Brain Decoding Using fMRI Images for Multiple Subjects through Deep Learning.

Substantial information related to human cerebral conditions can be decoded through various noninvasive evaluating techniques like fMRI. Exploration of the neuronal activity of the human brain can divulge the thoughts of a person like what the subject is perceiving, thinking, or visualizing. Furthermore, deep learning techniques can be used to decode the multifaceted patterns of the brain in response to external stimuli. Existing techniques are capable of exploring and classifying the thoughts of the human subject acquired by the fMRI imaging data. fMRI images are the volumetric imaging scans which are highly dimensional as well as require a lot of time for training when fed as an input in the deep learning network. However, the hassle for more efficient learning of highly dimensional high-level features in less training time and accurate interpretation of the brain voxels with less misclassification error is needed. In this research, we propose an improved CNN technique where features will be functionally aligned. The optimal features will be selected after dimensionality reduction. The highly dimensional feature vector will be transformed into low dimensional space for dimensionality reduction through autoadjusted weights and combination of best activation functions. Furthermore, we solve the problem of increased training time by using Swish activation function, making it denser and increasing efficiency of the model in less training time. Finally, the experimental results are evaluated and compared with other classifiers which demonstrated the supremacy of the proposed model in terms of accuracy.

Artificial Intelligence Algorithm-Based Computerized Tomography Image Features Combined with Serum Tumor Markers for Diagnosis of Pancreatic Cancer.

The objective of this study was to analyze the value of artificial intelligence algorithm-based computerized tomography (CT) image combined with serum tumor markers for diagnoses of pancreatic cancer. In the study, 68 hospitalized patients with pancreatic cancer were selected as the experimental group, and 68 hospitalized patients with chronic pancreatitis were selected as the control group, all underwent CT imaging. An image segmentation algorithm on account of two-dimensional (2D)-three-dimensional (3D) convolution neural network (CNN) was proposed. It also introduced full convolutional network (FCN) and UNet network algorithm. The diagnostic performance of CT, serum carbohydrate antigen-50 (CA-50), serum carbohydrate antigen-199 (CA-199), serum carbohydrate antigen-242 (CA-242), combined detection of tumor markers, and CT-combined tumor marker testing (CT-STUM) for pancreatic cancer were compared and analyzed. The results showed that the average Dice coefficient of 2D-3D training was 84.27%, which was higher than that of 2D and 3D CNNs. During the test, the maximum and average Dice coefficient of the 2D-3D CNN algorithm was 90.75% and 84.32%, respectively, which were higher than the other two algorithms, and the differences were statistically significant (P < 0.05). The penetration ratio of pancreatic duct in the experimental group was lower than that in the control group, the rest were higher than that in the control group, and the differences were statistically significant (P < 0.05). CA-50, CA-199, and CA-242 in the experimental group were 141.72 U/mL, 1548.24 U/mL, and 83.65 U/mL, respectively, which were higher than those in the control group, and the differences were statistically significant (P < 0.05). The sensitivity, specificity, positive predictive value, and authenticity of combined detection of serum tumor markers were higher than those of CA-50, CA-199, and CA-242, and the differences were statistically significant (P < 0.05). The results showed that the proposed algorithm 2D-3D CNN had good stability and image segmentation performance. CT-STUM had high sensitivity and specificity in diagnoses of pancreatic cancer.

Judgement of the Clinical Value of Spiral CT Three-Dimensional Reconstruction in the Diagnosis of Lumbar Degenerative Osteoporosis.

With the aging of the population, there are more and more degenerative diseases of the lumbar spine that accompany osteoporosis. Lumbar degenerative osteoporosis has also become fragile and high in incidence, which has also attracted the attention of experts and scientists in related fields. Degeneration of the lumbar spine often causes pain in the waist and surrounding patients and even affects their life safety. The lesions such as the shoulders and lower back often show varying degrees of softening or induration in the fracture line or osteoporosis will directly produce adverse reactions to joint activities and then cause the development and deterioration of various complications. At present, spiral CT three-dimensional reconstruction technology has been widely used in the field of medical imaging and has played a very important role in the diagnosis and treatment of some diseases. Therefore, combined with three-dimensional reconstruction of spiral CT, this paper discusses its clinical value in the diagnosis of lumbar degenerative osteoporosis. In this experiment, in order to understand the image results after three-dimensional reconstruction, five groups of cases were selected for testing. The test items include the whole lesion site, vertebral imaging, soft tissue lesion site, and lumbar lesion site. In addition, in order to understand the clinical value of spiral CT three-dimensional reconstruction in the diagnosis of lumbar degenerative osteoporosis, this technique was compared and tested with other imaging methods. The selected imaging methods include X-ray, CT, and MRI. The test items include sensitivity, accuracy, positive predictive value, and negative predictive value. To explore the clinical value of spiral CT three-dimensional reconstruction in the diagnosis of lumbar degenerative osteoporosis, from the experimental results, the relevant image clarity and accuracy of the five groups of cases are high, the image quality after three-dimensional reconstruction is good, and the clarity and accuracy are high. In addition, the sensitivity and accuracy of spiral CT three-dimensional reconstruction are higher than those of other imaging methods. It has great clinical value in the diagnosis and treatment of lumbar degenerative osteoporosis.

Compound W-Net with Fully Accumulative Residual Connections for Liver Segmentation Using CT Images.

Computed tomography (CT) is a common modality for liver diagnosis, treatment, and follow-up process. Providing accurate liver segmentation using CT images is a crucial step towards those tasks. In this paper, we propose a stacked 2-U-Nets model with three different types of skip connections. The proposed connections work to recover the loss of high-level features on the convolutional path of the first U-Net due to the pooling and the loss of low-level features during the upsampling path of the first U-Net. The skip connections concatenate all the features that are generated at the same level from the previous paths to the inputs of the convolutional layers in both paths of the second U-Net in a densely connected manner. We implement two versions of the model with different number of filters at each level of each U-Net by maximising the Dice similarity between the predicted liver region and that of the ground truth. The proposed models were trained with 3Dircadb public dataset that were released for Sliver and 3D liver and tumour segmentation challenges during MICCAI 2007-2008 challenge. The experimental results show that the proposed model outperformed the original U-Net and 2-U-Nets variants, and is comparable to the state-of-the-art mU-Net, DC U-Net, and Cascaded UNET.

Research on Diagnosis Architecture of Cardiovascular Diseases Based on Multimedical Images.

OBJECTIVE: To study the effect of a multi-image source 3D modeling imaging examination system on the diagnosis of cardiovascular diseases in cardiac surgery. METHODS: The data of 680 confirmed patients and 1590 suspected patients in the cardiac surgery department of all hospitals of a large chain hospital management group were selected. All patients gave the examination results of multiple image sources and independent examination results of multiple image sources, respectively, their examination sensitivity, specificity, and reliability were compared, and the treatment efficiency and nursing satisfaction of the virtual reference group were deduced in MATLAB. Perform the bivariate t-test and comparative statistics in SPSS. RESULTS: The multi-image source 3D modeling examination system had higher examination sensitivity, specificity, and reliability and higher examination sensitivity in the early stage of the disease. It was deduced that the clinical efficiency and nursing satisfaction based on the examination results were significantly improved (t < 10.000, p < 0.01). CONCLUSION: The multi-image source 3D modeling imaging examination system is suitable for the diagnosis of cardiovascular diseases in cardiac surgery.

3D-Slicer Software-Assisted Neuroendoscopic Surgery in the Treatment of Hypertensive Cerebral Hemorrhage.

OBJECTIVE: To explore the 3D-slicer software-assisted endoscopic treatment for patients with hypertensive cerebral hemorrhage. METHODS: A total of 120 patients with hypertensive cerebral hemorrhage were selected and randomly divided into control group and 3D-slicer group with 60 cases each. Patients in the control group underwent traditional imaging positioning craniotomy, and patients in the 3D-slicer group underwent 3D-slicer followed by precision puncture treatment. In this paper, we evaluate the hematoma clearance rate, nerve function, ability of daily living, complication rate, and prognosis. RESULTS: The 3D-slicer group is better than the control group in various indicators. Compared with the control group, the 3D-slicer group has lower complications, slightly higher hematoma clearance rate, and better recovery of nerve function and daily living ability before and after surgery. The incidence of poor prognosis is low. CONCLUSION: The 3D-slicer software-assisted endoscopic treatment for patients with hypertensive intracerebral hemorrhage has a better hematoma clearance effect, which is beneficial to the patient's early recovery and reduces the damage to the brain nerve of the patient.

Application and Evaluation of a 64-Slice CT Three-Dimensional Fusion Technique in the Determination of the Effective Ablation Margin after Radiofrequency Ablation of Hepatocellular Carcinoma.

Due to the low accuracy of traditional three-dimensional fusion technology in radiofrequency ablation of hepatocellular carcinoma, this paper studies the advantages of three-dimensional CT fusion technology over traditional two-dimensional imaging technology in preoperative visualization and radiofrequency ablation path selection of hepatocellular carcinoma. To study the prognostic differences of hepatocellular carcinoma patients with different ablation margins (AM) in the three groups, so as to explore the best AM value, so as to minimize the liver injury caused by radiofrequency ablation. The selected patients underwent CT plain scan and three-phase enhancement at 1, 3, 6, and 12 months after operation and were rechecked every 6 months. For recurrent patients, CT was rechecked every three months. The images were obtained by GE 64-slice spiral CT. The thickness of the reconstruction layer is 1 mm, and the interval is 1 mm. The reconstructed image is imported into 3D fusion software. The three-dimensional images of tumor focus, hepatic artery, portal vein, and hepatic vein were reconstructed by two experienced doctors by superimposing the saved tumor images, merging the vascular images into the display, and measuring the ablation boundary (AM value). The results showed that the recurrence rate in group A was higher than that in group B (P = 0.041), and there was no significant difference between group B and group C (P = 1.000). Compared with traditional two-dimensional imaging, three-dimensional CT fusion technology can display the anatomical structure and three-dimensional spatial relationship of tumors and blood vessels and select the best radiofrequency ablation path, so as to achieve accurate radiofrequency ablation.

Three-Dimensional Skin CT Based on Intelligent Algorithm in the Analysis of Skin Lesion Sites Features in Children with Psoriasis.

This research was to explore the application value of three-dimensional computed tomography (CT) based on artificial intelligent algorithm in analyzing the characteristics of skin lesions in children with psoriasis. In this study, 15 children with psoriasis were selected as the observation group, and 15 children with other skin diseases were selected as the control group. The CT images were optimized, and the feature selection was carried out based on artificial intelligent algorithm. Firstly, the results were compared with the results of simple skin three-dimensional CT to determine the effectiveness. Then, the two groups of three-dimensional skin CT image features of skin psoriasis-like hyperplasia, Munro microabscess, dermal papillary vascular dilation, and squamous epithelium based on intelligent algorithms were compared. After comparison, the detection rate of psoriasis-like hyperplasia, Munro microabscess, dermal papillary vascular dilation, and squamous epithelium in the observation group was higher than that in the control group, with significant difference and statistical significance (P < 0.05). In addition, the sensitivity of psoriasis-like hyperplasia, Munro microabscess, dermal papilla vascular dilatation, and squamous epithelium in children with psoriasis was 80.0%, 86.7%, 80.0%, and 93.3%, respectively. The specificity of psoriasis-like hyperplasia, Munro microabscess, dermal papilla vascular dilatation, and squamous epithelium in children with psoriasis was 86.7%, 93.3%, 60.0%, and 73.3%, respectively. The results showed that Munro microabscess and psoriasis-like hyperplasia had high sensitivity and specificity in all diagnostic items, which could be used as important features of skin lesion sites in the diagnosis of psoriasis in children. The research provides a basis for the clinical diagnosis of psoriasis in children, which is worthy of clinical promotion.

Intelligent Algorithm-Based Coronary Angiography Characteristics of Acute Non-ST-Segment Elevation Myocardial Infarction Patients with Different Genders.

OBJECTIVE: This study was aimed at comparing the characteristics of coronary angiography based on intelligent algorithm in patients with acute non-ST-segment elevation myocardial infarction (NSTEMI) of different genders. METHODS: Eighty patients were selected to segment the coronary angiogram using the convolutional neural network (CNN) algorithm, the input layer of the CNN was used to receive the image dataset, and three-dimensional data were input during semantic segmentation to achieve automatic segmentation of the target features. Segmentation results were quantitatively assessed by accuracy (Acc), sensitivity (Se), specificity (Sp), and Dice coefficient (Dice). The characteristics of coronary angiography were compared between the two groups. RESULTS: The CNN algorithm had good segmentation effect, complete vessel extraction, and little noise, and Acc, Se, Sp, and Dice were 90.32%, 93.39%, 91.25%, and 89.75%, respectively. The proportion of diabetes mellitus was higher in female patients with NSTEMI (68.8%) than that in male patients (46.3%); the proportion of the left main coronary artery (LM) and left anterior descending artery (LAD) was lower in the female group (7.5%, 41.3%) than that in the male group (13.8%, 81.3%), and the difference between the two groups was statistically significant (P < 0.05). CONCLUSION: The CNN algorithm achieves accurate extraction of vessels from coronary angiographic images, and women with diabetes and hyperlipidemia are more likely to have NSTEMI than men, especially the elderly.

Design Computer-Aided Diagnosis System Based on Chest CT Evaluation of Pulmonary Nodules.

At present, the diagnosis and treatment of lung cancer have always been one of the research hotspots in the medical field. Early diagnosis and treatment of this disease are necessary means to improve the survival rate of lung cancer patients and reduce their mortality. The introduction of computer-aided diagnosis technology can easily, quickly, and accurately identify the lung nodule area as an imaging feature of early lung cancer for the clinical diagnosis of lung cancer and is helpful for the quantitative analysis of the characteristics of lung nodules and is useful for distinguishing benign and malignant lung nodules. Growth provides an objective diagnostic reference standard. This paper studies ITK and VTK toolkits and builds a system platform with MFC. By studying the process of doctors diagnosing lung nodules, the whole system is divided into seven modules: suspected lung shadow detection, image display and image annotation, and interaction. The system passes through the entire lung nodule auxiliary diagnosis process and obtains the number of nodules, the number of malignant nodules, and the number of false positives in each set of lung CT images to analyze the performance of the auxiliary diagnosis system. In this paper, a lung region segmentation method is proposed, which makes use of the obvious differences between the lung parenchyma and other human tissues connected with it, as well as the position relationship and shape characteristics of each human tissue in the image. Experiments are carried out to solve the problems of lung boundary, inaccurate segmentation of lung wall, and depression caused by noise and pleural nodule adhesion. Experiments show that there are 2316 CT images in 8 sets of images of different patients, and the number of nodules is 56. A total of 49 nodules were detected by the system, 7 were missed, and the detection rate was 87.5%. A total of 64 false-positive nodules were detected, with an average of 8 per set of images. This shows that the system is effective for CT images of different devices, pixel pitch, and slice pitch and has high sensitivity, which can provide doctors with good advice.

The Value of CT Angiography Based on Intelligent Segmentation Algorithm for Survival of Hemodialysis Patients.

This study was to explore the application value for central venous stenosis and occlusion in hemodialysis patients under the CT angiography based on intelligent segmentation algorithm, so that patients can survive better. Spiral CT was used to examine upper limb swelling in 62 uremic hemodialysis patients at a speed of 3.8 mL/s. Nonionic iodine contrast agent was injected around the contralateral limb. The total dosage of 90-102 mL, it was scanned by intelligent trigger technology. The trigger scanning threshold was set. The monitoring point was located in the superior vena cava. CT with convolutional neural network intelligent segmentation algorithm was used to process image data. Finally, the quality of life and related biochemical levels of patients before and after hemodialysis were detected. Under the CT angiography of intelligent segmentation algorithm, 77 stenoses were found in 62 uremic patients, including 48 stenoses of the brachial vein and 17 stenoses of the superior vena cava. The correlation coefficient between CT angiography and digital subtraction angiography (DSA) imaging results of intelligent segmentation algorithm was 0.411. Segmentation effect of the algorithm in this study: automatic segmentation accuracy was greater than 79%. After hemodialysis treatment, the scores of physical fitness, pain, social function, and energy status of patients were significantly increased compared with those before treatment, and the levels of albumin, serum phosphorus, and parathyroid hormone were significantly decreased (P < 0.05). In summary, CT angiography with intelligent segmentation algorithm can obtain clear, intuitive, and complete vascular walking images, and better display subclavian vein, brachiocephalic vein, and superior vena cava. It can provide more valuable support for surgical intervention and has certain application value for better survival of hemodialysis patients.

Hand Gesture of Recognition Pattern Analysis by Image Treatment Techniques.

The goal of this project is to write a program in the C++ language that can recognize motions made by a subject in front of a camera. To do this, in the first place, a sequence of distance images has been obtained using a depth camera. Later, these images are processed through a series of blocks into which the program has been divided; each of them will yield a numerical or logical result, which will be used later by the following blocks. The blocks into which the program has been divided are three; the first detects the subject's hands, the second detects if there has been movement (and therefore a gesture has been made), and the last detects the type of gesture that has been made accomplished. On the other hand, it intends to present to the reader three unique techniques for acquiring 3D images: stereovision, structured light, and flight time, in addition to exposing some of the most used techniques in image processing, such as morphology and segmentation.

X-ray microscopy enables multiscale high-resolution 3D imaging of plant cells, tissues, and organs.

Capturing complete internal anatomies of plant organs and tissues within their relevant morphological context remains a key challenge in plant science. While plant growth and development are inherently multiscale, conventional light, fluorescence, and electron microscopy platforms are typically limited to imaging of plant microstructure from small flat samples that lack a direct spatial context to, and represent only a small portion of, the relevant plant macrostructures. We demonstrate technical advances with a lab-based X-ray microscope (XRM) that bridge the imaging gap by providing multiscale high-resolution three-dimensional (3D) volumes of intact plant samples from the cell to the whole plant level. Serial imaging of a single sample is shown to provide sub-micron 3D volumes co-registered with lower magnification scans for explicit contextual reference. High-quality 3D volume data from our enhanced methods facilitate sophisticated and effective computational segmentation. Advances in sample preparation make multimodal correlative imaging workflows possible, where a single resin-embedded plant sample is scanned via XRM to generate a 3D cell-level map, and then used to identify and zoom in on sub-cellular regions of interest for high-resolution scanning electron microscopy. In total, we present the methodologies for use of XRM in the multiscale and multimodal analysis of 3D plant features using numerous economically and scientifically important plant systems.

The accuracy of three-dimensional ultrasonography in the diagnosis of Müllerian duct anomalies and its concordance with magnetic resonance imaging.

This retrospective study was performed to comparatively evaluate the diagnostic accuracies of three-dimensional ultrasonography (3D-US) and magnetic resonance imaging (MRI) for identification of Müllerian duct anomalies (MDAs). A total of 27 women with suspected MDAs underwent gynaecological examination, 2D-US, 3D-US and MRI, respectively. The MDAs were classified with respect to the European Society of Human Reproduction and Embryology-European Society for Gynaecological Endoscopy (ESHRE/ESGE) and American Society of Reproductive Medicine (ASRM) systems. Based on the ESHRE/ESGE classification, there was a discrepancy for only one patient between US and MRI. Thus, the concordance between US and MRI was 26/27 (96.3%). With respect to ASRM classification, there was a disagreement between MRI and 3D-US in three patients, thus the concordance between MRI and 3D-US was 24/27 (88.9%). To conclude, the 3D-US has a good level of agreement with MRI for recognition of MDAs.Impact StatementWhat is already known on this subject? Müllerian duct anomalies (MDAs) are relatively common malformations of the female genital tract and they may adversely affect the reproductive potential. The establishment of accurate and timely diagnosis of these malformations is critical to overcome clinical consequences of MDAs.What the results of this study add? The concordance between US and MRI for diagnosis of MDAs based on ESHRE-ESGE classification and ASRM were 96.3% and 88.9%, respectively. These results indicate that 3D US has a satisfactory level of diagnostic accuracy for MDAs and it can be used in conjunction with MRI. Minimisation of diagnostic errors is important to improve reproductive outcome and to avoid unnecessary surgical interventions.What the implications are of these findings for clinical practice and/or further research? Efforts must be spent to eliminate the discrepancies between the clinical and radiological diagnosis of MDAs. Further trials should be implemented for establishment and standardisation of radiological images for identification and classification of MDAs.

Multislice Spiral Computed Tomography Postprocessing Technology in the Imaging Diagnosis of Extremities and Joints.

OBJECTIVE: To improve the clinical detection rate of bone and joint fractures of the extremities and to explore the value and significance of the application of multislice spiral computed tomography (MSCT) postprocessing technology in diagnosis. METHODS: 80 patients with bone and joint fractures of the extremities admitted to the hospital were selected as the research objects. The patients received X-ray digital radiography (DR) plain film examination and then MSCT examination. At the same time, multiplane reconstruction (MPR) and surface shadow display (SSD) and volume rendering three-dimensional imaging (VRT) technology and other postprocessing technologies compare the differences in the detection rate of limbs and joint fractures between the two inspection methods. RESULTS: A total of 100 fractures were found in 80 patients. The detection rate of X-ray DR was 69%. After MSCT postprocessing technology, the detection rates of MPR, SSD, and VRT were 96%, 98%, and 99%, respectively. The accuracy of MSCT postprocessing technology in diagnosing extremity bone and joint fractures was significantly higher than that of DR, and the difference between groups was statistically significant. CONCLUSION: MSCT postprocessing technology for patients with extremity bone and joint fractures has a good effect. It is not only noninvasive but also has a high detection rate. It can significantly reduce the missed and misdiagnosed rate and provide detailed imaging data for the formulation of clinical treatment plans.

Clinical Research of Orthopedic Trauma Based on Computer 3D Image Analysis.

In order to improve the clinical research effect of orthopedic trauma, this paper applies computer 3D image analysis technology to the clinical research of orthopedic trauma and proposes the BOS technology based on FFT phase extraction. The background image in this technique is a "cosine blob" background image. Moreover, this technology uses the FFT phase extraction method to process this background image to extract the image point displacement. The BOS technology based on FFT phase extraction does not need to select a diagnostic window. Finally, this paper combines computer 3D image analysis technology to build an intelligent system. According to the experimental research results, the clinical analysis system of orthopedic trauma based on computer 3D image analysis proposed in this paper can play an important role in the clinical diagnosis and treatment of orthopedic trauma and improve the diagnosis and treatment effect of orthopedic trauma.

Segmentation and Automatic Identification of Vasculature in Coronary Angiograms.

Coronary angiography is the "gold standard" for the diagnosis of coronary heart disease, of which vessel segmentation and identification technologies are paid much attention to. However, because of the characteristics of coronary angiograms, such as the complex and variable morphology of coronary artery structure and the noise caused by various factors, there are many difficulties in these studies. To conquer these problems, we design a preprocessing scheme including block-matching and 3D filtering, unsharp masking, contrast-limited adaptive histogram equalization, and multiscale image enhancement to improve the quality of the image and enhance the vascular structure. To achieve vessel segmentation, we use the C-V model to extract the vascular contour. Finally, we propose an improved adaptive tracking algorithm to realize automatic identification of the vascular skeleton. According to our experiments, the vascular structures can be successfully highlighted and the background is restrained by the preprocessing scheme, the continuous contour of the vessel is extracted accurately by the C-V model, and it is verified that the proposed tracking method has higher accuracy and stronger robustness compared with the existing adaptive tracking method.

A Liver Segmentation Method Based on the Fusion of VNet and WGAN.

Accurate segmentation of liver images is an essential step in liver disease diagnosis, treatment planning, and prognosis. In recent years, although liver segmentation methods based on 2D convolutional neural networks have achieved good results, there is still a lack of interlayer information that causes severe loss of segmentation accuracy to a certain extent. Meanwhile, making the best of high-level and low-level features more effectively in a 2D segmentation network is a challenging problem. Therefore, we designed and implemented a 2.5-dimensional convolutional neural network, VNet_WGAN, to improve the accuracy of liver segmentation. First, we chose three adjacent layers of a liver model as the input of our network and adopted two convolution kernels in series connection, which can integrate cross-sectional spatial information and interlayer information of liver models. Second, a chain residual pooling module is added to fuse multilevel feature information to optimize the skip connection. Finally, the boundary loss function in the generator is employed to compensate for the lack of marginal pixel accuracy in the Dice loss function. The effectiveness of the proposed method is verified on two datasets, LiTS and CHAOS. The Dice coefficients are 92% and 90%, respectively, which are better than those of the compared segmentation networks. In addition, the experimental results also show that the proposed method can reduce computational consumption while retaining higher segmentation accuracy, which is significant for liver segmentation in practice and provides a favorable reference for clinicians in liver segmentation.

Segmentation of Prefrontal Lobe Based on Improved Clustering Algorithm in Patients with Diabetes.

Diabetics are prone to postoperative cognitive dysfunction (POCD). The occurrence may be related to the damage of the prefrontal lobe. In this study, the prefrontal lobe was segmented based on an improved clustering algorithm in patients with diabetes, in order to evaluate the relationship between prefrontal lobe volume and COPD. In this study, a total of 48 diabetics who underwent selective noncardiac surgery were selected. Preoperative magnetic resonance imaging (MRI) images of the patients were segmented based on the improved clustering algorithm, and their prefrontal volume was measured. The correlation between the volume of the prefrontal lobe and Z-score or blood glucose was analyzed. Qualitative analysis shows that the gray matter, white matter, and cerebrospinal fluid based on the improved clustering algorithm were easy to distinguish. Quantitative evaluation results show that the proposed segmentation algorithm can obtain the optimal Jaccard coefficient and the least average segmentation time. There was a negative correlation between the volume of the prefrontal lobe and the Z-score. The cut-off value of prefrontal lobe volume for predicting POCD was <179.8, with the high specificity. There was a negative correlation between blood glucose and volume of the prefrontal lobe. From the results, we concluded that the segmentation of the prefrontal lobe based on an improved clustering algorithm before operation may predict the occurrence of POCD in diabetics.

Classification of Alzheimer's Disease Using Gaussian-Based Bayesian Parameter Optimization for Deep Convolutional LSTM Network.

Alzheimer's disease (AD) is one of the most important causes of mortality in elderly people, and it is often challenging to use traditional manual procedures when diagnosing a disease in the early stages. The successful implementation of machine learning (ML) techniques has also shown their effectiveness and its reliability as one of the better options for an early diagnosis of AD. But the heterogeneous dimensions and composition of the disease data have undoubtedly made diagnostics more difficult, needing a sufficient model choice to overcome the difficulty. Therefore, in this paper, four different 2D and 3D convolutional neural network (CNN) frameworks based on Bayesian search optimization are proposed to develop an optimized deep learning model to predict the early onset of AD binary and ternary classification on magnetic resonance imaging (MRI) scans. Moreover, certain hyperparameters such as learning rate, optimizers, and hidden units are to be set and adjusted for the performance boosting of the deep learning model. Bayesian optimization enables to leverage advantage throughout the experiments: A persistent hyperparameter space testing provides not only the output but also about the nearest conclusions. In this way, the series of experiments needed to explore space can be substantially reduced. Finally, alongside the use of Bayesian approaches, long short-term memory (LSTM) through the process of augmentation has resulted in finding the better settings of the model that too in less iterations with an relative improvement (RI) of 7.03%, 12.19%, 10.80%, and 11.99% over the four systems optimized with manual hyperparameters tuning such that hyperparameters that look more appealing from past data as well as the conventional techniques of manual selection.