The greatest risk factor for many non-communicable diseases is aging. Studies on model organisms have demonstrated that genetic and chemical perturbation alterations can lengthen longevity and overall health. However, finding longevity-enhancing medications and their related targets is difficult.
In this work, we designed a novel drug repurposing model by identifying the interaction between aging-related genes or targets and drugs similar to aging disease. Each disease is associated with certain specific genetic factors for the occurrence of that disease. The factors include gene expression, pathway, miRNA, and degree of genes in the protein-protein interaction network. In this paper, we aim to find the drugs that prolong the life span of humans with their aging-related targets using the above-mentioned factors. In addition, the contribution or importance of each factor may vary among drugs and targets. Therefore, we designed a novel multi-layer random walk-based network representation learning model including node and edge weight to learn the features of drugs and targets respectively.
The performance of the proposed model is demonstrated using k-fold cross-validation (k = 5). This model achieved better performance with scores of 0.93 and 0.91 for precision and recall respectively. The drugs identified by the system are evaluated to be potential candidates for aging since the degree of interaction between the potential drugs and their gene sets are high. In addition, the genes that are interacting with drugs produce the same biological functions. Hence the life span of the human will be increased or prolonged.
Numerous automatic sleep stage classification systems have been developed, but none have become effective assistive tools for sleep technicians due to issues with generalization. Four key factors hinder the generalization of these models are instruments, montage of recording, subject type, and scoring manual factors. This study aimed to develop a deep learning model that addresses generalization problems by integrating enzyme-inspired specificity and employing separating training approaches. Subject type and scoring manual factors were controlled, while the focus was on instruments and montage of recording factors. The proposed model consists of three sets of signal-specific models including EEG-, EOG-, and EMG-specific model. The EEG-specific models further include three sets of channel-specific models. All signal-specific and channel-specific models were established with data manipulation and weighted loss strategies, resulting in three sets of data manipulation models and class-specific models, respectively. These models were CNNs. Additionally, BiLSTM models were applied to EEG- and EOG-specific models to obtain temporal information. Finally, classification task for sleep stage was handled by ‘the-last-dense’ layer. The optimal sampling frequency for each physiological signal was identified and used during the training process. The proposed model was trained on MGH dataset and evaluated using both within dataset and cross-dataset. For MGH dataset, overall accuracy of 81.05 %, MF1 of 79.05 %, Kappa of 0.7408, and per-class F1-scores: W (84.98 %), N1 (58.06 %), N2 (84.82 %), N3 (79.20 %), and REM (88.17 %) can be achieved. Performances on cross-datasets are as follows: SHHS1 200 records reached 79.54 %, 70.56 %, and 0.7078; SHHS2 200 records achieved 76.77 %, 66.30 %, and 0.6632; Sleep-EDF 153 records gained 78.52 %, 72.13 %, and 0.7031; and BCI-MU (local dataset) 94 records achieved 83.57 %, 82.17 %, and 0.7769 for overall accuracy, MF1, and Kappa respectively. Additionally, the proposed model has approximately 9.3 M trainable parameters and takes around 26 s to process one PSG record. The results indicate that the proposed model demonstrates generalizability in sleep stage classification and shows potential as a feasibility tool for real-world applications. Additionally, enzyme-inspired specificity effectively addresses the challenges posed by varying montage of recording, while the identified optimal frequencies mitigate instrument-related issues.
Scaphoid fractures, a common type of clinical fracture, often require screw placement surgery to achieve optimal therapeutic outcomes. Path planning algorithms can avoid more risks and have vital potential for developing precise and automatic surgeries. Despite the success of surgical path planning algorithms, automatic path planning for scaphoid fractures remains challenging owing to the complex bone structure and individual variations.
Thus, we propose a Multi-objective constrained Path planning Algorithm (MPA) for fracture screw placement, which includes the identification of the center of the fracture surface. Further, three constraint conditions were introduced to eliminate infeasible paths, followed by adding three objectives to the remaining paths for more accurate planning. Finally, the Nondominated Sorting Genetic Algorithms (NSGA)-II algorithm was used to optimize the surgical paths.
We defined the vertical compression distance (VCD), a common observation index in clinics. The experiments show that the average VCD of the MPA paths is measured at 23.88 mm, outperforming the clinical planning paths by 21.71 mm. Ablation experiments demonstrated that all three objectives (distance, length, and angle) effectively optimized the path planning. Additionally, we also used finite element analysis to compare and analyze the MPA path and clinical path. The experimental results showed that the MPA path always outperformed the clinical path in terms of scaphoid strain and screw stress.
This study presents a solution for the path planning of scaphoid fractures. Our future research will attempt to enhance the model's performance and extend its application to a broader range of fracture types.
Segmentation of the coronary vessel wall in intravascular ultrasound is a fundamental step in guiding coronary intervention. However, it is an challenging task, even for highly skilled cardiologists, due to image artefacts and shadowed regions caused by calcified plaque, guide wires and vessel side branches. Recently, dense-based neural networks have been applied to this task, however, they often fail to predict anatomically plausible contours in these low-signal areas. We propose a novel methodology called Polygon-based Contour Refiner (POLYCORE) that addresses topological error in dense-based segmentation networks using a relational inductive bias through higher-order connections between vertices to learn anatomically rational contours. Our approach remedies the over-smoothing phenomena common in polygon networks by introducing a new vector field refinement module which enables pixel-level detail to be added in an iterative process. POLYCORE is enhanced with augmented polygon aggregation which we show is more effective than typical dense-based test-time augmentation strategies. We achieve state-of-the-art results on two diverse datasets, observing particular improvements when segmenting the lumen structure and in topologically-challenging regions containing shadow artefacts. Our source code is available here: http://orcid.org/https://github.com/kitbransby/POLYCORE.
Pilomatricoma, a benign childhood skin tumor, presents diagnostic challenges due to its manifestation variations and requires surgical excision upon histological confirmation of its characteristic cellular features. Recent artificial intelligence (AI) advancements in pathology promise enhanced diagnostic accuracy and treatment approaches for this neoplasm.
We employed a multiscale transfer learning model, initiating the training process at high resolutions and adapting to broader scales. For evaluation purposes, we applied metrics such as accuracy, precision, recall, the F1 score, and the area under the receiver operating characteristic curve (AUROC) to measure the performance of the model, with the statistical significance of the results assessed via two-sided P tests. Our novel approach also included a retrosynthetic saliency mapping technique to achieve enhanced lesion visualization in whole-slide images (WSIs), supporting pathologists' diagnostic processes.
Our model effectively navigated the challenges of global-scale classification, achieving a high validation accuracy of up to 0.973 despite some initial fluctuations. This method displayed excellent accuracy in terms of identifying basaloid and ghost cells, especially at lower scales, with slight variability in its ghost cell accuracy and more noticeable changes in the ‘Other’ category at higher scales. The consistent performance attained for basaloid cells was clear across all scales, whereas areas for improvement were identified in the ‘Other’ category. The model also excelled at generating detailed and interpretable saliency maps for lesion visualization purposes, thereby enhancing its value in digital pathology diagnostics.
Our pilomatricoma study demonstrates the efficacy of a deep learning-based histopathological diagnosis model, as validated by its high performance across various scales, and it is enhanced by an innovative retrosynthetic approach for saliency mapping.
The objective of this study is to validate a novel workflow for implementing patient-specific finite element (FE) simulations to virtually replicate the Transcatheter Aortic Valve Implantation (TAVI) procedure.
Seven patients undergoing TAVI were enrolled. Patient-specific anatomical models were reconstructed from pre-operative computed tomography (CT) scans and subsequentially discretized, considering the native aortic leaflets and calcifications. Moreover, high-fidelity models of CoreValve Evolut R and Acurate Neo2 valves were built. To determine the most suitable material properties for the two stents, an accurate calibration process was undertaken. This involved conducting crimping simulations and fine-tuning Nitinol parameters to fit experimental force-diameter curves. Subsequently, FE simulations of TAVI procedures were conducted. To validate the reliability of the implemented implantation simulations, qualitative and quantitative comparisons with post-operative clinical data, such as angiographies and CT scans, were performed.
For both devices, the simulation curves closely matched the experimental data, indicating successful validation of the valves mechanical behaviour. An accurate qualitative superimposition with both angiographies and CTs was evident, proving the reliability of the simulated implantation. Furthermore, a mean percentage difference of 1,79 ± 0,93 % and 3,67 ± 2,73 % between the simulated and segmented final configurations of the stents was calculated in terms of orifice area and eccentricity, respectively.
This study shows the successful validation of TAVI simulations in patient-specific anatomies, offering a valuable tool to optimize patients care through personalized pre-operative planning. A systematic approach for the validation is presented, laying the groundwork for enhanced predictive modeling in clinical practice.
The findings from forensic autopsies, where cause of death must be established and reported to legal authorities, are reported in paper-based formats. Practitioners are required to map 3D injury findings to 2D space. Here, we design and describe a digital Forensic AuTopsy Annotation tooL (FATAL), that can be used by practitioners to record systematically detailed autopsy findings onto an interactive 3D body model.
We employ a user-centred design process involving an expert forensic medicine team. We describe the iteration process and the final functionality determined, based on in-depth analyses of forensic clinical workflows, and feedback on the types of complex cases confronting practitioners.
FATAL functions include freehand drawing, a layer system for injury categorisation, trajectory plotting, surface area markings, and point-of-interest marking. Relevant external images, such as investigative report or autopsy photographs, can be loaded into the FATAL tool and assigned to individual annotations. The application streamlines workflows, supports template-driven documentation, and collates all forensic data into a single interface. Findings from the digital tool can be exported to a 2D report (PDF).
We highlight the advancements in accuracy, efficiency, and reproducibility afforded by a digital tool for forensic autopsy documentation. Potential applications in forensic medical examinations beyond autopsies are described, along with specific areas for extension, such as supporting touch screen and pen inputs, export for 3D printing models and extending the tool's compatibility with custom 3D body models.