Vascular segmentation of head phase-contrast magnetic resonance angiograms using grayscale and shape features

A review of uncertainty quantification in medical image analysis: Probabilistic and non-probabilistic methods

The comprehensive integration of machine learning healthcare models within clinical practice remains suboptimal, notwithstanding the proliferation of high-performing solutions reported in the literature. A predominant factor hindering widespread adoption pertains to an insufficiency of evidence affirming the reliability of the aforementioned models. Recently, uncertainty quantification methods have been proposed as a potential solution to quantify the reliability of machine learning models and thus increase the interpretability and acceptability of the results. In this review, we offer a comprehensive overview of the prevailing methods proposed to quantify the uncertainty inherent in machine learning models developed for various medical image tasks. Contrary to earlier reviews that exclusively focused on probabilistic methods, this review also explores non-probabilistic approaches, thereby furnishing a more holistic survey of research pertaining to uncertainty quantification for machine learning models. Analysis of medical images with the summary and discussion on medical applications and the corresponding uncertainty evaluation protocols are presented, which focus on the specific challenges of uncertainty in medical image analysis. We also highlight some potential future research work at the end. Generally, this review aims to allow researchers from both clinical and technical backgrounds to gain a quick and yet in-depth understanding of the research in uncertainty quantification for medical image analysis machine learning models.

VCerebrovascular Segmentation in Phase-Contrast Magnetic Resonance Angiography by a Radon Projection Composition Network

Cerebrovascular segmentation based on phase-contrast magnetic resonance angiography (PC-MRA) provides patient-specific intracranial vascular structures for neurosurgery planning. However, the vascular complex topology and spatial sparsity make the task challenging. Inspired by the computed tomography reconstruction, this paper proposes a Radon Projection Composition Network (RPC-Net) for cerebrovascular segmentation in PC-MRA, aiming to enhance distribution probability of vessels and fully obtain the vascular topological information. Multi-directional Radon projections of the images are introduced and a two-stream network is used to learn the features of the 3D images and projections. The projection domain features are remapped to the 3D image domain by filtered back-projection transform to obtain the image-projection joint features for predicting vessel voxels. A four-fold cross-validation experiment was performed on a local dataset containing 128 PC-MRA scans. The average Dice similarity coefficient, precision and recall of the RPC-Net achieved 86.12%, 85.91% and 86.50%, respectively, while the average completeness and validity of the vessel structure were 85.50% and 92.38%, respectively. The proposed method outperformed the existing methods, especially with significant improvement on the extraction of small and low-intensity vessels. Moreover, the applicability of the segmentation for electrode trajectory planning was also validated. The results demonstrate that the RPC-Net realizes an accurate and complete cerebrovascular segmentation and has potential applications in assisting neurosurgery preoperative planning.

Inverse Fourier transformation of combined first order derivative and intensity-curvature functional of magnetic resonance angiography of the human brain

BACKGROUND AND OBJECTIVE

This paper reports a novel image processing technique based on inverse Fourier transformation and its validation procedure.

METHODS

Magnetic Resonance Angiography (MRA) data of the human brain is fitted on a pixel-by-pixel basis with bivariate linear model polynomial function. Polynomial fitting allows the formulation of two measures: the first order derivative (FOD), which is an edge finder, and the intensity-curvature functional (ICF), which is a high pass filter. The calculation of FOD and ICF uses knowledge provided by existing research and is performed through resampling. ICF and FOD are direct Fourier transformed, and their k-space is combined through a nonlinear convolution of terms. The resulting k-space is inverse Fourier transformed so to obtain a novel image called Fourier Convolution Image (FCI).

RESULTS

FCI possesses the characteristics of an edge finder (FOD) and a high pass filter (ICF).

CONCLUSIONS

FC images yield the following properties versus MRA: 1. Change of the contrast; 2. Increased sharpness in the proximity of human brain vessels; 3. Increased visualization of vessel connectivity. The implication of this study is to provide FCI as another viable option for MRA evaluation.

DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images

(1) Background: COVID-19 has been global epidemic. This work aims to extract 3D infection from COVID-19 CT images; (2) Methods: Firstly, COVID-19 CT images are processed with lung region extraction and data enhancement. In this strategy, gradient changes of voxels in different directions respond to geometric characteristics. Due to the complexity of tubular tissues in lung region, they are clustered to the lung parenchyma center based on their filtered possibility. Thus, infection is improved after data enhancement. Then, deep weighted UNet is established to refining 3D infection texture, and weighted loss function is introduced. It changes cost calculation of different samples, causing target samples to dominate convergence direction. Finally, the trained network effectively extracts 3D infection from CT images by adjusting driving strategy of different samples. (3) Results: Using Accuracy, Precision, Recall and Coincidence rate, 20 subjects from a private dataset and eight subjects from Kaggle Competition COVID-19 CT dataset tested this method in hold-out validation framework. This work achieved good performance both in the private dataset (99.94–00.02%, 60.42–11.25%, 70.79–09.35% and 63.15–08.35%) and public dataset (99.73–00.12%, 77.02–06.06%, 41.23–08.61% and 52.50–08.18%). We also applied some extra indicators to test data augmentation and different models. The statistical tests have verified the significant difference of different models. (4) Conclusions: This study provides a COVID-19 infection segmentation technology, which provides an important prerequisite for the quantitative analysis of COVID-19 CT images.

Algorithm of Pulmonary Vascular Segment and Centerline Extraction

Because pulmonary vascular lesions are harmful to the human body and difficult to detect, computer-assisted diagnosis of pulmonary blood vessels has become the focus and difficulty of the current research. An algorithm of pulmonary vascular segment and centerline extraction which is consistent with the physician's diagnosis process is proposed for the first time. We construct the projection of maximum density, restore the vascular space information, and correct random walk algorithm to satisfy automatic and accurate segmentation of blood vessels. Construct a local 3D model to restrain Hessian matrix when extracting centerline. In order to assist the physician to make a correct diagnosis and verify the effectiveness of the algorithm, we proposed a visual expansion model. According to the 420 high-resolution CT data of lung blood vessels labeled by physicians, the accuracy of segmentation algorithm AOM reached 93%, and the processing speed was 0.05 s/frame, which achieved the clinical application standards.

An Effective Deep Neural Network for Lung Lesions Segmentation From COVID-19 CT Images

Automatic segmentation of lung lesions from COVID-19 computed tomography (CT) images can help to establish a quantitative model for diagnosis and treatment. For this reason, this article provides a new segmentation method to meet the needs of CT images processing under COVID-19 epidemic. The main steps are as follows: First, the proposed region of interest extraction implements patch mechanism strategy to satisfy the applicability of 3-D network and remove irrelevant background. Second, 3-D network is established to extract spatial features, where 3-D attention model promotes network to enhance target area. Then, to improve the convergence of network, a combination loss function is introduced to lead gradient optimization and training direction. Finally, data augmentation and conditional random field are applied to realize data resampling and binary segmentation. This method was assessed with some comparative experiment. By comparison, the proposed method reached the highest performance. Therefore, it has potential clinical applications.

The Preventive Effect of Computed Tomography Image-Guided Electroacupuncture Combined with Continuous Femoral Nerve Block on Deep Vein Thrombosis After Total Knee Arthroplasty Based on an Adaptive Algorithm

Based on an adaptive algorithm model, this study proposed 2 special model structures of randomized fusion and an optimized convolution kernel and use it for image recognition. The adaptive algorithm model combined image-guided electroacupuncture with a continuous femoral nerve block to prevent deep vein thrombosis after total knee arthroplasty. A total of 200 patients after total knee arthroplasty were randomly divided into 4 groups. We assessed the incidence of postoperative lower limb deep vein thrombosis and platelet count before and after surgery. Electroacupuncture combined with continuous femoral nerve block can reduce the incidence of deep vein thrombosis and has obvious advantages in multimode prevention. The effective analgesia provided by electroacupuncture combined with continuous femoral nerve block relieved postoperative pain. It also enabled patients to participate in joint movement and lower limb muscle strength training as soon as possible, which not only is conducive to postoperative functional recovery, but also reduces the body stress response triggered by pain and the hypercoagulable state. Moreover, electroacupuncture stimulation of electroacupuncture points can reduce the inflammatory edema associated with surgery, improve blood circulation at the surgical site, and activate the body's anticoagulation mechanism. This study provides new ideas and references for formulating multimode prevention and control strategies.