Results of the 2023 ISBI challenge to reduce GABA-edited MRS acquisition time.

PURPOSE: Use a conference challenge format to compare machine learning-based gamma-aminobutyric acid (GABA)-edited magnetic resonance spectroscopy (MRS) reconstruction models using one-quarter of the transients typically acquired during a complete scan. METHODS: There were three tracks: Track 1: simulated data, Track 2: identical acquisition parameters with in vivo data, and Track 3: different acquisition parameters with in vivo data. The mean squared error, signal-to-noise ratio, linewidth, and a proposed shape score metric were used to quantify model performance. Challenge organizers provided open access to a baseline model, simulated noise-free data, guides for adding synthetic noise, and in vivo data. RESULTS: Three submissions were compared. A covariance matrix convolutional neural network model was most successful for Track 1. A vision transformer model operating on a spectrogram data representation was most successful for Tracks 2 and 3. Deep learning (DL) reconstructions with 80 transients achieved equivalent or better SNR, linewidth and fit error compared to conventional 320 transient reconstructions. However, some DL models optimized linewidth and SNR without actually improving overall spectral quality, indicating a need for more robust metrics. CONCLUSION: DL-based reconstruction pipelines have the promise to reduce the number of transients required for GABA-edited MRS.

A review of machine learning applications for the proton MR spectroscopy workflow.

This literature review presents a comprehensive overview of machine learning (ML) applications in proton MR spectroscopy (MRS). As the use of ML techniques in MRS continues to grow, this review aims to provide the MRS community with a structured overview of the state-of-the-art methods. Specifically, we examine and summarize studies published between 2017 and 2023 from major journals in the MR field. We categorize these studies based on a typical MRS workflow, including data acquisition, processing, analysis, and artificial data generation. Our review reveals that ML in MRS is still in its early stages, with a primary focus on processing and analysis techniques, and less attention given to data acquisition. We also found that many studies use similar model architectures, with little comparison to alternative architectures. Additionally, the generation of artificial data is a crucial topic, with no consistent method for its generation. Furthermore, many studies demonstrate that artificial data suffers from generalization issues when tested on in vivo data. We also conclude that risks related to ML models should be addressed, particularly for clinical applications. Therefore, output uncertainty measures and model biases are critical to investigate. Nonetheless, the rapid development of ML in MRS and the promising results from the reviewed studies justify further research in this field.

Temporal dynamics of awakenings from slow-wave sleep in non-rapid eye movement parasomnia.

Non-rapid eye movement parasomnia disorders, also called disorders of arousal, are characterized by abnormal nocturnal behaviours, such as confusional arousals or sleep walking. Their pathophysiology is not yet fully understood, and objective diagnostic criteria are lacking. It is known, however, that behavioural episodes occur mostly in the beginning of the night, after an increase in slow-wave activity during slow-wave sleep. A better understanding of the prospect of such episodes may lead to new insights in the underlying mechanisms and eventually facilitate objective diagnosis. We investigated temporal dynamics of transitions from slow-wave sleep of 52 patients and 79 controls. Within the patient group, behavioural and non-behavioural N3 awakenings were distinguished. Patients showed a higher probability to wake up after an N3 bout ended than controls, and this probability increased with N3 bout duration. Bouts longer than 15 min resulted in an awakening in 73% and 34% of the time in patients and controls, respectively. Behavioural episodes reduced over sleep cycles due to a reduction in N3 sleep and a reducing ratio between behavioural and non-behavioural awakenings. In the first two cycles, N3 bouts prior to non-behavioural awakenings were significantly shorter than N3 bouts advancing behavioural awakenings in patients, and N3 awakenings in controls. Our findings provide insights in the timing and prospect of both behavioural and non-behavioural awakenings from N3, which may result in prediction and potentially prevention of behavioural episodes. This work, moreover, leads to a more complete characterization of a prototypical hypnogram of parasomnias, which could facilitate diagnosis.

A review on B/A measurement methods with a clinical perspective.

The nonlinear parameter of ultrasound B/A has shown to be a useful diagnostic parameter, reflecting medium content, structure, and temperature. Despite its recognized values, B/A is not yet used as a diagnostic tool in the clinic due to the limitations of current measurement and imaging techniques. This review presents an extensive and comprehensive overview of the techniques developed for B/A measurement of liquid and liquid-like media (e.g., tissue), identifying the methods that are most promising from a clinical perspective. This work summarizes the progress made in the field and the typical challenges on the way to B/A estimation. Limitations and problems with the current techniques are identified, suggesting directions that may lead to further improvement. Since the basic theory of the physics behind the measurement strategies is presented, it is also suited for a reader who is new to nonlinear ultrasound.

Detection of clinically significant prostate cancer in biopsy-naïve men: direct comparison of systematic biopsy, multiparametric MRI- and contrast-ultrasound-dispersion imaging-targeted biopsy.

OBJECTIVES: To compare and evaluate a multiparametric magnetic resonance imaging (mpMRI)-targeted biopsy (TBx) strategy, contrast-ultrasound-dispersion imaging (CUDI)-TBx strategy and systematic biopsy (SBx) strategy for the detection of clinically significant prostate cancer (csPCa) in biopsy-naïve men. PATIENTS AND METHODS: A prospective, single-centre paired diagnostic study included 150 biopsy-naïve men, from November 2015 to November 2018. All men underwent pre-biopsy mpMRI and CUDI followed by a 12-core SBx taken by an operator blinded from the imaging results. Men with suspicious lesions on mpMRI and/or CUDI also underwent MRI-TRUS fusion-TBx and/or cognitive CUDI-TBx after SBx by a second operator. A non-inferiority analysis of the mpMRI- and CUDI-TBx strategies in comparison with SBx for International Society of Urological Pathology Grade Group [GG] ≥2 PCa in any core with a non-inferiority margin of 1 percentage point was performed. Additional analyses for GG ≥2 PCa with cribriform growth pattern and/or intraductal carcinoma (CR/IDC), and GG ≥3 PCa were performed. Differences in detection rates were tested using McNemar's test with adjusted Wald confidence intervals. RESULTS: After enrolment of 150 men, an interim analysis was performed. Both the mpMRI- and CUDI-TBx strategies were inferior to SBx for GG ≥2 PCa detection and the study was stopped. SBx found significantly more GG ≥2 PCa: 39% (56/142), as compared with 29% (41/142) and 28% (40/142) for mpMRI-TBx and CUDI-TBx, respectively (P < 0.05). SBx found significantly more GG = 1 PCa: 14% (20/142) compared to 1% (two of 142) and 3% (four of 142) with mpMRI-TBx and CUDI-TBx, respectively (P < 0.05). Detection of GG ≥2 PCa with CR/IDC and GG ≥3 PCa did not differ significantly between the strategies. The mpMRI- and CUDI-TBx strategies were comparable in detection but the mpMRI-TBx strategy had less false-positive findings (18% vs 53%). CONCLUSIONS: In our study in biopsy-naïve men, the mpMRI- and CUDI-TBx strategies had comparable PCa detection rates, but the mpMRI-TBX strategy had the least false-positive findings. Both strategies were inferior to SBx for the detection of GG ≥2 PCa, despite reduced detection of insignificant GG = 1 PCa. Both strategies did not significantly differ from SBx for the detection of GG ≥2 PCa with CR/IDC and GG ≥3 PCa.

Contrast-enhanced ultrasound with dispersion analysis for the localization of prostate cancer: correlation with radical prostatectomy specimens.

PURPOSE: To determine the value of two-dimensional (2D) contrast-enhanced ultrasound (CEUS) imaging and the additional value of contrast ultrasound dispersion imaging (CUDI) for the localization of clinically significant prostate cancer (csPCa). METHODS: In this multicentre study, subjects scheduled for a radical prostatectomy underwent 2D CEUS imaging preoperatively. CUDI maps were generated from the CEUS recordings. Both CEUS recordings and CUDI maps were scored on the likelihood of presenting csPCa (any Gleason ≥ 4 + 3 and Gleason 3 + 4 larger than 0.5 mL) by five observers and compared to radical prostatectomy histopathology. An automated three-dimensional (3D) fusion protocol was used to match imaging with histopathology. Receiver operator curve (ROC) analysis was performed per observer and imaging modality. RESULTS: 133 of 216 (62%) patients were included in the final analysis. Average area under the ROC for all five readers for CEUS, CUDI and the combination was 0.78, 0.79 and 0.78, respectively. This yields a sensitivity and specificity of 81 and 64% for CEUS, 83 and 56% for CUDI and 83 and 55% for the combination. Interobserver agreement for CEUS, CUDI and the combination showed kappa values of 0.20, 0.18 and 0.18 respectively. CONCLUSION: The sensitivity and specificity of 2D CEUS and CUDI for csPCa localization are moderate. Despite compressing CEUS in one image, CUDI showed a similar performance to 2D CEUS. With a sensitivity of 83% at cutoff point 3, it could become a useful imaging procedure, especially with 4D acquisition, improved quantification and combination with other US imaging techniques such as elastography.

Automated multiparametric localization of prostate cancer based on B-mode, shear-wave elastography, and contrast-enhanced ultrasound radiomics.

OBJECTIVES: The aim of this study was to assess the potential of machine learning based on B-mode, shear-wave elastography (SWE), and dynamic contrast-enhanced ultrasound (DCE-US) radiomics for the localization of prostate cancer (PCa) lesions using transrectal ultrasound. METHODS: This study was approved by the institutional review board and comprised 50 men with biopsy-confirmed PCa that were referred for radical prostatectomy. Prior to surgery, patients received transrectal ultrasound (TRUS), SWE, and DCE-US for three imaging planes. The images were automatically segmented and registered. First, model-based features related to contrast perfusion and dispersion were extracted from the DCE-US videos. Subsequently, radiomics were retrieved from all modalities. Machine learning was applied through a random forest classification algorithm, using the co-registered histopathology from the radical prostatectomy specimens as a reference to draw benign and malignant regions of interest. To avoid overfitting, the performance of the multiparametric classifier was assessed through leave-one-patient-out cross-validation. RESULTS: The multiparametric classifier reached a region-wise area under the receiver operating characteristics curve (ROC-AUC) of 0.75 and 0.90 for PCa and Gleason > 3 + 4 significant PCa, respectively, thereby outperforming the best-performing single parameter (i.e., contrast velocity) yielding ROC-AUCs of 0.69 and 0.76, respectively. Machine learning revealed that combinations between perfusion-, dispersion-, and elasticity-related features were favored. CONCLUSIONS: In this paper, technical feasibility of multiparametric machine learning to improve upon single US modalities for the localization of PCa has been demonstrated. Extended datasets for training and testing may establish the clinical value of automatic multiparametric US classification in the early diagnosis of PCa. KEY POINTS: • Combination of B-mode ultrasound, shear-wave elastography, and contrast ultrasound radiomics through machine learning is technically feasible. • Multiparametric ultrasound demonstrated a higher prostate cancer localization ability than single ultrasound modalities. • Computer-aided multiparametric ultrasound could help clinicians in biopsy targeting.

Multiparametric Ultrasound for Prostate Cancer Detection and Localization: Correlation of B-mode, Shear Wave Elastography and Contrast Enhanced Ultrasound with Radical Prostatectomy Specimens.

PURPOSE: Similar to multiparametric magnetic resonance imaging, multiparametric ultrasound represents a promising approach to prostate cancer imaging. We determined the diagnostic performance of B-mode, shear wave elastography and contrast enhanced ultrasound with quantification software as well as the combination, multiparametric ultrasound, for clinically significant prostate cancer localization using radical prostatectomy histopathology as the reference standard. MATERIALS AND METHODS: From May 2017 to July 2017, 50 men with biopsy proven prostate cancer underwent multiparametric ultrasound before radical prostatectomy at 1 center. Three readers independently evaluated 12 anatomical regions of interest for the likelihood of clinically significant prostate cancer on a 5-point Likert scale for all separate ultrasound modalities and multiparametric ultrasound. A logistic linear mixed model was used to estimate diagnostic performance for the localization of clinically significant prostate cancer (any tumor with Gleason score 3 + 4 = 7 or greater, tumor volume 0.5 ml or greater, extraprostatic extension or stage pN1) using a Likert score of 3 or greater and 4 or greater as the threshold. To detect the index lesion the readers selected the 2 most suspicious regions of interest. RESULTS: A total of 48 men were included in the final analysis. The region of interest specific sensitivity of multiparametric ultrasound (Likert 3 or greater) for clinically significant prostate cancer was 74% (95% CI 67-80) compared to 55% (95% CI 47-63), 55% (95% CI 47-63) and 59% (95% CI 51-67) for B-mode, shear wave elastography and contrast enhanced ultrasound, respectively. Multiparametric ultrasound sensitivity was significantly higher for Likert thresholds and all different clinically significant prostate cancer definitions (all p <0.05). Multiparametric ultrasound improved the detection of index lesion prostate cancer. CONCLUSIONS: Multiparametric ultrasound of the prostate, consisting of B-mode, shear wave elastography and contrast enhanced ultrasound with parametric maps, improved localization and index lesion detection of clinically significant prostate cancer compared to single ultrasound modalities, yielding good sensitivity.

Ultrasound Viscoelastography by Acoustic Radiation Force: A State-of-the-Art Review.

Ultrasound elastography (USE) is a promising tool for tissue characterization as several diseases result in alterations of tissue structure and composition, which manifest as changes in tissue mechanical properties. By imaging the tissue response to an applied mechanical excitation, USE mimics the manual palpation performed by clinicians to sense the tissue elasticity for diagnostic purposes. Next to elasticity, viscosity has recently been investigated as an additional, relevant, diagnostic biomarker. Moreover, since biological tissues are inherently viscoelastic, accounting for viscosity in the tissue characterization process enhances the accuracy of the elasticity estimation. Recently, methods exploiting different acquisition and processing techniques have been proposed to perform ultrasound viscoelastography. After introducing the physics describing viscoelasticity, a comprehensive overview of the currently available USE acquisition techniques is provided, followed by a structured review of the existing viscoelasticity estimators classified according to the employed processing technique. These estimators are further reviewed from a clinical usage perspective, and current outstanding challenges are discussed.

Dehazing Ultrasound using Diffusion Models.

Echocardiography has been a prominent tool for the diagnosis of cardiac disease. However, these diagnoses can be heavily impeded by poor image quality. Acoustic clutter emerges due to multipath reflections imposed by layers of skin, subcutaneous fat, and intercostal muscle between the transducer and heart. As a result, haze and other noise artifacts pose a real challenge to cardiac ultrasound imaging. In many cases, especially with difficult-to-image patients such as patients with obesity, a diagnosis from B-Mode ultrasound imaging is effectively rendered unusable, forcing sonographers to resort to contrast-enhanced ultrasound examinations or refer patients to other imaging modalities. Tissue harmonic imaging has been a popular approach to combat haze, but in severe cases is still heavily impacted by haze. Alternatively, denoising algorithms are typically unable to remove highly structured and correlated noise, such as haze. It remains a challenge to accurately describe the statistical properties of structured haze, and develop an inference method to subsequently remove it. Diffusion models have emerged as powerful generative models and have shown their effectiveness in a variety of inverse problems. In this work, we present a joint posterior sampling framework that combines two separate diffusion models to model the distribution of both clean ultrasound and haze in an unsupervised manner. Furthermore, we demonstrate techniques for effectively training diffusion models on radio-frequency ultrasound data and highlight the advantages over image data. Experiments on both in-vitro and in-vivo cardiac datasets show that the proposed dehazing method effectively removes haze while preserving signals from weakly reflected tissue.

Maximum a posteriori detection of heartbeats from a chest-worn accelerometer.

Objective. Unobtrusive long-term monitoring of cardiac parameters is important in a wide variety of clinical applications, such as the assesment of acute illness severity and unobtrusive sleep monitoring. Here we determined the accuracy and robustness of heartbeat detection by an accelerometer worn on the chest.Approach. We performed overnight recordings in 147 individuals (69 female, 78 male) referred to two sleep centers. Two methods for heartbeat detection in the acceleration signal were compared: one previously described approach, based on local periodicity, and a novel extended method incorporating maximumaposterioriestimation and a Markov decision process to approach an optimal solution.Main results. The maximumaposterioriestimation significantly improved performance, with a mean absolute error for the estimation of inter-beat intervals of only 3.5 ms, and 95% limits of agreement of -1.7 to +1.0 beats per minute for heartrate measurement. Performance held during posture changes and was only weakly affected by the presence of sleep disorders and demographic factors.Significance. The new method may enable the use of a chest-worn accelerometer in a variety of applications such as ambulatory sleep staging and in-patient monitoring.

Single-channel EOG sleep staging on a heterogeneous cohort of subjects with sleep disorders.

Objective.Sleep staging based on full polysomnography is the gold standard in the diagnosis of many sleep disorders. It is however costly, complex, and obtrusive due to the use of multiple electrodes. Automatic sleep staging based on single-channel electro-oculography (EOG) is a promising alternative, requiring fewer electrodes which could be self-applied below the hairline. EOG sleep staging algorithms are however yet to be validated in clinical populations with sleep disorders.Approach.We utilized the SOMNIA dataset, comprising 774 recordings from subjects with various sleep disorders, including insomnia, sleep-disordered breathing, hypersomnolence, circadian rhythm disorders, parasomnias, and movement disorders. The recordings were divided into train (574), validation (100), and test (100) groups. We trained a neural network that integrated transformers within a U-Net backbone. This design facilitated learning of arbitrary-distance temporal relationships within and between the EOG and hypnogram.Main results.For 5-class sleep staging, we achieved median accuracies of 85.0% and 85.2% and Cohen's kappas of 0.781 and 0.796 for left and right EOG, respectively. The performance using the right EOG was significantly better than using the left EOG, possibly because in the recommended AASM setup, this electrode is located closer to the scalp. The proposed model is robust to the presence of a variety of sleep disorders, displaying no significant difference in performance for subjects with a certain sleep disorder compared to those without.Significance.The results show that accurate sleep staging using single-channel EOG can be done reliably for subjects with a variety of sleep disorders.

Artificial intelligence based cardiotocogram assessment during labor.

OBJECTIVE: To assess whether artificial intelligence, inspired by clinical decision-making procedures in delivery rooms, can correctly interpret cardiotocographic tracings and distinguish between normal and pathological events. STUDY DESIGN: A method based on artificial intelligence was developed to determine whether a cardiotocogram shows a normal response of the fetal heart rate to uterine activity (UA). For a given fetus and given the UA and previous FHR, the method predicts a fetal heart rate response, under the assumption that the fetus is still in good condition and based on how that specific fetus has responded so far. We hypothesize that this method, when having only learned from fetuses born in good condition, is incapable of predicting the response of a compromised fetus or an episode of transient fetal distress. The (in)capability of the method to predict the fetal heart rate response would then yield a method that can help to assess fetal condition when the obstetrician is in doubt. Cardiotocographic data of 678 deliveries during labor were selected based on a healthy outcome just after birth. The method was trained on the cardiotocographic data of 548 fetuses of this group to learn their heart rate response. Subsequently it was evaluated on 87 fetuses, by assessing whether the method was able to predict their heart rate responses. The remaining 43 cardiotocograms were segment-by-segment annotated by three experienced gynecologists, indicating normal, suspicious, and pathological segments, while having access to the full recording and neonatal outcome. This future knowledge makes the expert annotations of a quality that is unachievable during live interpretation. RESULTS: The comparison between abnormalities detected by the method (only using past and present input) and the annotated CTG segments by gynecologists (also looking at future input) yields an area under the curve of 0.96 for the distinction between normal and pathological events in majority-voted annotations. CONCLUSION: The developed method can distinguish between normal and pathological events in near real-time, with a performance close to the agreement between three gynecologists with access to the entire CTG tracing and fetal outcome. The method has a strong potential to support clinicians in assessing fetal condition in clinical practice.

A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning.

The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities. Over the past years, the machine learning community has proposed several extensions of this trick to facilitate, e.g., drawing multiple samples, sampling from structured domains, or gradient estimation for error backpropagation in neural network optimization. The goal of this survey article is to present background about the Gumbel-max trick, and to provide a structured overview of its extensions to ease algorithm selection. Moreover, it presents a comprehensive outline of (machine learning) literature in which Gumbel-based algorithms have been leveraged, reviews commonly-made design choices, and sketches a future perspective.

Ultrasound Signal Processing: From Models to Deep Learning.

Medical ultrasound imaging relies heavily on high-quality signal processing to provide reliable and interpretable image reconstructions. Conventionally, reconstruction algorithms have been derived from physical principles. These algorithms rely on assumptions and approximations of the underlying measurement model, limiting image quality in settings where these assumptions break down. Conversely, more sophisticated solutions based on statistical modeling or careful parameter tuning or derived from increased model complexity can be sensitive to different environments. Recently, deep learning-based methods, which are optimized in a data-driven fashion, have gained popularity. These model-agnostic techniques often rely on generic model structures and require vast training data to converge to a robust solution. A relatively new paradigm combines the power of the two: leveraging data-driven deep learning and exploiting domain knowledge. These model-based solutions yield high robustness and require fewer parameters and training data than conventional neural networks. In this work we provide an overview of these techniques from the recent literature and discuss a wide variety of ultrasound applications. We aim to inspire the reader to perform further research in this area and to address the opportunities within the field of ultrasound signal processing. We conclude with a future perspective on model-based deep learning techniques for medical ultrasound.

Modeling the Impact of Inter-Rater Disagreement on Sleep Statistics Using Deep Generative Learning.

Sleep staging is the process by which an overnight polysomnographic measurement is segmented into epochs of 30 seconds, each of which is annotated as belonging to one of five discrete sleep stages. The resulting scoring is graphically depicted as a hypnogram, and several overnight sleep statistics are derived, such as total sleep time and sleep onset latency. Gold standard sleep staging as performed by human technicians is time-consuming, costly, and comes with imperfect inter-scorer agreement, which also results in inter-scorer disagreement about the overnight statistics. Deep learning algorithms have shown promise in automating sleep scoring, but struggle to model inter-scorer disagreement in sleep statistics. To that end, we introduce a novel technique using conditional generative models based on Normalizing Flows that permits the modeling of the inter-rater disagreement of overnight sleep statistics, termed U-Flow. We compare U-Flow to other automatic scoring methods on a hold-out test set of 70 subjects, each scored by six independent scorers. The proposed method achieves similar sleep staging performance in terms of accuracy and Cohen's kappa on the majority-voted hypnograms. At the same time, U-Flow outperforms the other methods in terms of modeling the inter-rater disagreement of overnight sleep statistics. The consequences of inter-rater disagreement about overnight sleep statistics may be great, and the disagreement potentially carries diagnostic and scientifically relevant information about sleep structure. U-Flow is able to model this disagreement efficiently and can support further investigations into the impact inter-rater disagreement has on sleep medicine and basic sleep research.

Shear-Wave Particle-Velocity Estimation and Enhancement Using a Multi-Resolution Convolutional Neural Network.

OBJECTIVE: Tissue mechanical properties are valuable markers for tissue characterization, aiding in the detection and staging of pathologies. Shear wave elastography (SWE) offers a quantitative assessment of tissue mechanical characteristics based on the SW propagation profile, which is derived from the SW particle motion. Improving the signal-to-noise ratio (SNR) of the SW particle motion would directly enhance the accuracy of the material property estimates such as elasticity or viscosity. METHODS: In this paper, we present a 3-D multi-resolution convolutional neural network (MRCNN) to perform improved estimation of the SW particle velocity Vz. Additionally, we propose a novel approach to generate training data from real acquisitions, providing high SNR ground truth target data, one-to-one paired to inputs that are corrupted with real-world noise and disturbances. DISCUSSION: By testing the network on in vitro data acquired from a commercial breast elastography phantom, we show that the MRCNN outperforms Loupas' autocorrelation algorithm with an improved SNR of 4.47 dB for the Vz signals, a two-fold decrease in the standard deviation of the downstream elasticity estimates, and a two-fold increase in the contrast-to-noise ratio of the elasticity maps. The generalizability of the network was further demonstrated with a set of ex vivo porcine liver data. CONCLUSION: The proposed MRCNN outperforms the standard autocorrelation method, in particular in low SNR regimes.

Interpretation and further development of the hypnodensity representation of sleep structure.

Objective.The recently-introduced hypnodensity graph provides a probability distribution over sleep stages per data window (i.e. an epoch). This work explored whether this representation reveals continuities that can only be attributed to intra- and inter-rater disagreement of expert scorings, or also to co-occurrence of sleep stage-dependent features within one epoch.Approach.We proposed a simplified model for time series like the ones measured during sleep, and a second model to describe the annotation process by an expert. Generating data according to these models, enabled controlled experiments to investigate the interpretation of the hypnodensity graph. Moreover, the influence of both the supervised training strategy, and the used softmax non-linearity were investigated. Polysomnography recordings of 96 healthy sleepers (of which 11 were used as independent test set), were subsequently used to transfer conclusions to real data.Main results.A hypnodensity graph, predicted by a supervised neural classifier, represents the probability with which the sleep expert(s) assigned a label to an epoch. It thus reflects annotator behavior, and is thereby only indirectly linked to the ratio of sleep stage-dependent features in the epoch. Unsupervised training was shown to result in hypnodensity graph that were slightly less dependent on this annotation process, resulting in, on average, higher-entropy distributions over sleep stages (Hunsupervised= 0.41 versusHsupervised= 0.29). Moreover, pre-softmax predictions were, for both training strategies, found to better reflect the ratio of sleep stage-dependent characteristics in an epoch, as compared to the post-softmax counterparts (i.e. the hypnodensity graph). In real data, this was observed from the linear relation between pre-softmax N3 predictions and the amount of delta power.Significance.This study provides insights in, and proposes new, representations of sleep that may enhance our comprehension about sleep and sleep disorders.

Improving Lateral Resolution in 3-D Imaging With Micro-beamforming Through Adaptive Beamforming by Deep Learning.

There is an increased desire for miniature ultrasound probes with small apertures to provide volumetric images at high frame rates for in-body applications. Satisfying these increased requirements makes simultaneous achievement of a good lateral resolution a challenge. As micro-beamforming is often employed to reduce data rate and cable count to acceptable levels, receive processing methods that try to improve spatial resolution will have to compensate the introduced reduction in focusing. Existing beamformers do not realize sufficient improvement and/or have a computational cost that prohibits their use. Here we propose the use of adaptive beamforming by deep learning (ABLE) in combination with training targets generated by a large aperture array, which inherently has better lateral resolution. In addition, we modify ABLE to extend its receptive field across multiple voxels. We illustrate that this method improves lateral resolution both quantitatively and qualitatively, such that image quality is improved compared with that achieved by existing delay-and-sum, coherence factor, filtered-delay-multiplication-and-sum and Eigen-based minimum variance beamformers. We found that only in silica data are required to train the network, making the method easily implementable in practice.