FIT-graph: A multi-grained evolutionary graph based framework for disease diagnosis.

Early assessment, with the help of machine learning methods, can aid clinicians in optimizing the diagnosis and treatment process, allowing patients to receive critical treatment time. Due to the advantages of effective information organization and interpretable reasoning, knowledge graph-based methods have become one of the most widely used machine learning algorithms for this task. However, due to a lack of effective organization and use of multi-granularity and temporal information, current knowledge graph-based approaches are hard to fully and comprehensively exploit the information contained in medical records, restricting their capacity to make superior quality diagnoses. To address these challenges, we examine and study disease diagnosis applications in-depth, and propose a novel disease diagnosis framework named FIT-Graph. With novel medical multi-grained evolutionary graphs, FIT-Graph efficiently organizes the extracted information from various granularities and time stages, maximizing the retention of valuable information for disease inference and ensuring the comprehensiveness and validity of the final disease inference. We compare FIT-Graph with two real-world clinical datasets from cardiology and respiratory departments with the baseline. The experimental results show that its effect is better than the baseline model, and the baseline performance of the task is improved by about 5% in multiple indices.

Using Multi-Task Learning-Based Framework to Detect ST-Segment and J-Point Deviation From Holter.

Artificial intelligence is increasingly being used on the clinical electrocardiogram workflows. Few electrocardiograms based on artificial intelligence algorithms have focused on detecting myocardial ischemia using long-term electrocardiogram data. A main reason for this is that interference signals generated from daily activities while wearing the Holter monitor lowered the ability of artificial intelligence to detect myocardial ischemia. In this study, an automatic system combining denoising and segmentation modules was developed to detect the deviation of the ST-segment and J point. We proposed a ECG Bidirectional Transformer network that applied in both denoising and segmentation tasks. The denoising model achieved RMSEde, SNRimp, and PRD values of 0.074, 10.006, and 16.327, respectively. The segmentation model achieved precision, sensitivity (recall), and F1-score of 96.00, 93.06, and 94.51%, respectively. The system's ability to distinguish the depression and elevation of the ST-segment and J point was also verified by cardiologists as well. From our ECG dataset, 103 patients with ST-segment depression and 10 patients with ST-segment elevation were detected with positive predictive values of 80.6 and 60% respectively. Using Holter ECG and transformer-based deep neural networks, we can detect subtle ST-segment changes in noisy ECG signals. This system has the potential to improve the efficacy of daily medicine and to provide a broader population-level screening for asymptomatic myocardial ischemia.

Practical fine-grained learning based anomaly classification for ECG image.

As a widely used vital sign within cardiology, Electrocardiography (ECG) provides the basis for assessing heart function and diagnosing cardiovascular diseases. Automated anomaly detection for ECG plays an important role in improving patient diagnosis efficiency and reducing healthcare costs. Practically, due to the limits of electronics support or the medical system setting, image is a more common format for large-scale ECG storage in most clinical institutions. To guarantee an automated ECG detection model's scalability and practicality in clinical applications, taking good advantage of ECG images is crucial. However, existing time digital-based discriminative models fail to learn from images effectively for two reasons. First of all, the signals recorded on images have much lower resolution and higher noise, which makes it impractical to extract precise ECG signals following existing techniques. Meanwhile, the differences between abnormal signals are usually subtle, and they may be overwhelmed by the noises in the images as well. Towards this end, we design a novel neural framework that can be directly applied to massive ECG images determining various types of cardiology abnormalities. It classifies fine-grained ECG images based on weakly supervised strategy, in which case only image-level labeling is required. By eliminating the need for part annotations, the proposed method can result in significant savings in annotation time and cost. The effectiveness of the method is demonstrated by experimental results on two real ECG datasets.

Evaluation of a computer-aided method for measuring the Cobb angle on chest X-rays.

OBJECTIVES: To automatically measure the Cobb angle and diagnose scoliosis on chest X-rays, a computer-aided method was proposed and the reliability and accuracy were evaluated. METHODS: Two Mask R-CNN models as the core of a computer-aided method were used to separately detect and segment the spine and all vertebral bodies on chest X-rays, and the Cobb angle of the spinal curve was measured from the output of the Mask R-CNN models. To evaluate the reliability and accuracy of the computer-aided method, the Cobb angles on 248 chest X-rays from lung cancer screening were measured automatically using a computer-aided method, and two experienced radiologists used a manual method to separately measure Cobb angles on the aforementioned chest X-rays. RESULTS: For manual measurement of the Cobb angle on chest X-rays, the intraclass correlation coefficients (ICC) of intra- and inter-observer reliability analysis was 0.941 and 0.887, respectively, and the mean absolute differences were < 3.5°. The ICC between the computer-aided and manual methods for Cobb angle measurement was 0.854, and the mean absolute difference was 3.32°. These results indicated that the computer-aided method had good reliability for Cobb angle measurement on chest X-rays. Using the mean value of Cobb angles in manual measurements > 10° as a reference standard for scoliosis, the computer-aided method achieved a high level of sensitivity (89.59%) and a relatively low level of specificity (70.37%) for diagnosing scoliosis on chest X-rays. CONCLUSION: The computer-aided method has potential for automatic Cobb angle measurement and scoliosis diagnosis on chest X-rays. These slides can be retrieved under Electronic Supplementary Material.

Patterning N-type and S-type neuroblastoma cells with Pluronic F108 and ECM proteins.

Influencing cell shape using micropatterned substrates affects cell behaviors, such as proliferation and apoptosis. Cell shape may also affect these behaviors in human neuroblastoma (NBL) cancer, but to date, no substrate design has effectively patterned multiple clinically important human NBL lines. In this study, we investigated whether Pluronic F108 was an effective antiadhesive coating for human NBL cells and whether it would localize three NBL lines to adhesive regions of tissue culture plastic or collagen I on substrate patterns. The adhesion and patterning of an S-type line, SH-EP, and two N-type lines, SH-SY5Y and IMR-32, were tested. In adhesion assays, F108 deterred NBL adhesion equally as well as two antiadhesive organofunctional silanes and far better than bovine serum albumin. Patterned stripes of F108 restricted all three human NBL lines to adhesive stripes of tissue culture plastic. We then investigated four schemes of applying collagen and F108 to different regions of a substrate. Contact with collagen obliterates the ability of F108 to deter NBL adhesion, limiting how both materials can be applied to substrates to produce high fidelity NBL patterning. This patterned substrate design should facilitate investigations of the role of cell shape in NBL cell behavior.

Aligned electrospun nanofibers specify the direction of dorsal root ganglia neurite growth.

Nerve injury, a significant cause of disability, may be treated more effectively using nerve guidance channels containing longitudinally aligned fibers. Aligned, electrospun nanofibers direct the neurite growth of immortalized neural stem cells, demonstrating potential for directing regenerating neurites. However, no study of neurite guidance on these fibers has yet been performed with primary neurons. Here, we examined neurites from dorsal root ganglia explants on electrospun poly-L-lactate nanofibers of high, intermediate, and random alignment. On aligned fibers, neurites grew radially outward from the ganglia and turned to follow the fibers upon contact. Neurite guidance was robust, with neurites never leaving the fibers to grow on the surrounding cover slip. To compare the alignment of neurites to that of the nanofiber substrates, Fourier methods were used to quantify the alignment. Neurite alignment, however striking, was inferior to fiber alignment on all but the randomly aligned fibers. Neurites on highly aligned substrates were 20 and 16% longer than neurites on random and intermediate fibers, respectively. Schwann cells on fibers assumed a very narrow morphology compared to those on the surrounding coverslip. The robust neurite guidance demonstrated here is a significant step toward the use of aligned, electrospun nanofibers for nerve regeneration. (c) 2007 Wiley Periodicals, Inc. J Biomed Mater Res, 2007.