Usage of intelligent medical aided diagnosis system under the deep convolutional neural network in lumbar disc herniation

Policy Learning for Actively Labeled Sample Selection on Lumbar Semi-supervised Classification

Large labeled data bring significant performance improvement, but acquiring labeled medical data is particularly challenging due to the laborious, time-consuming, and medically qualified annotation. Semi-supervised learning has been employed to leverage unlabeled data. However, the quality and quantity of annotated data have a great influence on the performance of the semi-supervised model. Selecting informative samples through active learning is crucial and could improve model performance. Therefore, we propose a unified semi-supervised active learning architecture (RL-based SSAL) that alternately trains a semi-supervised network and performs active sample selection. Semi-supervised model is first well trained for sample selection, and selected label-required samples are annotated and added to the previously labeled dataset for subsequent semi-supervised model training. To learn to select the most informative samples, we adopt a policy learning-based approach that treats sample selection as a decision-making process. A novel reward function based on the product of predictive confidence and uncertainty is designed, aiming to select samples with high confidence and uncertainty. Comparisons with a semi-supervised baseline on collected lumbar disc herniation dataset demonstrate the effectiveness of the proposed RL-based SSAL, achieving over 3% promotion across different amounts of labeled data. Comparisons with other active learning methods and ablation studies reveal the superiority of proposed policy learning based on active sample selection and reward function. Our model trained with only 200 labeled data achieves an accuracy of 89.32% which is comparable to the performance achieved with the entire labeled dataset, demonstrating its significant advantage.

Assessment of lumbar disc herniation-impaired gait by using IMU data fusion method

The inertial motion unit (IMU) is an effective tool for monitoring and assessing gait impairment in patients with lumbar disc herniation(LDH). However, the current clinical assessment methods for LDH gait focus on patients' subjective scoring indicators and lack the assessment of kinematic ability; at the same time, individual differences in the motor function degradation of the healthy and affected lower limbs of LDH patients are also ignored. To solve this problem, we propose an LDH gait feature model based on multi-source adaptive Kalman data fusion of acceleration and angular velocity. The gait phase is segmented by using an adaptive Kalman data fusion algorithm to estimate the attitude angle, and obtaining gait events through a zero-velocity update technique and a peak detection algorithm. Two IMUs were used to analyze the gait characteristics of lumbar disc patients and healthy gait people, including 12 gait characteristics such as gait spatiotemporal parameters, kinematic parameters, gait variability and stability. Statistical methods were used to analyze the characteristic model and verify the biological differences between the healthy affected side of LDH and healthy subjects. Finally, feature engineering and machine learning technology were used to identify the gait pattern of inertial movement units in patients with lumbar intervertebral disc disease, and achieved a classification accuracy of 95.50%, providing an effective gait feature set and method for clinical evaluation of LDH.

3D multi-scale feature extraction and recalibration network for spinal structure and lesion segmentation

BACKGROUND

Automatic segmentation has emerged as a promising technique for the diagnosis of spinal conditions.

PURPOSE

To design and evaluate a deep convolution network for segmenting the intervertebral disc, spinal canal, facet joint, and herniated disk on magnetic resonance imaging (MRI) scans.

MATERIAL AND METHODS

MRI scans of 70 patients with disc herniation were gathered and manually annotated by radiologists. A novel deep neural network was developed, comprising 3D squeeze-and-excitation blocks and multi-scale feature extraction blocks for automated segmentation of spinal structure and lesion. To address the issue of class imbalance, a weighted cross-entropy loss was introduced for training. In addition, semi-supervision segmentation was accomplished to reduce annotation labor cost.

RESULTS

The proposed model achieved 77.67% mean intersection over union, with 9.56% and 11.11% gains over typical V-Net and U-Net respectively, outperforming the other models in ablation experiments. In addition, the semi-supervision segmentation method was proven to work.

CONCLUSION

The 3D multi-scale feature extraction and recalibration network achieved an excellent segmentation performance of intervertebral disc, spinal canal, facet joint, and herniated disk, outperforming typical encoder-decoder networks.

A Series-Based Deep Learning Approach to Lung Nodule Image Classification

Although many studies have shown that deep learning approaches yield better results than traditional methods based on manual features, CADs methods still have several limitations. These are due to the diversity in imaging modalities and clinical pathologies. This diversity creates difficulties because of variation and similarities between classes. In this context, the new approach from our study is a hybrid method that performs classifications using both medical image analysis and radial scanning series features. Hence, the areas of interest obtained from images are subjected to a radial scan, with their centers as poles, in order to obtain series. A U-shape convolutional neural network model is then used for the 4D data classification problem. We therefore present a novel approach to the classification of 4D data obtained from lung nodule images. With radial scanning, the eigenvalue of nodule images is captured, and a powerful classification is performed. According to our results, an accuracy of 92.84% was obtained and much more efficient classification scores resulted as compared to recent classifiers.

Evaluation of the Effect of Integrated Care on Preoperative Anxiety in Day Surgery Patients Based on the MVPA Framework

Objective

To investigate the effect of receiving comprehensive care on preoperative anxiety in patients admitted to the operating room at different times.

Methods

A generative model was applied to a patient's preoperative anxiety aid diagnostic model and used to address preoperative anxiety due to the patient. Group ICA first constructed a whole-brain dynamic functional connectivity network, and an initial dataset was constructed by Kendall's ranking correlation coefficient method; then, an expanded dataset was constructed by a conditional deep convolutional generative adversarial network (CDCGAN), and finally, a dynamic classification study of patients with preoperative anxiety and healthy subjects was conducted by feature selection and discriminant models in turn. Seventy patients who entered the operating theatre at different times were retrospectively analyzed. Children who entered the operating theatre after 14:00 were included in the control group (n = 35), and those who entered between 12:00 were included in the observation group (n = 35). Patients in both groups were given comprehensive care, and preoperative anxiety was compared between the two groups.

Results

The earlier the patients entered the operating room, the lower the preoperative anxiety.

Conclusion

Comprehensive care could reduce the patients' preoperative anxiety, keep their emotions stable, and improve their compliance with treatment.

Privacy-Preserving Multi-class Support Vector Machine Model on Medical Diagnosis

With the rapid development of machine learning in the medical cloud system, cloud-assisted medical computing provides a concrete platform for remote rapid medical diagnosis services. Support vector machine (SVM), as one of the important algorithms of machine learning, has been widely used in the field of medical diagnosis for its high classification accuracy and efficiency. In some existing schemes, healthcare providers train diagnostic models with SVM algorithms and provide online diagnostic services to doctors. Doctors send the patients case report to the diagnostic models to obtain the results and assist in clinical diagnosis. However, case report involves patients privacy, and patients do not want their sensitive information to be leaked. Therefore, the protection of patients privacy has become an important research direction in the field of online medical diagnosis. In this paper, we propose a privacy-preserving medical diagnosis scheme based on multi-class SVMs. The scheme is based on the distributed two trapdoors public key cryptosystem (DT-PKC) and Boneh-Goh-Nissim (BGN) cryptosystem. We design a secure computing protocol to compute the core process of the SVM classification algorithm. Our scheme can deal with both linearly separable data and nonlinear data while protecting the privacy of user data and support vectors. Compared to prior work, in certain circumstances, the elapsed time of the Gaussian kernel function is less than the linear kernel function. In addition, when the data number is more than 100, our secure computing protocol will not affect the classification results. The results show that our scheme is secure, reliable, scalable with high accuracy.