Predictive value of texture analysis on lumbar MRI in patients with chronic low back pain.

PURPOSE: The aim of this study was to determine whether MRI texture analysis could predict the prognosis of patients with non-specific chronic low back pain. METHODS: A prospective observational study was conducted on 100 patients with non-specific chronic low back pain, who underwent a conventional MRI, followed by rehabilitation treatment, and revisited after 6 months. Sociodemographic variables, numeric pain scale (NPS) value, and the degree of disability as measured by the Roland-Morris disability questionnaire (RMDQ), were collected. The MRI analysis included segmentation of regions of interest (vertebral endplates and intervertebral disks from L3-L4 to L5-S1, paravertebral musculature at the L4-L5 space) to extract texture variables (PyRadiomics software). The classification random forest algorithm was applied to identify individuals who would improve less than 30% in the NPS or would score more than 4 in the RMDQ at the end of the follow-up. Sensitivity, specificity, and the area under the ROC curve were calculated. RESULTS: The final series included 94 patients. The predictive model for classifying patients whose pain did not improve by 30% or more offered a sensitivity of 0.86, specificity 0.57, and area under the ROC curve 0.71. The predictive model for classifying patients with a RMDQ score 4 or more offered a sensitivity of 0.83, specificity of 0.20, and area under the ROC curve of 0.52. CONCLUSION: The texture analysis of lumbar MRI could help identify patients who are more likely to improve their non-specific chronic low back pain through rehabilitation programs, allowing a personalized therapeutic plan to be established.

Automated Whole-Liver MRI Segmentation to Assess Steatosis and Iron Quantification in Chronic Liver Disease.

Background Standardized manual region of interest (ROI) sampling strategies for hepatic MRI steatosis and iron quantification are time consuming, with variable results. Purpose To evaluate the performance of automatic MRI whole-liver segmentation (WLS) for proton density fat fraction (PDFF) and iron estimation (transverse relaxometry [R2*]) versus manual ROI, with liver biopsy as the reference standard. Materials and Methods This prospective, cross-sectional, multicenter study recruited participants with chronic liver disease who underwent liver biopsy and chemical shift-encoded 3.0-T MRI between January 2017 and January 2021. Biopsy evaluation included histologic grading and digital pathology. MRI liver sampling strategies included manual ROI (two observers) and automatic whole-liver (deep learning algorithm) segmentation for PDFF- and R2*-derived measurements. Agreements between segmentation methods were measured using intraclass correlation coefficients (ICCs), and biases were evaluated using Bland-Altman analyses. Linear regression analyses were performed to determine the correlation between measurements and digital pathology. Results A total of 165 participants were included (mean age ± standard deviation, 55 years ± 12; 96 women; 101 of 165 participants [61%] with nonalcoholic fatty liver disease). Agreements between mean measurements were excellent, with ICCs of 0.98 for both PDFF and R2*. The median bias was 0.5% (interquartile range, -0.4% to 1.2%) for PDFF and 2.7 sec-1 (interquartile range, 0.2-5.3 sec-1) for R2* (P < .001 for both). Margins of error were lower for WLS than ROI-derived parameters (-0.03% for PDFF and -0.3 sec-1 for R2*). ROI and WLS showed similar performance for steatosis (ROI AUC, 0.96; WLS AUC, 0.97; P = .53) and iron overload (ROI AUC, 0.85; WLS AUC, 0.83; P = .09). Correlations with digital pathology were high (P < .001) between the fat ratio and PDFF (ROI r = 0.89; WLS r = 0.90) and moderate (P < .001) between the iron ratio and R2* (ROI r = 0.65; WLS r = 0.64). Conclusion Proton density fat fraction and transverse relaxometry measurements derived from MRI automatic whole-liver segmentation (WLS) were accurate for steatosis and iron grading in chronic liver disease and correlated with digital pathology. Automated WLS estimations were higher, with a lower margin of error than manual region of interest estimations. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Moura Cunha and Fowler in this issue.

Machine Learning-Based Integration of Prognostic Magnetic Resonance Imaging Biomarkers for Myometrial Invasion Stratification in Endometrial Cancer.

BACKGROUND: Estimation of the depth of myometrial invasion (MI) in endometrial cancer is pivotal in the preoperatively staging. Magnetic resonance (MR) reports suffer from human subjectivity. Multiparametric MR imaging radiomics and parameters may improve the diagnostic accuracy. PURPOSE: To discriminate between patients with MI ≥ 50% using a machine learning-based model combining texture features and descriptors from preoperatively MR images. STUDY TYPE: Retrospective. POPULATION: One hundred forty-three women with endometrial cancer were included. The series was split into training (n = 107, 46 with MI ≥ 50%) and test (n = 36, 16 with MI ≥ 50%) cohorts. FIELD STRENGTH/SEQUENCES: Fast spin echo T2-weighted (T2W), diffusion-weighted (DW), and T1-weighted gradient echo dynamic contrast-enhanced (DCE) sequences were obtained at 1.5 or 3 T magnets. ASSESSMENT: Tumors were manually segmented slice-by-slice. Texture metrics were calculated from T2W and ADC map images. Also, the apparent diffusion coefficient (ADC), wash-in slope, wash-out slope, initial area under the curve at 60 sec and at 90 sec, initial slope, time to peak and peak amplitude maps from DCE sequences were obtained as parameters. MR diagnostic models using single-sequence features and a combination of features and parameters from the three sequences were built to estimate MI using Adaboost methods. The pathological depth of MI was used as gold standard. STATISTICAL TEST: Area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, accuracy, positive predictive value, negative predictive value, precision and recall were computed to assess the Adaboost models performance. RESULTS: The diagnostic model based on the features and parameters combination showed the best performance to depict patient with MI ≥ 50% in the test cohort (accuracy = 86.1% and AUROC = 87.1%). The rest of diagnostic models showed a worse accuracy (accuracy = 41.67%-63.89% and AUROC = 41.43%-63.13%). DATA CONCLUSION: The model combining the texture features from T2W and ADC map images with the semi-quantitative parameters from DW and DCE series allow the preoperative estimation of myometrial invasion. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 3.

Engaging in Awkward Social Interactions in a Virtual Environment Designed for Exposure-Based Psychotherapy for People with Generalized Social Anxiety Disorder: An International Multisite Study.

The effectiveness of in virtuo exposure-based treatment of performance-only social anxiety disorder (SAD) has been demonstrated in several studies. However, few studies have validated virtual environments with participants suffering from generalized SAD. The goal of this study is to confirm the potential of a virtual environment in inducing anxiety in adults suffering from generalized SAD, compared to adults without SAD, when engaged in awkward social interactions. Differences between participants from two different countries were also explored. The sample consisted of 15 participants with SAD from Canada, 17 participants without SAD from Canada, 16 participants with SAD from Spain, and 21 participants without SAD from Spain. All participants were immersed in a control virtual environment and in an experimental virtual environment considered potentially anxiety-inducing for individuals with generalized SAD. As hypothesized, results showed that the experimental virtual environment induced a higher level of anxiety than the control environment among participants with SAD compared to those without SAD. The impact on anxiety of each socially threatening task performed during the experimental immersion was statistically significant. In terms of anxiety responses, no significant differences were found between participants from Canada and Spain. However, spatial presence and ecological validity were higher in Canadians than in Spaniards. Unwanted negative side effects induced by immersions in virtual reality were higher in the SAD group. This study highlights the importance for therapists to engage people with SAD in clinically relevant tasks while immersed in VR psychotherapeutic applications.

Virtual representations of the self: engaging teenagers in emotional regulation strategies learning.

The aim of this paper is to present digital representations of humans (i.e., avatars) that look like the self, applied to the Mental Health (MH) field. Virtual Representations of the Self (VRS) are in our opinion a tool with a great potential for engaging teenagers in emotional regulation strategies learning and an excellent example of new technology application to the basic concept in psychology field such as Bandura's modeling [1]. VRSs have already demonstrated their potential on human behavior modification (e.g. modification of physical activity; eating habits) in general population [2]. Thus, the same technology can bring in our opinion a lot to the Mental Health field, especially in emotional regulation learning. This paper presents a theoretical background and describes the methodology that we plan to apply in order to validate the efficacy of VRSs in clinical settings. Also, the implications of such technology and future research lines are discussed.

Detection of Invisible Damages in 'Rojo Brillante' Persimmon Fruit at Different Stages Using Hyperspectral Imaging and Chemometrics.

The main cause of flesh browning in 'Rojo Brillante' persimmon fruit is mechanical damage caused during harvesting and packing. Innovation and research on nondestructive techniques to detect this phenomenon in the packing lines are necessary because this type of alteration is often only seen when the final consumer peels the fruit. In this work, we have studied the application of hyperspectral imaging in the range of 450-1040 nm to detect mechanical damage without any external symptoms. The fruit was damaged in a controlled manner. Later, images were acquired before and at 0, 1, 2 and 3 days after damage induction. First, the spectral data captured from the images were analysed through an algorithm based on principal component analysis (PCA). The aim was to automatically separate intact and damaged fruit, and to detect the damage in the PC images when present. With this algorithm, 90.0% of intact fruit and 90.8% of damaged fruit were correctly detected. A model based on partial least squares-discriminant analysis (PLS-DA), was later calibrated using the mean spectrum of the pixels detected as damaged, to determine the moment when the fruit was damaged. The model differentiated fruit corresponding correctly to 0, 1, 2 and 3 days after damage induction, achieving a total accuracy of 99.4%.

Quantification of H217O by 1H-MR imaging at 3 T: a feasibility study.

BACKGROUND: Indirect 1H-magnetic resonance (MR) imaging of 17O-labelled water allows imaging in vivo dynamic changes in water compartmentalisation. Our aim was to describe the feasibility of indirect 1H-MR methods to evaluate the effect of H217O on the MR relaxation rates by using conventional a 3-T equipment and voxel-wise relaxation rates. METHODS: MR images were used to calculate the R1, R2, and R2* relaxation rates in phantoms (19 vials with different H217O concentrations, ranging from 0.039 to 5.5%). Afterwards, an experimental animal pilot study (8 rats) was designed to evaluate the in vivo relative R2 brain dynamic changes related to the intravenous administration of 17O-labelled water in rats. RESULTS: There were no significant changes on the R1 and R2* values from phantoms. The R2 obtained with the turbo spin-echo T2-weighted sequence with 20-ms echo time interval had the higher statistical difference (0.67 s-1, interquartile range 0.34, p < 0.001) and Spearman correlation (rho 0.79). The R2 increase was adjusted to a linear fit between 0.25 and 5.5%, represented with equation R2 = 0.405 concentration + 0.3215. The highest significant differences were obtained for the higher concentrations (3.1-5.5%). The rat brain MR experiment showed a mean 10% change in the R2 value after the H217O injection with progressive normalisation. CONCLUSIONS: Indirect 1H-MR imaging method is able to measure H217O concentration by using R2 values and conventional 3-T MR equipment. Normalised R2 relative dynamic changes after the intravenous injection of a H217O saline solution provide a unique opportunity to map water pathophysiology in vivo, opening the analysis of aquaporins status and modifications by disease at clinically available 3-T proton MR scanners.

Digital pathology: accurate technique for quantitative assessment of histological features in metabolic-associated fatty liver disease.

BACKGROUND: Histological evaluation of metabolic-associated fatty liver disease (MAFLD) biopsies is subjective, descriptive and with interobserver variability. AIMS: To examine the relationship between different histological features (fibrosis, steatosis, inflammation and iron) measured with automated whole-slide quantitative digital pathology and corresponding semiquantitative scoring systems, and the distribution of digital pathology measurements across Fatty Liver Inhibition of Progression (FLIP) algorithm and Steatosis, Activity and Fibrosis (SAF) scoring system METHODS: We prospectively included 136 consecutive patients who underwent liver biopsy for MAFLD at three Spanish centres (January 2017-January 2020). Biopsies were scored by two blinded pathologists according to the Non-alcoholic Steatohepatitis (NASH) Clinical Research Network system for fibrosis staging, the FLIP/SAF classification for steatosis and inflammation grading and Deugnier score for iron grading. Proportionate areas of collagen, fat, inflammatory cells and iron deposits were measured with computer-assisted digital image analysis. A test-retest experiment was performed for precision repeatability evaluation. RESULTS: Digital pathology showed strong correlation with fibrosis (r = 0.79; P < 0.001), steatosis (r = 0.85; P < 0.001) and iron (r = 0.70; P < 0.001). Performance was lower when assessing the degree of inflammation (r = 0.35; P < 0.001). NASH cases had a higher proportion of collagen and fat compared to non-NASH cases (P < 0.005), whereas inflammation and iron quantification did not show significant differences between categories. Repeatability evaluation showed that all the coefficients of variation were ≤1.1% and all intraclass correlation coefficient values were ≥0.99, except those of collagen. CONCLUSION: Digital pathology allows an automated, precise, objective and quantitative assessment of MAFLD histological features. Digital analysis measurements show good concordance with pathologists´ scores.

Effect of varying dietary crude protein and metabolizable energy levels on leg abnormalities and performance in broiler chickens

Background: Nutrient restriction is a common strategy to prevent metabolic disorders in fast growing broiler chickens, but limited information is available regarding the impact of diets with low protein and energy on leg abnormalities Objective: Two experiments were conducted to evaluate the effect of varying crude protein (CP) and metabolizable energy (ME) levels on gastrocnemius tendon (GTeBS) and tibia breaking strength (TiBS), gait score (GS) and valgus/varus angulation (VAng). Methods: In Experiment 1, eight-d-old Ross 308 broilers (n=90) were randomly assigned into three treatments: 13/2,900 (13% CP and 2,900 kcal ME kg-1 of diet), 17/3,000 (17% CP and 3,000 kcal ME kg-1 of diet), and 21/3,025 or control (21% CP and 3,025 kcal ME kg-1 of diet). In Experiment 2, six-d-old Ross 308 chickens (n=192) were randomly distributed into two treatments: 16/3,000; 16% CP and 3,000 kcal ME kg-1 of diet and 21/3,000 or control; 21% CP and 3,000 kcal ME kg-1 of diet. In both experiments data were analyzed as one-way ANOVA. Results: In Experiment 1, broilers in the 17/3,000 and control treatments had similar (p>0.05) GTeBS (202 and 224 N, respectively), and TiBS (338 and 332 N, respectively). Birds in the 13/2,900 treatment showed higher GS (lower walking ability; 80% of birds with score >3), and greater VAng (53% of birds with score >2) than broilers in the control treatment (0% of birds with GS score >3 and 0% of birds with VAng score >2). Experiment 2, broilers in the 16/3,000 showed similar VAng, GS and TiBS than birds in the control treatment. However, birds in the 16/3,000 treatment showed lower (-26%) GTeBS than birds in the control treatment (p<0.05). Conclusions: Feeding broilers with 16% CP and 3,000 kcal ME kg-1 of diet did not affect tibia breaking strength, gait score and valgus/varus angulation. A diet containing 16% CP or less and 2,900-3,000 kcal ME kg-1 reduces tendon and tibia breaking strength.

Antecedentes: La restricción de nutrientes es una estrategia común para prevenir trastornos metabólicos en pollos de engorde, sin embargo, se dispone de información limitada sobre el impacto de las dietas bajas en proteína y energía en las anomalías de piernas. Objetivo: Se llevaron a cabo dos experimentos para evaluar el efecto de niveles variables de proteína cruda (PC) y energía metabolizable (EM) en la fuerza de rotura del tendón del gastrocnemio (GTeBS) y tibia (TiBS), la evaluación de marcha (GS) y la angulación en valgus/varus (VAng). Métodos: En el Experimento 1, pollos de engorde Ross 308 de ocho días de edad (n = 90) se asignaron al azar en tres tratamientos: 13/2.900; 13% PC y 2.900 kcal ME kg-1 de dieta, 17/3.000; 17% PC y 3.000 kcal ME kg-1 de dieta y 21/3.025 o control; 21% PC y 3.025 kcal ME kg-1 de dieta. En el Experimento 2, pollos Ross 308 de seis días de edad (n = 192) se distribuyeron aleatoriamente en dos tratamientos: 16/3.000; 16% PC y 3.000 kcal ME kg-1 de dieta y 21/3.000 o control; 21% PC y 3.000 kcal ME kg-1 de dieta. En ambos experimentos los datos se analizaron como ANOVA de una vía. Resultados: En el Experimento 1, los pollos de los tratamientos 17/3.000 y control tuvieron GTeBS (202 y 224 N, respectivamente) y TiBS (338 y 332 N, respectivamente) similares (p>0,05). Las aves del tratamiento 13/2.900 mostraron mayor GS (menor capacidad para caminar; 80% de las aves con puntaje >3) y mayor VAng (53% de las aves con puntaje >2) que los pollos del tratamiento control (0% de aves con un puntaje GS >3 y 0% de aves con un puntaje VAng >2). En el Experimento 2, los pollos del 16/3.000 mostraron VAng, GS y TiBS similares a los de las aves del tratamiento control. Sin embargo, las aves del tratamiento 16/3.000 mostraron menor (-26%) GTeBS que las aves control (p<0,05). Conclusiones: La alimentación de pollos de engorde con 16% PC y 3.000 kcal EM kg-1 de dieta no afecta la resistencia a la ruptura de la tibia, la marcha y la angulación valgus/varus. La dieta formulada con 16% de PC o menos y 2.900-3.000 kcal de EM kg-1 reduce la resistencia a la ruptura del tendón y de la tibia.

Antecedentes: A restrição de nutrientes é uma estratégia comum para prevenir distúrbios metabólicos em frangos de corte, no entanto, há informações limitadas disponíveis sobre o impacto de dietas de baixa proteína e baixa energia nas anormalidades de pernas destas aves. Objetivo: Dois experimentos foram realizados para avaliar o efeito de diferentes níveis de proteína bruta (PB) e energia metabolizável (EM) em força de ruptura do tendão do músculo gastrocnêmio (GTeBS), forca de ruptura da tíbia (TiBS), gait score (GS) e angulação em valgus/varus (VAng). Métodos: Experimento 1, foram utilizados 308 frangos de corte machos da linhagem Ross com oito dias de idade (n = 90) distribuidos aleatoriamente em três tratamentos: dieta controle com 21% PB e 3.025 kcal EM kg-1 13/2.900; dieta con 13% PB e 2.900 kcal EM kg-1, y 17% PB e 3.000 kcal EM kg-1 . Experimento 2, foram utilizados 308 frangos de corte da linhagem Ross com seis dias de idade (n = 192) distribuídos aleatoriamente em dois tratamentos: dieta controle con 21% PB e 3.000 kcal EM kg-1 e dieta com 16% PB e 3.000 kcal EM kg-1 . Em ambos os experimentos, os dados foram submetidos a ANOVA. Resultados: Experimento 1, os frangos de corte submetidos ao dos tratamentos 17/3.000 e controle nao apresentaram diferencas significativas (p>0,05) para as variáveis GteBS (202 y 224 N, respectivamente) e TiBS (338 y 332 N, respectivamente). Os frangos submetidos ao 13/2.900 apresentaram maior frequência de GS (menor capacidade de locomocao; 80% das aves com pontuação>3) e maior VAng (53% das aves com pontuação>2) do que os frangos do tratamento controle (0% das aves com pontuação GS>3 e 0% das aves com pontuação VAng>2). Experimento 2, os frangos do 16/3.000 apresentaram VAng, GS e TiBS semelhantes aos das aves do tratamento controle. Entretanto, as aves do tratamento 16/3.000 apresentaram GTeBS mais baixo (-26%) em comparacao as aves do tratamento de controle (p<0,05). Conclusões: A dieta com 16% PB e 3.000 kcal EM kg-1 não afetou a forca de ruptura da tíbia, gaite score marcha e angulação em valgus/varus de frangos de corte. Uma dieta com níveis de 16% de PB ou menos e 2.900-3.000 kcal EM kg-1 reduziu a resistência à ruptura do tendão e a resistência de tibia de frangos de corte.