An intensity-based self-supervised domain adaptation method for intervertebral disc segmentation in magnetic resonance imaging.

BACKGROUND AND OBJECTIVE: Accurate IVD segmentation is crucial for diagnosing and treating spinal conditions. Traditional deep learning methods depend on extensive, annotated datasets, which are hard to acquire. This research proposes an intensity-based self-supervised domain adaptation, using unlabeled multi-domain data to reduce reliance on large annotated datasets. METHODS: The study introduces an innovative method using intensity-based self-supervised learning for IVD segmentation in MRI scans. This approach is particularly suited for IVD segmentations due to its ability to effectively capture the subtle intensity variations that are characteristic of spinal structures. The model, a dual-task system, simultaneously segments IVDs and predicts intensity transformations. This intensity-focused method has the advantages of being easy to train and computationally light, making it highly practical in diverse clinical settings. Trained on unlabeled data from multiple domains, the model learns domain-invariant features, adeptly handling intensity variations across different MRI devices and protocols. RESULTS: Testing on three public datasets showed that this model outperforms baseline models trained on single-domain data. It handles domain shifts and achieves higher accuracy in IVD segmentation. CONCLUSIONS: This study demonstrates the potential of intensity-based self-supervised domain adaptation for IVD segmentation. It suggests new directions for research in enhancing generalizability across datasets with domain shifts, which can be applied to other medical imaging fields.

Unsupervised domain adaptation for the segmentation of breast tissue in mammography images.

BACKGROUND AND OBJECTIVE: Breast density refers to the proportion of glandular and fatty tissue in the breast and is recognized as a useful factor assessing breast cancer risk. Moreover, the segmentation of the high-density glandular tissue from mammograms can assist medical professionals visualizing and localizing areas that may require additional attention. Developing robust methods to segment breast tissues is challenging due to the variations in mammographic acquisition systems and protocols. Deep learning methods are effective in medical image segmentation but they often require large quantities of labelled data. Unsupervised domain adaptation is an area of research that employs unlabelled data to improve model performance on variations of samples derived from different sources. METHODS: First, a U-Net architecture was used to perform segmentation of the fatty and glandular tissues with labelled data from a single acquisition device. Then, adversarial-based unsupervised domain adaptation methods were used to incorporate single unlabelled target domains, consisting of images from a different machine, into the training. Finally, the domain adaptation model was extended to include multiple unlabelled target domains by combining a reconstruction task with adversarial training. RESULTS: The adversarial training was found to improve the generalization of the initial model on new domain data, demonstrating clearly improved segmentation of the breast tissues. For training with multiple unlabelled domains, combining a reconstruction task with adversarial training improved the stability of the training and yielded adequate segmentation results across all domains with a single model. CONCLUSIONS: Results demonstrated the potential for adversarial-based domain adaptation with U-Net architectures for segmentation of breast tissue in mammograms coming from several devices and demonstrated that domain-adapted models could achieve a similar agreement with manual segmentations. It has also been found that combining adversarial and reconstruction-based methods can provide a simple and effective solution for training with multiple unlabelled target domains.

Square wave manoeuvre for apogeotropic variant of horizontal canal benign paroxysmal positional vertigo in neck restricted patients.

OBJECTIVE: We aimed to describe the clinical features of the apogeotropic variant of horizontal canal benign paroxysmal positional vertigo (HC BPPV-AG) in a cluster of patients with restrictive neck movement disorders and a new therapeutic manoeuvre for its management. METHODS: In a retrospective review of cases from an ambulatory tertiary referral center, patients with HC BPPV-AG in combination with neck movement restriction that prevented any classical manual repositioning procedure or who were refractory to canalith repositioning manoeuvres, were treated with a new manoeuvre comprised of sequential square-wave pattern of head and body supine rotations while nystagmus was being monitored, until either an apogeotropic to geotropic conversion or resolution of the nystagmus was observed. RESULTS: Fifteen patients were studied. All but one [14/15 cases] showed a positive therapeutic response to the repositioning procedure in a single session. In two cases, a direct relief of vertigo and elimination of nystagmus was observed without an intermediate geotropic phase. Although in three patients the affected ear was not initially identified, it was ultimately identified and successfully treated by the square wave manoeuvre in all of them. CONCLUSIONS: The square-wave manoeuvre is an alternative for HC BPPV-AG treatment in either cases with neck restriction, where the affected side is not well identified at the bedside or when other manoeuvres fail to resolve the HC BPPV-AG.

3D Pulmonary Artery Segmentation from CTA Scans Using Deep Learning with Realistic Data Augmentation.

The characterization of the vasculature in the mediastinum, more specifically the pulmonary artery, is of vital importance for the evaluation of several pulmonary vascular diseases. Thus, the goal of this study is to automatically segment the pulmonary artery (PA) from computed tomography angiography images, which opens up the opportunity for more complex analysis of the evolution of the PA geometry in health and disease and can be used in complex fluid mechanics models or individualized medicine. For that purpose, a new 3D convolutional neural network architecture is proposed, which is trained on images coming from different patient cohorts. The network makes use a strong data augmentation paradigm based on realistic deformations generated by applying principal component analysis to the deformation fields obtained from the affine registration of several datasets. The network is validated on 91 datasets by comparing the automatic segmentations with semi-automatically delineated ground truths in terms of mean Dice and Jaccard coefficients and mean distance between surfaces, which yields values of 0.89, 0.80 and 1.25 mm, respectively. Finally, a comparison against a Unet architecture is also included.