Enhanced Tunicate Swarm Optimization with Transfer Learning Enabled Medical Image Analysis System

Medical image analysis is an active research topic,with thousands of studies published in the past few years.Transfer learning(TL)including convolutional neural networks(CNNs)focused to enhance efficiency on an innovative task using the knowledge of the same tasks learnt in advance.It has played a major role in medical image analysis since it solves the data scarcity issue along with that it saves hardware resources and time.This study develops an EnhancedTunicate SwarmOptimization withTransfer Learning EnabledMedical Image Analysis System(ETSOTL-MIAS).The goal of the ETSOTL-MIAS technique lies in the identification and classification of diseases through medical imaging.The ETSOTL-MIAS technique involves the Chan Vese segmentation technique to identify the affected regions in the medical image.For feature extraction purposes,the ETSOTL-MIAS technique designs a modified DarkNet-53 model.To avoid the manual hyperparameter adjustment process,the ETSOTLMIAS technique exploits the ETSO algorithm,showing the novelty of the work.Finally,the classification of medical images takes place by random forest(RF)classifier.The performance validation of the ETSOTL-MIAS technique is tested on a benchmark medical image database.The extensive experimental analysis showed the promising performance of the ETSOTL-MIAS technique under different measures.

Analysis on Nutritional Risk Screening and Influencing Factors of Hospitalized Patients in Central Urban Area

Rational nutritional support shall be based on nutritional screening and nutritional assessment. This study is aimed to explore nutritional risk screening and its influencing factors of hospitalized patients in central urban area. It is helpful for the early detection of problems in nutritional supports, nutrition management and the implementation of intervention measures, which will contribute a lot to improving the patient＇s poor clinical outcome. A total of three tertiary medical institutions were enrolled in this study. From October 2015 to June 2016, 1202 hospitalized patients aged ≥18 years were enrolled in Nutrition Risk Screening 2002（NRS2002） for nutritional risk screening, including 8 cases who refused to participate, 5 cases of same-day surgery and 5 cases of coma. A single-factor chi-square test was performed on 312 patients with nutritional risk and 872 hospitalized patients without nutritional risk. Logistic regression analysis was performed with univariate analysis（P〈0.05）, to investigate the incidence of nutritional risk and influencing factors. The incidence of nutritional risk was 26.35% in the inpatients, 25.90% in male and 26.84% in female, respectively. The single-factor analysis showed that the age ≥60, sleeping disorder, fasting, intraoperative bleeding, the surgery in recent month, digestive diseases, metabolic diseases and endocrine system diseases had significant effects on nutritional risk（P〈0.05）. Having considered the above-mentioned factors as independent variables and nutritional risk（Y=1, N=0） as dependent variable, logistic regression analysis revealed that the age ≥60, fasting, sleeping disorders, the surgery in recent month and digestive diseases are hazardous factors for nutritional risk. Nutritional risk exists in hospitalized patients in central urban areas. Nutritional risk screening should be conducted for inpatients. Nutritional intervention programs should be formulated in consideration of those influencing factors, which enable to reduce the nutritional risk and to promote the rehabilitation of inpatients.

Unified Analysis Specific to the Medical Field in the Interpretation of Medical Images through the Use of Deep Learning

Deep learning (DL) has seen an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image. The purpose of the work converges in determining the importance of each component, describing the specificity and correlations of these elements involved in achieving the precision of interpretation of medical images using DL. The major contribution of this work is primarily to the updated characterisation of the characteristics of the constituent elements of the deep learning process, scientific data, methods of knowledge incorporation, DL models according to the objectives for which they were designed and the presentation of medical applications in accordance with these tasks. Secondly, it describes the specific correlations between the quality, type and volume of data, the deep learning patterns used in the interpretation of diagnostic medical images and their applications in medicine. Finally presents problems and directions of future research. Data quality and volume, annotations and labels, identification and automatic extraction of specific medical terms can help deep learning models perform image analysis tasks. Moreover, the development of models capable of extracting unattended features and easily incorporated into the architecture of DL networks and the development of techniques to search for a certain network architecture according to the objectives set lead to performance in the interpretation of medical images.

Intelligent Electrocardiogram Analysis in Medicine:Data,Methods,and Applications

Electrocardiogram(ECG)is a low-cost,simple,fast,and non-invasive test.It can reflect the heart’s electrical activity and provide valuable diagnostic clues about the health of the entire body.Therefore,ECG has been widely used in various biomedical applications such as arrhythmia detection,disease-specific detection,mortality prediction,and biometric recognition.In recent years,ECG-related studies have been carried out using a variety of publicly available datasets,with many differences in the datasets used,data preprocessing methods,targeted challenges,and modeling and analysis techniques.Here we systematically summarize and analyze the ECGbased automatic analysis methods and applications.Specifically,we first reviewed 22 commonly used ECG public datasets and provided an overview of data preprocessing processes.Then we described some of the most widely used applications of ECG signals and analyzed the advanced methods involved in these applications.Finally,we elucidated some of the challenges in ECG analysis and provided suggestions for further research.

Study of Professor Han Fei’s medication rules in treating infantile epilepsy

Objective:By data mining,to analyze the characteristics of Professor Han Fei’s medication in the treatment of children with epilepsy,to explore the rules of medication,in order to provide reference for clinical treatment of children with epilepsy by Chinese medicine.Methods:From January 2008 to March 2021,we collected the diagnosis and treatment data of the children with epilepsy who were treated by Professor Han Fei in the outpatient department of Guang’Anmen Hospital of Chinese Academy of Medical Sciences.Using the software of IBM SPSS Statistics 24.0 and IBM SPSS Modeler 18.0,the characteristics and rules of Professor Hanfei’s Chinese materia medica used were summarized through the descriptive analysis,correlation analysis and cluster analysis of drug cumulative frequency,drug flavor,drug channel tropism and efficacy.Results:A total of 224 cases were included in this study,excluding 1 case with other neurological disorders.Finally,223 prescriptions were included,involving 176 kinds of Chinese materia medica and the total medication frequency was 4712.The first 10 highfrequency Chinese materia medica were Chaihu(95.52%),Bombyx batryticatus(94.17%),keels(83.41%),oysters(72.65%),earthworm(72.20%),fructus aurantii(66.37%),Scorpion(64.57%),Gastrodia elata(60.99%),Acorus gramineus(59.19%)and Dannan Xing(58.30%).The main Chinese materia medica used were mainly for suppressing hyperactive liver for calming endogenous wind,relieving exterior syndromes and tranquillizing mind.The medicine properties were mainly to be flat,slight cold,pungent,bitter and willing,and they were mainly for liver,lung and heart meridian tropism.Correlation Analysis:Bupleurum chinense,Bombyx batryticatus,Dragon Bone,oyster as its core medicine group,Semen Ziziphi spinosae and semen platycladi are effective strong correlation medicine pair.Three medicine combinations were obtained by cluster analysis.Conclusion:Hanshi has the characteristics of“calming liver,tranquilizing mind,calming endogenous wind,removing the phlegm and extravasated blood”in treating epilepsy.

DeepSVDNet:A Deep Learning-Based Approach for Detecting and Classifying Vision-Threatening Diabetic Retinopathy in Retinal Fundus Images

Artificial Intelligence(AI)is being increasingly used for diagnosing Vision-Threatening Diabetic Retinopathy(VTDR),which is a leading cause of visual impairment and blindness worldwide.However,previous automated VTDR detection methods have mainly relied on manual feature extraction and classification,leading to errors.This paper proposes a novel VTDR detection and classification model that combines different models through majority voting.Our proposed methodology involves preprocessing,data augmentation,feature extraction,and classification stages.We use a hybrid convolutional neural network-singular value decomposition(CNN-SVD)model for feature extraction and selection and an improved SVM-RBF with a Decision Tree(DT)and K-Nearest Neighbor(KNN)for classification.We tested our model on the IDRiD dataset and achieved an accuracy of 98.06%,a sensitivity of 83.67%,and a specificity of 100%for DR detection and evaluation tests,respectively.Our proposed approach outperforms baseline techniques and provides a more robust and accurate method for VTDR detection.

ThyroidNet:A Deep Learning Network for Localization and Classification of Thyroid Nodules

Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques accurately.Methods:A novel method,ThyroidNet,is introduced and evaluated based on deep learning for the localization and classification of thyroid nodules.First,we propose the multitask TransUnet,which combines the TransUnet encoder and decoder with multitask learning.Second,we propose the DualLoss function,tailored to the thyroid nodule localization and classification tasks.It balances the learning of the localization and classification tasks to help improve the model’s generalization ability.Third,we introduce strategies for augmenting the data.Finally,we submit a novel deep learning model,ThyroidNet,to accurately detect thyroid nodules.Results:ThyroidNet was evaluated on private datasets and was comparable to other existing methods,including U-Net and TransUnet.Experimental results show that ThyroidNet outperformed these methods in localizing and classifying thyroid nodules.It achieved improved accuracy of 3.9%and 1.5%,respectively.Conclusion:ThyroidNet significantly improves the clinical diagnosis of thyroid nodules and supports medical image analysis tasks.Future research directions include optimization of the model structure,expansion of the dataset size,reduction of computational complexity and memory requirements,and exploration of additional applications of ThyroidNet in medical image analysis.

Enhancing Pneumonia Detection in Pediatric Chest X-Rays Using CGAN-Augmented Datasets and Lightweight Deep Transfer Learning Models

Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.

Medication patterns of ancient Chinese medicinal prescriptions fordiabetic retinopathy

Objective:To mine the medication patterns of ancient prescriptions for diabetic retinopathy(DR)from databases of traditional Chinese medicine(TCM)ancient books,and provide evidence for clinical practice and scientific research of TCM treatment for DR.Methods:The traditional library retrieval and modern data retrieval technology were combined to collect the ancient prescriptions in these databases,including the library ofHunan University ofChinese Medicine,Chinese Medical Dictionary,Duxiu,and Chaoxing Digital Library.And the TCM inheritance auxiliary platform(V3.0)was used for data mining,mainly including drug frequency analysis,medicinal property and meridian tropism analysis,efficacy analysis,correlation analysis,complex network analysis,and cluster analysis.Results:A total of 271 ancient prescriptions for the treatment of DR were collected,involving 296 drugs.The total medication frequency was 2,727.Most of them were cold and sweet drugs.The meridians primarily targeted were the liver,kidney,and spleen.The main effects of drugs were supplementing deficiency,clearing heat,releasing the exterior,inducing urination to drain dampness,pacifying liver and extinguishing wind,and circulating blood and transforming stasis.Saposhnikovia divaricata was the most frequently Chinese herbal medicine for DR in TCM ancient books.Saposhnikovia divaricata and ligusticum wallichi,saposhnikovia divaricata and notopterygium root,angelica sinensis and ligusticum wallichii were common herbal pairs.Saposhnikovia divaricata,ginseng,plantain seed,angelica sinensis,prepared rehmannia root and cassia seed constituted the core formula with the highest frequency.Conclusion:The core prescriptions for treating DR are mainly crafted from Dihuang pill,Ruiren powder,Siwu decoction,and Zhujing pill.Saposhnikovia divaricata is an important meridian-guiding medicine to open Xuanfu for DR.In clinical practice,the prescriptions should be modified according to the evolution of pathogenesis.

Convolutional neural networks for the diagnosis and prognosis of the coronavirus disease pandemic

A neural network is one of the current trends in deep learning,which is increasingly gaining attention owing to its contribution in transforming the different facets of human life.It also paves a way to approach the current crisis caused by the coronavirus disease(COVID-19)from all scientific directions.Convolutional neural network(CNN),a type of neural network,is extensively applied in the medical field,and is particularly useful in the current COVID-19 pandemic.In this article,we present the application of CNNs for the diagnosis and prognosis of COVID-19 using X-ray and computed tomography(CT)images of COVID-19 patients.The CNN models discussed in this review were mainly developed for the detection,classification,and segmentation of COVID-19 images.The base models used for detection and classification were AlexNet,Visual Geometry Group Network with 16 layers,residual network,DensNet,GoogLeNet,MobileNet,Inception,and extreme Inception.U-Net and voxel-based broad learning network were used for segmentation.Even with limited datasets,these methods proved to be beneficial for efficiently identifying the occurrence of COVID-19.To further validate these observations,we conducted an experimental study using a simple CNN framework for the binary classification of COVID-19 CT images.We achieved an accuracy of 93%with an F1-score of 0.93.Thus,with the availability of improved medical image datasets,it is evident that CNNs are very useful for the efficient diagnosis and prognosis of COVID-19.

Screening of COVID-19 Patients Using Deep Learning and IoT Framework

In March 2020,the World Health Organization declared the coronavirus disease(COVID-19)outbreak as a pandemic due to its uncontrolled global spread.Reverse transcription polymerase chain reaction is a laboratory test that is widely used for the diagnosis of this deadly disease.However,the limited availability of testing kits and qualified staff and the drastically increasing number of cases have hampered massive testing.To handle COVID19 testing problems,we apply the Internet of Things and artificial intelligence to achieve self-adaptive,secure,and fast resource allocation,real-time tracking,remote screening,and patient monitoring.In addition,we implement a cloud platform for efficient spectrum utilization.Thus,we propose a cloudbased intelligent system for remote COVID-19 screening using cognitiveradio-based Internet of Things and deep learning.Specifically,a deep learning technique recognizes radiographic patterns in chest computed tomography(CT)scans.To this end,contrast-limited adaptive histogram equalization is applied to an input CT scan followed by bilateral filtering to enhance the spatial quality.The image quality assessment of the CT scan is performed using the blind/referenceless image spatial quality evaluator.Then,a deep transfer learning model,VGG-16,is trained to diagnose a suspected CT scan as either COVID-19 positive or negative.Experimental results demonstrate that the proposed VGG-16 model outperforms existing COVID-19 screening models regarding accuracy,sensitivity,and specificity.The results obtained from the proposed system can be verified by doctors and sent to remote places through the Internet.

Pseudo Zernike Moment and Deep Stacked Sparse Autoencoder for COVID-19 Diagnosis

(Aim)COVID-19 is an ongoing infectious disease.It has caused more than 107.45 m confirmed cases and 2.35 m deaths till 11/Feb/2021.Traditional computer vision methods have achieved promising results on the automatic smart diagnosis.(Method)This study aims to propose a novel deep learning method that can obtain better performance.We use the pseudo-Zernike moment(PZM),derived from Zernike moment,as the extracted features.Two settings are introducing:(i)image plane over unit circle;and(ii)image plane inside the unit circle.Afterward,we use a deep-stacked sparse autoencoder(DSSAE)as the classifier.Besides,multiple-way data augmentation is chosen to overcome overfitting.The multiple-way data augmentation is based on Gaussian noise,salt-and-pepper noise,speckle noise,horizontal and vertical shear,rotation,Gamma correction,random translation and scaling.(Results)10 runs of 10-fold cross validation shows that our PZM-DSSAE method achieves a sensitivity of 92.06%±1.54%,a specificity of 92.56%±1.06%,a precision of 92.53%±1.03%,and an accuracy of 92.31%±1.08%.Its F1 score,MCC,and FMI arrive at 92.29%±1.10%,84.64%±2.15%,and 92.29%±1.10%,respectively.The AUC of our model is 0.9576.(Conclusion)We demonstrate“image plane over unit circle”can get better results than“image plane inside a unit circle.”Besides,this proposed PZM-DSSAE model is better than eight state-of-the-art approaches.

Rules and Characteristics of TCM Treatment Prescriptions for Patients with Decreased Ovarian Reserve

[Objectives]To analyze the characteristics and rules of traditional Chinese medicine(TCM)in the treatment of decreased ovarian reserve(DOR)in Suzhou TCM Hospital Affiliated to Nanjing University of Chinese Medicine.[Methods]A total of 107 patients with DOR in Suzhou TCM Hospital Affiliated to Nanjing University of Chinese Medicine were selected for sorting,and the usage,classification,nature,taste and meridian homing of the used drugs were statistically analyzed.[Results]A total of 107 patients were included in this stud and a total of 189 flavors of TCM are used.The total frequency of drugs was 4345 times,and a total of 535 prescriptions were issued.The top five frequency of drug use were 2261 times(50.04%)of Paeoniae Radix Alba(Cynanchum otophyllum Schneid.),2037 times(46.88%)of Corni Fructus(Cornus officinalis Sieb.et Zucc.),1818 times(41.84%)of Rehmanniae Radix Praeparata[Rehmannia glutinosa(Gaertn.)Libosch EX Fisch.et Mey.],1610 times(37.05%)of Guiban[Chinemys reevesii(Gray)],and 1303 times(29.99%)of Uncariae Ramulus Cum Uncis(Uncariar hynchophylla Miq.ex Havil.).Kidney deficiency syndrome accounted for the largest proportion at 51.40%,and the use frequency of tonic drugs accounted for the highest at 50.64%;heat-clearing drugs and qi and blood-boosting drugs separately accounted for 19.24%and 17.39%;the top 3 medicinal tastes are sweet(52.02%),pungent(20.71%)and bitter(20.32%);medicinal properties are ranked as warm(60.54%),cold(24.16%),hot(8.72%)and cool(6.49%);the main meridians are spleen,lung,liver,stomach and kidney.[Conclusions]The basic pathogenesis of DOR is deficiency of qi and blood,mainly due to dysfunction of the spleen,lung,liver,liver,stomach and other organs,and kidney deficiency and spleen deficiency are more common.

A Post-Processing Algorithm for Boosting Contrast of MRI Images

Low contrast of Magnetic Resonance(MR)images limits the visibility of subtle structures and adversely affects the outcome of both subjective and automated diagnosis.State-of-the-art contrast boosting techniques intolerably alter inherent features of MR images.Drastic changes in brightness features,induced by post-processing are not appreciated in medical imaging as the grey level values have certain diagnostic meanings.To overcome these issues this paper proposes an algorithm that enhance the contrast of MR images while preserving the underlying features as well.This method termed as Power-law and Logarithmic Modification-based Histogram Equalization(PLMHE)partitions the histogram of the image into two sub histograms after a power-law transformation and a log compression.After a modification intended for improving the dispersion of the sub-histograms and subsequent normalization,cumulative histograms are computed.Enhanced grey level values are computed from the resultant cumulative histograms.The performance of the PLMHE algorithm is comparedwith traditional histogram equalization based algorithms and it has been observed from the results that PLMHE can boost the image contrast without causing dynamic range compression,a significant change in mean brightness,and contrast-overshoot.

Information engineering at Oxford

Information engineering mainly focus on application,uncertainty and information for its utility.This lecture discussed several aspects of information engineering research in Oxford,included the areas of mobile robotics,signal processing,real-time computer vision for object tracking,3D reconstruction of space,medical image analysis and artificial intelligence.Then what information engineering really means was discussed and the possibilities for the future of this field was prospected finally.

Image Color Rendering Based on Hinge-Cross-Entropy GAN in Internet of Medical Things

Computer-aided diagnosis based on image color rendering promotes medical image analysis and doctor-patient communication by highlighting important information of medical diagnosis.To overcome the limitations of the color rendering method based on deep learning,such as poor model stability,poor rendering quality,fuzzy boundaries and crossed color boundaries,we propose a novel hinge-cross-entropy generative adversarial network(HCEGAN).The self-attention mechanism was added and improved to focus on the important information of the image.And the hinge-cross-entropy loss function was used to stabilize the training process of GAN models.In this study,we implement the HCEGAN model for image color rendering based on DIV2K and COCO datasets,and evaluate the results using SSIM and PSNR.The experimental results show that the proposed HCEGAN automatically re-renders images,significantly improves the quality of color rendering and greatly improves the stability of prior GAN models.

Simply Fine-Tuned Deep Learning-Based Classification for Breast Cancer with Mammograms

A lump growing in the breast may be referred to as a breast mass related to the tumor.However,not all tumors are cancerous or malignant.Breast masses can cause discomfort and pain,depending on the size and texture of the breast.With an appropriate diagnosis,non-cancerous breast masses can be diagnosed earlier to prevent their cultivation from being malignant.With the development of the artificial neural network,the deep discriminative model,such as a convolutional neural network,may evaluate the breast lesion to distinguish benign and malignant cancers frommammogram breast masses images.This work accomplished breastmasses classification relative to benign and malignant cancers using a digital database for screening mammography image datasets.A residual neural network 50(ResNet50)model along with an adaptive gradient algorithm,adaptive moment estimation,and stochastic gradient descent optimizers,as well as data augmentations and fine-tuning methods,were implemented.In addition,a learning rate scheduler and 5-fold cross-validation were applied with 60 training procedures to determine the best models.The results of training accuracy,p-value,test accuracy,area under the curve,sensitivity,precision,F1-score,specificity,and kappa for adaptive gradient algorithm 25%,75%,100%,and stochastic gradient descent 100%fine-tunings indicate that the classifier is feasible for categorizing breast cancer into benign and malignant from the mammographic breast masses images.

Acral melanoma detection using dermoscopic images and convolutional neural networks

Acral melanoma(AM)is a rare and lethal type of skin cancer.It can be diagnosed by expert dermatologists,using dermoscopic imaging.It is challenging for dermatologists to diagnose melanoma because of the very minor differences between melanoma and non-melanoma cancers.Most of the research on skin cancer diagnosis is related to the binary classification of lesions into melanoma and non-melanoma.However,to date,limited research has been conducted on the classification of melanoma subtypes.The current study investigated the effectiveness of dermoscopy and deep learning in classifying melanoma subtypes,such as,AM.In this study,we present a novel deep learning model,developed to classify skin cancer.We utilized a dermoscopic image dataset from the Yonsei University Health System South Korea for the classification of skin lesions.Various image processing and data augmentation techniques have been applied to develop a robust automated system for AM detection.Our custombuilt model is a seven-layered deep convolutional network that was trained from scratch.Additionally,transfer learning was utilized to compare the performance of our model,where AlexNet and ResNet-18 were modified,fine-tuned,and trained on the same dataset.We achieved improved results from our proposed model with an accuracy of more than 90%for AM and benign nevus,respectively.Additionally,using the transfer learning approach,we achieved an average accuracy of nearly 97%,which is comparable to that of state-of-the-art methods.From our analysis and results,we found that our model performed well and was able to effectively classify skin cancer.Our results show that the proposed system can be used by dermatologists in the clinical decision-making process for the early diagnosis of AM.

Deep Learning Framework for the Prediction of Childhood Medulloblastoma

This research work develops new and better prognostic markers for predicting Childhood MedulloBlastoma(CMB)using a well-defined deep learning architecture.A deep learning architecture could be designed using ideas from image processing and neural networks to predict CMB using histopathological images.First,a convolution process transforms the histopathological image into deep features that uniquely describe it using different two-dimensional filters of various sizes.A 10-layer deep learning architecture is designed to extract deep features.The introduction of pooling layers in the architecture reduces the feature dimension.The extracted and dimension-reduced deep features from the arrangement of convolution layers and pooling layers are used to classify histopathological images using a neural network classifier.The performance of the CMB classification system is evaluated using 1414(10×magnification)and 1071(100×magnification)augmented histopathological images with five classes of CMB such as desmoplastic,nodular,large cell,classic,and normal.Experimental results show that the average classification accuracy of 99.38%(10×)and 99.07%(100×)is attained by the proposed CNB classification system.