Artificial intelligence (AI) advancements, especially deep learning, have significantly improved medical image processing and analysis in various tasks such as disease detection, classification, and anatomical structure segmentation. This work overviews fundamental concepts, state-of-the-art models, and publicly available datasets in the field of medical imaging. First, we introduce the types of learning problems commonly employed in medical image processing and then proceed to present an overview of commonly used deep learning methods, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs), with a focus on the image analysis task they are solving, including image classification, object detection/localization, segmentation, generation, and registration. Further, we highlight studies conducted in various application areas, encompassing neurology, brain imaging, retinal analysis, pulmonary imaging, digital pathology, breast imaging, cardiac imaging, bone analysis, abdominal imaging, and musculoskeletal imaging. The strengths and limitations of each method are carefully examined, and the paper identifies pertinent challenges that still require attention, such as the limited availability of annotated data, variability in medical images, and the interpretability issues. Finally, we discuss future research directions with a particular focus on developing explainable deep learning methods and integrating multi-modal data.

An accurate whole heart segmentation (WHS) on medical images, including computed tomography (CT) and magnetic resonance (MR) images, plays a crucial role in many clinical applications, such as cardiovascular disease diagnosis, pre-surgical planning, and intraoperative treatment. Manual whole-heart segmentation is a time-consuming process, prone to subjectivity and error. Therefore, there is a need to develop a quick, automatic, and accurate whole heart segmentation systems. Nowadays, convolutional neural networks (CNNs) emerged as a robust approach for medical image segmentation. In this paper, we first introduce a novel connectivity structure of residual unit that we refer to as a feature merge residual unit (FM-Pre-ResNet). The proposed connectivity allows the creation of distinctly deep models without an increase in the number of parameters compared to the pre-activation residual units. Second, we propose a three-dimensional (3D) encoder–decoder based architecture that successfully incorporates FM-Pre-ResNet units and variational autoencoder (VAE). In an encoding stage, FM-Pre-ResNet units are used for learning a low-dimensional representation of the input. After that, the variational autoencoder (VAE) reconstructs the input image from the low-dimensional latent space to provide a strong regularization of all model weights, simultaneously preventing overfitting on the training data. Finally, the decoding stage creates the final whole heart segmentation. We evaluate our method on the 40 test subjects of the MICCAI Multi-Modality Whole Heart Segmentation (MM-WHS) Challenge. The average dice values of whole heart segmentation are 90.39% (CT images) and 89.50% (MRI images), which are both highly comparable to the state-of-the-art.

Accurate segmentation of cardiovascular structures plays an important role in many clinical applications. Recently, fully convolutional networks (FCNs), led by the UNet architecture, have significantly improved the accuracy and speed of semantic segmentation tasks, greatly improving medical segmentation and analysis tasks. The UNet architecture makes heavy use of contextual information. However, useful channel features are not fully exploited. In this work, we present an improved UNet architecture that exploits residual learning, squeeze and excitation operations, Atrous Spatial Pyramid Pooling (ASPP), and the attention mechanism for accurate and effective segmentation of complex cardiovascular structures and name it AB-ResUNet+. The channel attention block is inserted into the skip connection to optimize the coding ability of each layer. The ASPP block is located at the bottom of the network and acts as a bridge between the encoder and decoder. This increases the field of view of the filters and allows them to include a wider context. The proposed AB-ResUNet+ is evaluated on eleven datasets of different cardiovascular structures, including coronary sinus (CS), descending aorta (DA), inferior vena cava (IVC), left atrial appendage (LAA), left atrial wall (LAW), papillary muscle (PM), posterior mitral leaflet (PML), proximal ascending aorta (PAA), pulmonary aorta (PA), right ventricular wall (RVW), and superior vena cava (SVC). Our experimental evaluations show that the proposed AB-ResUNet+ significantly outperforms the UNet, ResUNet, and ResUNet++ architecture by achieving higher values in terms of Dice coefficient and mIoU.

Contour detection is an important step in contour based object analysis in 2D images. We present a novel method for contour detection optimized for contour traversal tasks in 2D images. The method is based on morphological operations and detects a one-pixel wide contour around objects in binary images. Performance of the method is evaluated on ground truth images from our dataset created by manually tracing the contour in images. Proposed method achieves high DICE coefficient overlap to ground truth images and superior detection compared to other state-of-the-art methods.

Camera based assistance systems for the blind and visually impaired are still in a preliminary stage. Image processing techniques have already been used for the obstacle detection but the real-time processing still significantly depends on the input image resolution. This paper elaborates on the problem of staircase detection for the blind and visually impaired emphasizing the input image resolution. The evaluation of successful staircase detection is made by using different input resolutions. Choosing the appropriate input resolution is crucial to achieve optimal performance and find the compromise between accuracy and processing speed. The experiment is conducted on a dataset of frames in 5 different resolutions taken from video sequences.