Computer methods and programs in biomedicine最新文献

Background

Acute heart failure (AHF) in the intensive care unit (ICU) is characterized by its criticality, rapid progression, complex and changeable condition, and its pathophysiological process involves the interaction of multiple organs and systems. This makes it difficult to predict in-hospital mortality events comprehensively and accurately. Traditional analysis methods based on statistics and machine learning suffer from insufficient model performance, poor accuracy caused by prior dependence, and difficulty in adequately considering the complex relationships between multiple risk factors. Therefore, the application of deep neural network (DNN) techniques to the specific scenario, predicting mortality events of patients with AHF under intensive care, has become a research frontier.

Methods

This research utilized the MIMIC-IV critical care database as the primary data source and employed the synthetic minority over-sampling technique (SMOTE) to balance the dataset. Deep neural network models—backpropagation neural network (BPNN) and recurrent neural network (RNN), which are based on electronic medical record data mining, were employed to investigate the in-hospital death event judgment task of patients with AHF under intensive care. Additionally, multiple single machine learning models and ensemble learning models were constructed for comparative experiments. Moreover, we achieved various optimal performance combinations by modifying the classification threshold of deep neural network models to address the diverse real-world requirements in the ICU. Finally, we conducted an interpretable deep model using SHapley Additive exPlanations (SHAP) to uncover the most influential medical record features for each patient from the aspects of global and local interpretation.

Results

In terms of model performance in this scenario, deep neural network models outperform both single machine learning models and ensemble learning models, achieving the highest Accuracy, Precision, Recall, F1 value, and Area under the ROC curve, which can reach 0.949, 0.925, 0.983, 0.953, and 0.987 respectively. SHAP value analysis revealed that the ICU scores (APSIII, OASIS, SOFA) are significantly correlated with the occurrence of in-hospital fatal events.

Conclusions

Our study underscores that DNN-based mortality event classifier offers a novel intelligent approach for forecasting and assessing the prognosis of AHF patients in the ICU. Additionally, the ICU scores stand out as the most predictive features, which implies that in the decision-making process of the models, ICU scores can provide the most crucial information, making the greatest positive or negative contribution to influence the incidence of in-hospital mortality among patients with acute heart failure.

Background and Objectives:

Genome-scale metabolic networks (GEMs) represent a valuable modeling and computational tool in the broad field of systems biology. Their ability to integrate constraints and high-throughput biological data enables the study of intricate metabolic aspects and processes of different cell types and conditions. The past decade has witnessed an increasing number and variety of applications of GEMs for the study of human diseases, along with a huge effort aimed at the reconstruction, integration and analysis of a high number of organisms. This paper presents a systematic review of the scientific literature, to pursue several important questions about the application of constraint-based modeling in the investigation of human diseases. Hopefully, this paper will provide a useful reference for researchers interested in the application of modeling and computational tools for the investigation of metabolic-related human diseases.

Methods:

This systematic review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Elsevier Scopus®, National Library of Medicine PubMed® and Clarivate Web of Science™ databases were enquired, resulting in 566 scientific articles. After applying exclusion and eligibility criteria, a total of 169 papers were selected and individually examined.

Results:

The reviewed papers offer a thorough and up-to-date picture of the latest modeling and computational approaches, based on genome-scale metabolic models, that can be leveraged for the investigation of a large variety of human diseases. The numerous studies have been categorized according to the clinical research area involved in the examined disease. Furthermore, the paper discusses the most typical approaches employed to derive clinically-relevant information using the computational models.

Conclusions:

The number of scientific papers, utilizing GEM-based approaches for the investigation of human diseases, suggests an increasing interest in these types of approaches; hopefully, the present review will represent a useful reference for scientists interested in applying computational modeling approaches to investigate the aetiopathology of human diseases; we also hope that this work will foster the development of novel applications and methods for the discovery of clinically-relevant insights on metabolic-related diseases.

Background and Objective

Registration of pulmonary computed tomography (CT) images with radiation-induced lung diseases (RILD) was essential to investigate the voxel-wise relationship between the formation of RILD and the radiation dose received by different tissues. Although various approaches had been developed for the registration of lung CTs, their performances remained clinically unsatisfactory for registration of lung CT images with RILD. The main difficulties arose from the longitudinal change in lung parenchyma, including RILD and volumetric change of lung cancers, after radiation therapy, leading to inaccurate registration and artifacts caused by erroneous matching of the RILD tissues.

Methods

To overcome the influence of the parenchymal changes, a divide-and-conquer approach rooted in the coherent point drift (CPD) paradigm was proposed. The proposed method was based on two kernel ideas. One was the idea of component structure wise registration. Specifically, the proposed method relaxed the intrinsic assumption of equal isotropic covariances in CPD by decomposing a lung and its surrounding tissues into component structures and independently registering the component structures pairwise by CPD. The other was the idea of defining a vascular subtree centered at a matched branch point as a component structure. This idea could not only provide a sufficient number of matched feature points within a parenchyma, but avoid being corrupted by the false feature points resided in the RILD tissues due to globally and indiscriminately sampling using mathematical operators. The overall deformation model was built by using the Thin Plate Spline based on all matched points.

Results

This study recruited 30 pairs of lung CT images with RILD, 15 of which were used for internal validation (leave-one-out cross-validation) and the other 15 for external validation. The experimental results showed that the proposed algorithm achieved a mean and a mean of maximum 1 % of average surface distances <2 and 8 mm, respectively, and a mean and a maximum target registration error <2 mm and 5 mm on both internal and external validation datasets. The paired two-sample t-tests corroborated that the proposed algorithm outperformed a recent method, the Stavropoulou's method, on the external validation dataset (p < 0.05).

Conclusions

The proposed algorithm effectively reduced the influence of parenchymal changes, resulting in a reasonably accurate and artifact-free registration.

Background

This study aimed to predict early adolescent sleep problems using pregnancy and childbirth risk factors through machine learning algorithms, and to evaluate model performance internally and externally.

Methods

Data from the China Jintan Child Cohort study (CJCC; n=848) for model development and the US Healthy Brain and Behavior Study (HBBS; n=454) for external validation were employed. Maternal pregnancy histories, obstetric data, and adolescent sleep problems were collected. Several machine learning techniques were employed, including least absolute shrinkage and selection operator, logistic regression, random forest, naïve bayes, extreme gradient boosting, decision tree, and neural network. The area under the receiver operating characteristic curve, sensitivity, specificity, accuracy, and root mean square of residuals were used to evaluate model performance.

Results

Key predictors for CJCC adolescents’ sleep problems include gestational age, birthweight, duration of delivery, and maternal happiness during pregnancy. In HBBS adolescents, the duration of postnatal depressive emotions was the primary perinatal predictor. The prediction models developed in the CJCC had good-to-excellent internal validation performance but poor performance in predicting the sleep problems in HBBS adolescents.

Conclusion

The identification of specific perinatal risk factors associated with adolescent sleep problems can inform targeted interventions during and after pregnancy to mitigate these risks. Health providers should consider integrating these predictive factors into routine pre- and postnatal assessments to identify at-risk populations. The variability in model performance across different cohorts highlights the need for context-specific models and the cautious application of predictive analytics across diverse populations. Future research should focus on refining predictive models to account for such variations, potentially through the incorporation of additional socio-cultural factors and genetic markers. This study emphasizes the importance of personalized and culturally sensitive approaches in the prediction and management of adolescent sleep problems, leveraging advanced computational methods to enhance maternal and child health outcomes.

Background and Objective:

Tendon segmentation is crucial for studying tendon-related pathologies like tendinopathy, tendinosis, etc. This step further enables detailed analysis of specific tendon regions using automated or semi-automated methods. This study specifically aims at the segmentation of Achilles tendon, the largest tendon in the human body.

Methods:

This study proposes a comprehensive end-to-end tendon segmentation module composed of a preliminary superpixel-based coarse segmentation preceding the final segmentation task. The final segmentation results are obtained through two distinct approaches. In the first approach, the coarsely generated superpixels are subjected to classification using Random Forest (RF) and Support Vector Machine (SVM) classifiers to classify whether each superpixel belongs to a tendon class or not (resulting in tendon segmentation). In the second approach, the arrangements of superpixels are converted to graphs instead of being treated as conventional image grids. This classification process uses a graph-based convolutional network (GCN) to determine whether each superpixel corresponds to a tendon class or not.

Results:

All experiments are conducted on a custom-made ankle MRI dataset. The dataset comprises 76 subjects and is divided into two sets: one for training (Dataset 1, trained and evaluated using leave-one-group-out cross-validation) and the other as unseen test data (Dataset 2). Using our first approach, the final test AUC (Area Under the ROC Curve) scores using RF and SVM classifiers on the test data (Dataset 2) are 0.992 and 0.987, respectively, with sensitivities of 0.904 and 0.966. On the other hand, using our second approach (GCN-based node classification), the AUC score for the test set is 0.933 with a sensitivity of 0.899.

Conclusions:

Our proposed pipeline demonstrates the efficacy of employing superpixel generation as a coarse segmentation technique for the final tendon segmentation. Whether utilizing RF, SVM-based superpixel classification, or GCN-based classification for tendon segmentation, our system consistently achieves commendable AUC scores, especially the non-graph-based approach. Given the limited dataset, our graph-based method did not perform as well as non-graph-based superpixel classifications; however, the results obtained provide valuable insights into how well the models can distinguish between tendons and non-tendons. This opens up opportunities for further exploration and improvement.

Background and objective:

The use of deep learning to undertake shape analysis of the complexities of the human head holds great promise. However, there have traditionally been a number of barriers to accurate modelling, especially when operating on both a global and local level.

Methods:

In this work, we will discuss the application of the Swap Disentangled Variational Autoencoder (SD-VAE) with relevance to Crouzon, Apert and Muenke syndromes. The model is trained on a dataset of 3D meshes of healthy and syndromic patients which was increased in size with a novel data augmentation technique based on spectral interpolation. Thanks to its semantically meaningful and disentangled latent representation, SD-VAE is used to analyse and generate head shapes while considering the influence of different anatomical sub-units.

Results:

Although syndrome classification is performed on the entire mesh, it is also possible, for the first time, to analyse the influence of each region of the head on the syndromic phenotype. By manipulating specific parameters of the generative model, and producing procedure-specific new shapes, it is also possible to approximate the outcome of a range of craniofacial surgical procedures.

Conclusion:

This work opens new avenues to advance diagnosis, aids surgical planning and allows for the objective evaluation of surgical outcomes. Our code is available at github.com/simofoti/CraniofacialSD-VAE.

Background and Objective

During open surgeries, telementoring serves as a valuable tool for transferring surgical knowledge from a specialist surgeon (mentor) to an operating surgeon (mentee). Depicting the intended movements of the surgical instruments over the operative field improves the understanding of the required tool-tissue interaction. The objective of this work is to develop a telementoring system tailored for open surgeries, enabling the mentor to remotely demonstrate the necessary motions of surgical instruments to the mentee.

Methods

A remote telementoring system for open surgery was implemented. The system generates visual cues in the form of virtual surgical instrument motion augmented onto the live view of the operative field. These cues can be rendered on both conventional screens in the operating room and as dynamic holograms on a head mounted display device worn by the mentee. The technical performance of the system was evaluated, where the operating room and remote location were geographically separated and connected via the Internet. Additionally, user studies were conducted to assess the effectiveness of the system as a mentoring tool.

Results

The system took 307 ± 12 ms to transmit an operative field view of 1920  ×  1080 resolution, along with depth information spanning 36 cm, from the operating room to the remote location. Conversely, it took 145 ± 14 ms to receive the motion of virtual surgical instruments from the remote location back to the operating room. Furthermore, the user studies demonstrated: (a) mentor's capability to annotate the operative field with an accuracy of 3.92 ± 2.1 mm, (b) mentee's ability to comprehend and replicate the motion of surgical instruments in real-time with an average deviation of 12.8 ± 3 mm, (c) efficacy of the rendered dynamic holograms in conveying information intended for surgical instrument motion.

Conclusions

The study demonstrates the feasibility of transmitting information over the Internet from the mentor to the mentee in the form of virtual surgical instruments’ motion and projecting it as holograms onto the live view of the operative field. This holds potential to enhance real-time collaborative capabilities between the mentor and the mentee during an open surgery.

A deep understanding of neuron structure and function is crucial for elucidating brain mechanisms, diagnosing and treating diseases. Optical microscopy, pivotal in neuroscience, illuminates neuronal shapes, projections, and electrical activities. To explore the projection of specific functional neurons, scientists have been developing optical-based multimodal imaging strategies to simultaneously capture dynamic in vivo signals and static ex vivo structures from the same neuron. However, the original position of neurons is highly susceptible to displacement during ex vivo imaging, presenting a significant challenge for integrating multimodal information at the single-neuron level. This study introduces a graph-model-based approach for cell image matching, facilitating precise and automated pairing of sparsely labeled neurons across different optical microscopic images. It has been shown that utilizing neuron distribution as a matching feature can mitigate modal differences, the high-order graph model can address scale inconsistency, and the nonlinear iteration can resolve discrepancies in neuron density. This strategy was applied to the connectivity study of the mouse visual cortex, performing cell matching between the two-photon calcium image and the HD-fMOST brain-wide anatomical image sets. Experimental results demonstrate 96.67% precision, 85.29% recall rate, and 90.63% F1 Score, comparable to expert technicians. This study builds a bridge between functional and structural imaging, offering crucial technical support for neuron classification and circuitry analysis.

Introduction

This study aimed to investigate the efficacy of a small-gauge microwave ablation antenna (MWA) with an enhanced cooling system (ECS) for generating more spherical ablation zones.

Methods

A comparison was made between two types of microwave ablation antennas, one with ECS and the other with a conventional cooling system (CCS). The finite element method was used to simulate in vivo ablation. Two types of antennas were used to create MWA zones for 5, 8, 10 min at 50, 60, and 80 W in ex vivo bovine livers (n = 6) and 5 min at 60 W in vivo porcine livers (n = 16). The overtreatment ratio, ablation aspect ratio, carbonization area, and other characteristcs of antennas were measured and compared using numerical simulation and gross pathologic examination.

Results

In numerical simulation, the ECS antenna demonstrated a lower overtreatment ratio than the CCS antenna (1.38 vs 1.43 at 50 W 5 min, 1.19 vs 1.35 at 50 W 8 min, 1.13 vs 1.32 at 50 W 10 min, 1.28 vs 1.38 at 60 W 5 min, 1.14 vs 1.32 at 60 W 8 min, 1.10 vs 1.30 at 60 W 10 min). The experiments revealed that the ECS antenna generated ablation zones with a more significant aspect ratio (0.92 ± 0.03 vs 0.72 ± 0.01 at 50 W 5 min, 0.95 ± 0.02 vs 0.70 ± 0.01 at 50 W 8 min, 0.96 ± 0.01 vs 0.71 ± 0.04 at 50 W 10 min, 0.96 ± 0.01 vs 0.73 ± 0.02 at 60 W 5 min, 0.94 ± 0.03 vs 0.71 ± 0.03 at 60 W 8 min, 0.96 ± 0.02 vs 0.69 ± 0.04 at 60 W 10 min) and a smaller carbonization area (0.00 ± 0.00 cm² vs 0.54 ± 0.06 cm² at 50 W 5 min, 0.13 ± 0.03 cm² vs 0.61 ± 0.09 cm² at 50 W 8 min, 0.23 ± 0.05 cm² vs 0.73 ± 0.05 m² at 50 W 10 min, 0.00 ± 0.00 cm² vs 1.59 ± 0.41 cm² at 60 W 5 min, 0.23 ± 0.22 cm² vs 2.11 ± 0.63 cm² at 60 W 8 min, 0.57 ± 0.09 cm² vs 2.55 ± 0.51 cm² at 60 W 10 min). Intraoperative ultrasound images revealed a hypoechoic area instead of a hyperechoic area near the antenna. Hematoxylin-eosin staining of the dissected tissue revealed a correlation between the edge of the ablation zone and that of the hypoechoic area.

Conclusions

The ECS antenna can produce more spherical ablation zones with less charring and a clearer intraoperative ultrasound image of the ablation area than the CCS antenna.