Unpaired, unsupervised domain adaptation assumes your domains are already similar.

Unsupervised domain adaptation is a popular method in medical image analysis, but it can be tricky to make it work: without labels to link the domains, domains must be matched using feature distributions. If there is no additional information, this often leaves a choice between multiple possibilities to map the data that may be equally likely but not equally correct. In this paper we explore the fundamental problems that may arise in unsupervised domain adaptation, and discuss conditions that might still make it work. Focusing on medical image analysis, we argue that images from different domains may have similar class balance, similar intensities, similar spatial structure, or similar textures. We demonstrate how these implicit conditions can affect domain adaptation performance in experiments with synthetic data, MNIST digits, and medical images. We observe that practical success of unsupervised domain adaptation relies on existing similarities in the data, and is anything but guaranteed in the general case. Understanding these implicit assumptions is a key step in identifying potential problems in domain adaptation and improving the reliability of the results.

MRI changes in diaphragmatic motion and curvature in Pompe disease over time.

OBJECTIVES: To evaluate changes in diaphragmatic function in Pompe disease using MRI over time, both during natural disease course and during treatment with enzyme replacement therapy (ERT). METHODS: In this prospective study, 30 adult Pompe patients and 10 healthy controls underwent pulmonary function tests and spirometry-controlled MRI twice, with an interval of 1 year. In the sagittal view of 3D gradient echo breath-hold acquisitions, diaphragmatic motion (cranial-caudal ratio between end-inspiration and end-expiration) and curvature (diaphragm height and area ratio) were calculated using a machine learning algorithm based on convolutional neural networks. Changes in outcomes after 1 year were compared between Pompe patients and healthy controls using the Mann-Whitney test. RESULTS: Pulmonary function outcomes and cranial-caudal ratio in Pompe patients did not change significantly over time compared to healthy controls. Diaphragm height ratio increased by 0.04 (-0.38 to 1.79) in Pompe patients compared to -0.02 (-0.18 to 0.25) in healthy controls (p = 0.02). An increased diaphragmatic curvature over time was observed in particular in untreated Pompe patients (p = 0.03), in those receiving ERT already for over 3 years (p = 0.03), and when severe diaphragmatic weakness was found on the initial MRI (p = 0.01); no progression was observed in Pompe patients who started ERT less than 3 years ago and in Pompe patients with mild diaphragmatic weakness on their initial MRI. CONCLUSIONS: MRI enables to detect small changes in diaphragmatic curvature over 1-year time in Pompe patients. It also showed that once severe diaphragmatic weakness has occurred, improvement of diaphragmatic muscle function seems unlikely. KEY POINTS: • Changes in diaphragmatic curvature in Pompe patients over time assessed with 3D MRI may serve as an outcome measure to evaluate the effect of treatment on diaphragmatic function. • Diaphragmatic curvature showed a significant deterioration after 1 year in Pompe patients compared to healthy controls, but the curvature seems to remain stable over this period in patients who were treated with enzyme replacement therapy for less than 3 years, possibly indicating a positive effect of ERT. • Improvement of diaphragmatic curvature over time is rarely seen in Pompe patients once diaphragmatic motion shows severe impairment (cranial-caudal inspiratory/expiratory ratio < 1.4).

Diaphragmatic dysfunction in neuromuscular disease, an MRI study.

The aim of this exploratory study was to evaluate diaphragmatic function across various neuromuscular diseases using spirometry-controlled MRI. We measured motion of the diaphragm relative to that of the thoracic wall (cranial-caudal ratio vs. anterior posterior ratio; CC-AP ratio), and changes in the diaphragmatic curvature (diaphragm height and area ratio) during inspiration in 12 adults with a neuromuscular disease having signs of respiratory muscle weakness, 18 healthy controls, and 35 adult Pompe patients - a group with prominent diaphragmatic weakness. CC-AP ratio was lower in patients with myopathies (n=7, 1.25±0.30) and motor neuron diseases (n=5, 1.30±0.10) than in healthy controls (1.37±0.14; p=0.001 and p=0.008), but not as abnormal as in Pompe patients (1.12±0.18; p=0.011 and p=0.024). The mean diaphragm height ratio was 1.17±0.33 in patients with myopathies, pointing at an insufficient diaphragmatic contraction. This was also seen in patients with Pompe disease (1.28±0.36), but not in healthy controls (0.82±0.33) or patients with motor neuron disease (0.82±0.24). We conclude that spirometry-controlled MRI enables us to investigate respiratory dysfunction across neuromuscular diseases, suggesting that the diaphragm is affected in a different way in myopathies and motor neuron diseases. Whether MRI can also be used to evaluate progression of diaphragmatic dysfunction requires additional studies.

An end-to-end approach to segmentation in medical images with CNN and posterior-CRF.

Conditional Random Fields (CRFs) are often used to improve the output of an initial segmentation model, such as a convolutional neural network (CNN). Conventional CRF approaches in medical imaging use manually defined features, such as intensity to improve appearance similarity or location to improve spatial coherence. These features work well for some tasks, but can fail for others. For example, in medical image segmentation applications where different anatomical structures can have similar intensity values, an intensity-based CRF may produce incorrect results. As an alternative, we propose Posterior-CRF, an end-to-end segmentation method that uses CNN-learned features in a CRF and optimizes the CRF and CNN parameters concurrently. We validate our method on three medical image segmentation tasks: aorta and pulmonary artery segmentation in non-contrast CT, white matter hyperintensities segmentation in multi-modal MRI, and ischemic stroke lesion segmentation in multi-modal MRI. We compare this with the state-of-the-art CNN-CRF methods. In all applications, our proposed method outperforms the existing methods in terms of Dice coefficient, average volume difference, and lesion-wise F1 score.

Automated Segmentation and Volume Measurement of Intracranial Internal Carotid Artery Calcification at Noncontrast CT.

PURPOSE: To develop and evaluate a fully-automated deep learning-based method for assessment of intracranial internal carotid artery calcification (ICAC). MATERIALS AND METHODS: This was a secondary analysis of prospectively collected data from the Rotterdam study (2003-2006) to develop and validate a deep learning-based method for automated ICAC delineation and volume measurement. Two observers manually delineated ICAC on noncontrast CT scans of 2319 participants (mean age, 69 years ± 7 [standard deviation]; 1154 women [53.2%]), and a deep learning model was trained to segment ICAC and quantify its volume. Model performance was assessed by comparing manual and automated segmentations and volume measurements to those produced by an independent observer (available on 47 scans), comparing the segmentation accuracy in a blinded qualitative visual comparison by an expert observer, and comparing the association with first stroke incidence from the scan date until 2016. All method performance metrics were computed using 10-fold cross-validation. RESULTS: The automated delineation of ICAC reached a sensitivity of 83.8% and positive predictive value (PPV) of 88%. The intraclass correlation between automatic and manual ICAC volume measures was 0.98 (95% CI: 0.97, 0.98; computed in the entire dataset). Measured between the assessments of independent observers, sensitivity was 73.9%, PPV was 89.5%, and intraclass correlation coefficient was 0.91 (95% CI: 0.84, 0.95; computed in the 47-scan subset). In the blinded visual comparisons of 294 regions, automated delineations were judged as more accurate than manual delineations in 131 regions, less accurate in 94 regions, and equally accurate in the rest of the regions (131 of 225, 58.2%; P = .01). The association of ICAC volume with incident stroke was similarly strong for both automated (hazard ratio, 1.38 [95% CI: 1.12, 1.75]) and manually measured volumes (hazard ratio, 1.48 [95% CI: 1.20, 1.87]). CONCLUSION: The developed model was capable of automated segmentation and volume quantification of ICAC with accuracy comparable to human experts.Keywords CT, Neural Networks, Carotid Arteries, Calcifications/Calculi, Arteriosclerosis, Segmentation, Vision Application Domain, Stroke Supplemental material is available for this article. © RSNA, 2021.

Chest MRI to diagnose early diaphragmatic weakness in Pompe disease.

BACKGROUND: In Pompe disease, an inherited metabolic muscle disorder, severe diaphragmatic weakness often occurs. Enzyme replacement treatment is relatively ineffective for respiratory function, possibly because of irreversible damage to the diaphragm early in the disease course. Mildly impaired diaphragmatic function may not be recognized by spirometry, which is commonly used to study respiratory function. In this cross-sectional study, we aimed to identify early signs of diaphragmatic weakness in Pompe patients using chest MRI. METHODS: Pompe patients covering the spectrum of disease severity, and sex and age matched healthy controls were prospectively included and studied using spirometry-controlled sagittal MR images of both mid-hemidiaphragms during forced inspiration. The motions of the diaphragm and thoracic wall were evaluated by measuring thoracic cranial-caudal and anterior-posterior distance ratios between inspiration and expiration. The diaphragm shape was evaluated by measuring the height of the diaphragm curvature. We used multiple linear regression analysis to compare different groups. RESULTS: We included 22 Pompe patients with decreased spirometry results (forced vital capacity in supine position < 80% predicted); 13 Pompe patients with normal spirometry results (forced vital capacity in supine position ≥ 80% predicted) and 18 healthy controls. The mean cranial-caudal ratio was only 1.32 in patients with decreased spirometry results, 1.60 in patients with normal spirometry results and 1.72 in healthy controls (p < 0.001). Anterior-posterior ratios showed no significant differences. The mean height ratios of the diaphragm curvature were 1.41 in patients with decreased spirometry results, 1.08 in patients with normal spirometry results and 0.82 in healthy controls (p = 0.001), indicating an increased curvature of the diaphragm during inspiration in Pompe patients. CONCLUSIONS: Even in early-stage Pompe disease, when spirometry results are still within normal range, the motion of the diaphragm is already reduced and the shape is more curved during inspiration. MRI can be used to detect early signs of diaphragmatic weakness in patients with Pompe disease, which might help to select patients for early intervention to prevent possible irreversible damage to the diaphragm.

Learning Cross-Modality Representations From Multi-Modal Images.

Machine learning algorithms can have difficulties adapting to data from different sources, for example from different imaging modalities. We present and analyze three techniques for unsupervised cross-modality feature learning, using a shared autoencoder-like convolutional network that learns a common representation from multi-modal data. We investigate a form of feature normalization, a learning objective that minimizes cross-modality differences, and modality dropout, in which the network is trained with varying subsets of modalities. We measure the same-modality and cross-modality classification accuracies and explore whether the models learn modality-specific or shared features. This paper presents experiments on two public data sets, with knee images from two MRI modalities, provided by the Osteoarthritis Initiative, and brain tumor segmentation on four MRI modalities from the BRATS challenge. All three approaches improved the cross-modality classification accuracy, with modality dropout and per-feature normalization giving the largest improvement. We observed that the networks tend to learn a combination of cross-modality and modality-specific features. Overall, a combination of all three methods produced the most cross-modality features and the highest cross-modality classification accuracy, while maintaining most of the same-modality accuracy.

Combining Generative and Discriminative Representation Learning for Lung CT Analysis With Convolutional Restricted Boltzmann Machines.

The choice of features greatly influences the performance of a tissue classification system. Despite this, many systems are built with standard, predefined filter banks that are not optimized for that particular application. Representation learning methods such as restricted Boltzmann machines may outperform these standard filter banks because they learn a feature description directly from the training data. Like many other representation learning methods, restricted Boltzmann machines are unsupervised and are trained with a generative learning objective; this allows them to learn representations from unlabeled data, but does not necessarily produce features that are optimal for classification. In this paper we propose the convolutional classification restricted Boltzmann machine, which combines a generative and a discriminative learning objective. This allows it to learn filters that are good both for describing the training data and for classification. We present experiments with feature learning for lung texture classification and airway detection in CT images. In both applications, a combination of learning objectives outperformed purely discriminative or generative learning, increasing, for instance, the lung tissue classification accuracy by 1 to 8 percentage points. This shows that discriminative learning can help an otherwise unsupervised feature learner to learn filters that are optimized for classification.