Uncertainty-aware refinement framework for ovarian tumor segmentation in CECT volume.

BACKGROUND: Ovarian cancer is a highly lethal gynecological disease. Accurate and automated segmentation of ovarian tumors in contrast-enhanced computed tomography (CECT) images is crucial in the radiotherapy treatment of ovarian cancer, enabling radiologists to evaluate cancer progression and develop timely therapeutic plans. However, automatic ovarian tumor segmentation is challenging due to factors such as inhomogeneous background, ambiguous tumor boundaries, and imbalanced foreground-background, all of which contribute to high predictive uncertainty for a segmentation model. PURPOSE: To tackle these challenges, we propose an uncertainty-aware refinement framework that aims to estimate and refine regions with high predictive uncertainty for accurate ovarian tumor segmentation in CECT images. METHODS: To this end, we first employ an approximate Bayesian network to detect coarse regions of interest (ROIs) of both ovarian tumors and uncertain regions. These ROIs allow a subsequent segmentation network to narrow down the search area for tumors and prioritize uncertain regions, resulting in precise segmentation of ovarian tumors. Meanwhile, the framework integrates two guidance modules that learn two implicit functions capable of mapping query features sampled according to their uncertainty to organ or boundary manifolds, guiding the segmentation network to facilitate information encoding of uncertain regions. RESULTS: Firstly, 367 CECT images are collected from the same hospital for experiments. Dice score, Jaccard, Recall, Positive predictive value (PPV), 95% Hausdorff distance (HD95) and Average symmetric surface distance (ASSD) for the testing group of 77 cases are 86.31%, 73.93%, 83.95%, 86.03%, 15.17  mm and 2.57  mm, all of which are significantly better than that of the other state-of-the-art models. And results of visual comparison shows that the compared methods have more mis-segmentation than our method. Furthermore, our method achieves a Dice score that is at least 20% higher than the Dice scores of other compared methods when tumor volumes are less than 20 cm 3 $^3$ , indicating better recognition ability to small regions by our method. And then, 38 CECT images are collected from another hospital to form an external testing group. Our approach consistently outperform the compared methods significantly, with the external testing group exhibiting substantial improvements across key evaluation metrics: Dice score (83.74%), Jaccard (69.55%), Recall (82.12%), PPV (81.61%), HD95 (12.31 mm), and ASSD (2.32 mm), robustly establishing its superior performance. CONCLUSIONS: Experimental results demonstrate that the framework significantly outperforms the compared state-of-the-art methods, with decreased under- or over-segmentation and better small tumor identification. It has the potential for clinical application.

Pulmonary Function in Metabolic Syndrome: A Meta-Analysis.

Background: This study aims to systematically evaluate the association between metabolic syndrome (MS) and pulmonary function through meta-analysis. Methods: Electronic databases, including PubMed, Embase, Web of Science, and Cochrane Library, were systematically searched to obtain articles associated with MS and lung function published before December 31, 2021. According to the including and excluding criteria, certain studies were obtained and data were extracted. The Newcastle Ottawa Scale was used to evaluate the quality of the studies. A pooled standardized mean difference (SMD) was calculated by means of random-effects meta-analysis. Different effect models were used according to the heterogeneity. Meta-regression and sensitivity analyses were performed to examine the possible sources of heterogeneity. The Begg's funnel plot and Egger's test were used to evaluate publication bias. Analyses were performed using Stata MP, version14.0 (StataCorp LP, College Station, TX, USA). Results: A total of 15 studies, involving 10,285 cases of MS and 25,416 cases of control, were included in this meta-analysis on the relationship between MS and forced vital capacity (FVC). The pooled SMD for FVC was -0.247 (95% CI = -0.327 to -0.2167, P < 0.001) using random effect model, indicating the decrease of FVC in the patients with MS. In the same studies, the pooled SMD for forced expiratory volume in 1 sec (FEV1) was -0.205 (95% CI = -0.3278 to -0.133, P < 0.001), indicating the decrease of FEV1 also existed in the MS cases. A total of 13 studies, involving 8167 cases of MS and 19,788 cases of control, were included in this meta-analysis on the relationship between MS and FEV1/FVC. The pooled SMD for FEV1/FVC was 0.011 (95% CI = -0.072 to 0.093, P = 0.798) using random effect model, indicating that there was no significant difference between the patients with MS and the control. After introducing the diastolic blood pressure and glycemia into the regression model of the relationship between MS and FVC, the variance of the studies (tau2) decreased from 0.0190 to 0.006694 and 0.007205, which could explain 66.70% and 78.04% of the sources of heterogeneity, and the P values were 0.038 and 0.023. The results suggested that hypertension (diastolic pressure) and hyperglycemia were the factors linked to the heterogeneity among the included studies on both FVC and FEV1. The Begg's funnel plot and Egger's test both showed no evidence of publication bias. Conclusions: Our results show that FVC and FEV1 decrease in MS patients, while FEV1/FVC has no significant difference compared with the control group. It indicates that the patients with MS have restrictive ventilatory functional disturbance. Meta-regression analysis suggests that hypertension (diastolic pressure) and hyperglycemia are the factors linked to the heterogeneity among the included studies on both FVC and FEV1.

With or without human interference for precise age estimation based on machine learning?

Age estimation can aid in forensic medicine applications, diagnosis, and treatment planning for orthodontics and pediatrics. Existing dental age estimation methods rely heavily on specialized knowledge and are highly subjective, wasting time, and energy, which can be perfectly solved by machine learning techniques. As the key factor affecting the performance of machine learning models, there are usually two methods for feature extraction: human interference and autonomous extraction without human interference. However, previous studies have rarely applied these two methods for feature extraction in the same image analysis task. Herein, we present two types of convolutional neural networks (CNNs) for dental age estimation. One is an automated dental stage evaluation model (ADSE model) based on specified manually defined features, and the other is an automated end-to-end dental age estimation model (ADAE model), which autonomously extracts potential features for dental age estimation. Although the mean absolute error (MAE) of the ADSE model for stage classification is 0.17 stages, its accuracy in dental age estimation is unsatisfactory, with the MAE (1.63 years) being only 0.04 years lower than the manual dental age estimation method (MDAE model). However, the MAE of the ADAE model is 0.83 years, being reduced by half that of the MDAE model. The results show that fully automated feature extraction in a deep learning model without human interference performs better in dental age estimation, prominently increasing the accuracy and objectivity. This indicates that without human interference, machine learning may perform better in the application of medical imaging.

RGB-D Point Cloud Registration Based on Salient Object Detection.

We propose a robust algorithm for aligning rigid, noisy, and partially overlapping red green blue-depth (RGB-D) point clouds. To address the problems of data degradation and uneven distribution, we offer three strategies to increase the robustness of the iterative closest point (ICP) algorithm. First, we introduce a salient object detection (SOD) method to extract a set of points with significant structural variation in the foreground, which can avoid the unbalanced proportion of foreground and background point sets leading to the local registration. Second, registration algorithms that rely only on structural information for alignment cannot establish the correct correspondences when faced with the point set with no significant change in structure. Therefore, a bidirectional color distance (BCD) is designed to build precise correspondence with bidirectional search and color guidance. Third, the maximum correntropy criterion (MCC) and trimmed strategy are introduced into our algorithm to handle with noise and outliers. We experimentally validate that our algorithm is more robust than previous algorithms on simulated and real-world scene data in most scenarios and achieve a satisfying 3-D reconstruction of indoor scenes.