Medical & Biological Engineering & Computing最新文献

Breast cancer image classification remains a challenging task due to the high-resolution nature of pathological images and their complex feature distributions. Graph neural networks (GNNs) offer promising capabilities to capture local structural information but often suffer from limited generalization and reliance on shortcut features. This study proposes a novel causal discovery attention-based graph neural network (CDA-GNN) model. The model converts high-resolution image data into graph data using superpixel segmentation and employs a causal attention mechanism to identify and utilize key causal features. A backdoor adjustment strategy further disentangles causal features from shortcut features, enhancing model interpretability and robustness. Experimental evaluations on the 2018 BACH breast cancer image dataset demonstrate that CDA-GNN achieves a classification accuracy of 86.36%. Additional metrics, including F1-score and ROC, validate the superior performance and generalization of the proposed approach. The CDA-GNN model, with its powerful automated cancer image analysis capabilities and strong interpretability, provides an effective tool for clinical applications. It significantly reduces the workload of healthcare professionals while facilitating the early detection and diagnosis of breast cancer, thereby improving diagnostic efficiency and accuracy.

Diagnosing Parkinson's disease (PD) via speech is crucial for its non-invasive and convenient data collection. However, the small sample size of PD speech data impedes accurate recognition of PD speech. Therefore, we propose a novel multi-source sparse broad transfer learning (SBTL) method, inspired by incremental broad learning, which balances model learning capability and the overfitting associated with limited sample size of PD speech data. Specifically, SBTL initially leverages a sparse network to preprocess highly overlapping PD speech data, facilitating the identification of intrinsic invariant features between the multi-source auxiliary domain and the target data, which contributes to reducing model complexity. Subsequently, SBTL evaluate transfer effectiveness by virtue of the incremental learning mechanism, adaptively adjusting model structure to ensure the positive transfer of knowledge from the multi-source auxiliary domains to the target domain. Numerous experimental results show that, compared to transfer learning methods for PD diagnosis via speech, SBTL consistently demonstrates significant advantages with a smaller standard deviation, particularly leading by at least 2.58%, 5.71%, 12%, and 14.81% in accuracy, precision, sensitivity, and F1-score, respectively. Even when compared to some well-known transfer learning methods, SBTL still exhibits significant advantages in most cases while maintaining comparable sensitivity. These demonstrate that SBTL is an effective, efficient, and stable multi-source transfer learning method for PD speech recognition, giving more accurate assistance information for clinicians on decision-making for PD in practice.

The medial displacement calcaneal osteotomy (MDCO) is one of commonly used procedures to restore the hindfoot alignment of the flatfoot deformity. However, the selection of the amount of translation for MDCO and its biomechanical effect on the hindfoot was rarely reported. This study employs finite element analysis to investigate stress distribution in the hindfoot following MDCO across varying translation distances. An adult-acquired flatfoot deformity (AAFD) finite element (FE) model consisting of 16 bones, 56 ligaments, and soft tissues was used. MDCO procedure was simulated with the translation distance of 0 mm, 2 mm, 4 mm, 6 mm, 8 mm, 10 mm, 12 mm, and 14 mm. Contact pressure on the plantar surface, the articular surface of the tibiotalar joint and the subtalar joint, and von Mises stress on the resection surface of the calcaneus under different translation distances were analyzed and compared. Results showed the MDCO reduces 12.46 to 33.32% peak contact pressure on the plantar surface, the tibiotalar joint, and the posterior facet of the subtalar joint, and shifts pressure from lateral to medial. But the difference in peak pressure for different translation distances larger than 4 mm was small. The MDCO also reduces the stress on the distal calcaneal resected surface. The study highlights the use of patient-specific computational modeling for preoperative plans.

Recent advancements in deep learning have significantly improved the intelligent classification of gastrointestinal (GI) diseases, particularly in aiding clinical diagnosis. This paper seeks to review a computer-aided diagnosis (CAD) system for GI diseases, aligning with the actual clinical diagnostic process. It offers a comprehensive survey of deep learning (DL) techniques tailored for classifying GI diseases, addressing challenges inherent in complex scenes, clinical constraints, and technical obstacles encountered in GI imaging. Firstly, the esophagus, stomach, small intestine, and large intestine were located to determine the organs where the lesions were located. Secondly, location detection and classification of a single disease are performed on the premise that the organ's location corresponding to the image is known. Finally, comprehensive classification for multiple diseases is carried out. The results of single and multi-classification are compared to achieve more accurate classification outcomes, and a more effective computer-aided diagnosis system for gastrointestinal diseases was further constructed.

An optimal pillow effectively increases sleep quality and prevents cervical symptoms. However, the influence of body dimension on optimal pillow design or selection strategy has not been clarified quantitatively. This study aims to investigate the individualized optimal pillow height and neck support for side sleepers. Nine healthy subjects were recruited and laid laterally on foam-latex pillow with four height levels (8 cm, 10 cm, 12 cm, 14 cm) and with/without neck support, respectively. Healthiness was evaluated using cervical spine morphology (measured by motion capturing system) and musculoskeletal internal force (simulated by a multi-body model). Comfortability was evaluated by a deviation standardized overall comfort rating. Individualized pillow height was identified by Hφ (calculated by the subject's shoulder width and absolute pillow height). Correlation analysis and linear mixed model were performed between C1-T1 slope and Hφ. A paired-t test was performed on the cervical curve and comfort score comparisons between neck support pillow and flat pillow. The C1-T1 slope of the cervical curve showed statistically significant correlation to Hφ and was well predicted by Hφ through linear relation (R² = 0.80 for flat pillow, R² = 0.82 for neck support pillow). The correlation between comfort score and Hφ was moderate or weak. Medium individualized height pillow (Hφ 9.74-11.76 cm) with neck support showed a cervical curve closest to natural standing and the lowest musculoskeletal internal force. Sub-low individualized height pillow (Hφ 11.76-13.78 cm) with neck support showed the highest average comfort score. For side sleepers, cervical curve morphology and optimal individualized pillow height are well predicted by Hφ. Comfortability perception is not sensitive to Hφ. Sub-low individualized height pillow showed the best comfortability and relatively good healthiness. Medium individualized height pillow with neck support showed the best healthiness.

The uncalibrated brain-computer interface (BCI) system based on steady-state visual evoked potential (SSVEP) can omit the training process and is closer to the practical application. Filter bank canonical correlation analysis (FBCCA), as a classical approach of uncalibrated SSVEP-based BCI, extracts the fundamental and harmonic ingredients through filter bank decomposition. Nevertheless, this method fails to fully leverage the temporal feature of the signal. The paper suggested utilizing reconstructed data with temporal delay in the computation of the canonical correlation coefficient, and the different combinations of the time-delayed embedding and FBCCA were discussed. We selected the data from seven participants in the Benchmark dataset for parameter optimization and evaluated the method across all participants. The experimental results showed that only embedding the time-delayed version into the first subband (FBdCCA) was better than embedding it into all subbands (FBdCCA(all)), and the accuracy of FBdCCA surpassed that of FBCCA significantly. This suggests that the approach of time-delayed embedding can further enhance the performance of FBCCA.

Research on degenerative spondylolisthesis (DS) has focused primarily on the biomechanical responses of pathological segments, with few studies involving muscle modelling in simulated analysis, leading to an emphasis on the back muscles in physical therapy, neglecting the ventral muscles. The purpose of this study was to quantitatively analyse the biomechanical response of the spinopelvic complex and surrounding muscle groups in DS patients using integrative modelling. The findings may aid in the development of more comprehensive rehabilitation strategies for DS patients. Two new finite element spinopelvic complex models with detailed muscles for normal spine and DS spine (L4 forwards slippage) modelling were established and validated at multiple levels. Then, the spinopelvic position parameters including peak stress of the lumbar isthmic-cortical bone, intervertebral discs, and facet joints; peak strain of the ligaments; peak force of the muscles; and percentage difference in the range of motion were analysed and compared under flexion-extension (F-E), lateral bending (LB), and axial rotation (AR) loading conditions between the two models. Compared with the normal spine model, the DS spine model exhibited greater stress and strain in adjacent biological tissues. Stress at the L4/5 disc and facet joints under AR and LB conditions was approximately 6.6 times greater in the DS spine model than in the normal model, the posterior longitudinal ligament peak strain in the normal model was 1/10 of that in the DS model, and more high-stress areas were found in the DS model, with stress notably transferring forwards. Additionally, compared with the normal spine model, the DS model exhibited greater muscle tensile forces in the lumbosacral muscle groups during F-E and LB motions. The psoas muscle in the DS model was subjected to 23.2% greater tensile force than that in the normal model. These findings indicated that L4 anterior slippage and changes in lumbosacral-pelvic alignment affect the biomechanical response of muscles. In summary, the present work demonstrated a certain level of accuracy and validity of our models as well as the differences between the models. Alterations in spondylolisthesis and the accompanying overall imbalance in the spinopelvic complex result in increased loading response levels of the functional spinal units in DS patients, creating a vicious cycle that exacerbates the imbalance in the lumbosacral region. Therefore, clinicians are encouraged to propose specific exercises for the ventral muscles, such as the psoas group, to address spinopelvic imbalance and halt the progression of DS.

Behavioral recordings annotated by human observers (HOs) from video recordings are a fundamental component of preclinical animal behavioral models of neurobiological diseases. These models are often criticized for their vulnerability to reproducibility issues. Here, we present the EthoWatcher-Open Source (EW-OS), with tools and procedures for the use of blind-to-condition categorical transcriptions that are simultaneous with tracking, for the assessment of HOs intra- and interobserver reliability during training and data collection, for producing video clips of samples of behavioral categories that are useful for observer training. The use of these tools can inform and optimize the performance of observers, thus favoring the reproducibility of the data obtained. Categorical and machine vision-derived outputs are presented in an open data format for increased interoperability with other applications, where behavioral categories are associated frame-by-frame with tracking, morphological and kinematic attributes of an animal's image. The center of mass (X and Y pixel coordinates), the animal's area in square millimeters, the length and width in millimeters, and the angle in degrees were recorded. It also assesses the variation in each morphological descriptor to produce kinematic descriptors. While the initial measurements are in pixels, they are later converted to millimeters using the scale calibrated by the user via the graphical user interfaces. This process enables the creation of databases suitable for machine learning processing and behavioral pharmacology studies. EW-OS is constructed for continued collaborative development, available through an open-source platform, to support initiatives toward the adoption of good scientific practices in behavioral analysis, including tools for evaluating the quality of the data that can alleviate problems associated with low reproducibility in the behavioral sciences.

Early detection of dementia is essential to reduce the decline in quality of life (QoL) and the increase in medical and nursing care costs associated with dementia in an aging society. In this study, we aimed to develop a simple screening test for mild cognitive impairment (MCI), a preliminary stage of dementia, by creating an analytical method to accurately detect MCI through finger-tapping measurement. We extracted 248 characteristics from the finger-tapping waveforms of 182 MCI patients and 352 normal controls, applying five conventional classification methods along with an improved Random Forest (RF) method proposed in this study (Integrated RF). In the proposed method, the RF classification model for the MCI and normal control groups is supplementally integrated with the RF classification model for the Alzheimer's disease and normal control groups to generate a new classification model. When comparing the discrimination accuracy of each method, the proposed method achieved the highest accuracy, with an F1-score of 0.795 (recall = 0.778 and precision = 0.814). These results demonstrate the potential of finger-tapping measurement as a highly accurate screening test for MCI.

Electrohysterogram (EHG) is an electrophysiological signal describing uterine contractions that can be non-invasively measured on maternal abdominal surface. This signal contains vital physiological and pathological information for assessing delivery abnormalities, such as preterm birth. However, extracting information that effectively characterizes the association with abnormal delivery from the weak EHG signal is challenging. We present a preterm birth predicting method using multivariate empirical mode decomposition (MEMD) algorithm that adaptively decomposes multichannel EHG signals into different intrinsic mode functions (IMFs). MEMD maintains spectral consistency across channels and avoids mode-mixing problems across IMFs due to its powerful fine-grained signal structure decoupling capability. On this basis, a total of 180 features were extracted from the IMFs and the final eight features were chosen using a two-step feature selection algorithm. A support vector machine (SVM) classifier was employed for decision-making. Specifically, cost-sensitive algorithm was used to solve the data imbalance problem. The proposed method was evaluated using 300 EHG recordings in TPEHG database. The results show that our method outperforms other state-of-the-art methods in terms of sensitivity (85.16%), specificity (96.54%), ${F1}_{\text{score}}$ (91.04%), accuracy (94.36%), and AUC (97.31%). This study provides a powerful tool with wide applications for preterm birth risk diagnosis in clinical obstetric.