Generative Adversarial Networks in Ultrasound Imaging: Extending Field of View Beyond Conventional Limits

Transthoracic Echocardiography (TTE) is a fundamental, non-invasive diagnostic tool in cardiovascular medicine, enabling detailed visualization of cardiac structures crucial for diagnosing various heart conditions. Despite its widespread use, TTE ultrasound imaging faces inherent limitations, notably the trade-off between field of view (FoV) and resolution. This paper introduces a novel application of conditional Generative Adversarial Networks (cGANs), specifically designed to extend the FoV in TTE ultrasound imaging while maintaining high resolution. Our proposed cGAN architecture, termed echoGAN, demonstrates the capability to generate realistic anatomical structures through outpainting, effectively broadening the viewable area in medical imaging. This advancement has the potential to enhance both automatic and manual ultrasound navigation, offering a more comprehensive view that could significantly reduce the learning curve associated with ultrasound imaging and aid in more accurate diagnoses. The results confirm that echoGAN reliably reproduce detailed cardiac features, thereby promising a significant step forward in the field of non-invasive cardiac naviagation and diagnostics.

End-to-end Deformable Attention Graph Neural Network for Single-view Liver Mesh Reconstruction

Intensity modulated radiotherapy (IMRT) is one of the most common modalities for treating cancer patients. One of the biggest challenges is precise treatment delivery that accounts for varying motion patterns originating from free-breathing. Currently, image-guided solutions for IMRT is limited to 2D guidance due to the complexity of 3D tracking solutions. We propose a novel end-to-end attention graph neural network model that generates in real-time a triangular shape of the liver based on a reference segmentation obtained at the preoperative phase and a 2D MRI coronal slice taken during the treatment. Graph neural networks work directly with graph data and can capture hidden patterns in non-Euclidean domains. Furthermore, contrary to existing methods, it produces the shape entirely in a mesh structure and correctly infers mesh shape and position based on a surrogate image. We define two on-the-fly approaches to make the correspondence of liver mesh vertices with 2D images obtained during treatment. Furthermore, we introduce a novel task-specific identity loss to constrain the deformation of the liver in the graph neural network to limit phenomenons such as flying vertices or mesh holes. The proposed method achieves results with an average error of 3.06 +- 0.7 mm and Chamfer distance with L2 norm of 63.14 +- 27.28.

Ensembled Autoencoder Regularization for Multi-Structure Segmentation for Kidney Cancer Treatment

The kidney cancer is one of the most common cancer types. The treatment frequently include surgical intervention. However, surgery is in this case particularly challenging due to regional anatomical relations. Organ delineation can significantly improve surgical planning and execution. In this contribution, we propose ensemble of two fully convolutional networks for segmentation of kidney, tumor, veins and arteries. While SegResNet architecture achieved better performance on tumor, the nnU-Net provided more precise segmentation for kidneys, arteries and veins. So in our proposed approach we combine these two networks, and further boost the performance by mixup augmentation.

Self-supervised deep convolutional neural network for chest X-ray classification

Chest radiography is a relatively cheap, widely available medical procedure that conveys key information for making diagnostic decisions. Chest X-rays are almost always used in the diagnosis of respiratory diseases such as pneumonia or the recent COVID-19. In this paper, we propose a self-supervised deep neural network that is pretrained on an unlabeled chest X-ray dataset. The learned representations are transferred to downstream task - the classification of respiratory diseases. The results obtained on four public datasets show that our approach yields competitive results without requiring large amounts of labeled training data.

Feature Selection Based on Sparse Neural Network Layer with Normalizing Constraints

Feature selection is important step in machine learning since it has shown to improve prediction accuracy while depressing the curse of dimensionality of high dimensional data. The neural networks have experienced tremendous success in solving many nonlinear learning problems. Here, we propose new neural-network based feature selection approach that introduces two constrains, the satisfying of which leads to sparse FS layer. We have performed extensive experiments on synthetic and real world data to evaluate performance of the proposed FS. In experiments we focus on the high dimension, low sample size data since those represent the main challenge for feature selection. The results confirm that proposed Feature Selection Based on Sparse Neural Network Layer with Normalizing Constraints (SNEL-FS) is able to select the important features and yields superior performance compared to other conventional FS methods.