Multi-modal deep learning for joint prediction of otitis media and diagnostic difficulty.

Objectives: In this study, we propose a diagnostic model for automatic detection of otitis media based on combined input of otoscopy images and wideband tympanometry measurements. Methods: We present a neural network-based model for the joint prediction of otitis media and diagnostic difficulty. We use the subclassifications acute otitis media and otitis media with effusion. The proposed approach is based on deep metric learning, and we compare this with the performance of a standard multi-task network. Results: The proposed deep metric approach shows good performance on both tasks, and we show that the multi-modal input increases the performance for both classification and difficulty estimation compared to the models trained on the modalities separately. An accuracy of 86.5% is achieved for the classification task, and a Kendall rank correlation coefficient of 0.45 is achieved for difficulty estimation, corresponding to a correct ranking of 72.6% of the cases. Conclusion: This study demonstrates the strengths of a multi-modal diagnostic tool using both otoscopy images and wideband tympanometry measurements for the diagnosis of otitis media. Furthermore, we show that deep metric learning improves the performance of the models.

Classification of fetal and adult red blood cells based on hydrodynamic deformation and deep video recognition.

Flow based deformation cytometry has shown potential for cell classification. We demonstrate the principle with an injection moulded microfluidic chip from which we capture videos of adult and fetal red blood cells, as they are being deformed in a microfluidic chip. Using a deep neural network - SlowFast - that takes the temporal behavior into account, we are able to discriminate between the cells with high accuracy. The accuracy was larger for adult blood cells than for fetal blood cells. However, no significant difference was observed between donors of the two types.

Effect of Histopathological Explanations for Dermoscopic Criteria on Learning Curves in Skin Cancer Training: a Randomized Controlled Trial.

INTRODUCTION: Case-based training improves novices pattern recognition and diagnostic accuracy in skin cancer diagnostics. However, it is unclear how pattern recognition is best taught in conjunction with the knowledge needed to justify a diagnosis. OBJECTIVES: The aim of this study was to examine whether an explanation of the underlying histopathological reason for dermoscopic criteria improves skill acquisition and retention during case-based training in skin cancer diagnostics. METHODS: In this double-blinded randomized controlled trial, medical students underwent eight days of case-based training in skin cancer diagnostics, which included access to written diagnosis modules. The modules dermoscopic subsections differed between the study groups. All participants received a general description of the criteria, but the intervention group additionally received a histopathological explanation. RESULTS: Most participants (78%) passed a reliable test in skin cancer diagnostics, following a mean training time of 217 minutes. Access to histopathological explanations did not affect participants' learning curves or skill retention. CONCLUSIONS: The histopathological explanation did not affect the students, but the overall educational approach was efficient and scalable.

Multi-centre deep learning for placenta segmentation in obstetric ultrasound with multi-observer and cross-country generalization.

The placenta is crucial to fetal well-being and it plays a significant role in the pathogenesis of hypertensive pregnancy disorders. Moreover, a timely diagnosis of placenta previa may save lives. Ultrasound is the primary imaging modality in pregnancy, but high-quality imaging depends on the access to equipment and staff, which is not possible in all settings. Convolutional neural networks may help standardize the acquisition of images for fetal diagnostics. Our aim was to develop a deep learning based model for classification and segmentation of the placenta in ultrasound images. We trained a model based on manual annotations of 7,500 ultrasound images to identify and segment the placenta. The model's performance was compared to annotations made by 25 clinicians (experts, trainees, midwives). The overall image classification accuracy was 81%. The average intersection over union score (IoU) reached 0.78. The model's accuracy was lower than experts' and trainees', but it outperformed all clinicians at delineating the placenta, IoU = 0.75 vs 0.69, 0.66, 0.59. The model was cross validated on 100 2nd trimester images from Barcelona, yielding an accuracy of 76%, IoU 0.68. In conclusion, we developed a model for automatic classification and segmentation of the placenta with consistent performance across different patient populations. It may be used for automated detection of placenta previa and enable future deep learning research in placental dysfunction.

A Deep Learning Approach for Detecting Otitis Media From Wideband Tympanometry Measurements.

OBJECTIVE: In this study, wepropose an automatic diagnostic algorithm for detecting otitis media based on wideband tympanometry measurements. METHODS: We develop a convolutional neural network for classification of otitis media based on the analysis of the wideband tympanogram. Saliency maps are computed to gain insight into the decision process of the convolutional neural network. Finally, we attempt to distinguish between otitis media with effusion and acute otitis media, a clinical subclassification important for the choice of treatment. RESULTS: The approach shows high performance on the overall otitis media detection with an accuracy of 92.6%. However, the approach is not able to distinguish between specific types of otitis media. CONCLUSION: Out approach can detect otitis media with high accuracy and the wideband tympanogram holds more diagnostic information than the commonly used techniques wideband absorbance measurements and simple tympanograms. SIGNIFICANCE: This study shows how advanced deep learning methods enable automatic diagnosis of otitis media based on wideband tympanometry measurements, which could become a valuable diagnostic tool.

Inter-rater reliability of the diagnosis of otitis media based on otoscopic images and wideband tympanometry measurements.

OBJECTIVES: This study aims to investigate the inter-rater reliability and agreement of the diagnosis of otitis media with effusion, acute otitis media, and no effusion cases based on an otoscopy image and in some cases an additional wideband tympanometry measurement of the patient. METHODS: 1409 cases were examined and diagnosed by an otolaryngologist in the clinic, and otoscopy examination and wideband tympanometry (WBT) measurement were conducted. Afterwards, four otolaryngologists (Ear, Nose, and Throat doctors, ENTs), who did not perform the acute examination of the patients, evaluated the otoscopy images and WBT measurements results for diagnosis (acute otitis media, otitis media with effusion, or no effusion). They also specified their diagnostic certainty for each case, and reported whether they used the image, wideband tympanometry, or both, for diagnosis. RESULTS: All four ENTs agreed on the diagnosis in 57% of the cases, with a pairwise agreement of 74%, and a Light's Kappa of 0.58. There are, however, large differences in agreement and certainty between the three diagnoses. Acute otitis media yields the highest agreement (77% between all four ENTs) and certainty (0.90), while no effusion shows much lower agreement and certainty (34% and 0.58, respectively). There is a positive correlation between certainty and agreement between the ENTs across all cases, and both certainty and agreement increase for cases where a WBT measurement is shown in addition to the otoscopy image. CONCLUSIONS: The inter-rater reliability between four ENTs was high when diagnosing acute otitis media and lower when diagnosing otitis media with effusion. However, WBT can add valuable information to get closer to the ground-truth diagnosis without myringotomy. Furthermore, the diagnostic certainty increases when the WBT is examined together with the otoscopy image.

Improved dynamic imaging of multiphase flow by constrained tomographic reconstruction.

Dynamic tomography has become an important technique to study fluid flow processes in porous media. The use of laboratory X-ray tomography instruments is, however, limited by their low X-ray brilliance. The prolonged exposure times, in turn, greatly limit temporal resolution. We have developed a tomographic reconstruction algorithm that maintains high image quality, despite reducing the exposure time and the number of projections significantly. Our approach, based on the Simultaneous Iterative Reconstruction Technique, mitigates the problem of few and noisy exposures by utilising a high-quality scan of the system before the dynamic process is started. We use the high-quality scan to initialise the first time step of the dynamic reconstruction. We further constrain regions of the dynamic reconstruction with a segmentation of the static system. We test the performance of the algorithm by reconstructing the dynamics of fluid separation in a multiphase system. The algorithm is compared quantitatively and qualitatively with several other reconstruction algorithms and we show that it can maintain high image quality using only a fraction of the normally required number of projections and with a substantially larger noise level. By robustly allowing fewer projections and shorter exposure, our algorithm enables the study of faster flow processes using laboratory tomography instrumentation but it can also be used to improve the reconstruction quality of dynamic synchrotron experiments.

Deep metric learning for otitis media classification.

In this study, we propose an automatic diagnostic algorithm for detecting otitis media based on otoscopy images of the tympanic membrane. A total of 1336 images were assessed by a medical specialist into three diagnostic groups: acute otitis media, otitis media with effusion, and no effusion. To provide proper treatment and care and limit the use of unnecessary antibiotics, it is crucial to correctly detect tympanic membrane abnormalities, and to distinguish between acute otitis media and otitis media with effusion. The proposed approach for this classification task is based on deep metric learning, and this study compares the performance of different distance-based metric loss functions. Contrastive loss, triplet loss and multi-class N-pair loss are employed, and compared with the performance of standard cross-entropy and class-weighted cross-entropy classification networks. Triplet loss achieves high precision on a highly imbalanced data set, and the deep metric methods provide useful insight into the decision making of a neural network. The results are comparable to the best clinical experts and paves the way for more accurate and operator-independent diagnosis of otitis media.

Effects of High-Intensity Exercise Training on Adipose Tissue Mass, Glucose Uptake and Protein Content in Pre- and Post-menopausal Women.

The menopausal transition is accompanied by changes in adipose tissue storage, leading to an android body composition associated with increased risk of type 2 diabetes and cardiovascular disease in post-menopausal women. Estrogens probably affect local adipose tissue depots differently. We investigated how menopausal status and exercise training influence adipose tissue mass, adipose tissue insulin sensitivity and adipose tissue proteins associated with lipogenesis/lipolysis and mitochondrial function. Healthy, normal-weight pre- (n = 21) and post-menopausal (n = 20) women participated in high-intensity exercise training three times per week for 12 weeks. Adipose tissue distribution was determined by dual-energy x-ray absorptiometry and magnetic resonance imaging. Adipose tissue glucose uptake was assessed by positron emission tomography/computed tomography (PET/CT) by the glucose analog [18F]fluorodeoxyglucose ([18F]FDG) during continuous insulin infusion (40 mU·m-2·min-1). Protein content associated with insulin signaling, lipogenesis/lipolysis, and mitochondrial function were determined by western blotting in abdominal and femoral white adipose tissue biopsies. The mean age difference between the pre- and the post-menopausal women was 4.5 years. Exercise training reduced subcutaneous (~4%) and visceral (~6%) adipose tissue masses similarly in pre- and post-menopausal women. Insulin-stimulated glucose uptake, assessed by [18F]FDG-uptake during PET/CT, was similar in pre- and post-menopausal women in abdominal, gluteal, and femoral adipose tissue depots, despite skeletal muscle insulin resistance in post- compared to pre-menopausal women in the same cohort. Insulin-stimulated glucose uptake in adipose tissue depots was not changed after 3 months of high-intensity exercise training, but insulin sensitivity was higher in visceral compared to subcutaneous adipose tissue depots (~139%). Post-menopausal women exhibited increased hexokinase and adipose triglyceride lipase content in subcutaneous abdominal adipose tissue. Physical activity in the early post-menopausal years reduces abdominal obesity, but insulin sensitivity of adipose tissue seems unaffected by both menopausal status and physical activity.

How does 6 months of active bike commuting or leisure-time exercise affect insulin sensitivity, cardiorespiratory fitness and intra-abdominal fat? A randomised controlled trial in individuals with overweight and obesity.

OBJECTIVES: To evaluate effects of active bike commuting or leisure-time exercise of two intensities on peripheral insulin sensitivity (primary outcome), cardiorespiratory fitness and intra-abdominal adipose tissue mass (secondary outcomes). METHODS: 188 physically inactive, healthy women and men (20-45 years) with overweight or class 1 obesity were recruited. In the 6-month trial, 130 participants were randomised to either: no intervention (CON), active commuting (BIKE) or leisure-time exercise of moderate (MOD, 50% VO2peak) or vigorous (VIG, 70% VO2peak) intensity. 100 completed follow-up testing. Exercise prescription was 5 days/week with a weekly exercise energy expenditure of 1600 kcal for women and 2100 kcal for men. Testing was performed at baseline, 3 months and 6 months. RESULTS: Peripheral insulin sensitivity (ml/min/pmol insulin/L) increased (improved) by 24% (95% CI 6% to 46%, p=0.01) in VIG compared with CON at 3 months. Peripheral insulin sensitivity increased (improved) by 20% in BIKE (95% CI 1% to 43%, p=0.04) and 26% in VIG (95% CI 7% to 47%, p<0.01) compared with CON at 6 months. Cardiorespiratory fitness increased in all exercise groups compared with CON at 6 months; but the increase was higher in those that undertook vigorous exercise than those who did moderate exercise. Intra-abdominal adipose tissue mass diminished across all exercise groups in comparison to CON at 6 months. CONCLUSIONS: Active bike commuting improved cardiometabolic health; as did leisure-time exercise. Leisure-time exercise of vigorous intensity conferred more rapid effects on peripheral insulin sensitivity as well as additional effects on cardiorespiratory fitness than did moderate intensity exercise. TRIAL REGISTRATION: NCT01962259.

A 16-Week Aerobic Exercise Intervention Does Not Affect Hippocampal Volume and Cortical Thickness in Mild to Moderate Alzheimer's Disease.

Introduction: Brain imaging studies in healthy elderly subjects suggest a positive effect of aerobic exercise on both brain structure and function, while the effects of aerobic exercise in Alzheimer's Disease (AD) has been scarcely investigated. Methods: In a single-blinded randomized MRI study, we assessed the effects of an aerobic exercise intervention on brain volume as measured by magnetic resonance imaging (MRI) and its correlation to cognitive functioning in patients with AD. The study was a sub-study of a larger randomized controlled trial (ADEX study). Forty-one patients were assigned to a control or exercise group. The exercise group performed 60-min of aerobic exercise three times per week for 16 weeks. All participants underwent whole-brain MRI at 3 Tesla and cognitive assessment at baseline and after 16 weeks. Attendance and intensity were monitored providing a total exercise load. Changes in regional brain volumes and cortical thickness were analyzed using Freesurfer software. Results: There was no effect of the type of intervention on MRI-derived brain volumes. In the entire group with and without training, Exercise load showed a positive correlation with changes in volume in the hippocampus, as well as frontal cortical thickness. Volume changes in frontal cortical thickness correlated with changes in measures of mental speed and attention and exercise load in the exercise group. Conclusion: We did not find evidence to support an effect of 16 weeks of aerobic exercise on brain volume changes in patients with AD. Longer intervention periods may be needed to affect brain structure as measured with volumetric MRI. Clinical Trial registration: ClinicalTrials.gov Identifier: NCT01681602, registered September 10th, 2012 (Retrospectively registered).

Effects of menopause and high-intensity training on insulin sensitivity and muscle metabolism.

OBJECTIVE: To investigate peripheral insulin sensitivity and skeletal muscle glucose metabolism in premenopausal and postmenopausal women, and evaluate whether exercise training benefits are maintained after menopause. METHODS: Sedentary, healthy, normal-weight, late premenopausal (n = 21), and early postmenopausal (n = 20) women were included in a 3-month high-intensity exercise training intervention. Body composition was assessed by magnetic resonance imaging and dual-energy x-ray absorptiometry, whole body glucose disposal rate (GDR) by hyperinsulinemic euglycemic clamp (40 mU/m/min), and femoral muscle glucose uptake by positron emission tomography/computed tomography, using the glucose analog fluorodeoxyglucose, expressed as estimated metabolic rate (eMR). Insulin signaling was investigated in muscle biopsies. RESULTS: Age difference between groups was 4.5 years, and no difference was observed in body composition. Training increased lean body mass (estimate [95% confidence interval] 0.5 [0.2-0.9] kg, P < 0.01) and thigh muscle mass (0.2 [-0.1 to 0.6] kg, P < 0.01), and decreased fat percentage (1.0 [0.5-1.5]%, P < 0.01) similarly in the two groups. The postmenopausal women had lower eMR in vastus lateralis muscle than the premenopausal women (-14.0 [-26.0 to -2.0] µmol/min/kg, P = 0.02), and tended to have lower eMR in femoral muscles (-11.2 [-22.7 to 0.4] µmol/min/kg, P = 0.06), and also GDR (-59.3 [-124.8 to 6.3] mg/min, P = 0.08), but increased similarly in both groups with training (eMR vastus lateralis muscle: 27.8 [19.6-36.0] µmol/min/kg, P < 0.01; eMR femoral muscle: 20.0 [13.1-26.7] µmol/min/kg, P < 0.01, respectively; GDR: 43.6 [10.4-76.9] mg/min, P = 0.01). Potential mechanisms underlying the training-induced increases in insulin sensitivity included increased expression of hexokinase (19.2 [5.0-24.7] AU, P = 0.02) and glycogen synthase (32.4 [15.0-49.8] AU, P < 0.01), and also increased insulin activation of Akt2 (20.6 [3.4-29.0], P = 0.03) and dephosphorylation of glycogen synthase (-41.8 [-82.9 to -0.7], P = 0.05). CONCLUSIONS: Insulin sensitivity was reduced in early postmenopausal women. However, postmenopausal women increased peripheral insulin sensitivity, skeletal muscle insulin-stimulated glucose uptake, and skeletal muscle mass to the same extent as premenopausal women after 3 months of high-intensity exercise training.