Prognostic Imaging Research Articles

Ultrasound Radiomics-Guided Iliac Fascia Block on Postoperative Cognitive Dysfunction in Elderly Patients Undergoing Hip Surgery.

Objective Elderly patients with hip surgery are prone to postoperative cognitive dysfunction (POCD), leading to health management difficulties. This study is aimed at investigating the effect of ultrasound radiomics-guided iliac fascia block on POCD. Methods A total of 67 cases of patients who had undergone hip joint surgery were divided into a training set (n = 47) and a validation set (radiomics-guided group, n = 20). The patients were intervened with ultrasound radiomics-guided iliac fascia block, and the maximum relevance minimum redundancy sifts out the image omics features obtained from 2D ultrasound images of patients. Another 20 patients undergone general anesthesia served as control. The incidence of POCD, the total amount of fentanyl, the visual analogue score (VAS) at different time points, and the levels of CRP and NSE in plasma were compared between the two groups. Results The AUC on the training and validation sets were higher than 0.940. The incidence of POCD in the radiomics-guided and general anesthesia group was 5% and 30%, respectively (P = 0.037). Compared with the general anesthesia group, the dosage of fentanyl in the radiomics-guided was lower, the VAS score at 6 h, 1 d, and 2 d after operation was smaller, and the levels of CRP and NSE were lower (all P < 0.05). Conclusions For elderly patients with hip surgery, the ultrasound radiomics-guided iliac fascia block can reduce the incidence of POCD and improve the effect of nerve block.

Progress in Precision Medicine of Radiomics in Abdominal Tumors Practice

With the advent of the era of artificial intelligence, as an emerging technology, radiomics can extract a large amount of quantitative information describing the physiological condition and phenotypic characteristics of tumors with high throughput from the massive data of CT, MRI and other imaging tomography, and analyze these high-dimensional imaging omics features containing disease pathophysiological information can be used to accurately determine tumor differentiation, staging, and predict tumor behavior, which has broad application prospects. This article aims to introduce the technical principles of radiomics and its abdominal tumor application status, and to prospect its application prospects in pediatric abdominal neuroblastoma.

Construction of a Diagnostic Model for Lymph Node Metastasis of the Papillary Thyroid Carcinoma Using Preoperative Ultrasound Features and Imaging Omics.

In this paper, we mainly adopted 337 patients who had undergone the surgery on lymph node metastasis of papillary thyroid carcinoma (PTC) as the sample population. In order to provide clinical reference for the intelligent decision-making in treatment plan and improvement of prognosis, we utilized ultrasound features and imaging features to construct five early diagnosis models for patients based on the ultrasound features, imaging features, and combined features. The model integrated with broad learning system (BLS) showed the best performance, with the area under the curve (AUC) of 0.857 (95% confidence interval (CI): 0.811–0.902)) and the accuracy of 0.805 (95% CI: 0.759–0.850). For demographic and clinical features, the prediction effect was also good, with the AUC more than 0.700.

Research progress in CT-based radiomics constructing hypopharyngeal cancer and multisystem tumor prediction model

Radiomics, a technique for quantitative analysis of tumor imaging information through high-throughput extraction, uses a non-invasive way to capture a large number of internal heterogeneity characteristics of tumors, providing imaging basis for tumor staging and typing, tumor invasion site and distant metastasis, postoperative induction chemotherapy and prognosis, and providing new ideas and new thinking for the field of personalized precision medicine of tumors. This review aims to briefly summarize the latest research progress of imaging omics in the diagnosis and treatment design of head and neck tumor, and to discuss the research progress of constructing the treatment plan and prognosis evaluation model of hypopharyngeal cancer based on imaging omics, and to predict and forecast its development direction and clinical application.

Application of CT Imaging in Differential Diagnosis and Nursing of Endocrine Tumors.

In order to investigate the value of preoperative X-ray computed tomography (CT) in predicting the pathological grade of pancreatic neuroendocrine tumors. This paper retrospectively analyzed the CT image examination of pancreatic neuroendocrine tumors, the image characteristics of G-NEC detected by CT image, and the detection of GST by spiral CT. In order to clearly diagnose and evaluate the size and scope of the focus, whether there is adjacent tissue invasion, metastasis, and treatment effect, CT, MR, PET-CT, nuclide specific imaging, and other imaging methods are widely used in the medical treatment of pNEN patients. These imaging methods have the advantages of noninvasive, rapid imaging, objective image medium, and strong repeatability. If the pathological grade of pNEN patients can be obtained by imaging examination before operation, it will be of great benefit to the formulation of treatment strategies and the prediction of clinical outcomes. Combining CT image performance with imaging omics characteristics to establish a prediction model that can develop a better auxiliary decision-making tool for clinical practice. Different pathological grades prompt clinicians to provide personalized and accurate medical treatment for patients, and reduce excessive medical treatment or wrong judgment caused by unclear preoperative diagnostic information.

MRI Imaging Omics and Risk Factors Analysis of PWMD in Premature Infants Based on Fuzzy Clustering Algorithm.

The magnetic resonance imaging (MRI) characteristics of periventricular white matter damage (PWMD) in premature infants using the fuzzy c-means clustering algorithm (FCM) is explored, and the influencing factors are further clarified. A total of 100 premature infants admitted to the neonatal department of our hospital from February 2020 to February 2022 are selected for in-depth investigation. According to the occurrence of PWMD, they are divided into the PWMD group and the simple premature delivery group, with 50 cases in each group. All preterm infants are examined by MRI and the changes in image characteristics and apparent diffusion coefficient (ADC) values are analyzed. Clinical information of the subjects is collected and the influencing factors of PWMD in preterm infants are analyzed by multivariate regression analysis. In the first magnetic resonance imaging (MRI) examination, the cases of punctured, clustered, and linear lesions are 28 cases, 12 cases, and 10 cases, respectively. The experimental results showed that PWMD of preterm infants presented punctate, clustered, and high linear T1 signal MRI manifestations, which caused a downward trend of ADC value, and caused respiratory distress, low birth weight, premature rupture of membranes, respiratory tract infection, and other risk symptoms.

Computerized Tomography Imaging Omics under Iterative Reconstruction Algorithm in Diagnosis of Gastric Cancer

This study aimed to explore the application value of computed tomography (CT) imaging radiomics based on a sinogram-affirmed iterative reconstruction algorithm (SAFIRE) in the diagnosis of gastric cancer. 59 patients who were clinically diagnosed with gastric cancer were selected as research objects and arranged CT examinations. The images obtained were optimized by the SAFIRE for the staging of gastric cancer. The pathological biopsy results were used as the gold standard to evaluate its diagnostic effect and compared with the filtered back-projection (FBP) method. The results showed that the carrier-to-noise ratio (CNR) (0.979) and signal-to-noise ratio (SNR) (0.967) of the CT image after the algorithm processing were significantly higher than those (0.781, 0.744) before ( P &lt; 0.05 ). There was no significant difference in CT values between the FBP algorithm and S1, S2, and S3 ( P &gt; 0.05 ); the area under the curve (AUC) (0.999) and sensitivity (0.98) of the CT training group under the SAFIRE algorithm for gastric cancer classification were higher than those of the verification group (0.958, 0.92). The preoperative CT staging kappa value was consistent with the postoperative pathological diagnosis of 0.882. CT images guided by SAFIRE can objectively and noninvasively assess the tumor asymmetry, discover additional information from subjective evaluation beyond the naked eye, and perform reasonable staging diagnosis of gastric cancer, which was useful for clinicians to develop high-quality individualized treatment plans.

Predictive effect of computed tomography imaging omics features under deep learning on metastatic lymph nodes of nasopharyngeal carcinoma

AbstractThis article was to explore the adoption value of deep learning combined with computed tomography (CT) imaging omics in the prediction of metastatic lymph nodes of nasopharyngeal carcinoma (NPC). An end‐to‐end neural network architecture was designed based on the fully convolutional neural network (FCNN), which was applied to the CT image analysis of 52 patients with lymphatic metastasis and 36 patients without lymphatic metastasis. Patient's lymph node volume (V), the largest cross‐sectional shortest diameter (d‐value), and other macro characteristics were recorded. The microscopic features of its CT imaging omics were extracted. Moreover, receiver operating characteristic (ROC) curve was utilized to analyse the prediction performance (accuracy, area under the curve [AUC], and Youden index) of each feature for lymphatic metastasis. The results showed that the lymph node volume (4.37 ± 0.67) and the shortest diameter of the largest cross section (12.35 ± 2.31) of patients with lymph node metastasis were greatly larger than those without lymph node metastasis (1.84 ± 0.65, 7.98 ± 2.04) (P &lt; 0.05). There were five features that met the conditions of AUC &gt; 0.7 and Yoden index&gt;0.5, including lymph node volume (AUC area 0.945, Youden index 0.597), the shortest diameter of the largest cross section (AUC area 0.746, Youden index 0.539), Surface Area Density (AUC area 0.809, Youden index 0.552), Compactness1 (AUC area 0.751, Youden index 0.537), and Convex Hull Volume (AUC area 0.751, Youden index 0.537). The AUC of V+ Surface Area Density + Compactness1 + Convex Hull Volume was 0.876, and the prediction accuracy was 92.11%. In short, the prediction model composed of the macroscopic features of CT images and some imaging omics features based on deep learning showed high accuracy and AUC for the prediction of NPC metastatic lymph nodes. Moreover, V + Surface Area Density + Compactness1 + Convex Hull Volume can be used as the optimal feature combination model for predicting NPC lymphatic metastasis.

Value of breast MRI omics features and clinical characteristics in Breast Imaging Reporting and Data System (BI-RADS) category 4 breast lesions: an analysis of radiomics-based diagnosis.

BackgroundThe Breast Imaging Reporting and Data System (BI-RADS) category 4 breast lesions is categorized into 4A, 4B, and 4C, which reflect an increasing malignancy potential from low (2–10%) moderate (10–50%) and high (50–95%). Determining the benign and malignant of BI-RADS category 4 breast lesions is very important for accurate diagnosis and follow-up treatment. This study aimed to explore the value of breast magnetic resonance imaging (MRI) omics features and clinical characteristics in the assessment of BI-RADS category 4 breast lesions.MethodsThis retrospective study analyzed 96 lesions (39 benign and 57 malignant) from 92 patients diagnosed with MRI BI-RADS category 4 lesions in the Second Affiliated Hospital of Dalian Medical University between May 2017 and December 2019. The lesions were sub-categorized as BI-RADS 4A, 4B, or 4C based on the MRI findings. An imaging omics analysis model was applied to extract the MRI features. The positive predictive value (PPV) of each subcategory was calculated, and the area under the curve (AUC) was used to describe the efficiency for different diagnoses. Moreover, we analyzed 17 clinical indicators to assess their diagnostic value for BI-RADS category 4 breast lesions.ResultsThe PPVs of BI-RADS 4A, 4B, and 4C were 7.1% (2/28), 41.2% (7/17), and 94.1% (48/51), respectively. The AUC, sensitivity, and specificity were 0.919, 84.2%, and 92.3%, respectively. The combination of T1-weighted images (T1WI) with dynamic contrast-enhanced (DCE) MRI yielded the best diagnostic results among all dual sequences. Two clinical indicators [progesterone receptor (PR) and Ki-67 expression] achieved an AUC almost equal to 1.0. The radiomics and redundancy reduction methods reduced the clinical data features from 1,233 to 14.ConclusionsHigh diagnostic performance can be achieved in distinguishing malignant breast BI-RADS category 4 lesions using the combination of T1WI and DCE in MRI. Combining the PR and Ki-67 expression variables can further improve MRI accuracy for breast BI-RADS category 4 lesions.

Computed Tomography Angiography under Deep Learning in the Treatment of Atherosclerosis with Rapamycin.

The clinical characteristics and vascular computed tomography (CT) imaging characteristics of patients were explored so as to assist clinicians in diagnosing patients with atherosclerosis. 316 patients with atherosclerosis who were hospitalized for emergency treatment were treated with rapamycin (RAPA) in the hospital. A group of manually delineated left ventricular myocardia (LVM) on the patient's coronary computed tomography angiography (CCTA) were selected as the region of interest for imaging features extracted. The CCTA images of 80% of patients were randomly selected for training, and those of 20% of patients were used for verification. The correlation matrix method was used to remove redundant image omics features under different correlation thresholds. In the validation set, CCTA diagnostic parameters were about 40 times higher than the manually segmented data. The average dice similarity coefficient was 91.6%. The proposed method also produced a very small centroid distance (mean 1.058 mm, standard deviation 1.245 mm) and volume difference (mean 1.640), with a segmentation time of about 1.45 ± 0.51 s, compared to about 744.8 ± 117.49 s for physician manual segmentation. Therefore, the deep learning model effectively segmented the atherosclerotic lesion area, measured and assisted the diagnosis of future atherosclerosis clinical cases, improved medical efficiency, and accurately identified the patient's lesion area. It had great application potential in helping diagnosis and curative effect analysis of atherosclerosis.

Prediction Algorithm of Regional Lymph Node Metastasis of Rectal Cancer Based on Improved Deep Neural Network

MR imaging omics is an emerging method that uses data representation algorithms to transform image data into high-dimensional digable feature spaces that capture different tumor phenotypic differences and may have predictive prognostic capabilities. In this paper, the MR imaging omics method is used to construct a predefined image omics quantitative feature database to quantitatively describe tumor heterogeneity. Combining traditional machine learning models, constructing image omics tags to create a scientific, quantitative and easy to use Prognostic analysis model for rectal cancer can predict and analyze the prognosis of patients with rectal cancer before surgery. The improved neural network-based method proposed in this paper does not require manual selection of parameters, and only a large amount of training data can train accurate prediction models. In addition, this paper also introduces the method of extracting lymph node metastasis parameters from MR image rectal cancer area, and the strategy for data missing value completion. Experiments show that the MR imaging of regional rectal cancer regional lymph node metastasis prediction model based on improved deep neural network is better than formula prediction method and traditional artificial neural network based model, which reduces the prediction error. Further analysis also shows the missing value completion proposed in this paper. The method can effectively strengthen the training of deep neural networks.

Brain Perfusion Mediates the Relationship Between miRNA Levels and Postural Control.

Transcriptomics, regional cerebral blood flow (rCBF), and a virtual reality-based spatial motor task were integrated using mediation analysis in a novel demonstration of “imaging omics.” Data collected in National Collegiate Athletic Association (NCAA) Division I football athletes cleared for play before in-season training showed significant relationships in 1) elevated levels of miR-30d and miR-92a to elevated putamen rCBF, 2) elevated putamen rCBF to compromised Balance scores, and 3) compromised Balance scores to elevated microRNA (miRNA) levels. rCBF acted as a consistent mediator variable (Sobel’s test P < 0.05) between abnormal miRNA levels and compromised Balance scores. Given the involvement of these miRNAs in inflammation and immune function and that vascular perfusion is a component of the inflammatory response, these findings support a chronic inflammatory model in these athletes with 11 years of average football exposure. rCBF, a systems biology measure, was necessary for miRNA to affect behavior.

CT radiomics model for differentiating malignant and benign thyroid nodules

Objective To investigate the value of CT radiomics mode in differential diagnosis of benign and malignant thyroid nodules. Methods The clinical and imaging data of 179 patients with thyroid nodules confirmed by pathology from May 2017 to August 2018 were retrospectively analyzed in the Affiliated Huaian First People′s Hospital of Nanjing Medical University. Among the patients, 89 cases were benign nodules and 90 cases were malignant nodules. All patients underwent unenhanced and enhanced CT scan before operation. The stratified random sampling method was used to divide patients into a training group (143 cases) and a testing group (36 cases) according to a ratio of 8∶2. The A.K software was used to extract 378 imaging omics features based on preoperative CT images, and then Spearman correlation analysis and least absolute shrinkage and selection operator regression analysis were used for feature selection and model construction. The receiver operating characteristic (ROC) curve was used to verify the model in the training group and the testing group, and the efficacy of imaging omics features to predict benign and malignant thyroid nodules was evaluated. Results After feature screening, 16 radiomics features were used to construct an identification model between benign and malignant thyroid nodules. In the training group, the area under the ROC curve (AUC) was 0.92 [95% confidence interval (CI): 0.88-0.97], the sensitivity and specificity were 88.7%, 82.0%, and the diagnostic accuracy of the model was 91.1%. In the testing group, AUC was 0.90 (95%CI: 0.81-0.98), sensitivity and specificity were 88.5%, 84.6%, and the diagnostic accuracy of the model was 88.2%. Conclusion The CT radiomics mode has a good diagnostic performance in the identification of benign and malignant thyroid nodules. Key words: Tomography, X-Ray computed; Thyroid nodule; Diagnosis, differential; Radiomics

Prediction of white matter hyperintensities progression based on radiomics of whole-brain MRI: a study of risk factors

Objective To explore the risk factors of predicting white matter hyperintensities progression based on radiomics of MRI of whole-brain white matter. Methods The imaging and clinical data of 152 patients with white matter hyperintensities admitted to Zhejiang People′s Hospital from March 2014 to October 2018 were retrospectively analyzed. The whole brain white matter on baseline T1WI images of each patient were segmented by SPM12 software package, and images of white matter were imported into AK software for texture feature extraction and dimensionality reduction. At last, least absolute shrinkage and selection operator(LASSO) was used to calculate the score of radiomics signature of each patient. According to the improved Fazekas scale, patients with WMH progression were divided into three groups: any white matter hyperintensities (AWMH), periventricular white matter hyperintensities (PWMH) and deep white matter hyperintensities (DWMH). Statistical differences of clinical factors and radiomics signature between WMH progression subgroups and non-progression subgroups were compared with independent sample t test or Mann-Whitney U test, and Univariate logistic regression was used to select independent clinical risk factors and multivariate logistic regression along with imaging omics tags were used to construct predictive models, which was evaluated by ROC curve. And the correlation between the clinical indicators of independent risk factors and the texture feature of radiomics signature was analyzed. Results The efficacy of the model for the detection for AWMH progression, PWMH progression and DWMH progression was 0.818,0.778 and 0.824, respectively. Age is an independent risk factor for AWMH progression and DWMH progression[OR(95%CI), 4.776(2.152-10.601) vs. 3.851(1.101-8.245); P<0.05]. BMI is an independent risk factor for DWMH[OR(95%CI), 3.004(1.204-7.370); P<0.05], and hyperlipidemia is an independent risk factor for AWMH and PWMH[OR(95%CI), 4.062(1.834-8.998) vs. 3.549(1.666-7.563); P<0.05]. In AWMH subgroup, Surface Area was negatively correlated with age and low density lipoprotein(LDL) (r=-0.401, -0.312), and Inverse Difference Moment_ALLDirection_offset 1_SD was negatively correlated with age(r=-0.412). In PWMH subgroup, Compactness 1 was negatively correlated with LDL(r=-0.198), and Inverse Difference Moment_angle 0_offset 7 was positively correlated with LDL(r=0.252). In DWMH subgroup, LongRunEmphasis_ALLDirection_offset 7 was negatively correlated with age(r=-0.322), and GLCMEntropy_angle0_offset 4 was negatively correlated with age(r=-0.278). GLCMEntropy_AllDirection_offset4 was negatively correlated with body mass index(r=-0.514). Conclusion Radiomics based on whole-brain white matter MR imaging can predict WMH progression and identify the risk factors in high-risk populations, thus providing early additional information to conventional magnetic resonance imaging to predict WMH progression. Key words: Radiomics; White matter hyperintensities; Risk factors; Magnetic resonance imaging

Benign and malignant classification of renal occupancy lesions CT images using convolutional neural networks

Objective To investigate the feasibility and application value of the benign and malignant classificational methods of renal occupying CT images based on convolutional neural networks (CNN). Methods An image omics method that can automatically learn the image features and classify CT images was used. Firstly, the CNN model obtained by large-scale natural image training was used to migrate the characteristics of the renal occupancy lesions CT images, and then the fine-tuning of the full connection layer was used to realize the benign and malignant classification of the images. Results The evaluation indexes of the VGG19 model were lower than ResNet50 and Inception V3, and the training result showed obvious overfitting. The accuracy, sensitivity and negative prediction values of the Inception V3 model was 93.8%, 99.5% and 99.1%, respectively, which were higher than that of the ResNet50 model. Conclusions The benign and malignant classification of renal occupancy lesions CT images using CNN is a reasonable and feasible method, and the fine-tuned Inception V3 model has a better classification performance. Key words: Convolutional neural networks; Transfer learning; Renal occupancy lesions; CT images; Benign and malignant classification