Search

Automatic detection of pulmonary nodules is critical for the early diagnosis and prevention of lung cancer. Computed tomography (CT) is an effective and economical lung cancer detection method. In CT images, the size and shape of pulmonary nodules appear different, and some nodules appear similar to the surrounding tissues. Therefore, the automatic localization of pulmonary nodules in CT images is a challenging task. An attention-embedded three-dimensional convolutional neural network is proposed for pulmonary nodule detection in the current study. Specifically, 1) channel-spatial attention guides 3D ResNet to down sample the input 3D CT patch. The channel pays attention to important features and the space to the region of interest. The two form a complementary feature extraction mechanism to effectively help the global flow of information in the network and refine the feature mapping to extract the nodule context features. 2) The channel-spatial attention module changes the fusion model of the feature pyramid, adaptively adjusts the pixel-level weight between features and extracts multi-scale representative node features. 3) The deep separable convolution is used to replace the standard convolution of ResNet, reducing the time cost and improving the efficiency of model training on the premise of ensuring the model’s performance. 4) To adapt the distribution of nodule scale, different characteristic layers correspond to two sizes of anchors. Under the condition of ensuring the detection rate of nodules, the number of anchor frames is reduced, and the network sensitivity is improved. Finally, several ablation experiments are carried out using the LUNA16 dataset. The results revealed that the attention-guided network could extract the multi-scale representative features of nodules, and the average sensitivity was 97.7%. Additionally, the CMP score reached 0.912. The extensive experiments demonstrate that the proposed approach can effectively improve the detection sensitivity and control the number of false positive nodules, which has clinical application value and a certain reference value.

Various fields in medicine require scientific research and computer application. This results in computation time optimization becoming a task that is of increasing importance due to its highly parallel architecture. As is well-known, the graphics processing unit (GPU) is regarded as a powerful engine for application programs that demand fairly high computation capabilities. Our study is based on the deep analysis of the parallelism pertaining to the calculation of the gray level co-occurrence matrix, whereby an algorithm was introduced to optimize the method used to compute the gray-level co-occurrence matrix (GLCM) of an image. Furthermore, strategies (e.g., copying, image partitioning, and so on) were proposed to optimize the parallel algorithm. Our experiments indicate that without losing the computational accuracy, the speed-up ratio of the GLCM computation of images with different resolutions by GPU utilizing compute unified device architecture was at least 50 times faster than that of the GLCM computation by the central processing unit. This manifestation of a significantly improved performance can lead to the development of a very useful computational tool in medical computer vision.

Reliable human pose estimation (HPE) is essential to many clinical applications, such as surgical workflow analysis, radiation safety monitoring and human-robot cooperation. Proposed methods for the operating room (OR) rely either on foreground estimation using a multi-camera system, which is a challenge in real ORs due to color similarities and frequent illumination changes, or on wearable sensors or markers, which are invasive and therefore difficult to introduce in the room. Instead, we propose a novel approach based on Pictorial Structures (PS) and on RGB-D data, which can be easily deployed in real ORs. We extend the PS framework in two ways. First, we build robust and discriminative part detectors using both color and depth images. We also present a novel descriptor for depth images, called histogram of depth differences (HDD). Second, we extend PS to 3D by proposing 3D pairwise constraints and a new method that makes exact inference tractable. Our approach is evaluated for pose estimation and clinician detection on a challenging RGB-D dataset recorded in a busy operating room during live surgeries. We conduct series of experiments to study the different part detectors in conjunction with the various 2D or 3D pairwise constraints. Our comparisons demonstrate that 3D PS with RGB-D part detectors significantly improves the results in a visually challenging operating environment. [ABSTRACT FROM AUTHOR]

Vision Transformers (ViTs), with the magnificent potential to unravel the information contained within images, have evolved as one of the most contemporary and dominant architectures that are being used in the field of computer vision. These are immensely utilized by plenty of researchers to perform new as well as former experiments. Here, in this article, we investigate the intersection of vision transformers and medical images. We proffered an overview of various ViT based frameworks that are being used by different researchers to decipher the obstacles in medical computer vision. We surveyed the applications of Vision Transformers in different areas of medical computer vision such as image-based disease classification, anatomical structure segmentation, registration, region-based lesion detection, captioning, report generation, and reconstruction using multiple medical imaging modalities that greatly assist in medical diagnosis and hence treatment process. Along with this, we also demystify several imaging modalities used in medical computer vision. Moreover, to get more insight and deeper understanding, the self-attention mechanism of transformers is also explained briefly. Conclusively, the ViT based solutions for each image analytics task are critically analyzed, open challenges are discussed and the pointers to possible solutions for future direction are deliberated. We hope this review article will open future research directions for medical computer vision researchers. [ABSTRACT FROM AUTHOR]