Should Preoperative Computed Tomography Be Routine Examination For Cervicofacial Space Infections?

Background: Cervicofacial space infections are potentially life-threatening, which require accurate diagnosis, early incision, and adequate drainage. The utilization of computed tomography (CT) in cervicofacial space infections has significantly increased. However, the clinical value of preoperative CT imaging in cervicofacial space infections remains controversial. We, therefore, investigated whether CT examination should be used as a routine examination in the treatment of patients with cervicofacial space infections.Methods: A retrospective study of all patients affected by cervicofacial space infections that received incision and drainage surgery from Jan 2016 to Dec 2020 was performed. Patients were divided into 2 groups: the group with preoperative CT and the group without preoperative CT. Outcomes, including re-operation rate, missed diagnosis rate, days of symptom relief, length of stay, duration of surgery, and total cost of hospitalization, were analyzed.Results: Of 153 patients, 108 patients underwent surgery with preoperative CT and 45 patients without preoperative CT. The re-operation rate in the preoperative CT group (6/108, 5.6%) was significantly lower (P<0.05) than that in the group without preoperative CT (10/45, 22.2%). Significant reduction of missed diagnosis rate, days of symptom relief, length of stay, and duration of surgery (P<0.05) were detected in the preoperative CT group. Conclusions: Preoperative CT examination should be recommended as a routine examination in the treatment of cervicofacial space infections for its usefulness in reducing the missed diagnosis rate and repeated surgery complication.

Research on grounding grid corrosion detection based on hybrid artificial intelligence algorithm

As an important part of substation, grounding grid is the main approach to release short-circuit current. Grounding grid is in the complex electromagnetic compund,and with increasely being operated, it is easily corroded for various reasons, resulting in short-circuit current not being discharged normally. It is difficult to detect the grounding grid without excavation, because it is generally buried underground. Therefore, it is very important to accurately detect the grounding grid without excavation. In this paper, a grounding grid detection method based on artificial intelligence hybrid algorithm is proposed. In order to verify the accuracy of the detection method, the grounding grid model is established by using electromagnetic transient simulation software ATP-EMTP. According to the ATP-EMTP simulation model, the node potential of each point of the grounding grid is detected as the reference object for verification. In order to remove the randomness of the simulation results, the average value of 20 tests was used as the corrosion diagnosis result. The results show that the missed diagnosis rate of the proposed in paper was 2.1%, which was reduced by 12.1%, 7.1% and 7.5% respectively compared with the other three algorithms. At the same time, the misdiagnosis is 2.1%, which is reduced by 10%, 6.2% and 12.9% respectively for the other three algorithms. In sum, the corrosion leakage diagnosis rate and misdiagnosis rate of the proposed artificial intelligence algorithm are lower than those of the other three optimization algorithms, and have higher accuracy and stability in corrosion diagnosis.

Aortic Dissection Auxiliary Diagnosis Model and Applied Research Based on Ensemble Learning

Aortic dissection (AD), a dangerous disease threatening to human beings, has a hidden onset and rapid progression and has few effective methods in its early diagnosis. At present, although CT angiography acts as the gold standard on AD diagnosis, it is so expensive and time-consuming that it can hardly offer practical help to patients. Meanwhile, the artificial intelligence technology may provide a cheap but effective approach to building an auxiliary diagnosis model for improving the early AD diagnosis rate by taking advantage of the data of the general conditions of AD patients, such as the data about the basic inspection information. Therefore, this study proposes to hybrid five types of machine learning operators into an integrated diagnosis model, as an auxiliary diagnostic approach, to cooperate with the AD-clinical analysis. To improve the diagnose accuracy, the participating rate of each operator in the proposed model may adjust adaptively according to the result of the data learning. After a set of experimental evaluations, the proposed model, acting as the preliminary AD-discriminant, has reached an accuracy of over 80%, which provides a promising instance for medical colleagues.

BreastNet18: A High Accuracy Fine-Tuned VGG16 Model Evaluated Using Ablation Study for Diagnosing Breast Cancer from Enhanced Mammography Images

Background: Identification and treatment of breast cancer at an early stage can reduce mortality. Currently, mammography is the most widely used effective imaging technique in breast cancer detection. However, an erroneous mammogram based interpretation may result in false diagnosis rate, as distinguishing cancerous masses from adjacent tissue is often complex and error-prone. Methods: Six pre-trained and fine-tuned deep CNN architectures: VGG16, VGG19, MobileNetV2, ResNet50, DenseNet201, and InceptionV3 are evaluated to determine which model yields the best performance. We propose a BreastNet18 model using VGG16 as foundational base, since VGG16 performs with the highest accuracy. An ablation study is performed on BreastNet18, to evaluate its robustness and achieve the highest possible accuracy. Various image processing techniques with suitable parameter values are employed to remove artefacts and increase the image quality. A total dataset of 1442 preprocessed mammograms was augmented using seven augmentation techniques, resulting in a dataset of 11,536 images. To investigate possible overfitting issues, a k-fold cross validation is carried out. The model was then tested on noisy mammograms to evaluate its robustness. Results were compared with previous studies. Results: Proposed BreastNet18 model performed best with a training accuracy of 96.72%, a validating accuracy of 97.91%, and a test accuracy of 98.02%. In contrast to this, VGGNet19 yielded test accuracy of 96.24%, MobileNetV2 77.84%, ResNet50 79.98%, DenseNet201 86.92%, and InceptionV3 76.87%. Conclusions: Our proposed approach based on image processing, transfer learning, fine-tuning, and ablation study has demonstrated a high correct breast cancer classification while dealing with a limited number of complex medical images.

Molecular Diagnosis of Muscular Dystrophy Patients in Western Indian Population: A Comprehensive Mutation Analysis Using Amplicon Sequencing

Muscular Dystrophies (MDs) are a group of inherited diseases and heterogeneous in nature. To date, 40 different genes have been reported for the occurrence and/or progression of MDs. This study was conducted to demonstrate the application of next-generation sequencing (NGS) in developing a time-saving and cost-effective diagnostic method to detect single nucleotide variants (SNVs) and copy number variants (CNVs) in a single test. A total of 123 cases clinically suspected of MD were enrolled in this study. Amplicon panel-based diagnosis was carried out for 102 (DMD/BMD) cases and the results were further screened using multiplex ligation-dependent probe amplification (MLPA). Whilst in the case of LGMD (N = 19) and UMD (N = 2), only NGS panel-based analysis was carried out. We identified the large deletions in 74.50% (76/102) of the cases screened with query DMD or BMD. Further, the large deletion in CAPN3 gene (N = 3) and known SNV mutations (N = 4) were identified in LGMD patients. Together, the total diagnosis rate for this amplicon panel was 70.73% (87/123) which demonstrated the utility of panel-based diagnosis for high throughput, affordable, and time-saving diagnostic strategy. Collectively, present study demonstrates that the panel based NGS sequencing could be superior over to MLPA.

The impact of the Covid-19 pandemic on care of women with ectopic pregnancy in a tertiary London hospital

Background: In response to the COVID-19 pandemic, a central London tertiary referral hospital’s nurse-led Early Pregnancy & Acute Gynaecology Unit (EPAGU) suspended its walk-in service in favour of a telephone triage system with scheduled appointments. Objective: To assess if the pandemic and this adaptation to clinical services had an impact on the presentation, management and complication rate of ectopic pregnancies. Materials and Methods: A retrospective review was performed of ectopic pregnancies diagnosed in the EPAGU between 5th of March 2020 – 15th of July 2020 (pandemic) and 5th of March 2019 – 15th of July 2019 (pre-pandemic). Main outcome measures: Ultrasound findings, patient demographics, serum hCG concentrations, operative findings and complications. Results: There was a 36% reduction in attendances to the unit during the pandemic. Allowing for this, there was no significant difference in the diagnosis rate between the two periods. There was no significant difference in the gestation at diagnosis, serum hCG concentration or volume of mass at presentation. There was also no significant difference in rate of surgical intervention or complications including rupture of fallopian tube, haemoperitoneum or need for blood transfusion. Conclusion: This study suggests this is a safe means of caring for women with ectopic pregnancies which does not limit management options nor lead to higher complication rates. What is new: Other EPAGUs may choose to adopt a telephone triage system with reassurance of its safety.

Analysis of Sports Knee Fractures Based on X-Ray and Computed Tomography Imaging

Objective. To analyse the X-ray and computed tomography (CT) findings of 128 patients with sports-related knee fractures and to improve the diagnosis rate based on the existing methods of diagnosis of sports knee fractures on X-ray and CT images. Method. In this study, we retrospectively analyse the medical records of 128 cases of sports-related fractures in the hospital, analyse the results of X-ray examination and CT imaging of patients with sports knee fractures, and compare the results obtained by the two examination methods, while referring to MRI images performed. Results. CT examination of knee fractures, tibial plateau fractures, and knee joint free body results were compared with X-ray results ( P < 0.05 ), while CT examination of patella fractures and X-ray results were compared. The difference was not statistically significant ( P > 0.05 ). Conclusion. For imaging examination of knee fractures, a single ordinary X-ray or CT scan should be selected according to the specific situation of the patient. For patients with suspected unstable fractures, when the patient’s informed consent and the condition are not allowed, ordinary X-ray film combined with CT examination is used to improve the accuracy of diagnosis and avoid the existence of hidden fractures, resulting in medical accidents.

Medical Image Diagnostic Value of Computed Tomography for Bladder Tumors

Objective. To study computed tomography (CT) imaging characteristics of bladder tumors, to explore the value of CT in tumor diagnosis, and to identify the relevant factors of CT missed diagnosis so that medical staff can be more accurate in the diagnosis of bladder tumors. Methods. To retrospectively analyze the CT manifestations of 153 bladder tumor cases confirmed by paraffin pathology in our hospital and to study the difference between the benign and CT imaging features. CT indicators mainly include the number, location, morphology, calcification, bladder wall smoothness, CT value, degree of enhancement, and invasion of surrounding tissues and organs. Then, we retrospectively analyze 17 cases of CT missed diagnosis of bladder tumors, analyze related factors, and discuss the role of CT in the diagnosis of bladder tumors. Results. This study has shown that with the help of CT images, the diagnosis rate of bladder tumors has been greatly improved. Of the 153 patients studied, noninvasive urothelial carcinoma accounted for 18.95% of all benign and malignant bladder tumors, invasive urothelial carcinoma accounted for 67.93%, prostatic metastatic carcinoma and inflammatory myofibroblastoma accounted for 8.47%, pheochromocytoma accounted for 1.31%, inverted papilloma accounted for 1.31%, tubular choriocarcinoma accounted for 0.63%, and endocystitis accounted for 1.31%. In addition, the blood supply level, CT index bladder wall smoothness, and CT value are also statistically significant ( P < 0.05 ). Conclusions. CT is of high value in the diagnosis of bladder tumors, and benign and malignant bladder tumors have CT and CT imaging features. The size of bladder tumors is related to the missed diagnosis rate of CT. The application of CT examination technology can improve the accuracy of diagnosis of bladder tumors.

Epigenotype, Genotype, and Phenotype Analysis of Taiwanese Patients with Silver–Russell Syndrome

Background: Silver–Russell syndrome (SRS) is a clinically and genetically heterogeneous disorder characterized by severe intrauterine growth retardation, poor postnatal growth, characteristic facial features, and body asymmetry. Hypomethylation of the imprinted genes of the chromosome 11p15.5 imprinting gene cluster and maternal uniparental disomy of chromosome 7 (mUPD7) are the major epigenetic disturbances. The aim of this study was to characterize the epigenotype, genotype, and phenotype of these patients in Taiwan. Methods: Two hundred and six subjects with clinically suspected SRS were referred for diagnostic testing, which was performed by profiling the methylation of H19-associated imprinting center (IC) 1 and the imprinted PEG1/MEST region using methylation-specific multiplex ligation-dependent probe amplification and high-resolution melting analysis with a methylation-specific polymerase chain reaction assay. We also applied a whole genome strategy to detect copy number changes and loss of heterozygosity. Clinical manifestations were recorded and analyzed according to the SRS scoring system proposed by Bartholdi et al. Results: Among the 206 referred subjects, 100 were classified as having a clinical diagnosis of SRS (score ≥ 8, maximum = 15) and 106 had an SRS score ≤ 7. Molecular lesions were detected in 45% (45/100) of the subjects with a clinical diagnosis of SRS, compared to 5% (5/106) of those with an SRS score ≤ 7. Thirty-seven subjects had IC1 hypomethylation, ten subjects had mUPD7, and three subjects had microdeletions. Several clinical features were found to be statistically different (p < 0.05) between the “IC1 hypomethylation” and “mUPD7” groups, including relative macrocephaly at birth (89% vs. 50%), triangular shaped face (89% vs. 50%), clinodactyly of the fifth finger (68% vs. 20%), and SRS score (11.4 ± 2.2 vs. 8.3 ± 2.5). Conclusions: The SRS score was positively correlated with the molecular diagnosis rate (p < 0.001). The SRS subjects with mUPD7 seemed to have fewer typical features and lower SRS scores than those with IC1 hypomethylation. Careful clinical observation and timely molecular confirmation are important to allow for an early diagnosis and multidisciplinary management of these patients.

The role of dementia diagnostic delay in the inverse cancer-dementia association

Background Cancer is inversely associated with dementia. Using simulations, we examined whether this inverse association may be explained by dementia diagnosis timing, including death before dementia diagnosis and differential diagnosis patterns by cancer history. Methods We used multistate Markov simulation models to generate cohorts 65 years of age and free of cancer and dementia at baseline; follow-up for incident cancer (all cancers, breast, prostate, and lung cancer), dementia, dementia diagnosis among those with dementia, and death occurred monthly over 30 years. Models specified no true effect of cancer on dementia, and used age-specific transition rates calibrated to US population and cohort data. We varied the average lapse between dementia onset and diagnosis, including non-differential and differential delays by cancer history, and examined observed incidence rate ratios (IRRs) for the effect of cancer on dementia diagnosis. Results Non-differential dementia diagnosis delay introduced minimal bias (IRRs=0.98-1.02) for all cancer, breast, and prostate models and substantial bias (IRR=0.78) in lung cancer models. For the differential dementia diagnosis delay model of all cancer types combined, simulation scenarios with ≥20% lower dementia diagnosis rate (additional 4.5-month delay) in those with cancer history versus without yielded results consistent with literature estimates. Longer dementia diagnosis delays in those with cancer and higher mortality in those with cancer and dementia yielded more bias. Conclusions Delays in dementia diagnosis may play a role in the inverse cancer-dementia relationship, especially for more fatal cancers, but moderate differential delays in those with cancer were needed to fully explain the literature-reported IRRs.