Three-dimensional discrete element method for the prediction of protoplasmic seepage through membrane in a biological cell

Contrast-enhanced magnetic resonance image segmentation based on improved U-Net and Inception-ResNet in the diagnosis of spinal metastases

Objective

The objective of this study was to investigate the use of contrast-enhanced magnetic resonance imaging (CE-MRI) combined with radiomics and deep learning technology for the identification of spinal metastases and primary malignant spinal bone tumor.

Methods

The region growing algorithm was utilized to segment the lesions, and two parameters were defined based on the region of interest (ROI). Deep learning algorithms were employed: improved U-Net, which utilized CE-MRI parameter maps as input, and used 10 layers of CE images as input. Inception-ResNet model was used to extract relevant features for disease identification and construct a diagnosis classifier.

Results

The diagnostic accuracy of radiomics was 0.74, while the average diagnostic accuracy of improved U-Net was 0.98, respectively. the PA of our model is as high as 98.001%. The findings indicate that CE-MRI based radiomics and deep learning have the potential to assist in the differential diagnosis of spinal metastases and primary malignant spinal bone tumor.

Conclusion

CE-MRI combined with radiomics and deep learning technology can potentially assist in the differential diagnosis of spinal metastases and primary malignant spinal bone tumor, providing a promising approach for clinical diagnosis.

Bone tumor examination based on FCNN-4s and CRF fine segmentation fusion algorithm

Background and objective

Bone tumor is a kind of harmful orthopedic disease, there are benign and malignant points. Aiming at the problem that the accuracy of the existing machine learning algorithm for bone tumor image segmentation is not high, a bone tumor image segmentation algorithm based on improved full convolutional neural network which consists fully convolutional neural network (FCNN-4s) and conditional random field (CRF).

Methodology

The improved fully convolutional neural network (FCNN-4s) was used to perform coarse segmentation on preprocessed images. Batch normalization layers were added after each convolutional layer to accelerate the convergence speed of network training and improve the accuracy of the trained model. Then, a fully connected conditional random field (CRF) was fused to refine the bone tumor boundary in the coarse segmentation results, achieving the fine segmentation effect.

Results

The experimental results show that compared with the traditional convolutional neural network bone tumor image segmentation algorithm, the algorithm has a great improvement in segmentation accuracy and stability, the average Dice can reach 91.56%, the real-time performance is better.

Conclusion

Compared with the traditional convolutional neural network segmentation algorithm, the algorithm in this paper has a more refined structure, which can effectively solve the problem of over-segmentation and under-segmentation of bone tumors. The segmentation prediction has better real-time performance, strong stability, and can achieve higher segmentation accuracy.

Deep learning-based image segmentation model using an MRI-based convolutional neural network for physiological evaluation of the heart

Background and Objective: Cardiovascular disease is a high-fatality health issue. Accurate measurement of cardiovascular function depends on precise segmentation of physiological structure and accurate evaluation of functional parameters. Structural segmentation of heart images and calculation of the volume of different ventricular activity cycles form the basis for quantitative analysis of physiological function and can provide the necessary support for clinical physiological diagnosis, as well as the analysis of various cardiac diseases. Therefore, it is important to develop an efficient heart segmentation algorithm. Methods: A total of 275 nuclear magnetic resonance imaging (MRI) heart scans were collected, analyzed, and preprocessed from Huaqiao University Affiliated Strait Hospital, and the data were used in our improved deep learning model, which was designed based on the U-net network. The training set included 80% of the images, and the remaining 20% was the test set. Based on five time phases from end-diastole (ED) to end-systole (ES), the segmentation findings showed that it is possible to achieve improved segmentation accuracy and computational complexity by segmenting the left ventricle (LV), right ventricle (RV), and myocardium (myo). Results: We improved the Dice index of the LV to 0.965 and 0.921, and the Hausdorff index decreased to 5.4 and 6.9 in the ED and ES phases, respectively; RV Dice increased to 0.938 and 0.860, and the Hausdorff index decreased to 11.7 and 12.6 in the ED and ES, respectively; myo Dice increased to 0.889 and 0.901, and the Hausdorff index decreased to 8.3 and 9.2 in the ED and ES, respectively. Conclusion: The model obtained in the final experiment provided more accurate segmentation of the left and right ventricles, as well as the myocardium, from cardiac MRI. The data from this model facilitate the prediction of cardiovascular disease in real-time, thereby providing potential clinical utility.

Fast detection method for prostate cancer cells based on an integrated ResNet50 and YoloV5 framework

PURPOSE

To propose a fast detection method for prostate cancer abnormal cells based on deep learning. The purpose of this method is to quickly and accurately locate and identify abnormal cells, so as to improve the efficiency of prostate precancerous screening and promote the application and popularization of prostate cancer cell assisted screening technology.

METHOD

The method includes two stages: preliminary screening of abnormal cell images and accurate identification of abnormal cells. In the preliminary screening stage of abnormal cell images, ResNet50 model is used as the image classification network to judge whether the local area contains cell clusters. In the another stage, YoloV5 model is used as the target detection network to locate and recognize abnormal cells in the image containing cell clusters.

RESULTS

This detection method aims at the pathological cell images obtained by the membrane method. And the double stage models proposed in this paper are compared with the single stage model method using only the target detection model. The results show that through the image classification network based on deep learning, we can first judge whether there are abnormal cells in the local area. If there are abnormal cells, we can further use the target detection method based on candidate box for analysis, which can reduce the reasoning time by 50% and improve the efficiency of abnormal cell detection under the condition of losing a small amount of accuracy and slightly increasing the complexity of the model.

CONCLUSION

This study proposes a fast detection method for prostate cancer abnormal cells based on deep learning, which can greatly shorten the reasoning time and improve the detection speed. It is able to improve the efficiency of prostate precancerous screening.

Transcription factor NFE2L3 promotes the proliferation of esophageal squamous cell carcinoma cells and causes radiotherapy resistance by regulating IL-6

OBJECTIVE

To scrutinize the impact of overexpression and interference of NFE2L3 on radiosensitivity of esophageal squamous cell carcinoma cells (ESCC) and its downstream mechanism and to assess whether NFE2L3 expression alters in vivo radiosensitivity of ESCC by developing a subcutaneous tumor model in mice.

METHODS

Through RNA-Seq, we compared the differentially expressed genes between the ECA-109R cell line and its parent ECA-109 cell line. The differentially expressed genes were selected and verified by qRT-PCR. Transfection of ESCC cell lines with NFE2L3 inhibitor or mimic lentivirus constructs was done to study the activity of NFE2L3. To assess the effect of NFE2L3 on cellular growth and proliferation, clonogenic survival assay, EdU incorporation assay, and CCK-8 assay were done after irradiation. To probe how many irradiated DNA double-strand breaks were produced, the corresponding intensity of γ-H2AX foci were detected by immunofluorescence. Apoptotic cells were assayed by flow cytometry assay after irradiation; To investigate the downstream genes of NFE2L3, we knocked NFE2L3, and RNA-Seq was used to find out the downstream genes. qRT-PCR and western blot ensued to score associated protein profiles. The in vivo ESCC cell radiosensitivity was scrutinized by nude mouse xenograft models.

RESULTS

The differential genes between ECA-109R cells and its parent ECA-109 cells were compared by qRT-PCR to unveil a significant increase in NFE2L3 expression. Functional analysis indicated that NFE2L3 increased radioresistance in ESCC cells. Then, through high-throughput sequencing and bioinformatics analysis, IL-6 was found to be a hub gene that played a role downstream of NFE2L3 and was verified by qRT-PCR, western blot, and double luciferase reporter gene experiment. NFE2L3 could regulate ESCC cell radiosensitivity via the IL-6-STAT3 signaling pathway, and downregulation of IL-6 expression could reverse the effects of highly expressed NFE2L3. In vivo tumor xenograft experiments confirmed that NFE2L3 affects the sensitivity to radiation therapy.

CONCLUSION

NFE2L3 can affect the radiosensitivity of ESCC cells through IL-6 transcription and IL-6/STAT3 signaling pathway. This makes NFE2L3 a putative target to regulate ESCC cell radiosensitivity.

Femoral image segmentation based on two-stage convolutional network using 3D-DMFNet and 3D-ResUnet

OBJECTIVE

The femur is a typical human long bone with an irregular spatial structure. Femoral fractures are the most common occurrence in middle-aged and older adults. The structure of human bone tissue is very complex, and there are significant differences between individuals. Segmenting bone tissue is a challenging task and of great practical significance.

METHODS

Our research is based on segmenting and the three-dimensional reconstruction of femoral images using X-ray imaging. The currently commonly used two-dimensional fully convolutional network Unet has the problem of ignoring spatial position information and losing too much feature information. The commonly used three-dimensional fully convolutional network 3D Unet has the problem of ignoring spatial position information and losing too much feature information. For the problem of many model parameters, we proposes a two-stage network segmentation model composed of 3D-DMFNet and 3D-ResUnet networks and trains the network in stages to segment the femur. One stage is used to detect the coarse segmentation of the femur range, and one stage is used for the fine segmentation of the femur so that the training speed is fast and the segmentation accuracy is moderate, which is suitable for detecting the femur range.

RESULTS

The experimental dataset used in this paper is from The Second Affiliated Hospital of Fujian Medical University, which consists of 30 sets of femur X-ray images. The experiment compares the accuracy and loss value of Unet and the two-stage convolutional network. The image shows that the two-stage convolutional network has higher accuracy. At the same time, this paper shows the effect of the two-stage coarse segmentation and fine segmentation of medical images. Subsequently, this paper applies the model to practice and obtains the model's Dice, Sensitivity, Specificity and Pixel Accuracy values. After comparative analysis, the experimental results show that the two-stage network segmentation model composed of 3D-DMFNet and 3D-ResUnet network designed in this paper has higher accuracy, intuitiveness, and more application value than traditional image segmentation algorithms.

CONCLUSION

With the continuous application of X-ray images in clinical diagnosis using femoral images, the method in this paper is expected to become a diagnostic tool that can effectively improve the accuracy and loss of femoral image segmentation and the three-dimensional reconstruction.

Patellar Height after High Tibial Osteotomy of the Distal Tibial Tuberosity: A Retrospective Study of Age Stratification

Objective

To explore the effect of age stratification on patellar height after single-plane high tibial osteotomy of the distal tibial tuberosity (DTT-HTO).

Methods

A retrospective analysis was performed on 110 knee joints undergoing DTT-HTO. Patients were divided into three groups according to age: under 60 years old, 28 cases; 60 to 70 years old, 61 cases; and over 70 years old, 21 cases. All patients were followed up for no less than 12 months, and at each follow-up, short-leg radiographs and whole-leg radiographs were taken. The values of the Caton-Deschamps index (CDI) and Blackburne-Peel index (BPI) of single-short-leg radiographs and the femoral-tibial angle (FTA) and weight-bearing line ratio (WBLR) of whole-leg radiographs were measured before and at the last follow-up. The Lysholm score before and at the last follow-up and the visual analogue scale (VAS) score before and 3 days after surgery and at the last follow-up were calculated. The frequency of classification of the normal-height patella, patella alta, and patella baja before and after surgery was recorded.

Results

There were no significant differences in CDI and BPI preoperatively or postoperatively among the three groups (P > 0.05), and there were no statistically significant differences in FTA and WBLR. There were no significant differences in CDI, BPI, FTA, or WBLR between the three groups before and after the operation (P > 0.05). The Lysholm score increased from 48.84 ± 10.10 before surgery to 91.96 ± 3.082 after surgery (P < 0.05); the VAS score decreased from 8.23 ± 0.99 before surgery to 1.93 ± 0.953 at 3 days after surgery and 1.07 ± 0.53 at the last follow-up (P < 0.01). No significant difference was observed in the incidence of each patellar height classification between the three groups preoperatively and postoperatively.

Conclusion

Patellar height is not influenced by DTT-HTO. The age of patients is not a limiting factor for the selection of this surgical procedure. Without affecting the height of the patella, DTT-HTO can effectively reduce pain in the knee joint, restore the function of the knee joint, and delay the progression of patellar arthritis.

Magnetic resonance image diagnosis of femoral head necrosis based on ResNet18 network

PURPOSE

In order to enhance the practicability of the application of Magnetic Resonance Imaging (MRI) in the diagnosis of femoral head necrosis, combined with the convolutional neural network (CNN), we propose an automatic identification of femoral head necrosis model based on the ResNet18 network.

METHODS

In order to verify that MRI has a higher detection rate for early femoral head necrosis, we collected 360 cases of femoral MRI and the same number of femoral CT. Combining this method with ResNet18, AlexNet, and VGG16, compare the clinical staging and typical signs of femoral head necrosis with 8 diagnostic methods.

RESULTS

The total detection rate of MRI combined with ResNet18 is as high as 99.27%, which is much higher than the other three comparison methods. The sensitivity is 97%, the specificity is 98.99%, and the accuracy is 98.23%. The difference is statistically significant.

CONCLUSION

The automatic recognition femoral MRI model based on the ResNet18 network has a high detection rate for early femoral head necrosis, and can effectively detect bone marrow edema, line-like signs and other signs, providing a reliable reference for early treatment.

Modelling tri-cortical pedicle screw fixation in thoracic vertebrae under osteoporotic condition: A finite element analysis based on computed tomography

BACKGROUND AND OBJECTIVE

The technique of tri-cortical pedicle screw (TCPS) has been used to improve the anchoring strength in the sacral vertebrae. However, no studies have reported their application in the thoracic vertebrae. Our research is aimed to assess the stability and strength of the TCPS in thoracic vertebrae under osteoporotic condition by three dimensional (3D) finite element method on the basis of medical image reconstruction using computed tomography (CT), and verifying its effectiveness in clinical application.

MATERIALS AND METHODS

The 3D finite element models were constructed using Mimcs to transfer two dimensional CT images into 3D models by marching cubes algorithm of six-partition. Six physiological activities were simulated in 3D finite element models. Compared with the strength and stability of the uni-cortical pedicle screw (UCPS) and bi-cortical pedicle screw (BCPS), the effectiveness of TCPS was assessed. The stress distribution and maximum stress were measured to evaluate the strength. The maximum displacement and the range of motion were analysed to assessed the stability.

EXPERIMENTAL RESULTS

Four geometrically accurate and nonlinear T7-T9 finite element models were constructed successfully by 3D finite element method based on the CT images. Three kinds of internal fixation methods in the osteoporotic thoracic vertebral body can improved the maximum stress, decrease the maximum displacement and range of motion in six physiological activities. The range of motion and maximum displacement of TCPS decreased more significantly than that of UCPS and BCPS. The maximum von Mises stress of TCPS was minimum and UCPS was maximum under the condition of extension, right lateral bending, left rotation and right rotation.

CONCLUSIONS

Effectively, TCPS can provide better stability and strength than that of UCPS and BCPS techniques in the osteoporotic thoracic vertebrae. In practice, the technique of TCPS can be applied in the osteoporotic thoracic vertebral body to enhance the griping strength of the screws and reduce the risk of pedicle screw loosening. However, further cadaver experiments and more biomechanical analysis are necessary to confirmed our findings.

Deciphering the bacterial composition in the rhizosphere of Baphicacanthus cusia (NeeS) Bremek

Rhizobacteria is an important ingredient for growth and health of medicinal herbs, and synthesis of pharmacological effective substances from it. In this study, we investigated the community structure and composition of rhizobacteria in Baphicacanthus cusia (NeeS) Bremek via 16S rRNA amplicon sequencing. We obtained an average of 3,371 and 3,730 OTUs for bulk soil and rhizosphere soil samples respectively. Beta diversity analysis suggested that the bacterial community in the rhizosphere was distinctive from that in the bulk soil, which indicates that B.cusia can specifically recruit microbes from bulk soil and host in the rhizosphere. Burkholderia was significantly enriched in the rhizosphere. Burkholderia is a potentially beneficial bacteria that has been reported to play a major role in the synthesis of indigo, which was a major effective substances in B. cusia. In addition, we found that Bacilli were depleted in the rhizosphere, which are useful for biocontrol of soil-borne diseases, and this may explain the continuous cropping obstacles in B. cusia. Our results revealed the structure and composition of bacterial diversity in B. cusia rhizosphere, and provided clues for improving the medicinal value of B. cusia in the future.

Colonoscopy procedure simulation: virtual reality training based on a real time computational approach

BACKGROUND

Colonoscopy plays an important role in the clinical screening and management of colorectal cancer. The traditional 'see one, do one, teach one' training style for such invasive procedure is resource intensive and ineffective. Given that colonoscopy is difficult, and time-consuming to master, the use of virtual reality simulators to train gastroenterologists in colonoscopy operations offers a promising alternative.

METHODS

In this paper, a realistic and real-time interactive simulator for training colonoscopy procedure is presented, which can even include polypectomy simulation. Our approach models the colonoscopy as thick flexible elastic rods with different resolutions which are dynamically adaptive to the curvature of the colon. More material characteristics of this deformable material are integrated into our discrete model to realistically simulate the behavior of the colonoscope.

CONCLUSION

We present a simulator for training colonoscopy procedure. In addition, we propose a set of key aspects of our simulator that give fast, high fidelity feedback to trainees. We also conducted an initial validation of this colonoscopic simulator to determine its clinical utility and efficacy.