Automated treatment planning for proton pencil beam scanning using deep learning dose prediction and dose-mimicking optimization.

PURPOSE: The purpose of this study is to investigate the use of a deep learning architecture for automated treatment planning for proton pencil beam scanning (PBS). METHODS: A 3-dimensional (3D) U-Net model has been implemented in a commercial treatment planning system (TPS) that uses contoured regions of interest (ROI) binary masks as model inputs with a predicted dose distribution as the model output. Predicted dose distributions were converted to deliverable PBS treatment plans using a voxel-wise robust dose mimicking optimization algorithm. This model was leveraged to generate machine learning (ML) optimized plans for patients receiving proton PBS irradiation of the chest wall. Model training was carried out on a retrospective set of 48 previously-treated chest wall patient treatment plans. Model evaluation was carried out by generating ML-optimized plans on a hold-out set of 12 contoured chest wall patient CT datasets from previously treated patients. Clinical goal criteria and gamma analysis were used to compare dose distributions of the ML-optimized plans against the clinically approved plans across the test patients. RESULTS: Statistical analysis of mean clinical goal criteria indicates that compared to the clinical plans, the ML optimization workflow generated robust plans with similar dose to the heart, lungs, and esophagus while achieving superior dosimetric coverage to the PTV chest wall (clinical mean V95 = 97.6% vs. ML mean V95 = 99.1%, p < 0.001) across the 12 test patients. CONCLUSIONS: ML-based automated treatment plan optimization using the 3D U-Net model can generate treatment plans of similar clinical quality compared to human-driven optimization.

Does the oral steroid treatment of patients with nasal polyposis cause osteopenia or osteoporosis?

OBJECTIVES: We aimed to investigate the bone mineral density (BMD) in a group of Swedish patients with chronic rhinosinusitis with nasal polyposis (CRSwNP) with or without asthma, as well as to evaluate whether the treatment of this patient group is in accordance with the EPOS recommendations. DESIGN, SETTINGS AND PARTICIPANTS: Adult patients with a diagnosis of CRSwNP, and a history of at least two courses of oral corticosteroids (OCS) during the last year, were consecutively included in this study at five centres. MAIN OUTCOME MEASURES: The BMD of the patients was measured by Dual-energy X-ray absorptiometry (DXA), which is the only technology for classifying BMD according to the criteria established by WHO. RESULTS: A total of 51 patients, with an average number of 7 years with OCS treatment, were enrolled. During the last 12 months, the mean number of OCS courses was 2.76, and the total mean intake was 891 mg of Prednisone equivalents. According to the T-scores, 17 patients were measured to have ≤-1 SD T-score lumbar spine, which is considered to be osteopenia, and five patients had <-2.5 SD T-score, considered as osteoporosis. However, when taking age and gender into account and analysing the Z-scores, only 2 patients had a reduced density of the spine and none in the hip, which is no difference compared to a matched Swedish population. CONCLUSIONS: This prospective study shows that 2-3 moderate courses of OCS annually may be used without high risk of causing osteopenia/osteoporosis in patients with CRSwNP.

Voice Quality in Adults Treated for Unilateral Cleft Lip and Palate: Long-Term Follow-Up After One- or Two-Stage Palate Repair.

OBJECTIVES: The aim of the current study was to assess voice quality among adults treated for unilateral cleft lip and palate (UCLP), after one- or two-stage palate closure, and compare it to a noncleft control group. STUDY DESIGN: Cross-sectional study of patients with UCLP with long-term follow-up and noncleft controls. PARTICIPANTS: Patients with UCLP born between 1960 and 1987, treated at Uppsala University Hospital, Sweden, were examined (n = 73) at a mean of 35 years after primary surgery. Forty-seven (64%) patients had been treated with 1-stage palate closure and 26 with 2-stage closure (36%). The noncleft control group consisted of 63 age-matched volunteers. MAIN OUTCOME MEASURES: Ratings of perceptual voice characteristics from blinded voice recordings with Swedish Voice Evaluation Approach method. Acoustic voice analysis including pitch and spectral measures. RESULTS: Among the patients, the mean values for the 12 evaluated variables on a visual analog scale (0 = no abnormality, 100 = maximal abnormality) ranged between 0.1 and 17, and the mean for all was 6 mm. Voice variables were similar between patients and controls, except the total mean of all the perceptual voice variables, as well as "vocal fry"; both slightly lower among patients ( P = .018 and P = .009). There was no difference in any variable between patients treated with 1-stage and 2-stage palate closure. No clear relationship was found between velopharyngeal insufficiency and dysphonia. CONCLUSIONS: The voice characteristics among adults treated for UCLP in childhood are not different from those of individuals without cleft.

Voice Quality in Adults Treated for Unilateral Cleft Lip and Palate: Long-term Follow-up After 1- or 2-Stage Palate Repair.

OBJECTIVES: The aim of the current study was to assess voice quality among adults treated for unilateral cleft lip and palate (UCLP), after 1- or 2-stage palate closure, and compare it to a noncleft control group. STUDY DESIGN: Cross-sectional study in UCLP patients with long-term follow-up and noncleft controls. PARTICIPANTS: UCLP patients born 1960-1987, treated at Uppsala University Hospital, Sweden, were examined (n = 73) at a mean of 35 years after primary surgery. Forty-seven patients (64%) had been treated with 1-stage palate closure and 26 with 2-stage closure (36%). The noncleft control group consisted of 63 age-matched volunteers. MAIN OUTCOME MEASURE(S): Ratings of perceptual voice characteristics from blinded voice recordings with Swedish Voice Evaluation Approach (SVEA) method. Acoustic voice analysis including pitch and spectral measures. RESULTS: Among the patients, the mean values for the 12 evaluated variables on a VAS scale (0 = no abnormality, 100 = maximal abnormality) ranged between 1 and 22 and the mean for all was 6 mm. Voice variables were similar between patients and controls except the total mean of all the perceptual voice variables, as well as "vocal fry"-both slightly lower among patients ( P = .018 and P = .009). There was no difference in any variable between patients treated with 1-stage and 2-stage palate closure. No clear relationship was found between VPI and dysphonia. CONCLUSION: The voice characteristics among adults treated for UCLP in childhood are not different from those of individuals without cleft.

Speech in Adults Treated for Unilateral Cleft Lip and Palate: Long-Term Follow-Up After One- or Two-Stage Palate Repair.

OBJECTIVE: To evaluate speech in adults treated for unilateral cleft lip and palate with one-stage or two-stage palate closure and compare the speech of the patients with that of a noncleft control group. DESIGN: Cross-sectional study with long-term follow-up. PARTICIPANTS/SETTING: All unilateral cleft lip and palate patients born from 1960 to 1987 and treated at Uppsala University Hospital, Sweden, were invited (n = 109). Participation rate was 67% (n = 73) at a mean of 35 years after primary surgery. Forty-seven had been treated according to one-stage palate closure and 26 according to two-stage palate closure. Pharyngeal flap surgery had been performed in 11 of the 73 patients (15%). The noncleft control group consisted of 63 age-matched volunteers. MAIN OUTCOME MEASURE(S): Speech-language pathologists rated perceptual speech characteristics from blinded audio recordings. RESULTS: Among patients, seven (10%) presented with hypernasality, 12 (16%) had audible nasal emission and/or nasal turbulence, five (7%) had consonant production errors, one (2%) had glottal reinforcements/substitutions, and one (2%) had reduced intelligibility. Controls had no audible signs of velopharyngeal insufficiency and no quantifiable problems with the other speech production variables. No significant differences were identified between patients treated with one-stage and two-stage palate closure for any of the variables. CONCLUSIONS: The prevalence of speech outcome indicative of velopharyngeal insufficiency among adult patients treated for unilateral cleft lip and palate was low but higher compared with individuals without cleft. Whether palatal closure is performed in one or two stages does not seem to affect the speech outcome at a mean age of 35 years.

Early childhood IgE reactivity to pathogenesis-related class 10 proteins predicts allergic rhinitis in adolescence.

BACKGROUND: Component-resolved diagnosis might improve the prediction of future allergy in young children. OBJECTIVE: We sought to investigate the association between IgE reactivity to the pathogenesis-related class 10 (PR-10) protein family and allergic rhinitis to birch pollen (ARbp) from early childhood up to age 16 years. METHOD: Questionnaire data and sera obtained at 4, 8, and 16 years of age from the Barn/Children Allergi/Allergy Milieu Stockholm Epidemiologic (BAMSE) study birth cohort were used. Sera from 764 children were analyzed for IgE reactivity to 9 PR-10 allergen proteins at the 3 time points by using an allergen chip based on ISAC technology. ARbp was defined as upper airway symptoms during birch pollen exposure. RESULTS: IgE reactivity to Bet v 1 was found in 12%, 17%, and 25% of children at 4, 8, and 16 years of age. IgE reactivity of PR-10 proteins showed a hierarchic intrarelationship: Bet v 1 > Mal d 1 > Cor a 1.04 > Ara h 8 > Pru p 1 > Aln g 1 > Api g 1 > Act d 8 > Gly m 4. There was an increased risk of incidence and persistence of ARbp up to age 16 years with increasing levels of Bet v 1-specific IgE or increasing numbers of IgE-reactive PR-10 proteins at 4 years. Children with severe ARbp at age 16 years had higher levels of Bet v 1-specific IgE at age 4 years compared with children with mild symptoms. CONCLUSION: ARbp at age 16 years can be predicted by analysis of IgE reactivity to PR-10 proteins in early childhood.

Impact of nasal obstruction on sleep quality: a community-based study of women.

The aim of the study was to analyse the impact of self-reported nasal obstruction on sleep quality in women. A community-based sample of 400 women underwent a full night of polysomnography. Airway diseases, allergies and sleep-related symptoms were assessed by questionnaires. Women with subjective nasal obstruction were subdivided into three groups: persistent nasal obstruction (PNO, n = 46), hay fever (n = 88) and nasal obstruction at night (NON, n = 30). Sleep problems and related daytime symptoms were most prevalent among women with NON. After adjusting for age, BMI, smoking and asthma, NON was an independent predictor of 'Difficulties inducing sleep due to nasal obstruction' [adjusted odds ratio (95 % CI): 89.5 (27.0-296.7)], 'Snoring' [4.2 (1.7-10.2)], 'Sweating at night' [2.6 (1.1-6.1)], 'Difficulties maintaining sleep' [2.7 (1.2-6.2)], and 'Waking up hastily gasping for breath' [32.2 (8.7-119.1)]. 'Dry mouth on awakening' [7.7 (3.2-18.4)], 'Waking up unrefreshed' [2.7 (1.2-6.0)], 'Excessive daytime sleepiness' [2.6 (1.1-6.0)], and 'Daytime nasal obstruction' [12.2 (4.8-31.2)] were also associated with NON. Persistent nasal obstruction and hay fever were both associated with some reported sleep problems due to an overlap with NON. When women with NON were excluded, only 'Daytime nasal obstruction' was still significantly associated with PNO, while hay fever was associated with 'Daytime nasal obstruction' and 'Waking up hastily gasping for breath'. There were no significant differences in objectively measured sleep variables between any of the three subgroups and the study cohort. Self-reported nasal obstruction at night in women has a significant effect on several subjective day- and nighttime symptoms, but it does not appear to affect objectively measured sleep quality.

Future opportunities in solar system plasma science through ESA's exploration programme.

The solar wind interacts with all solar system bodies, inducing different types of dynamics depending on their atmospheric and magnetic environments. We here outline some key open scientific questions related to this interaction, with a focus on the Moon and Mars, that may be addressed by future Mars and Moon missions by the European Space Agency's Human and Robotic Exploration programme. We describe possible studies of plasma interactions with bodies with and without an atmosphere, using multi-point and remote measurements, and energetic particle observations, as well as recommend some actions to take.

Factors related to quality of life and satisfaction with nasal appearance in patients treated for unilateral cleft lip and palate.

Objective : To identify factors related to quality of life (QoL) and satisfaction with nasal appearance among patients treated for unilateral cleft lip and palate (UCLP). Design : Cross-sectional population study with long-term follow-up. Patients/Settings : All patients with UCLP born between 1960 and 1987, treated at Uppsala University Hospital, were invited (n  =  109); 86 (79%) participated. Mean follow-up time was 35 years. Main Outcome Measures : Quality of life was measured with Short Form-36 (SF-36) and analyzed using mental and physical cluster scores (MCS and PCS). Nasal appearance was self-assessed with the "Satisfaction With Appearance" questionnaire and by panel judgment. Multivariate regression analyses explored endogenous factors (age, gender, infancy cleft width, nasal function, nasolabial appearance) and exogenous factors (marital status, number of children, education level, operation method, number of rhinoplasties performed). Results : A larger cleft width in infancy was associated with less satisfaction with nasal appearance as adults. A lower mental health QoL was associated with less satisfaction with nasal appearance. Despite female gender being linked to less satisfaction with nasal appearance, it was associated with higher mental health QoL. Higher resistance during nasal breathing was associated with lower physical health QoL. Conclusions : Gender and infant cleft width may affect QoL and satisfaction with nasal appearance among adults. They are potential predictive factors for satisfaction with nasal appearance and QoL during adulthood. The correlation of nasal function impairment and decreased physical health QoL underlines the importance of treatment of nasal symptoms in these patients.

Active anterior rhinomanometry: A study on nasal airway resistance, paradoxical reactions to decongestion, and repeatability in healthy subjects.

Objectives: Anterior active rhinomanometry (AAR) is widely used in Swedish routine clinical practice to decide if septoplasty is necessary. The scientific basis for the method needs to be strengthened. Therefore, the aims were to evaluate nasal airway resistance (NAR), paradoxical reactions to pharmacological decongestion, and test-retest characteristics of the Rhino-Comp® AAR in healthy subjects. Methods: A prospective longitudinal design was used. AAR was performed before and after decongestion at baseline and after ≥6 months on 60 healthy volunteers. The relationships between NAR, height, weight, BMI, sex, and allergic rhinitis were evaluated by regression analyses. Descriptive statistics were used to evaluate paradoxical reactions. Test-retest and repeatability characteristics were evaluated with intra-class coefficients (ICC), Cronbach's α, and standard error of measurement. Results: No statistically significant differences were found between genders or nasal cavity sides. NAR was statistically significantly related to height. Short- and long-term test-retest characteristics were good with ICC and Cronbach's α > .75. The minimal significant difference in NAR Log10V2 values between the two measurements was 0.11 and 0.09 (long- and short-term). Paradoxical reactions to pharmacological decongestion were rare, mostly weak, and not evidently reproducible. Conclusion: In this study, we report reference data for healthy subjects, test-retest capabilities, and the minimal relevant difference between two measurements for the Rhino-Comp® AAR, information that is vital and necessary for the appropriate use of AAR in clinical practice. An effective method for pharmacological decongestion is described and recommended for future studies and clinical practice. Paradoxical reactions to pharmacological decongestants exist but maybe without clinical significance. Level of Evidence: NA.

[Allergic rhinitis in children and adults - international recommendations adapted to the clinical situation in Sweden]. / Allergisk rinit hos barn och vuxna.

Allergic rhinitis is the most common chronic disease in Sweden, with impact on quality of life and with a heavy economic burden for the society. More than 20 years have passed since national recommendations were launched, and meanwhile both ARIA (Allergic rhinitis and its impact of asthma) and EUFOREA (The European Forum for Research and Education in Allergy and Airway Diseases) have presented international guidelines which in this article have been adapted to the clinical situation in Sweden. Visual analogue scale (VAS) is recommended for symptom evaluation, and the importance of correct allergen analysis and examination for coexisting asthma is emphasized. Treatment is recommended according to EUFOREA. Follow-up is important, and if VAS is ≥5 the disease is regarded as uncontrolled and must lead to a change of treatment. Since self-treatment is common in allergic rhinitis the importance of patient cooperation and information is underlined.

Machine learning-based automatic proton therapy planning: Impact of post-processing and dose-mimicking in plan robustness.

PURPOSE: Automated treatment planning strategies are being widely implemented in clinical routines to reduce inter-planner variability, speed up the optimization process, and improve plan quality. This study aims to evaluate the feasibility and quality of intensity-modulated proton therapy (IMPT) plans generated with four different knowledge-based planning (KBP) pipelines fully integrated into a commercial treatment planning system (TPS). MATERIALS/METHODS: A data set containing 60 oropharyngeal cancer patients was split into 11 folds, each containing 47 patients for training, five patients for validation, and five patients for testing. A dose prediction model was trained on each of the folds, resulting in a total of 11 models. Three patients were left out in order to assess if the differences introduced between models were significant. From voxel-based dose predictions, we analyze the two steps that follow the dose prediction: post-processing of the predicted dose and dose mimicking (DM). We focused on the effect of post-processing (PP) or no post-processing (NPP) combined with two different DM algorithms for optimization: the one available in the commercial TPS RayStation (RSM) and a simpler isodose-based mimicking (IBM). Using 55 test patients (five test patients for each model), we evaluated the quality and robustness of the plans generated by the four proposed KBP pipelines (PP-RSM, PP-IBM, NPP-RSM, NPP-IBM). After robust evaluation, dose-volume histogram (DVH) metrics in nominal and worst-case scenarios were compared to those of the manually generated plans. RESULTS: Nominal doses from the four KBP pipelines showed promising results achieving comparable target coverage and improved dose to organs at risk (OARs) compared to the manual plans. However, too optimistic post-processing applied to the dose prediction (i.e. important decrease of the dose to the organs) compromised the robustness of the plans. Even though RSM seemed to partially compensate for the lack of robustness in the PP plans, still 65% of the patients did not achieve the expected robustness levels. NPP-RSM plans seemed to achieve the best trade-off between robustness and OAR sparing. DISCUSSION/CONCLUSIONS: PP and DM strategies are crucial steps to generate acceptable robust and deliverable IMPT plans from ML-predicted doses. Before the clinical implementation of any KBP pipeline, the PP and DM parameters predefined by the commercial TPS need to be modified accordingly with a comprehensive feedback loop in which the robustness of the final dose calculations is evaluated. With the right choice of PP and DM parameters, KBP strategies have the potential to generate IMPT plans within clinically acceptable levels comparable to plans manually generated by dosimetrists.

Automated Robust Planning for IMPT in Oropharyngeal Cancer Patients Using Machine Learning.

PURPOSE: The aim of this study was to evaluate an automated treatment planning method for robustly optimized intensity modulated proton therapy (IMPT) plans for oropharyngeal carcinoma patients and to compare the results with manually optimized robust IMPT plans. METHODS AND MATERIALS: An atlas regression forest-based machine learning (ML) model for dose prediction was trained on CT scans, contours, and dose distributions of robust IMPT plans of 88 oropharyngeal cancer (OPC) patients. The ML model was combined with a robust voxel and dose volume histogram-based dose mimicking optimization algorithm for 21 perturbed scenarios to generate a machine-deliverable plan from the predicted dose distribution. Machine learning optimization (MLO) configuration was performed using a cross-validation approach with 3 × 8 tuning patients and comprised of adjustments to the mimicking optimization, to generate higher-quality MLO plans. Independent testing of the MLO algorithm was performed with another 25 patients. Plan quality of clinical and MLO plans was evaluated by the clinical target volume (D98% voxel-wise minimum dose >94%), organ at risk (OAR) doses, and the normal tissue complication probability (NTCP) (sum (Σ) of grade-2 and grade-3 dysphagia and xerostomia). RESULTS: Adequate robust target coverage was achieved in 24/25 clinical plans and in 23/25 MLO plans in the primary clinical target volume (CTV). In the elective CTV, 22/25 clinical plans and 24/25 MLO plans passed the robust target coverage evaluation threshold. The MLO average Σgrade 2 and Σgrade 3 NTCPs were comparable to the clinical plans (Σgrade 2 NTCPs: clinical 47.5% vs MLO 48.4%, Σgrade 3 NTCPs: clinical 11.9% vs MLO 12.3%). Significant increases in OAR average doses in MLO plans were found in the pharynx constrictor muscles (163 cGy, P = .002) and cervical esophagus (265 cGy, P = .002). The MLO plans were created within 45 minutes. CONCLUSION: This study showed that automated MLO planning can generate robustly optimized MLO plans with quality comparable to clinical plans in OPC patients.

Detection of magnetospheric ion drift patterns at Mars.

Mars lacks a global magnetic field, and instead possesses small-scale crustal magnetic fields, making its magnetic environment fundamentally different from intrinsic magnetospheres like those of Earth or Saturn. Here we report the discovery of magnetospheric ion drift patterns, typical of intrinsic magnetospheres, at Mars using measurements from Mars Atmosphere and Volatile EvolutioN mission. Specifically, we observe wedge-like dispersion structures of hydrogen ions exhibiting butterfly-shaped distributions (pitch angle peaks at 22.5°-45° and 135°-157.5°) within the Martian crustal fields, a feature previously observed only in planetary-scale intrinsic magnetospheres. These dispersed structures are the results of drift motions that fundamentally resemble those observed in intrinsic magnetospheres. Our findings indicate that the Martian magnetosphere embodies an intermediate case where both the unmagnetized and magnetized ion behaviors could be observed because of the wide range of strengths and spatial scales of the crustal magnetic fields around Mars.

Speech in adults treated for unilateral cleft lip and palate as rated by naïve listeners, speech-language pathologists, and patients.

Speech may be affected in patients with cleft lip and palate (CLP). Professional listeners, naïve listeners, and patients may perceive speech differently. The aim of the study was to assess speech among adults treated for unilateral CLP (UCLP) as rated by naïve listeners, speech-language pathologists (SLPs), and self-assessment and to evaluate how well these ratings correlate. All patients with complete UCLP treated at the Uppsala University Hospital, Uppsala, Sweden, in 1960-1987 were invited. A total of 73 of 109 patients (67%) participated, with a mean of 35 years since the initiation of treatment. The noncleft control group consisted of 55 volunteers. All participants answered questionnaires for self-rating of speech, and their speech was audio-recorded digitally. Fourteen naïve listeners and four SLPs rated the speech individually from blinded recordings. There were more speech abnormalities among patients compared to controls according to the ratings of naïve listeners and SLPs. In controls and patients, there were positive correlations between the speech ratings by naïve listeners and SLPs r = 0.44 to 0.71, p < 0.001, Spearman). The patients were less satisfied and rated to have more speech abnormalities than controls (p < 0.001). Although adults treated for UCLP considered their speech as fairly good, they were less satisfied than noncleft controls. The agreement between ratings by naïve listeners and SLPs were good, while the agreement between these ratings and self-assessment varied widely. When assessing speech in adults treated for UCLP, differences in perception of speech abnormalities by professionals, laymen, and patients should be considered.

Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency.

The interest in machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors' perspectives for the clinical implementation of ML.

A Swedish population-based study of complications due to acute rhinosinusitis in children 5-18 years old.

BACKGROUND: There are few population-based studies of complications due to acute rhinosinusitis in children. The aim was to clarify the admission and complication rate and analyze bacterial cultures in children five to 18 years old in Stockholm, Sweden. METHODS: This was a population-based observational cohort study with retrospectively collected data from individual medical records, from 1 July 2003 to 30 June 2016 in Stockholm, Sweden. Hospital admissions of children with a discharge diagnosis of rhinosinusitis and related complications were reviewed. RESULTS: Incidence of admission due to acute rhinosinusitis was 7.8 per 100 000 children per year (boys 9.2, girls 6.2) and 61% of the admitted children were boys. A severe - postseptal orbital, intracranial or osseous - complication, was present in 34% of admissions (postseptal orbital 28%, intracranial 6%, osseous 4%), resulting in an incidence of 2.6 severe complications per 100 000 children per year (boys 3.6, girls 1.6). Orbital preseptal cellulitis was present in 88% of admissions. Incidence of surgery was 1.3 per 100 000 per year (boys 1.8, girls 0.8) and the percentage of admitted children that had surgery increased with age. S. pyogenes was the most common pathogen found in the whole cohort (29 admissions), while S. milleri was the most common pathogen found among the children with severe complication and surgery. CONCLUSIONS: There is a relative high risk of severe complications in children between five to 18 years that are admitted due to acute rhinosinusitis. There is a need for prospective studies to further analyze the pathogens involved in complications due to acute rhinosinusitis.

Artificial intelligence and machine learning for medical imaging: A technology review.

Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.

The use of objective measures in selecting patients for septal surgery.

To improve results in septal surgery patient selection is the mainstay of a successful outcome. Patient history is the basis as well as clinical examination but both are subjective and must be considered towards a background with a high frequency of septal deviation in the population and a lack of good correlation between function and status. Rhinomanometry and acoustic rhinometry as well as nasal peak inspiratory flow are tests of different nasal parameters as resistance to breathing, nasal dimensions and flow. This article illuminates the use of these more objective tests in selection of patients for septo plasty. Objective tests have in several studies shown to predict postoperative satisfaction while normal values can be a marker for a poor surgical outcome. Pros and cons with objective tests are discussed and the conclusion is: operate when there is a good correlation between the patientA`s status, history and the results of rhinometry!