Diagnostic Accuracy Rate Research Articles

A preliminary animal study on the prediction of nerve block success using ultrasonographic parameters

This study aimed to evaluate the diagnostic value of ultrasonographic parameters as an indicator for predicting regional nerve block success. Ultrasound-guided sciatic nerve block was performed in seven dogs using either 2% mepivacaine (nerve-block group) or saline (sham-block group). The cross-sectional area (CSA), nerve blood flow (NBF), and shear wave velocity (SWV) of the sciatic nerve (SWVN), SWV of the biceps femoris muscle (SWVM), and their ratio (SWVNMR) were measured at 0, 30, 60, and 90 min after the nerve block as well as the change rate of each parameter from the baseline. A receiver operating characteristic (ROC) curve analysis was performed to determine the diagnostic value of each parameter in the prediction of nerve block success. No significant changes were observed in the CSA or NBF in association with the nerve block. The SWVN and SWVNMR in the nerve-block group were significantly higher than those in the sham-block group at 90 min and at 30, 60, and 90 min, respectively (p < 0.05). The change rates of SWVN and SWVNMR in the nerve-block group were significantly higher than those in the sham-block group at all time points (p < 0.05). The ROC curve analysis showed that SWVN had a moderate diagnostic accuracy (area under the curve [AUC], 0.779), whereas SWVNMR and change rates of SWVN and SWVNMR had a high diagnostic accuracy (AUC, 0.947, 0.998, and 1.000, respectively). Ultrasonographic evaluation of the SWVN and SWVNMR could be used as indicators for predicting nerve block success.

Screening of Common Retinal Diseases Using Six-Category Models Based on EfficientNet

PurposeA six-category model of common retinal diseases is proposed to help primary medical institutions in the preliminary screening of the five common retinal diseases.MethodsA total of 2,400 fundus images of normal and five common retinal diseases were provided by a cooperative hospital. Two six-category deep learning models of common retinal diseases based on the EfficientNet-B4 and ResNet50 models were trained. The results from the six-category models in this study and the results from a five-category model in our previous study based on ResNet50 were compared. A total of 1,315 fundus images were used to test the models, the clinical diagnosis results and the diagnosis results of the two six-category models were compared. The main evaluation indicators were sensitivity, specificity, F1-score, area under the curve (AUC), 95% confidence interval, kappa and accuracy, and the receiver operator characteristic curves of the two six-category models were compared in the study.ResultsThe diagnostic accuracy rate of EfficientNet-B4 model was 95.59%, the kappa value was 94.61%, and there was high diagnostic consistency. The AUC of the normal diagnosis and the five retinal diseases were all above 0.95. The sensitivity, specificity, and F1-score for the diagnosis of normal fundus images were 100, 99.9, and 99.83%, respectively. The specificity and F1-score for RVO diagnosis were 95.68, 98.61, and 93.09%, respectively. The sensitivity, specificity, and F1-score for high myopia diagnosis were 96.1, 99.6, and 97.37%, respectively. The sensitivity, specificity, and F1-score for glaucoma diagnosis were 97.62, 99.07, and 94.62%, respectively. The sensitivity, specificity, and F1-score for DR diagnosis were 90.76, 99.16, and 93.3%, respectively. The sensitivity, specificity, and F1-score for MD diagnosis were 92.27, 98.5, and 91.51%, respectively.ConclusionThe EfficientNet-B4 model was used to design a six-category model of common retinal diseases. It can be used to diagnose the normal fundus and five common retinal diseases based on fundus images. It can help primary doctors in the screening for common retinal diseases, and give suitable suggestions and recommendations. Timely referral can improve the efficiency of diagnosis of eye diseases in rural areas and avoid delaying treatment.

The Utility of Frozen Sections in the Evaluation of Clear Margins in Oral Squamous Cell Carcinomas: A Cross-Sectional Study From a Tertiary Care Center.

Background and objectiveHead and neck cancers are prevalent in Pakistan. Oral squamous cell carcinomas are primarily treated via surgical removal, and complete surgical resection is the paramount prognostic factor. A resection margin of 5 mm on the final histopathology report has been accepted as adequate in the existing literature. Negative margins on the frozen section do not guarantee adequate disease-free resections on the final histopathology report. In this study, we aimed to ascertain how accurately tumor-free margins can be detected on frozen sections, which are reported intraoperatively compared to permanent sections of the same tissues reported after proper staining in oral squamous cell carcinoma patients.MethodsA cross-sectional study was conducted at a tertiary care hospital in Karachi, Pakistan; 94 patients presenting between January and October 2016 were included in this study and a total of 432 tumor margins were assessed.ResultsAmong the total 94 patients included in the study, 79% were male and 21% were female. Buccal mucosa was the most commonly involved subsite (57%), followed by the tongue (25%). The most common T stage was T4 (33%), followed by T2 and T3 at 28% and 21% respectively, while the most common N stage was N0 (55%) followed by N1 at 16% and N2 at 22%. The sensitivity of the frozen section in comparison to the permanent section was found to be 50%, while specificity was calculated to be 99.8%. The positive predictive value was 75% and the negative predictive value was 99.3%.ConclusionThe frozen section is a highly useful tool for the evaluation of tumor margins. However, while it has high diagnostic accuracy rates, it can produce altered results and therefore requires high clinical correlation.

Incorporating uncertainty in learning to defer algorithms for safe computer-aided diagnosis

Deep neural networks are increasingly being used for computer-aided diagnosis, but erroneous diagnoses can be extremely costly for patients. We propose a learning to defer with uncertainty (LDU) algorithm which identifies patients for whom diagnostic uncertainty is high and defers them for evaluation by human experts. LDU was evaluated on the diagnosis of myocardial infarction (using discharge summaries), the diagnosis of any comorbidities (using structured data), and the diagnosis of pleural effusion and pneumothorax (using chest x-rays), and compared with ‘learning to defer without uncertainty information’ (LD) and ‘direct triage by uncertainty’ (DT) methods. LDU achieved the same F1 score as LD but deferred considerably fewer patients (e.g. 36% vs. 69% deferral rate for diagnosing pleural effusion with an F1 score of 0.96). Furthermore, even when many patients were assigned the wrong diagnosis with high confidence (e.g. for the diagnosis of any comorbidities) LDU achieved a 17% increase in F1 score, whereas DT was not applicable. Importantly, the weight of the defer loss in LDU can be easily adjusted to obtain the desired trade-off between diagnostic accuracy and deferral rate. In conclusion, LDU can readily augment any existing diagnostic network to reduce the risk of erroneous diagnoses in clinical practice.

Multi-channel convolutional neural network architectures for thyroid cancer detection.

Early detection of malignant thyroid nodules leading to patient-specific treatments can reduce morbidity and mortality rates. Currently, thyroid specialists use medical images to diagnose then follow the treatment protocols, which have limitations due to unreliable human false-positive diagnostic rates. With the emergence of deep learning, advances in computer-aided diagnosis techniques have yielded promising earlier detection and prediction accuracy; however, clinicians’ adoption is far lacking. The present study adopts Xception neural network as the base structure and designs a practical framework, which comprises three adaptable multi-channel architectures that were positively evaluated using real-world data sets. The proposed architectures outperform existing statistical and machine learning techniques and reached a diagnostic accuracy rate of 0.989 with ultrasound images and 0.975 with computed tomography scans through the single input dual-channel architecture. Moreover, the patient-specific design was implemented for thyroid cancer detection and has obtained an accuracy of 0.95 for double inputs dual-channel architecture and 0.94 for four-channel architecture. Our evaluation suggests that ultrasound images and computed tomography (CT) scans yield comparable diagnostic results through computer-aided diagnosis applications. With ultrasound images obtained slightly higher results, CT, on the other hand, can achieve the patient-specific diagnostic design. Besides, with the proposed framework, clinicians can select the best fitting architecture when making decisions regarding a thyroid cancer diagnosis. The proposed framework also incorporates interpretable results as evidence, which potentially improves clinicians’ trust and hence their adoption of the computer-aided diagnosis techniques proposed with increased efficiency and accuracy.

The diagnostic value of second ultrasound-guided fine-needle aspiration for thyroid nodules.

This study aimed to investigate the diagnostic value of doing a second ultrasound-guided fine-needle aspiration (US-FNA) for thyroid nodules of different sizes that could not be diagnosed by the first US-FNA. One hundred and forty-three patients (162 nodules) were diagnosed with suspected malignant thyroid nodules in a routine ultrasound examination, but since the diagnosis could not be confirmed by the cytology of the samples collected in the first US-FNA, the patients underwent US-FNA again 3 months later. The ultrasound results, cytology results, and postoperative pathology of these nodules were collected. The nodules were divided into three groups according to the largest diameter (L) of the thyroid nodules: Group 1, L < 0.5cm, 26 nodules; Group 2, L=0.5-1.0cm, 76 nodules; and Group 3, L > 1.0cm, 60 nodules. In the second US-FNA, the overall diagnosis rate of the 162 thyroid nodules that could not be given a definitive diagnosis by the first US-FNA was 51.8% (84/162). The definitive diagnosis rates of the nodules in Groups 1, 2, and 3 were 30.8% (8/26), 67.1% (51/76), and 41.7% (25/60), respectively. The diagnosis rate was the highest in Group 2, and the differences between this group and the other two groups were statistically significant (χ2 =10.489, 8.801, p < 0.05 for both). The diagnostic accuracy rates of Groups 1, 2, and 3 were 100% (8/8), 96.1% (49/51), and 92% (23/25), respectively. Second US-FNA is highly recommended for such nodules.

Impact of Antibiotic Prophylaxis on Infection Rate after Endoscopic Ultrasound Through-the-Needle Biopsy of Pancreatic Cysts: A Propensity Score-Matched Study.

Background: Despite weak evidence, antibiotic prophylaxis prior to endoscopic ultrasound-guided through-the-needle biopsy (EUS-TTNB) of pancreatic cystic lesions (PCLs) is routinely used in clinical practice. We aim to compare a group of patients treated with antibiotics before EUS-TTNB of PCLs and a group who did not undergo antimicrobial prophylaxis. Methods: Out of 236 patients with pancreatic cystic lesions referred to two high-volume centers between 2016 and 2021, after propensity score matching, two groups were compared: 98 subjects who underwent EUS-TTNB under antibiotic prophylaxis and 49 subjects without prophylaxis. Results: There was no difference in terms of baseline parameters between groups. Final diagnosis was serous cystadenoma in 36.7% of patients in the group not treated with prophylaxis and in 37.7% of patients in the control group, whereas IPMN and mucinous cystadenoma were diagnosed in 3 (6.1%) and 16 (32.6%) versus 6 (6.1%) and 32 (32.6%) patients in the two groups, respectively (p = 0.23). Overall, the adverse event rate was 6.1% in the group not treated with antibiotic prophylaxis and 5.1% in the control group (p = 0.49). Only a single infectious adverse event occurred in each group (p = 0.48). The diagnostic yields were 89.7% and 90.8% in the two groups (p = 0.7), and the diagnostic accuracy rate was 81.6% in both groups (p = 1.0). Conclusions: Prophylactic antibiotics do not seem to influence the risk of infection, and their routine use should be discouraged.

A Comparative Study of Modified Alvarado Score Vs Routine Clinical Assessment in the Management of Acute Appendicitis

Background: Pain in right Iliac fossa is one of the most common presenting symptom in the surgical emergency in which acute appendicitis is the most probable amongst the differentials. Patients with equivocal signs and symptoms pose a significant diagnostic dilemma for which they are admitted for observation. Aim: To compare the efficacy of modified Alvarado scoring system with the routine clinical diagnosis. Study design: A randomized controlled trial was set up to compare clinical diagnosis (control group) with a diagnostic protocol using modified Alvarado scoring system (intervention group). Setting: This study was conducted in a government administered tertiary care referral center (Mayo Hospital Lahore), Pakistan, from Septembers 15, 2019 to September 14, 2020. Method: A total of 256 patients referred to surgical department with suspected appendicitis were included in the study. Patients above the age of 12 years were included in the study. Patients were randomly divided into two groups. Group A included 128 patients who were assessed on the basis of the Modified Alvarado score while the Group B also included 128 patients which were assessed on routine clinical evaluation. Histopathology was the Gold Standard which determined the Diagnostic Accuracy (DA) and Negative Appendectomy Rate (NAR), which were duly recorded. Results: The Diagnostic Accuracy (DA) of the Group A evaluated on the Modified Alvarado Scoring System was 88% in which 113 out of 128 patients were positive for acute appendicitis on histopathology while Negative Appendectomy Rate(NAR) was 12%.Only 15 out of 128 were negative on histopathology . However the Group B had a (DA) of 79% in which 101 patients out of 128 were proven positive through the histopathology while (NAR) was 21%. The mean age of the was found to be 25.34 years with a male to female preponderance ratio of 1.22:1 Conclusion: we have found the Alvarado scoring system to be an effective and a convenient scoring tool. We recommend its regular application in the emergency for the diagnosis of Acute Appendicitis. Keywords: Alvarado score, Acute appendicitis, Histopathology, Clinical diagnosis.

Yield of flow cytometry in addition to cytology for lymph node sampling in patients with incidental axillary adenopathy without a concurrent diagnosis of primary breast malignancy.

PurposeNon-specific lymphadenopathy is increasingly being reported especially given the COVID-19 vaccination campaign and is a diagnostic dilemma especially in oncology patients. The purpose of this study was to evaluate the diagnostic accuracy and discordance rate between fine-needle aspiration (FNA) cytology and flow cytometry (FC) immunophenotyping in axillary FNA in patients with morphologically abnormal axillary lymph nodes on imaging and no concurrent diagnosis of primary breast malignancy.MethodsThis retrospective study included 222 patients who underwent screening or diagnostic axillary ultrasound that yielded suspicious lymphadenopathy without concurrent or recent prior diagnosis of breast cancer and who had subsequent image-guided axillary FNA and FC. Diagnostic accuracy, sensitivity, specificity, and positive and negative predictive value (PPV and NPV) were reported for FNA with cytology alone, and FC alone, and in combination. Discordance rate between FNA cytology and FC was assessed. Discordant cases were evaluated with histology or clinical and imaging follow-up.ResultsDiagnostic sensitivity, specificity, PPV, NPV, and diagnostic accuracy were 88%, 92%, 77%, 96%, and 91%, for FNA alone, 98%, 98%, 92%, 99%, and 98% for FC alone, and 100%, 92%, 79%, 100%, and 94% when combined. The overall discordance rate between FNA and FC was 7% (16/222). 7/16 (44%) patients with discordant results were diagnosed with lymphoma, while 9/16 (56%) patients with discordant results had benign findings.ConclusionWith a diagnostic accuracy of 91%, FNA with cytology is sufficient to screen patients with indeterminate and incidental lymphadenopathy. Flow cytometry could be initially deferred in patients with low pretest probability of lymphoma.

Ileosigmoid knotting: A review of 923 cases.

Objectives:Ileosigmoid knotting (ISK) is a rare intestinal obstruction form worldwide. The aim of this study was to investigate changing trends in ISK.Methods:The Web of Science and PubMed databases were electronically searched to find all publications to evaluate all epidemiological, etiological, clinical, laboratory, radiological, therapeutic, and prognostic factors in ISK.Results:Most of the cases were reported from Asian and African countries. Mean age was 43.9 years with a 79.9%/20.1% of male/female ratio. Main symptom period was 48.1 hours, while the most common clinical features were abdominal pain/tenderness (99.1%), distention (88.3%), and obstipation/constipation (58.8%). Abdominal X-ray radiography, computerized tomography (CT), and magnetic resonance imaging (MRI) were diagnostic in 8.2%, 96.2%, and 100.0%, respectively, while the total diagnostic accuracy rate was 20.8%. Bowels were gangrenous in 85.6% of the patients. Ileum resection was applied in 14.0% of the cases, while sigmoid colon resection in 7.6%, and both segment resection in 67.1%. The mortality rate was 22.7%, while the morbidity rate was also 22.7%.Conclusion:ISK is a rare disease, but it is still catastrophic despite its two-century recognised past. As an exception, diagnostic convenience arising from CT or MRI looks like the most important change over the last half-century.

Diagnostic Value of Emission Computed Tomography Combined with Computed Tomography for Metastatic Malignant Tumor of Spine.

Objective To explore the diagnostic value of emission computed tomography (ECT) combined with computed tomography (CT) for metastatic malignant tumor of spine. Methods By means of retrospective study, a total of 102 patients with extraskeletal primary malignant tumor treated in our hospital from February 2019 to February 2021 were selected as the subjects. All patients had single lesion of the spine, of which 72 were malignant and 30 were benign according to the results of pathological examination. ECT and CT examinations were performed to all patients, and by taking the pathological findings as the gold standard, the sensitivity, specificity, positive predictive value and negative predictive value of ECT, CT, and their combination were calculated, and their efficacy in diagnosing metastatic malignant tumor of spine was analyzed. Results A total of 68 (94.4%) metastatic malignant spinal tumors were detected by ECT combined with CT, with a detection rate of 100% in breast cancer and lung cancer, 94.1% in liver cancer, and 78.6% in prostate cancer, respectively; the combined diagnosis had a diagnostic sensitivity of 94.4%, specificity of 73.3%, positive predictive value of 89.5%, negative predictive value of 84.6%, and diagnostic accuracy rate of 88.2%, and AUC (95% CI) = 0.839 (0.739–0.939). Conclusion Combining ECT with CT has a good diagnostic efficacy for metastatic malignant spinal tumors.

Data-driven Fault Diagnosis for PEM Fuel Cell System Using Sensor Pre-Selection Method and Artificial Neural Network Model

Fault diagnosis is a critical process for the reliability and durability of proton exchange membrane fuel cells (PEMFCs). Due to the complexity of internal transport processes inside the PEMFCs, developing an accurate model considering various failure mechanisms is extremely difficult. In this paper, a novel data-driven approach based on sensor pre-selection and artificial neural network (ANN) are proposed. Firstly, the features of sensor data in time-domain and frequency-domain are extracted for sensitivity analysis. The sensors with poor response to the changes of system states are filtered out. Then experimental data monitored by the remaining sensors are utilized to establish the fault diagnosis model by using the ANN model. Levenberg-Marquardt (LM) algorithm, resilient propagation (RP) algorithm, and scaled conjugate gradient (SCG) algorithm are utilized in the neural network training, respectively. The diagnostic results demonstrate that the diagnostic accuracy rate reaches 99.2% and the recall rate reaches 98.3% by the proposed methods. The effectiveness of the proposed method is verified by comparing the diagnostic results in this work and that by support vector machine (SVM) and logistic regression (LR). Besides, the high computational efficiency of the proposed method supports the possibility of online diagnosis. Meanwhile, detecting the faults in the early stage can provide effective guidance for fault tolerant control of the PEMFCs system.

Clinical Utility of the Prenatal Ultrasound Score of the Placenta Combined with Magnetic Resonance Imaging in Diagnosis of Placenta Accreta during the Second and Third Trimester of Pregnancy.

Objective The aim is to explore the clinical utility of the prenatal ultrasound score of the placenta combined with magnetic resonance imaging (MRI) in diagnosis of placenta accreta during the second and third trimester of pregnancy. Materials and Methods A total of 108 pregnant women with suspected placenta accreta treated in Wuhan Hankou Hospital and Yantaishan Hospital of Yantai from January 2019 to January 2022 were retrospectively analyzed, the enrolled pregnant women received MRI examination because of suspected results of ultrasonic diagnosis, and by taking pathologic findings as the gold standard, the diagnostic efficacy of the ultrasound score, MRI, and their combination to placenta accreta during the second and third trimester of pregnancy was analyzed, and the diagnostic sensitivity, specificity, the positive predictive value, and the negative predictive value of these diagnostic modalities were evaluated. Results Among 108 patients with suspected placenta accreta, 75 with pathologically confirmed placenta accreta were included in the accreta group, and 33 without placenta accreta were included in the non-accreta group; no statistical between-group differences in the patients' age, gestational weeks, educational degree, and other general data were observed (P > 0.05), but the history of cesarean section, history of induced abortion, and incidence rate of placenta praevia were significantly higher in the accreta group than in the non-accreta group (P < 0.05); the ultrasound score was significantly higher in the accreta group than in the non-accreta group (P < 0.05); the incidence rates of signs of “placental heterogeneity” and “bulge of lower segment of the uterus and local thickening of the placenta” were obviously higher in the accreta group than in the non-accreta group (P < 0.05); according to the comparison with pathologic findings, the accuracy rate, sensitivity, specificity, the positive predictive value, and the negative predictive value of combined diagnosis were significantly higher than those of single application of the ultrasound score and MRI diagnosis (P < 0.05); and ROC analysis found that the area under the curve of combined diagnosis was obviously larger than that of the ultrasound score and MRI diagnosis (P < 0.05). Conclusion A combining prenatal ultrasound score of the placenta with MRI plays an important role in the diagnosis of placenta accreta during the second and third trimester of pregnancy, which can further improve the diagnostic accuracy rate of placenta accreta and provide significant guidance in preventing high-risk complications during the perinatal period.

Evaluation of Covid-19 cases that applied to the hospital at the first peak of the pandemic

Early diagnosis in COVID-19 is essential in terms of treatment and prevention of contagiousness. In this study, we aimed to find an alternative diagnosis method by using fewer laboratory parameters in the early diagnosis of COVID-19 disease by creating a fast, easily accessible, cost-effective index and has a diagnostic accuracy rate of over 90%. All patients over the age of 18 who applied to Hitit University Erol Olçok Training and Research Hospital Emergency COVID Outpatient Clinic with a pre-diagnosis of COVID-19 between March and April 2020 were evaluated retrospectively. Patients were divided into two groups as COVID-19 positive and COVID-19 negative. It was aimed to create a HITIT-19 index by evaluating the cases according to the clinical and laboratory results. Between March and April 2020 (in the first peak of the pandemic), 1586 patients were applied to the Emergency COVID-19 outpatient clinic with a pre-diagnosis of COVID-19. According to COVID-19 RT-PCR, card test, and CT involvement, 285 (13%) patients were diagnosed with COVID-19. PCR was positive in 285 (18%) of 1586 patients, and PCR was negative in 1301 (82%). While 153 (53.7%) of the patients diagnosed with COVID-19 were male and the median age was 45 (28-62.75), 883 (55.7%) of the patients not diagnosed with COVID-19 were male, and the median age was 43 (31-65). Hypertension (HT) was the most common underlying disease in 10.5% of patients applied to the emergency room with a diagnosis of COVID-19, while 38.9% dyspnea and 35.1% fever were the most common symptoms. While 76% of Plaquenil and 58% azithromycin were the most frequently started treatments, 31.4% (28.4% of them were hospitalized in the service, 3% in the intensive care unit) of them hospitalized. It was to create a HITIT-19 index that is fast, easily accessible, cost-effective, and has a diagnostic accuracy rate of over 90% by using laboratory tests. However, we could not achieve this goal due to the low accuracy of the diagnostic tests and the lack of significant change in the laboratory levels of the patients at admission. Considering that the pandemic is continuing rapidly, there is still a need to develop practical diagnostic methods that are easier and cheaper in diagnosis. In this sense, we believe that our study will be a guiding study for other studies that will be designed for diagnostic index studies.

Diagnostic Accuracy and Detection Rate of Glaucoma Screening with Optic Disk Photos, Optical Coherence Tomography Images, and Telemedicine.

Purpose: The aim of this study was to evaluate the diagnostic accuracy of optical coherence tomography (OCT) and retinography in the detection of glaucoma through a telemedicine program. Methods: A population-based sample of 4113 persons was randomly selected. The screening examination included a fundus photograph and OCT images. Images were evaluated on a deferred basis. All participants were then invited to a complete glaucoma examination, including gonioscopy, visual field, and dilated fundus examination. The detection rate, sensitivity, specificity, and positive and negative predictive values were calculated. Results: We screened 1006 persons. Of these, 201 (19.9%) were classified as glaucoma suspects; 20.4% were identified only by retinographs, 11.9% only by OCT images, and 46.3% by both. On ophthalmic examination at the hospital (n = 481), confirmed glaucoma was found in 58 (12.1%), probable glaucoma in 76 (15.8%), and ocular hypertension in 10 (2.1%), and no evidence of glaucoma was found in 337 (70.0%). The detection rate for confirmed or probable glaucoma was 9.2%. Sensitivity ranged from 69.4% to 86.2% and specificity from 82.1% to 97.4%, depending on the definition applied. Conclusions: The combination of OCT images and fundus photographs yielded a detection rate of 9.2% in a population-based screening program with moderate sensitivity, high specificity, and predictive values of 84–96%.

Intelligent Fault Diagnosis Method for Blade Damage of Quad-Rotor UAV Based on Stacked Pruning Sparse Denoising Autoencoder and Convolutional Neural Network

This paper introduces a new intelligent fault diagnosis method based on stack pruning sparse denoising autoencoder and convolutional neural network (sPSDAE-CNN). This method processes the original input data by using a stack denoising autoencoder. Different from the traditional autoencoder, stack pruning sparse denoising autoencoder includes a fully connected autoencoding network, the features extracted from the front layer of the network are used for the operation of the subsequent layer, which means that some new connections will appear between the front and rear layers of the network, reduce the loss of information, and obtain more effective features. Firstly, a one-dimensional sliding window is introduced for data enhancement. In addition, transforming one-dimensional time-domain data into the two-dimensional gray image can further improve the deep learning (DL) ability of models. At the same time, pruning operation is introduced to improve the training efficiency and accuracy of the network. The convolutional neural network model with sPSDAE has a faster training speed, strong adaptability to noise interference signals, and can also suppress the over-fitting problem of the convolutional neural network to a certain extent. Actual experiments show that for the fault of unmanned aerial vehicle (UAV) blade damage, the sPSDAE-CNN model we use has better stability and reliable prediction accuracy than traditional convolutional neural networks. At the same time, For noise signals, better results can be obtained. The experimental results show that the sPSDAE-CNN model still has a good diagnostic accuracy rate in a high-noise environment. In the case of a signal-to-noise ratio of −4, it still has an accuracy rate of 90%.

An assessment of attenuation correction of SPECT MPI images generated by deep learning model

This article evaluates the effectiveness of using a deep learning network model to generate reliable attenuation corrected the single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). The authors collected myocardial perfusion imaging data of 88 patients from a SPECT/CT machine, with an average age of 62.47 years. Then, two datasets are created from the original data: set A includes the deep learning-based attenuation corrected images (Generated Attenuation Correction - GenAC), and the non-attenuation corrected images; set B contains only non-attenuation corrected images. These datasets were diagnosed by two doctors (in which, one has 7 years of experience and the other has 10 years of experience in reading SPECT MPI). The doctors diagnose based on the image data without knowing which dataset it belongs to. The sensitivity, specificity, diagnostic accuracy, and lesion rate were evaluated between the two data sets. Results: The average specificity, sensitivity, and accuracy of the set with the deep learning-based attenuation corrected images were 0.87, 0.86, 0.86, while the results with the non-attenuation corrected images are 0.69, 0.83, and 0.78.

A Comparison between the Diagnostic Accuracy of Alvarado and Tzanaki Scoring Systems in Acute Appendicitis

Aim: To find out how accurate the Alvarado and Tzanaki scoring systems are in diagnosing acute appendicitis taking histopathology as gold standard. Methods: A cross-sectional prospective study was conducted from August 2019 to July 2020 at Department of General Surgery, Pakistan Institute of Medical Sciences Islamabad. Sixty patients were included, all of whom had appendectomies after a clinical diagnosis of acute appendicitis. Samples were submitted for histopathology, which was used as the gold standard for the definitive diagnosis of acute appendicitis. The specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV), diagnostic accuracy and negative appendectomy rate of Alvarado and Tzanaki scoring systems was calculated using SPSS version 23. Results: The sensitivity, specificity, positive predictive value, negative predictive value and diagnostic accuracy of Alvarado score at optimal cut-off threshold of ≥7.0, were calculated as 74%, 55%, 90%, 27% and 71.66% respectively. The cut-off threshold point of Tzanaki score was set at more than 8, which yielded a 94.11% sensitivity and an 88.88% specificity. The positive predictive value was 99.95% and the negative predictive value was 72.72%. The Alvarado and Tzanaki scoring systems had negative appendectomy rates of 9.5% and 2.04%, respectively. Conclusion: The Tzanaki scoring system has a better diagnostic accuracy for acute appendicitis as compared to the Alvarado score. Keywords: Acute appendicitis, Alvarado score, Tzanaki score

MRI apparent diffusion coefficient (ADC): A biomarker for prostate cancer after radiation therapy.

Prostate specific antigen (PSA) remains the most used test to assess the response after therapies including the radiation therapy (RT). Apparent diffusion coefficient (ADC) derived from the conventional diffusionweighted imaging (DWI), as a part of noncontrast or biparametric MRI (bpMRI) (T2-weighted and DWI), offers diagnostic accuracy and cancer detection rate equivalent to that of multiparametric MRI. Cellular changes induced by RT can be quali-qualitatively demonstrated as early as 3months after RT as an increase in the signal intensity of the tumor on the ADC map. ADC, in association with PSA, represents a potential biomarker imaging for evaluating treatment efficacy in PCa both during and shortly after RT.

A Few-shot Learning Method for Aging Diagnosis of Oil-paper Insulation by Raman Spectroscopy Based on Graph Theory

Raman spectroscopy is an effective method for diagnosing the aging state of transformer oil-paper insulation. Aiming at overcoming the drawback of previous methods that require a large number of training samples, this research proposes a method for aging diagnosis of oil-paper insulation that can be used for few-shot learning. In this study, different Raman spectroscopy samples of aging insulating oil are obtained by accelerated thermal aging experiments. This paper uses identity matrix as node feature, calculates the connection weights between them by Gaussian kernel function, and constructs the graph structure of Raman spectroscopy library. Using graph convolutional neural network (GCN) based on the graph structure, a diagnosis model is established. The diagnostic accuracy rate is as high as 95.5%. This method provides a theoretical basis for establishing a new structured Raman spectroscopy library and assessing the aging state of transformer oil-paper insulation with a small number of training samples.