Image and Video Processing (eess.IV)

Abstract: Alzheimer's Disease is a devastating neurological disorder that is increasingly affecting the elderly population. Early and accurate detection of Alzheimer's is crucial for providing effective treatment and support for patients and their families. In this study, we present a novel approach for detecting four different stages of Alzheimer's disease from MRI scan images based on inertia tensor analysis and machine learning. From each available MRI scan image for different classes of Dementia, we first compute a very simple 2 x 2 matrix, using the techniques of forming a moment of inertia tensor, which is largely used in different physical problems. Using the properties of the obtained inertia tensor and their eigenvalues, along with some other machine learning techniques, we were able to significantly classify the different types of Dementia. This process provides a new and unique approach to identifying and classifying different types of images using machine learning, with a classification accuracy of (90%) achieved. Our proposed method not only has the potential to be more cost-effective than current methods but also provides a new physical insight into the disease by reducing the dimension of the image matrix. The results of our study highlight the potential of this approach for advancing the field of Alzheimer's disease detection and improving patient outcomes.

Abstract: Low-field (<1T) magnetic resonance imaging (MRI) scanners remain in widespread use in low- and middle-income countries (LMICs) and are commonly used for some applications in higher income countries e.g. for small child patients with obesity, claustrophobia, implants, or tattoos. However, low-field MR images commonly have lower resolution and poorer contrast than images from high field (1.5T, 3T, and above). Here, we present Image Quality Transfer (IQT) to enhance low-field structural MRI by estimating from a low-field image the image we would have obtained from the same subject at high field. Our approach uses (i) a stochastic low-field image simulator as the forward model to capture uncertainty and variation in the contrast of low-field images corresponding to a particular high-field image, and (ii) an anisotropic U-Net variant specifically designed for the IQT inverse problem. We evaluate the proposed algorithm both in simulation and using multi-contrast (T1-weighted, T2-weighted, and fluid attenuated inversion recovery (FLAIR)) clinical low-field MRI data from an LMIC hospital. We show the efficacy of IQT in improving contrast and resolution of low-field MR images. We demonstrate that IQT-enhanced images have potential for enhancing visualisation of anatomical structures and pathological lesions of clinical relevance from the perspective of radiologists. IQT is proved to have capability of boosting the diagnostic value of low-field MRI, especially in low-resource settings.

Abstract: Dataset expansion can effectively alleviate the problem of data scarcity for medical image segmentation, due to privacy concerns and labeling difficulties. However, existing expansion algorithms still face great challenges due to their inability of guaranteeing the diversity of synthesized images with paired segmentation masks. In recent years, Diffusion Probabilistic Models (DPMs) have shown powerful image synthesis performance, even better than Generative Adversarial Networks. Based on this insight, we propose an approach called DiffuseExpand for expanding datasets for 2D medical image segmentation using DPM, which first samples a variety of masks from Gaussian noise to ensure the diversity, and then synthesizes images to ensure the alignment of images and masks. After that, DiffuseExpand chooses high-quality samples to further enhance the effectiveness of data expansion. Our comparison and ablation experiments on COVID-19 and CGMH Pelvis datasets demonstrate the effectiveness of DiffuseExpand. Our code is released at https://anonymous.4open.science/r/DiffuseExpand.

Abstract: 360{\deg} omnidirectional images have gained research attention due to their immersive and interactive experience, particularly in AR/VR applications. However, they suffer from lower angular resolution due to being captured by fisheye lenses with the same sensor size for capturing planar images. To solve the above issues, we propose a two-stage framework for 360{\deg} omnidirectional image superresolution. The first stage employs two branches: model A, which incorporates omnidirectional position-aware deformable blocks (OPDB) and Fourier upsampling, and model B, which adds a spatial frequency fusion module (SFF) to model A. Model A aims to enhance the feature extraction ability of 360{\deg} image positional information, while Model B further focuses on the high-frequency information of 360{\deg} images. The second stage performs same-resolution enhancement based on the structure of model A with a pixel unshuffle operation. In addition, we collected data from YouTube to improve the fitting ability of the transformer, and created pseudo low-resolution images using a degradation network. Our proposed method achieves superior performance and wins the NTIRE 2023 challenge of 360{\deg} omnidirectional image super-resolution.

Abstract: The development of medical image segmentation using deep learning can significantly support doctors' diagnoses. Deep learning needs large amounts of data for training, which also requires data augmentation to extend diversity for preventing overfitting. However, the existing methods for data augmentation of medical image segmentation are mainly based on models which need to update parameters and cost extra computing resources. We proposed data augmentation methods designed to train a high accuracy deep learning network for medical image segmentation. The proposed data augmentation approaches are called KeepMask and KeepMix, which can create medical images by better identifying the boundary of the organ with no more parameters. Our methods achieved better performance and obtained more precise boundaries for medical image segmentation on datasets. The dice coefficient of our methods achieved 94.15% (3.04% higher than baseline) on CHAOS and 74.70% (5.25% higher than baseline) on MSD spleen with Unet.

Abstract: Needle positioning is essential for various medical applications such as epidural anaesthesia. Physicians rely on their instincts while navigating the needle in epidural spaces. Thereby, identifying the tissue structures may be helpful to the physician as they can provide additional feedback in the needle insertion process. To this end, we propose a deep neural network that classifies the tissues from the phase and intensity data of complex OCT signals acquired at the needle tip. We investigate the performance of the deep neural network in a limited labelled dataset scenario and propose a novel contrastive pretraining strategy that learns invariant representation for phase and intensity data. We show that with 10% of the training set, our proposed pretraining strategy helps the model achieve an F1 score of 0.84 whereas the model achieves an F1 score of 0.60 without it. Further, we analyse the importance of phase and intensity individually towards tissue classification.

Abstract: Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To address this issue, we propose a multimodal machine learning method for text-guided image compression, in which the semantic information of text is used as prior information to guide image compression for better compression performance. We fully study the role of text description in different components of the codec, and demonstrate its effectiveness. In addition, we adopt the image-text attention module and image-request complement module to better fuse image and text features, and propose an improved multimodal semantic-consistent loss to produce semantically complete reconstructions. Extensive experiments, including a user study, prove that our method can obtain visually pleasing results at extremely low bitrates, and achieves a comparable or even better performance than state-of-the-art methods, even though these methods are at 2x to 4x bitrates of ours.

Abstract: High-Dynamic-Range Visual-Difference-Predictor version 3, or HDR-VDP-3, is a visual metric that can fulfill several tasks, such as full-reference image/video quality assessment, prediction of visual differences between a pair of images, or prediction of contrast distortions. Here we present a high-level overview of the metric, position it with respect to related work, explain the main differences compared to version 2.2, and describe how the metric was adapted for the HDR Video Quality Measurement Grand Challenge 2023.

Abstract: Quantifying the phagocytosis of dynamic, unstained cells is essential for evaluating neurodegenerative diseases. However, measuring rapid cell interactions and distinguishing cells from backgrounds make this task challenging when processing time-lapse phase-contrast video microscopy. In this study, we introduce a fully automated, scalable, and versatile realtime framework for quantifying and analyzing phagocytic activity. Our proposed pipeline can process large data-sets and includes a data quality verification module to counteract potential perturbations such as microscope movements and frame blurring. We also propose an explainable cell segmentation module to improve the interpretability of deep learning methods compared to black-box algorithms. This includes two interpretable deep learning capabilities: visual explanation and model simplification. We demonstrate that interpretability in deep learning is not the opposite of high performance, but rather provides essential deep learning algorithm optimization insights and solutions. Incorporating interpretable modules results in an efficient architecture design and optimized execution time. We apply this pipeline to quantify and analyze microglial cell phagocytosis in frontotemporal dementia (FTD) and obtain statistically reliable results showing that FTD mutant cells are larger and more aggressive than control cells. To stimulate translational approaches and future research, we release an open-source pipeline and a unique microglial cells phagocytosis dataset for immune system characterization in neurodegenerative diseases research. This pipeline and dataset will consistently crystallize future advances in this field, promoting the development of efficient and effective interpretable algorithms dedicated to this critical domain. https://github.com/ounissimehdi/PhagoStat

Abstract: The classification of the origin of blood clots is a crucial step in diagnosing and treating ischemic stroke. Various imaging techniques such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound have been employed to detect and locate blood clots within the body. However, identifying the origin of a blood clot remains challenging due to the complexity of the blood flow dynamics and the limitations of the imaging techniques. The study suggests a novel methodology for classifying the source of a blood clot through the integration of data from whole-slide digital pathology images, which are utilized to fine-tune several cutting-edge computer vision models. Upon comparison, the SwinTransformerV2 model outperforms all the other models and achieves an accuracy score of 94.24%, precision score of 94.41%, recall score of 94.09%, and, f1-score of 94.06%. Our approach shows promising results in detecting the origin of blood clots in different vascular regions and can potentially improve the diagnosis and management of ischemic stroke.