Artificial Intelligence Deep Learning Research Articles

Readiness for Artificial Intelligence in Biobanking

Readiness for Artificial Intelligence in Biobanking

Artificial Intelligence Assisted Pharmacophore Design for Philadelphia Chromosome-Positive Leukemia with Gamma-Tocotrienol: A Toxicity Comparison Approach with Asciminib

BCR-ABL1 is a fusion protein as a result of a unique chromosomal translocation (producing the so-called Philadelphia chromosome) that serves as a clinical biomarker primarily for chronic myeloid leukemia (CML); the Philadelphia chromosome also occurs, albeit rather rarely, in other types of leukemia. This fusion protein has proven itself to be a promising therapeutic target. Exploiting the natural vitamin E molecule gamma-tocotrienol as a BCR-ABL1 inhibitor with deep learning artificial intelligence (AI) drug design, this study aims to overcome the present toxicity that embodies the currently provided medications for (Ph+) leukemia, especially asciminib. Gamma-tocotrienol was employed in an AI server for drug design to construct three effective de novo drug compounds for the BCR-ABL1 fusion protein. The AIGT's (Artificial Intelligence Gamma-Tocotrienol) drug-likeliness analysis among the three led to its nomination as a target possibility. The toxicity assessment research comparing AIGT and asciminib demonstrates that AIGT, in addition to being more effective nonetheless, is also hepatoprotective. While almost all CML patients can achieve remission with tyrosine kinase inhibitors (such as asciminib), they are not cured in the strict sense. Hence it is important to develop new avenues to treat CML. We present in this study new formulations of AIGT. The docking of the AIGT with BCR-ABL1 exhibited a binding affinity of -7.486 kcal/mol, highlighting the AIGT's feasibility as a pharmaceutical option. Since current medical care only exclusively cures a small number of patients of CML with utter toxicity as a pressing consequence, a new possibility to tackle adverse instances is therefore presented in this study by new formulations of natural compounds of vitamin E, gamma-tocotrienol, thoroughly designed by AI. Even though AI-designed AIGT is effective and adequately safe as computed, in vivo testing is mandatory for the verification of the in vitro results.

A trusted decision fusion approach for the power internet of things with federated learning

The power Internet of Things generates a large amount of data at any time, which can be transformed into precise decisions with the help of artificial intelligence approaches. However, the owners of electricity data with boundaries are often concerned with data leakage. Therefore, when building models that feed big data into deep learning artificial intelligence approaches for precise decision-making within the power Internet of Things, it is essential to ensure the data’s security. This paper proposes a framework for model training and decision making system applied to the field of power IoT, which consists of two parts: data security sharing and hierarchical decision making. The proposed framework utilizes a homomorphic encryption-based federated learning approach to protect private data from leakage. In addition, data augmentation and transfer learning are used to address the issue of insufficient local training data. Moreover, the framework attempts to incorporate the specialized nature of traditional manual decision-making in the power field by fusing expert and model values after stratifying the requirements. Experiments are conducted to simulate the decision requirements in the field of power Internet of Things (e.g., electrical material identification), using image recognition as an example. The experimental results show that the proposed models can achieve high accuracy rates and the fusion approach is feasible.

Improving detection of impacted animal bones on lateral neck radiograph using a deep learning artificial intelligence algorithm

ObjectiveWe aimed to develop a deep learning artificial intelligence (AI) algorithm to detect impacted animal bones on lateral neck radiographs and to assess its effectiveness for improving the interpretation of lateral neck radiographs.MethodsLateral neck radiographs were retrospectively collected for patients with animal bone impaction between January 2010 and March 2020. Radiographs were then separated into training, validation, and testing sets. A total of 1733 lateral neck radiographs were used to develop the deep learning algorithm. The testing set was assessed for the stand-alone deep learning AI algorithm and for human readers (radiologists, radiology residents, emergency physicians, ENT physicians) with and without the aid of the AI algorithm. Another radiograph cohort, collected from April 1, 2020, to June 30, 2020, was analyzed to simulate clinical application by comparing the deep learning AI algorithm with radiologists’ reports.ResultsIn the testing set, the sensitivity, specificity, and accuracy of the AI model were 96%, 90%, and 93% respectively. Among the human readers, all physicians of different subspecialties achieved a higher accuracy with AI-assisted reading than without. In the simulation set, among the 20 cases positive for animal bones, the AI model accurately identified 3 more cases than the radiologists’ reports.ConclusionOur deep learning AI model demonstrated a higher sensitivity for detection of animal bone impaction on lateral neck radiographs without an increased false positive rate. The application of this model in a clinical setting may effectively reduce time to diagnosis, accelerate workflow, and decrease the use of CT.

Implementation of deep learning artificial intelligence in vision-threatening disease screenings for an underserved community during COVID-19

Introduction Age-related macular degeneration, diabetic retinopathy, and glaucoma are vision-threatening diseases that are leading causes of vision loss. Many studies have validated deep learning artificial intelligence for image-based diagnosis of vision-threatening diseases. Our study prospectively investigated deep learning artificial intelligence applications in student-run non-mydriatic screenings for an underserved, primarily Hispanic community during COVID-19. Methods Five supervised student-run community screenings were held in West New York, New Jersey. Participants underwent non-mydriatic 45-degree retinal imaging by medical students. Images were uploaded to a cloud-based deep learning artificial intelligence for vision-threatening disease referral. An on-site tele-ophthalmology grader and remote clinical ophthalmologist graded images, with adjudication by a senior ophthalmologist to establish the gold standard diagnosis, which was used to assess the performance of deep learning artificial intelligence. Results A total of 385 eyes from 195 screening participants were included (mean age 52.43 ± 14.5 years, 40.0% female). A total of 48 participants were referred for at least one vision-threatening disease. Deep learning artificial intelligence marked 150/385 (38.9%) eyes as ungradable, compared to 10/385 (2.6%) ungradable as per the human gold standard (p < 0.001). Deep learning artificial intelligence had 63.2% sensitivity, 94.5% specificity, 32.0% positive predictive value, and 98.4% negative predictive value in vision-threatening disease referrals. Deep learning artificial intelligence successfully referred all 4 eyes with multiple vision-threatening diseases. Deep learning artificial intelligence graded images (35.6 ± 13.3 s) faster than the tele-ophthalmology grader (129 ± 41.0) and clinical ophthalmologist (68 ± 21.9, p < 0.001). Discussion Deep learning artificial intelligence can increase the efficiency and accessibility of vision-threatening disease screenings, particularly in underserved communities. Deep learning artificial intelligence should be adaptable to different environments. Consideration should be given to how deep learning artificial intelligence can best be utilized in a real-world application, whether in computer-aided or autonomous diagnosis.

Predicting Resident Intention Using Machine Learning

The smart home environment is embedded with technologies like machine learning, deep learning artificial intelligence and internet of things. The services intended by the resident are provided by the smart home environment through interactions with the home appliances. In recent years, predicting user intention and behaviour in real-time applications like e-commerce, smart home, and entertainment, healthcare has appeared as a popular research domain. Contextual modalities such as speech, activity, emotion, object affordances, and physiological parameters are the features through which the intention of the resident can be predicted concerning the home appliances like door, television, light, etc. Other examples of contextual modalities include gesture and mood. Home appliances can be made smart by embedding intelligent algorithms which in turn helps them to understand the residents' intentions. This creates a dynamic relationship between the resident &amp; home appliances thereby improving the resident’s satisfaction level. For example, the context: Resident issuing the command ‘OPEN’ by standing in front of the door illustrates that the intention is to get the door opened automatically. Contextual modalities are the main source for a system that works based on resident intention prediction. In this paper, an effort has been made to predict the resident intentions by applying machine learning algorithms like Decision Tree-based ID3, Naive Bayes classifier, and Rule-based classifier on context-aware door dataset.

Predicting Resident Intention Using Machine Learning

The smart home environment is embedded with technologies like machine learning, deep learning artificial intelligence and internet of things. The services intended by the resident are provided by the smart home environment through interactions with the home appliances. In recent years, predicting user intention and behaviour in real-time applications like e-commerce, smart home, and entertainment, healthcare has appeared as a popular research domain. Contextual modalities such as speech, activity, emotion, object affordances, and physiological parameters are the features through which the intention of the resident can be predicted concerning the home appliances like door, television, light, etc. Other examples of contextual modalities include gesture and mood. Home appliances can be made smart by embedding intelligent algorithms which in turn helps them to understand the residents' intentions. This creates a dynamic relationship between the resident &amp; home appliances thereby improving the resident’s satisfaction level. For example, the context: Resident issuing the command ‘OPEN’ by standing in front of the door illustrates that the intention is to get the door opened automatically. Contextual modalities are the main source for a system that works based on resident intention prediction. In this paper, an effort has been made to predict the resident intentions by applying machine learning algorithms like Decision Tree-based ID3, Naive Bayes classifier, and Rule-based classifier on context-aware door dataset.

Performance of an artificial intelligence automated system for diabetic eye screening in a large English population.

A diabetic eye screening programme has huge value in reducing avoidable sight loss by identifying diabetic retinopathy at a stage when it can be treated. Artificial intelligence automated systems can be used for diabetic eye screening but are not employed in the national English Diabetic Eye Screening Programme. The aim was to report the performance of a commercially available deep-learning artificial intelligence software in a large English population. 9817 anonymised image sets from 10,000 consecutive diabetic eye screening episodes were presented to an artificial intelligence software. The sensitivity and specificity of the artificial intelligence system for detecting diabetic retinopathy were determined using the diabetic eye screening programme manual grade according to national protocols as the reference standard. For no diabetic retinopathy versus any diabetic retinopathy, the sensitivity of the artificial intelligence grading system was 69.7% and specificity 92.2%. The performance of the artificial intelligence system was superior for no or mild diabetic retinopathy versus significant or referrable diabetic retinopathy with a sensitivity of 95.4% and specificity of 92.0%. No cases were identified in which the artificial intelligence grade had missed significant diabetic retinopathy. The performance of a commercially available deep-learning artificial intelligence system for identifying diabetic retinopathy in an English national Diabetic Eye Screening Programme is presented. Using the pre-defined settings artificial intelligence performance was highest when identifying diabetic retinopathy which requires an action by the screening programme.

Sex determination using color fundus parameters in older adults of Kumejima population study.

Deep learning artificial intelligence can determine the sex using only fundus photographs. However, the factors used by deep learning to determine the sex are not visible. Therefore, the purpose of the study was to determine whether the sex of an older individual can be determined by regression analysis of their color fundus photographs (CFPs). Forty-two parameters were analyzed by regression analysis using 1653 CFPs of normal subjects in the Kumajima study. The parameters included the mean values of red, green, and blue intensities; the tessellation fundus index; the optic disc ovality ratio; the papillomacular angle; and the retinal vessel angles. Finally, the L2 regularized binomial logistic regression was used to predict the sex using all the parameters, and the diagnostic ability was assessed through the leave-one-cross-validation. The mean age of the 838 men and 815 women were 52.8 and 54.0years, respectively. The ovality ratio and retinal artery angles in women were significantly smaller than that in men. The green intensity at all locations for the women were significantly higher than that of men (P < 0.001). The discrimination accuracy rate assessed by the area-under-the-curve was 80.4%. Our methods can determine the sex from the CFPs of the adult with an accuracy of 80.4%. The ovality ratio, retinal vessel angles, tessellation, and the green intensities of the fundus are important factors to identify the sex in individuals over 40years old.

Development of a tongue image-based machine learning tool for the diagnosis of gastric cancer: a prospective multicentre clinical cohort study

Tongue images (the colour, size and shape of the tongue and the colour, thickness and moisture content of the tongue coating), reflecting the health state of the whole body according to the theory of traditional Chinese medicine (TCM), have been widely used in China for thousands of years. Herein, we investigated the value of tongue images and the tongue coating microbiome in the diagnosis of gastric cancer (GC). From May 2020 to January 2021, we simultaneously collected tongue images and tongue coating samples from 328 patients with GC (all newly diagnosed with GC) and 304 non-gastric cancer (NGC) participants in China, and 16S rDNA was used to characterize the microbiome of the tongue coating samples. Then, artificial intelligence (AI) deep learning models were established to evaluate the value of tongue images and the tongue coating microbiome in the diagnosis of GC. Considering that tongue imaging is more convenient and economical as a diagnostic tool, we further conducted a prospective multicentre clinical study from May 2020 to March 2022 in China and recruited 937 patients with GC and 1911 participants with NGC from 10 centres across China to further evaluate the role of tongue images in the diagnosis of GC. Moreover, we verified this approach in another independent external validation cohort that included 294 patients with GC and 521 participants with NGC from 7 centres. This study is registered at ClinicalTrials.gov, NCT01090362. For the first time, we found that both tongue images and the tongue coating microbiome can be used as tools for the diagnosis of GC, and the area under the curve (AUC) value of the tongue image-based diagnostic model was 0.89. The AUC values of the tongue coating microbiome-based model reached 0.94 using genus data and 0.95 using species data. The results of the prospective multicentre clinical study showed that the AUC values of the three tongue image-based models for GCs reached 0.88-0.92 in the internal verification and 0.83-0.88 in the independent external verification, which were significantly superior to the combination of eight blood biomarkers. Our results suggest that tongue images can be used as a stable method for GC diagnosis and are significantly superior to conventional blood biomarkers. The three kinds of tongue image-based AI deep learning diagnostic models that we developed can be used to adequately distinguish patients with GC from participants with NGC, even early GC and precancerous lesions, such as atrophic gastritis (AG). The National Key R&D Program of China (2021YFA0910100), Program of Zhejiang Provincial TCM Sci-tech Plan (2018ZY006), Medical Science and Technology Project of Zhejiang Province (2022KY114, WKJ-ZJ-2104), Zhejiang Provincial Research Center for Upper Gastrointestinal Tract Cancer (JBZX-202006), Natural ScienceFoundation of Zhejiang Province (HDMY22H160008), Science and Technology Projects of Zhejiang Province (2019C03049), National Natural Science Foundation of China (82074245, 81973634, 82204828), and Chinese Postdoctoral Science Foundation (2022M713203).

Effect of 320-Row Computed Tomography Acquisition Technology on Coronary Computed Tomography Angiography-Derived Fractional Flow Reserve Based on Machine Learning: Systolic and Diastolic Scan Acquisition.

The aim of the study is to investigate the performance of coronary computed tomography angiography (CCTA)-derived fractional flow reserve (CT-FFR) in the same patient evaluated by different systolic and diastolic scans, aiming to explore whether 320-slice CT scanning acquisition protocol has an impact on CT-FFR value. One hundred forty-six patients with suspected coronary artery stenosis who underwent CCTA examination were included into the study. The prospective electrocardiogram gated trigger sequence scan was performed and electrocardiogram editors selected 2 optimal phases of systolic phase (preset collection trigger at 25% of R-R interval) and diastolic phase (preset collection trigger at 75% of R-R interval) for reconstruction. The lowest CT-FFR value (the CT-FFR value at the distal end of each vessel) and the lesion CT-FFR value (at 2 cm distal to the stenosis) after coronary artery stenosis were calculated for each vessel. The difference of CT-FFR values between the 2 scanning techniques was compared using paired Wilcoxon signed-rank test. Pearson correlation value and Bland-Altman were performed to evaluate the consistency of CT-FFR values. A total of 366 coronary arteries from the remaining 122 patients were analyzed. There was no significant difference regarding the lowest CT-FFR values between systole phase and diastole phase across all vessels. In addition, there was no significant difference in the lesion CT-FFR value after coronary artery stenosis between systole phase and diastole phase across all vessels. The CT-FFR value between the 2 reconstruction techniques had excellent correlation and minimal bias in all groups. The correlation coefficient of the lesion CT-FFR values for left anterior descending branch, left circumflex branch, and right coronary artery were 0.86, 0.84, and 0.76, respectively. Coronary computed tomography angiography-derived fractional flow reserve based on artificial intelligence deep learning neural network has stable performance, is not affected by the acquisition phase technology of 320-slice CT scan, and has high consistency with the evaluation of hemodynamics after coronary artery stenosis.

Automatic placental and fetal volume estimation by a convolutional neural network

IntroductionWe aimed to develop an artificial intelligence (AI) deep learning algorithm to efficiently estimate placental and fetal volumes from magnetic resonance (MR) scans. MethodsManually annotated images from an MRI sequence was used as input to the neural network DenseVNet. We included data from 193 normal pregnancies at gestational week 27 and 37. The data were split into 163 scans for training, 10 scans for validation and 20 scans for testing. The neural network segmentations were compared to the manual annotation (ground truth) using the Dice Score Coefficient (DSC). ResultsThe mean ground truth placental volume at gestational week 27 and 37 was 571 cm3 (Standard Deviation (SD) 293 cm3) and 853 cm3 (SD 186 cm3), respectively. Mean fetal volume was 979 cm3 (SD 117 cm3) and 2715 cm3 (SD 360 cm3). The best fitting neural network model was attained at 22,000 training iterations with mean DSC 0.925 (SD 0.041). The neural network estimated mean placental volumes at gestational week 27–870 cm3 (SD 202 cm3) (DSC 0.887 (SD 0.034), and to 950 cm3 (SD 316 cm3) at gestational week 37 (DSC 0.896 (SD 0.030)). Mean fetal volumes were 1292 cm3 (SD 191 cm3) and 2712 cm3 (SD 540 cm3), with mean DSC of 0.952 (SD 0.008) and 0.970 (SD 0.040). The time spent for volume estimation was reduced from 60 to 90 min by manual annotation, to less than 10 s by the neural network. ConclusionThe correctness of neural network volume estimation is comparable to human performance; the efficiency is substantially improved.

Complimentary genomic, pathologic, and artificial intelligence analysis on low-grade noninvasive bladder cancer to predict downstream recurrence.

553 Background: Low-grade noninvasive (LGTa) bladder cancer is a relatively quiescent but heterogenous malignancy, characterized by downstream recurrences requiring repeated transurethral resections and frequent surveillance. Investigations to elucidate drivers of recurrence have been sparse, but will help risk-stratify patients with LGTa and allow augmentation of follow up protocols. Methods: Patients with LGTa index tumors were stratified by those with no downstream recurrences (nonrecurrent) vs. those with later recurrences (recurrent). RNA sequencing identified differentially expressed genes (DEGs), deconvoluted for cell-type using xCell. Pathologic analysis was performed by a genitourinary pathologist, then a deep-learning artificial intelligence (AI) platform was leveraged to correlate recurrence risk and recurrence-free survival (RFS) based on deep-learning algorithm of segmented nuclei. Results: Thirty index bladder tumors/patients were identified, 18 (60%) of which had later recurrence (Table). There were 238 DEGs recognized, with recurrent tumors expressing signatures for epithelial mesenchymal transition, myogenesis, TNFα signaling via NFκB, and angiogenesis. Recurrent tumors also demonstrated a higher tissue micoenvironment, stroma, and cancer-associated fibroblast score. Pathologic TME analysis validated these findings, with recurrent tumors demonstrating a higher frequency of inverted growth pattern and a higher median stroma percentage. Finally, the AI-derived signature was predictive of recurrence and risk-stratified the cohort (HR= 5.43 [95% CI 1.1-26.76]) for predicting high vs. low risk of recurrence. Patients in the high risk group had a 87.5% recurrence rate while those in the low risk group had a 28.5% recurrence rate (p&lt;0.01). Conclusions: Using a multi-disciplinary approach, we identified key signatures in recurrent LGTa bladder cancer. Characterization of these factors is a critical first step in the risk-stratification of LGTa tumors, and may allow risk-stratification of surveillance protocols and identification of possible targets for chemoprevention trials. [Table: see text]

Application of artificial intelligence in predicting lymph node metastasis in breast cancer.

Breast cancer is a leading cause of death for women globally. A characteristic of breast cancer includes its ability to metastasize to distant regions of the body, and the disease achieves this through first spreading to the axillary lymph nodes. Traditional diagnosis of axillary lymph node metastasis includes an invasive technique that leads to potential clinical complications for breast cancer patients. The rise of artificial intelligence in the medical imaging field has led to the creation of innovative deep learning models that can predict the metastatic status of axillary lymph nodes noninvasively, which would result in no unnecessary biopsies and dissections for patients. In this review, we discuss the success of various deep learning artificial intelligence models across multiple imaging modalities in their performance of predicting axillary lymph node metastasis.

Pattern Recognition and Deep Learning Technologies, Enablers of Industry 4.0, and Their Role in Engineering Research

The purpose of this study is to summarize the pattern recognition (PR) and deep learning (DL) artificial intelligence methods developed for the management of data in the last six years. The methodology used for the study of documents is a content analysis. For this study, 186 references are considered, from which 120 are selected for the literature review. First, a general introduction to artificial intelligence is presented, in which PR/DL methods are studied and their relevance to data management evaluated. Next, a literature review is provided of the most recent applications of PR/DL, and the capacity of these methods to process large volumes of data is evaluated. The analysis of the literature also reveals the main applications, challenges, approaches, advantages, and disadvantages of using these methods. Moreover, we discuss the main measurement instruments; the methodological contributions by study areas and research domain; and major databases, journals, and countries that contribute to the field of study. Finally, we identify emerging research trends, their limitations, and possible future research paths.

Improvement of Concrete Crack Segmentation Performance Using Stacking Ensemble Learning

Signs of functional loss due to the deterioration of structures are primarily identified from cracks occurring on the surface of structures, and continuous monitoring of structural cracks is essential for socially important structures. Recently, many structural crack monitoring technologies have been developed with the development of deep-learning artificial intelligence (AI). In this study, stacking ensemble learning was applied to predict the structural cracks more precisely. A semantic segmentation model was primarily used for crack detection using a deep learning AI model. We studied the crack-detection performance by training UNet, DeepLabV3, DeepLabV3+, DANet, and FCN-8s. Owing to the unsuitable crack segmentation performance of the FCN-8s, stacking ensemble learning was conducted with the remaining four models. Individual models yielded an intersection over union (IoU) score ranging from approximately 0.4 to 0.6 for the test dataset. However, when the metamodel completed with stacking ensemble learning was used, the IoU score was 0.74, indicating a high-performance improvement. A total of 1235 test images was acquired with drones on the sea bridge, and the stacking ensemble model showed an IoU of 0.5 or higher for 64.4% of the images.

Automatic Detection, Classification, and Grading of Lumbar Intervertebral Disc Degeneration Using an Artificial Neural Network Model.

Intervertebral disc degeneration (IDD) is a common cause of symptomatic axial low back pain. Magnetic resonance imaging (MRI) is currently the standard for the investigation and diagnosis of IDD. Deep learning artificial intelligence models represent a potential tool for rapidly and automatically detecting and visualizing IDD. This study investigated the use of deep convolutional neural networks (CNNs) for the detection, classification, and grading of IDD. Sagittal images of 1000 IDD T2-weighted MRI images from 515 adult patients with symptomatic low back pain were separated into 800 MRI images using annotation techniques to create a training dataset (80%) and 200 MRI images to create a test dataset (20%). The training dataset was cleaned, labeled, and annotated by a radiologist. All lumbar discs were classified for disc degeneration based on the Pfirrmann grading system. The deep learning CNN model was used for training in detecting and grading IDD. The results of the training with the CNN model were verified by testing the grading of the dataset using an automatic model. The training dataset of the sagittal intervertebral disc lumbar MRI images found 220 IDDs of grade I, 530 of grade II, 170 of grade III, 160 of grade IV, and 20 of grade V. The deep CNN model was able to detect and classify lumbar IDD with an accuracy of more than 95%. The deep CNN model can reliably automatically grade routine T2-weighted MRIs using the Pfirrmann grading system, providing a quick and efficient method for lumbar IDD classification.

Deep learning-based multifeature integration robustly predicts central lymph node metastasis in papillary thyroid cancer

BackgroundFew highly accurate tests can diagnose central lymph node metastasis (CLNM) of papillary thyroid cancer (PTC). Genetic sequencing of tumor tissue has allowed the targeting of certain genetic variants for personalized cancer therapy development.MethodsThis study included 488 patients diagnosed with PTC by ultrasound-guided fine-needle aspiration biopsy, collected clinicopathological data, analyzed the correlation between CLNM and clinicopathological features using univariate analysis and binary logistic regression, and constructed prediction models.ResultsBinary logistic regression analysis showed that age, maximum diameter of thyroid nodules, capsular invasion, and BRAF V600E gene mutation were independent risk factors for CLNM, and statistically significant indicators were included to construct a nomogram prediction model, which had an area under the curve (AUC) of 0.778. A convolutional neural network (CNN) prediction model built with an artificial intelligence (AI) deep learning algorithm achieved AUCs of 0.89 in the training set and 0.78 in the test set, which indicated a high prediction efficacy for CLNM. In addition, the prediction models were validated in the subclinical metastasis and clinical metastasis groups with high sensitivity and specificity, suggesting the broad applicability of the models. Furthermore, CNN prediction models were constructed for patients with nodule diameters less than 1 cm. The AUCs in the training set and test set were 0.87 and 0.76, respectively, indicating high prediction efficacy.ConclusionsThe deep learning-based multifeature integration prediction model provides a reference for the clinical diagnosis and treatment of PTC.

Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model.

Diabetic peripheral neuropathy (DPN) is the leading cause of neuropathy worldwide resulting in excess morbidity and mortality. We aimed to develop an artificial intelligence deep learning algorithm to classify the presence or absence of peripheral neuropathy (PN) in participants with diabetes or pre-diabetes using corneal confocal microscopy (CCM) images of the sub-basal nerve plexus. A modified ResNet-50 model was trained to perform the binary classification of PN (PN+) versus no PN (PN-) based on the Toronto consensus criteria. A dataset of 279 participants (149 PN-, 130 PN+) was used to train (n = 200), validate (n = 18), and test (n = 61) the algorithm, utilizing one image per participant. The dataset consisted of participants with type 1 diabetes (n = 88), type 2 diabetes (n = 141), and pre-diabetes (n = 50). The algorithm was evaluated using diagnostic performance metrics and attribution-based methods (gradient-weighted class activation mapping (Grad-CAM) and Guided Grad-CAM). In detecting PN+, the AI-based DLA achieved a sensitivity of 0.91 (95%CI: 0.79-1.0), a specificity of 0.93 (95%CI: 0.83-1.0), and an area under the curve (AUC) of 0.95 (95%CI: 0.83-0.99). Our deep learning algorithm demonstrates excellent results for the diagnosis of PN using CCM. A large-scale prospective real-world study is required to validate its diagnostic efficacy prior to implementation in screening and diagnostic programmes.

Automatic Diagnosis of COVID-19 Pneumonia using Artificial Intelligence Deep Learning Algorithm Based on Lung Computed Tomography Images.

The lung computed tomography (CT) scan contains valuable information and patterns that provide the possibility of early diagnosis of COVID-19 disease as a global pandemic by the image processing software. In this research, based on deep learning of artificial intelligence, the software has been designed that is used clinically to diagnose COVID-19 disease with high accuracy. Convolutional neural network architecture developed based on Inception-V3 for deep learning of lung image patterns, feature extraction, and image classification. The theory of transfer learning was utilized to increase the learning power of the system. Changes applied in the network layers to increase the detection power. The process of learning was repeated 30 times. All diagnostic statistical parameters of the diagnostic were analyzed to validate the software. Based on the data of Imam Khomeini Hospital in Sari, the validity, sensitivity, and accuracy of the software in diagnosing of affected to COVID-19 and nonaffected to it were obtained 98%, 98%, and 98%, respectively. Diagnostic statistical parameters on some data were 100%. The modified algorithm of Inception-V3 applied to heterogeneous data also had acceptable precision. The proposed basic architecture of Inception-v3 utilized for this research has an admissible speed and exactness in learning CT scan images of patients' lungs, and diagnosis of COVID-19 pneumonia, which can be utilized clinically as a powerful diagnostic tool.