17%). The average age was 70.6 ± 12.03 years. Some patients (15.4%) came from the subregion. The patients were mostly of medium socio-economic level (53%); 14% were of low socio-economic level. Patients were symptomatic in 85% of cases (37.4% syncope). The indications were dominated by complete atrioventricular block (81.5%); sinus dysfunction accounted for 1.9% of them. A temporary pacemaker was used in 60% of cases for an average duration of 5.1 ± 6.3 days. Antibiotics, local anesthesia and analgesics were used in all cases. Implanted pacemakers were single chamber in 56% of cases and double chamber in 44% of cases. In 39 patients (6.4%), the pacemaker was a « re-used ¼ one. The atrial leads were most often placed in a lateral position (94.5%). The ventricular ones were predominantly tined (95.7%) and more often located at the apical level. Complications were noted in 24 patients (3.9%), dominated by devices externalizations and infections, which together accounted for 2.7% of cases. The number of people in the cathlab was significantly higher and the duration of the temporary pacemaker was longer for patients who had a complication. There was no significant difference depending on the type of pacemaker used (new or reused). Seven (7) in hospital death cases were reported. CONCLUSION: Cardiac pacing is a growing activity in Dakar.

High diversity, high insular endemism and recent origin in the lichen genus Sticta (lichenized Ascomycota, Peltigerales) in Madagascar and the Mascarenes.

Lichen biodiversity and its generative evolutionary processes are practically unknown in the MIOI (Madagascar and Indian Ocean Islands) biodiversity hotspot. We sought to test the hypothesis that lichenized fungi in this region have undergone a rapid radiation, following a single colonization event, giving rise to narrow endemics, as is characteristic of other lineages of plants. We extensively sampled specimens of the lichen genus Sticta in the Mascarene archipelago (mainly Réunion) and in Madagascar, mainly in the northern range (Amber Mt and Marojejy Mt) and produced the fungal ITS barcode sequence for 148 thalli. We further produced a four-loci data matrix for 68 of them, representing the diversity and geographical distribution of ITS haplotypes. We reconstructed the phylogenetic relationships within this group, established species boundaries with morphological context, and estimated the date of the most recent common ancestor. Our inferences resolve a robust clade comprising 31 endemic species of Sticta that arose from the diversification following a single recent (c. 11 Mya) colonization event. All but three species have a very restricted range, endemic to either the Mascarene archipelago or a single massif in Madagascar. The first genus of lichens to be studied with molecular data in this region underwent a recent radiation, exhibits micro-endemism, and thus exemplifies the biodiversity characteristics found in other taxa in Madagascar and the Mascarenes.

Marfan syndrome and cardiovascular complications: results of a family investigation.

BACKGROUND: Cardiovascular complications in Marfan syndrome (MFS) make all its seriousness. Taking as a basis the Ghent criteria, we conducted a family screening from an index case. The objective was to describe the clinical characteristics of MFS anomalies and to detect cardiovascular complications in our patients. CASE PRESENTATION: Six subjects were evaluated. Patients had to be in the same uterine siblings of the index case or be a descendant. The objective was to search for MFS based on the diagnostic criteria of Ghent and, subsequently, detecting cardiovascular damage. The average age was 24 years. The examination revealed three cases of sudden death in a context of chest pain. Five subjects had systemic involvement with a score ≥ 7 that allowed to the diagnosis of MFS. Two patients had simultaneously ectopia lentis and myopia. In terms of cardiovascular damage, there were three cases of dilatation of the aortic root, two cases of aortic dissection of Stanford's type A with severe aortic regurgitation in one case and moderate in the other. There were three patients with moderate mitral regurgitation with a case by valve prolapse. CONCLUSION: The family screening is crucial in Marfan syndrome. It revealed serious cardiovascular complications including sudden death and aortic dissection.

Knowledge, opinions and practices of French general practitioners in the assessment of caries risk: results of a national survey.

OBJECTIVES: The objective of this study was to describe the knowledge, opinions and practices of French general dental practitioners with respect to caries risk assessment (CRA) through the use of a national questionnaire survey. MATERIALS AND METHODS: A postal questionnaire survey was applied to a simple random sample of dentists (n = 2000) in France. Descriptive and logistic regression analyses were performed. RESULTS: The response rate was 34.7 %. Of the respondents, 38.4 % reported that CRA was not part of their routine practice. Among those who claimed to use CRA only 4.5 % did so using a specific evaluation form. Responses showed that there is great variation among respondents with respect to the importance given to different factors to be considered for the development of a treatment plan in adults. Moreover, 32.3 % of respondents reported no regular scheduling of preventive care based on the caries risk of their patients. Nearly 12 % of respondents admitted they did not know exactly what minimal intervention in caries management involved. The results also showed that socio-demographic characteristics of the practitioner influence the use of CRA and other practice patterns. CONCLUSIONS: CRA has not widely entered clinical practice in France. CLINICAL RELEVANCE: This study, the first of its nature in France, shows the need to develop the use of CRA in daily dental practice in France.

Superior vena cava syndrome revealing a Behçet's disease.

INTRODUCTION: Behçet's disease (BD) is a rare vasculitis in sub-Saharan Africa. Vascular thrombosis, especially venous, is common in this condition and also constitutes a basic diagnostic criterion. Its affection of the superior vena cava is rather rare with only a few cases described in the literature. CASE REPORT: A 42-year-old male patient was seen at consultation presenting with a pulsatile, warm and slightly painful right latero-cervical swelling extending to the supraclavicular fossa with the presence of collateral venous circulation for three weeks prior to presentation associated with a mild headache. There were oral and genital ulcerations and erythematous skin lesions associated with a history of inflammatory recurrent arthralgia. Chest computed tomo-angiography showed cruoric internal jugular vein thrombosis extending to the superior vena cava with significant venous collateral circulation. The patient was treated with prednisolone (1 mg/kg/day) and colchicine (2 mg/day), as well as anticoagulation with heparin and vitamin K antagonist (Acenocoumarol) with regular INR monitoring. Clinical evolution was favorable during hospitalization, with residual discrete right supraclavicular swelling. There was no bleeding associated with anticoagulants use. CONCLUSION: The case stresses the importance of maintaining a high degree of suspicion for Behçet's disease in all cases of venous thrombosis.

Multimodal fusion workflow for target delineation in cardiac radioablation of ventricular tachycardia.

BACKGROUND: Cardiac radioablation (CR) is an innovative treatment to ablate cardiac arrythmia sources by radiation therapy. CR target delineation is a challenging task requiring the exploitation of highly different imaging modalities, including cardiac electro-anatomical mapping (EAM). PURPOSE: In this work, a data integration process is proposed to alleviate the tediousness of CR target delineation by generating a fused representation of the heart, including all the information of interest resulting from the analysis and registration of electro-anatomical data, PET scan and planning computed tomography (CT) scan. The proposed process was evaluated by cardiologists during delineation trials. METHODS: The data processing pipeline was composed of the following steps. The cardiac structures of interest were segmented from cardiac CT scans using a deep learning method. The EAM data was registered to the cardiac CT scan using a point cloud based registration method. The PET scan was registered using rigid image registration. The EAM and PET information, as well as the myocardium thickness, were projected on the surface of the 3D mesh of the left ventricle. The target was identified by delineating a path on this surface that was further projected to the thickness of the myocardium to create the target volume. This process was evaluated by comparison with a standard slice-by-slice delineation with mental EAM registration. Four cardiologists delineated targets for three patients using both methods. The variability of target volumes, and the ease of use of the proposed method, were evaluated. RESULTS: All cardiologists reported being more confident and efficient using the proposed method. The inter-clinician variability in delineated target volume was systematically lower with the proposed method (average dice score of 0.62 vs. 0.32 with a classical method). Delineation times were also improved. CONCLUSIONS: A data integration process was proposed and evaluated to fuse images of interest for CR target delineation. It effectively reduces the tediousness of CR target delineation, while improving inter-clinician agreement on target volumes. This study is still to be confirmed by including more clinicians and patient data to the experiments.

One-year mortality and causes of death after stereotactic radiation therapy for refractory ventricular arrhythmias: A systematic review and pooled analysis.

Patients treated with cardiac stereotactic body radiation therapy (radioablation) for refractory ventricular arrhythmias are patients with advanced structural heart disease and significant comorbidities. However, data regarding 1-year mortality after the procedure are scarce. This systematic review and pooled analysis aimed at determining 1-year mortality after cardiac radioablation for refractory ventricular arrhythmias and investigating leading causes of death in this population. MEDLINE/EMBASE databases were searched up to January 2023 for studies including patients undergoing cardiac radioablation for the treatment of refractory ventricular arrhythmias. Quality of included trials was assessed using the NIH Tool for Case Series Studies (PROSPERO CRD42022379713). A total of 1,151 references were retrieved and evaluated for relevance. Data were extracted from 16 studies, with a total of 157 patients undergoing cardiac radioablation for refractory ventricular arrhythmias. Pooled 1-year mortality was 32 % (95 %CI: 23-41), with almost half of the deaths occurring within three months after treatment. Among the 157 patients, 46 died within the year following cardiac radioablation. Worsening heart failure appeared to be the leading cause of death (52 %), although non-cardiac mortality remained substantial (41 %) in this population. Age≥70yo was associated with a significantly higher 12-month all-cause mortality (p<0.022). Neither target volume size nor radiotherapy device appeared to be associated with 1-year mortality (p = 0.465 and p = 0.199, respectively). About one-third of patients undergoing cardiac stereotactic body radiation therapy for refractory ventricular arrhythmias die within the first year after the procedure. Worsening heart failure appears to be the leading cause of death in this population.

Impact of MLC leaf width on volumetric-modulated arc therapy planning for head and neck cancers.

This dosimetric study investigated the impact of multileaf collimators (MLC) leaf width in volumetric-modulated arc therapy (VMAT) for head and neck cancers (HNC), either with a "standard" simultaneously integrated boost technique (S-SIB) or with a "dose painting" SIB technique (DP-SIB). HNC patients were planned either with an S-SIB comprising three dose levels, from 56 to 70 Gy (16 patients), or with a DP-SIB comprising five dose levels, from 56 to 84 Gy (8 patients), in 35 fractions. Two VMAT plans were calculated for each SIB technique using two Elekta MLCs: MLCi2 with 10 mm leaf width and Beam Modulator (BM) with 4 mm leaf width. Dose distributions were evaluated by comparing doses on PTVs, main OARs, and healthy tissue, and by comparing conformation indexes. Treatment efficiencies were evaluated by comparing the number of monitor units and the number of needed arcs. Comparisons of the two MLCs depending on the two SIB techniques showed: i) Regarding PTVs: Dmean and D2% on lower doses PTV decreased respectively by 0.5 Gy (p = 0.01) and 0.9 Gy (p = 0.01) with BM than with MLCi2 for S-SIB; no significant difference was found for DP-SIB;ii) Regarding OARs: for spinal cord and brainstem, D2% decreased respectively by 1.2 Gy (p = 0.03) and 4.2 Gy (p = 0.04) with BM than with MLCi2 for S-SIB; for controlateral parotid, D50% decreased by 1.5 Gy (p = 0.01) with BM than with MLCi2 for S-SIB; iii) Regarding treatment efficiency: the number of monitor units was 44% (p = 0.00) and 51% (p = 0.01) higher with BM for S-SIB and DP-SIB, respectively. Two arcs were more frequently needed with BM to reach an acceptable dose distribution. This study demonstrated that Beam Modulator (4 mm leaf width) and MLCi2 (10 mm leaf width) MLCs from Elekta provided satisfactory dose distributions for treatment delivery with VMAT technique for complex HNC cases with standard and dose painting prescriptions. OAR sparing was better with BM, mainly for brainstem and spinal cord. However, delivery efficiency of VMAT plans was better with MLCi2.

Segmentation of cardiac infarction in delayed-enhancement MRI using probability map and transformers-based neural networks.

BACKGROUND AND OBJECTIVE: Automatic segmentation of myocardial infarction is of great clinical interest for the quantitative evaluation of myocardial infarction (MI). Late Gadolinium Enhancement cardiac MRI (LGE-MRI) is commonly used in clinical practice to quantify MI, which is crucial for clinical diagnosis and treatment of cardiac diseases. However, the segmentation of infarcted tissue in LGE-MRI is highly challenging due to its high anisotropy and inhomogeneities. METHODS: The innovative aspect of our work lies in the utilization of a probability map of the healthy myocardium to guide the localization of infarction, as well as the combination of 2D U-Net and U-Net transformers to achieve the final segmentation. Instead of employing a binary segmentation map, we propose using a probability map of the normal myocardium, obtained through a dedicated 2D U-Net. To leverage spatial information, we employ a U-Net transformers network where we incorporate the probability map into the original image as an additional input. Then, To address the limitations of U-Net in segmenting accurately the contours, we introduce an adapted loss function. RESULTS: Our method has been evaluated on the 2020 MICCAI EMIDEC challenge dataset, yielding competitive results. Specifically, we achieved a Dice score of 92.94% for the myocardium and 92.36% for the infarction. These outcomes highlight the competitiveness of our approach. CONCLUSION: In the case of the infarction class, our proposed method outperforms state-of-the-art techniques across all metrics evaluated in the challenge, establishing its superior performance in infarction segmentation. This study further reinforces the importance of integrating a contour loss into the segmentation process.

Federated learning for predicting histological response to neoadjuvant chemotherapy in triple-negative breast cancer.

Triple-negative breast cancer (TNBC) is a rare cancer, characterized by high metastatic potential and poor prognosis, and has limited treatment options. The current standard of care in nonmetastatic settings is neoadjuvant chemotherapy (NACT), but treatment efficacy varies substantially across patients. This heterogeneity is still poorly understood, partly due to the paucity of curated TNBC data. Here we investigate the use of machine learning (ML) leveraging whole-slide images and clinical information to predict, at diagnosis, the histological response to NACT for early TNBC women patients. To overcome the biases of small-scale studies while respecting data privacy, we conducted a multicentric TNBC study using federated learning, in which patient data remain secured behind hospitals' firewalls. We show that local ML models relying on whole-slide images can predict response to NACT but that collaborative training of ML models further improves performance, on par with the best current approaches in which ML models are trained using time-consuming expert annotations. Our ML model is interpretable and is sensitive to specific histological patterns. This proof of concept study, in which federated learning is applied to real-world datasets, paves the way for future biomarker discovery using unprecedentedly large datasets.

Stretched reconstruction based on 2D freehand ultrasound for peripheral artery imaging.

PURPOSE: Endovascular revascularization is becoming the established first-line treatment of peripheral artery disease (PAD). Ultrasound (US) imaging is used pre-operatively to make the first diagnosis and is often followed by a CT angiography (CTA). US provides a non-invasive and non-ionizing method for the visualization of arteries and lesion(s). This paper proposes to generate a 3D stretched reconstruction of the femoral artery from a sequence of 2D US B-mode frames. METHODS: The proposed method is solely image-based. A Mask-RCNN is used to segment the femoral artery on the 2D US frames. In-plane registration is achieved by aligning the artery segmentation masks. Subsequently, a convolutional neural network (CNN) predicts the out-of-plane translation. After processing all input frames and re-sampling the volume according to the vessel's centerline, the whole femoral artery can be visualized on a single slice of the resulting stretched view. RESULTS: 111 tracked US sequences of the left or right femoral arteries have been acquired on 18 healthy volunteers. fivefold cross-validation was used to validate our method and achieve an absolute mean error of 0.28 ± 0.28 mm and a median drift error of 8.98%. CONCLUSION: This study demonstrates the feasibility of freehand US stretched reconstruction following a deep learning strategy for imaging the femoral artery. Stretched views are generated and can give rich diagnosis information in the pre-operative planning of PAD procedures. This visualization could replace traditional 3D imaging in the pre-operative planning process, and during the pre-operative diagnosis phase, to identify, locate, and size stenosis/thrombosis lesions.