Advancements in computer-assisted diagnosis of Alzheimer's disease: A comprehensive survey of neuroimaging methods and AI techniques for early detection.

Alzheimer's Disease (AD) is a brain disorder that causes the brain to shrink and eventually causes brain cells to die. This neurological condition progressively hampers cognitive and memory functions, along with the ability to carry out fundamental tasks over time. From the symptoms it is very difficult to detect during its early stage. It has become necessary to develop a computer assisted diagnostic models for the early AD detection. This survey work, discussed about a review of 110 published AD detection methods and techniques from the year 2011 to till-date. This study lies in its comprehensive exploration of AD detection methods using a range of artificial intelligence (AI) techniques and neuroimaging modalities. By collecting and analysing 50 papers related to AD diagnosis datasets, the study provides a comprehensive understanding of the diversity of input types, subjects, and classes used in AD research. Summarizing 60 papers on methodologies gives researchers a succinct overview of various approaches that contribute to enhancing detection accuracy. From the review, data are acquired and pre-processed form multiple modalities of neuroimaging. This paper mainly focused on review of different datasets used, various feature extraction methods, parameters used in neuro images. To diagnosis the Alzheimer's disease, the existing methods utilized three most common artificial intelligence techniques such as machine learning, deep learning, and transfer learning. We conclude this survey work by providing future perspectives for AD diagnosis at early stage.

Efficient qualitative risk assessment of pipelines using relative risk score based on machine learning.

Pipelines are observed one of the economic modes of transport for transporting oil, gas, and water between various locations. Most of the countries in the world transport petroleum and other flammable products through underground pipelines. The underground and aboveground pipelines are facing various damages due to corrosion, dents, and ruptures due to the environment and operational fluid conditions. The danger of leaks and accidents increases as a result of these damages. Pipelines must be evaluated on a regular basis to make sure they are fit for transmission. By evaluating the effects of damages and the possibility of catastrophic failures using a variety of techniques, pipeline integrity is controlled. Applying the relative risk scoring (RRS) technique, pipeline failures are predicted. One of the probabilistic techniques used to forecast risk based on an impartial assessment is machine learning. With different parameters like corrosion, leakage, materials, atmosphere, surface, earth-movements, above-ground and underground facilities, etc., the RRS method provides an accuracy of 97.5% in identifying the risk and gives a precise classification of risk, whether the pipeline has a high, medium, or low risk without any delay on the prediction compared with Naive Bayes, decision tree, support vector machine, and graph convolutional network.

Learning without forgetting by leveraging transfer learning for detecting COVID-19 infection from CT images.

COVID-19, a global pandemic, has killed thousands in the last three years. Pathogenic laboratory testing is the gold standard but has a high false-negative rate, making alternate diagnostic procedures necessary to fight against it. Computer Tomography (CT) scans help diagnose and monitor COVID-19, especially in severe cases. But, visual inspection of CT images takes time and effort. In this study, we employ Convolution Neural Network (CNN) to detect coronavirus infection from CT images. The proposed study utilized transfer learning on the three pre-trained deep CNN models, namely VGG-16, ResNet, and wide ResNet, to diagnose and detect COVID-19 infection from the CT images. However, when the pre-trained models are retrained, the model suffers the generalization capability to categorize the data in the original datasets. The novel aspect of this work is the integration of deep CNN architectures with Learning without Forgetting (LwF) to enhance the model's generalization capabilities on both trained and new data samples. The LwF makes the network use its learning capabilities in training on the new dataset while preserving the original competencies. The deep CNN models with the LwF model are evaluated on original images and CT scans of individuals infected with Delta-variant of the SARS-CoV-2 virus. The experimental results show that of the three fine-tuned CNN models with the LwF method, the wide ResNet model's performance is superior and effective in classifying original and delta-variant datasets with an accuracy of 93.08% and 92.32%, respectively.

Review of Internet of Things-Based Artificial Intelligence Analysis Method through Real-Time Indoor Air Quality and Health Effect Monitoring: Focusing on Indoor Air Pollution That Are Harmful to the Respiratory Organ.

Everyone is aware that air and environmental pollutants are harmful to health. Among them, indoor air quality directly affects physical health, such as respiratory rather than outdoor air. However, studies that have examined the correlation between environmental and health information have been conducted with public data targeting large cohorts, and studies with real-time data analysis are insufficient. Therefore, this research explores the research with an indoor air quality monitoring (AQM) system based on developing environmental detection sensors and the internet of things to collect, monitor, and analyze environmental and health data from various data sources in real-time. It explores the usage of wearable devices for health monitoring systems. In addition, the availability of big data and artificial intelligence analysis and prediction has increased, investigating algorithmic studies for accurate prediction of hazardous environments and health impacts. Regarding health effects, techniques to prevent respiratory and related diseases were reviewed.

An Ensemble Method for Missing Data of Environmental Sensor Considering Univariate and Multivariate Characteristics.

With rapid urbanization, awareness of environmental pollution is growing rapidly and, accordingly, interest in environmental sensors that measure atmospheric and indoor air quality is increasing. Since these IoT-based environmental sensors are sensitive and value reliability, it is essential to deal with missing values, which are one of the causes of reliability problems. Characteristics that can be used to impute missing values in environmental sensors are the time dependency of single variables and the correlation between multivariate variables. However, in the existing method of imputing missing values, only one characteristic has been used and there has been no case where both characteristics were used. In this work, we introduced a new ensemble imputation method reflecting this. First, the cases in which missing values occur frequently were divided into four cases and were generated into the experimental data: communication error (aperiodic, periodic), sensor error (rapid change, measurement range). To compare the existing method with the proposed method, five methods of univariate imputation and five methods of multivariate imputation-both of which are widely used-were used as a single model to predict missing values for the four cases. The values predicted by a single model were applied to the ensemble method. Among the ensemble methods, the weighted average and stacking methods were used to derive the final predicted values and replace the missing values. Finally, the predicted values, substituted with the original data, were evaluated by a comparison between the mean absolute error (MAE) and the root mean square error (RMSE). The proposed ensemble method generally performed better than the single method. In addition, this method simultaneously considers the correlation between variables and time dependence, which are characteristics that must be considered in the environmental sensor. As a result, our proposed ensemble technique can contribute to the replacement of the missing values generated by environmental sensors, which can help to increase the reliability of environmental sensor data.

Ratio of Mediastinal Lymph Node SUV to Primary Tumor SUV in 18F-FDG PET/CT for Nodal Staging in Non-Small-Cell Lung Cancer.

PURPOSE: Following determination of the maximum standardized uptake values (SUVmax) of the mediastinal lymph nodes (SUV-LN) and of the primary tumor (SUV-T) on 18F-FDG PET/CT in patients with non-small-cell lung cancer (NSCLC), the aim of the study was to determine the value of the SUV-LN/SUV-T ratio in lymph node staging in comparison with that of SUV-LN. METHODS: We retrospectively reviewed a total of 289 mediastinal lymph node stations from 98 patients with NSCLC who were examined preoperatively for staging and subsequently underwent pathologic studies of the mediastinal lymph nodes. We determined SUV-LN and SUV-R for each lymph node station on 18F-FDG PET/CT and then classified each station into one of three groups based on SUV-T (low, medium and high SUV-T groups). Diagnostic performance was assessed based on receiver operating characteristic (ROC) curve analysis, and the optimal cut-off values that would best discriminate metastatic from benign lymph nodes were determined for each method. RESULTS: The average of SUV-R of malignant lymph nodes was significantly higher than that of benign lymph nodes (0.79 ± 0.45 vs. 0.36 ± 0.23, P < 0.0001). In the ROC curve analysis, the area under the curve (AUC) of SUV-R was significantly higher than that of SUV-LN in the low SUV-T group (0.885 vs. 0.810, P = 0.019). There were no significant differences between the AUCs of SUV-LN and of SUV-R in the medium and high SUV-T groups. The optimal cut-off value for SUV-R in the low SUV-T group was 0.71 (sensitivity 87.5 %, specificity 85.9 %). CONCLUSIONS: The SUV-R performed well in distinguishing between metastatic and benign lymph nodes. In particular, SUV-R was found to have a better diagnostic performance than SUV-LN in the low SUV-T group.

Correlation between Semi-Quantitative (18)F-FDG PET/CT Parameters and Ki-67 Expression in Small Cell Lung Cancer.

PURPOSE: The aim of this study was to evaluate the relationship between semiquantitative parameters on (18)F-FDG PET/CT including maximum standardized uptake value (SUVmax), mean standardized uptake value (SUVmean), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) and the expression level of Ki-67 in small-cell lung cancer (SCLC). METHODS: Ninety-four consecutive patients with SCLC were enrolled in this study. They underwent (18)F-FDG PET/CT for initial evaluation of SCLC, and we measured SUVmax, avgSUVmean, MTVsum, and TLGtotal on (18)F-FDG PET/CT images. The protein expression of Ki-67 was examined by immunohistochemical staining. RESULTS: Significant correlations were found between the MTVsum and Ki-67 labeling index (r = 0.254, p = 0.014) and the TLGtotal and Ki-67 labeling index (r = 0.239, p = 0.020). No correlation was found between the SUVmax and Ki-67 labeling index (r = 0.116, p = 0.264) and the avgSUVmean and Ki-67 labeling index (r = 0.031, p = 0.770). Dividing the Ki-67 expression level into three categories, it was suggested that increasing Ki-67 expression level caused a stepwise increase in the MTVsum and TLGtotal. (p = 0.028 and 0.039, respectively), but not the SUVmax and avgSUVmean (p = 0.526 and 0.729, respectively). CONCLUSION: In conclusion, the volume-based parameters of (18)F-FDG PET/CT correlate with immunohistochemical staining of Ki-67 in SCLC. Measurement of the MTVsum and TLGtotal by (18)F-FDG PET/CT might be a simple, noninvasive, and useful method to determine the proliferative potential of cancer cells.

Semi-Quantitative Analysis of Post-Transarterial Radioembolization (90)Y Microsphere Positron Emission Tomography Combined with Computed Tomography (PET/CT) Images in Advanced Liver Malignancy: Comparison With (99m)Tc Macroaggregated Albumin (MAA) Single Photon Emission Computed Tomography (SPECT).

OBJECTIVES: The purpose of this study is to evaluate the correlation between pretreatment planning technetium-99m ((99m)Tc) macroaggregated albumin (MAA) SPECT images and posttreatment transarterial radioembolization (TARE) yttirum-90 ((90)Y) PET/CT images by comparing the ratios of tumor-to-normal liver counts. METHODS: Fifty-two patients with advanced hepatic malignancy who underwent (90)Y microsphere radioembolization from January 2010 to December 2012 were retrospectively reviewed. Patients had undergone (99m)Tc MAA intraarterial injection SPECT for a pretreatment evaluation of microsphere distribution and therapy planning. After the administration of (90)Y microspheres, the patients underwent posttreatment (90)Y PET/CT within 24 h. For semiquantitative analysis, the tumor-to-normal uptake ratios in (90)Y PET/CT (TNR-yp) and (99m)Tc MAA SPECT (TNR-ms) as well as the tumor volumes measured in angiographic CT were obtained and analyzed. The relationship of TNR-yp and TNR-ms was evaluated by Spearman's rank correlation and Wilcoxon's matched pairs test. RESULTS: In a total of 79 lesions of 52 patients, the distribution of microspheres was well demonstrated in both the SPECT and PET/CT images. A good correlation was observed of between TNR-ms and TNR-yp (rho value = 0.648, p < 0.001). The TNR-yp (median 2.78, interquartile range 2.43) tend to show significantly higher values than TNR-ms (median 2.49, interquartile range of 1.55) (p = 0.012). The TNR-yp showed weak correlation with tumor volume (rho = 0.230, p = 0.041). CONCLUSIONS: The (99m)Tc MAA SPECT showed a good correlation with (90)Y PET/CT in TNR values, suggesting that (99m)Tc MAA can be used as an adequate pretreatment evaluation method. However, the (99m)Tc MAA SPECT image consistently shows lower TNR values compared to (90)Y PET/CT, which means the possibility of underestimation of tumorous uptake in the partition dosimetry model using (99m)Tc MAA SPECT. Considering that (99m)Tc MAA is the only clinically available surrogate marker for distribution of microsphere, we recommend measurement of tumorous uptake using (90)Y PET/CT should be included routinely in the posttherapeutic evaluation.

18F-FDG PET/CT of Bronchial Mucous Gland Adenoma.

Bronchial mucous gland adenoma is a very rare benign tumor that arises from the bronchial mucous-secreting glands. Its detection and appearance using F-FDG PET/CT has not been well characterized. We present a case of a 59-year-old man with FDG-avid mucous gland adenoma that mimicked lung cancer on F-FDG PET/CT.

Value of (18)F-FDG PET/CT in the Detection of Ovarian Malignancy.

PURPOSE: Ovarian cancer is a leading cause of gynecologic malignancy. As symptoms of ovarian cancer are nonspecific, only 20 % of ovarian cancers are diagnosed while they are still limited to the ovaries. Thus, early and accurate detection of disease is important for an improved prognosis. For the accurate and effective diagnosis of ovarian malignancy on (18)F-fluorodeoxyglucose ((18)F-FDG) positron emission tomography/computed tomography (PET/CT), we analyzed several parameters, including visual assessment. METHOD: A total of 51 peritoneal lesions in 19 patients who showed ovarian masses with diffuse peritoneal infiltration were enrolled. Twelve patients were confirmed to have ovarian malignancy and seven patients with benign disease by pathologic examination. All patients were examined by (18)F-FDG PET/CT, and an additional 2-h delayed (18)F-FDG PET/CT was also performed for 15 patients with 42 peritoneal lesions. We measured semiquantitative parameters including maximum and mean standardized uptake values (SUVmax, SUVmean), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) on a 1-h initial (18)F-FDG PET/CT image (Parameter1) and on a 2-h delayed image (Parameter2). Additionally, retention indices of each parameter were calculated, and each parameter among the malignant and benign lesions was compared by Mann-Whitney U test. We also assessed the visual characteristics of each peritoneal lesion, including metabolic extent, intensity, shape, heterogeneity, and total visual score. Associations between visual grades and malignancy were analyzed using linear by linear association methods. Moreover, a receiver operating characteristic (ROC) curve was analyzed to compare the effectiveness of significant parameters. RESULT: In a comparison between the malignant and benign groups in the analysis of 51 total peritoneal lesions, SUVmax1, SUVmean1, and TLG1 showed significant differences. Also, in the analysis of 42 peritoneal lesions that underwent an additional 2-h (18)F-FDG PET/CT examination, SUVmax1,2, SUVmean1,2, TLG2, and the RI of TLG showed significant differences between the malignant and benign groups. MTV did not show significant differences in either the analysis of 51 peritoneal lesions or of 42 lesions. Regarding visual assessments, metabolic intensity, shape, heterogeneity, and total visual score showed an association with malignancy. In the ROC analysis, the AUC of the visual score was larger than the AUC of other parameters in both the analyses of 51 peritoneal lesions and of 42 lesions. CONCLUSION: Although further study with a larger patient population is needed, the visual assessment of (18)F-FDG PET/CT imaging has a primary role in the detection of malignancy in ovarian cancer patients with assistance from other semi-quantitative parameters.

The role of interim 18F-FDG PET/CT in predicting early response to neoadjuvant chemotherapy in breast cancer.

AIM: The aim of this study was to prove the diagnostic value of interim 18F-Fluorodeoxyglucose-positron-emission tomography combined with computed tomography (PET/CT) scan for predicting pathological complete response (pCR) compared to other factors in neoadjuvant chemotherapy. PATIENTS AND METHODS: Twenty-seven patients with breast cancer were included in this retrospective study. They all underwent scheduled neoadjuvant chemotherapy. Patients underwent PET/CT at baseline, mid-point (interim), and preoperatively (after completion of chemotherapy). The metabolic response was calculated as follows: ΔStandardized uptake value (SUV)(%)=(1st SUV(max)-2nd SUV(max))/1st SUV(max) × 100. RESULTS: The change in SUVmax between baseline and interim PET/CT scans was significantly larger than between interim and preoperative PET/CT scan. An optimal cut-off ΔSUV value of 78.3% was proposed for discriminating patients with pCR from those without pCR. Metabolic CR, defined as a change of SUV(max) greater than the cut-off value, can predict pCR according to univariate analysis (p=0.012; Relative risk (RR)=25.3). Furthermore, metabolic CR was the most powerful factor for predicting pCR than other possible factors according to multivariate analysis (p=0.003). CONCLUSION: It is possible to use interim (18)F-FDG PET-CT as an effective method to predict early response in patients with breast cancer treated with neoadjuvant chemotherapy.

The Clinical Role of Dual-Time-Point (18)F-FDG PET/CT in Differential Diagnosis of the Thyroid Incidentaloma.

Thyroid incidentalomas are common findings during imaging studies including (18)F-fluorodeoxyglucose ((18)F-FDG) positron emission tomography/computed tomography (PET/CT) for cancer evaluation. Although the overall incidence of incidental thyroid uptake detected on PET imaging is low, clinical attention should be warranted owing to the high incidence of harboring primary thyroid malignancy. We retrospectively reviewed 2,368 dual-time-point (18)F-FDG PET/CT cases that were undertaken for cancer evaluation from November 2007 to February 2009, to determine the clinical impact of dual-time-point imaging in the differential diagnosis of thyroid incidentalomas. Focal thyroid uptake was identified in 64 PET cases and final diagnosis was clarified with cytology/histology in a total of 27 patients with (18)F-FDG-avid incidental thyroid lesion. The maximum standardized uptake value (SUVmax) of the initial image (SUV1) and SUVmax of the delayed image (SUV2) were determined, and the retention index (RI) was calculated by dividing the difference between SUV2 and SUV1 by SUV1 (i.e., RI = [SUV2 - SUV1]/SUV1 × 100). These indices were compared between patient groups that were proven to have pathologically benign or malignant thyroid lesions. There was no statistically significant difference in SUV1 between benign and malignant lesions. SUV2 and RI of the malignant lesions were significantly higher than the benign lesions. The areas under the ROC curves showed that SUV2 and RI have the ability to discriminate between benign and malignant thyroid lesions. The predictability of dual-time-point PET parameters for thyroid malignancy was assessed by ROC curve analyses. When SUV2 of 3.9 was used as cut-off threshold, malignancy on the pathology could be predicted with a sensitivity of 87.5 % and specificity of 75 %. A thyroid lesion that shows RI greater than 12.5 % could be expected to be malignant (sensitivity 88.9 %, specificity 66.3 %). All malignant lesions showed an increase in SUVmax on the delayed images compared with the initial images. But in the group of benign lesions, 37.5 % (6/16) showed a decrease or no change in SUVmax. Dual-time-point (18)F-FDG PET/CT, obtaining additional images 2 h after injection, seems to be a complementary method for the differentiation between malignancy and benignity of incidental thyroid lesions.