Compare deep learning model and conventional logistic regression model for the identification of unstable saccular intracranial aneurysms in computed tomography angiography.

Background: It is crucial to distinguish unstable from stable intracranial aneurysms (IAs) as early as possible to derive optimal clinical decision-making for further treatment or follow-up. The aim of this study was to investigate the value of a deep learning model (DLM) in identifying unstable IAs from computed tomography angiography (CTA) images and to compare its discriminatory ability with that of a conventional logistic regression model (LRM). Methods: From August 2011 to May 2021, a total of 1,049 patients with 681 unstable IAs and 556 stable IAs were retrospectively analyzed. IAs were randomly divided into training (64%), internal validation (16%), and test sets (20%). Convolutional neural network (CNN) analysis and conventional logistic regression (LR) were used to predict which IAs were unstable. The area under the curve (AUC), sensitivity, specificity and accuracy were calculated to evaluate the discriminating ability of the models. One hundred and ninety-seven patients with 229 IAs from Banan Hospital were used for external validation sets. Results: The conventional LRM showed 11 unstable risk factors, including clinical and IA characteristics. The LRM had an AUC of 0.963 [95% confidence interval (CI): 0.941-0.986], a sensitivity, specificity and accuracy on the external validation set of 0.922, 0.906, and 0.913, respectively, in predicting unstable IAs. In predicting unstable IAs, the DLM had an AUC of 0.771 (95% CI: 0.582-0.960), a sensitivity, specificity and accuracy on the external validation set of 0.694, 0.929, and 0.782, respectively. Conclusions: The CNN-based DLM applied to CTA images did not outperform the conventional LRM in predicting unstable IAs. The patient clinical and IA morphological parameters remain critical factors for ensuring IA stability. Further studies are needed to enhance the diagnostic accuracy.

Peri-lesion regions in differentiating suspicious breast calcification-only lesions specifically on contrast enhanced mammography.

PURPOSE: The explore the added value of peri-calcification regions on contrast-enhanced mammography (CEM) in the differential diagnosis of breast lesions presenting as only calcification on routine mammogram. METHODS: Patients who underwent CEM because of suspicious calcification-only lesions were included. The test set included patients between March 2017 and March 2019, while the validation set was collected between April 2019 and October 2019. The calcifications were automatically detected and grouped by a machine learning-based computer-aided system. In addition to extracting radiomic features on both low-energy (LE) and recombined (RC) images from the calcification areas, the peri-calcification regions, which is generated by extending the annotation margin radially with gradients from 1 mm to 9 mm, were attempted. Machine learning (ML) models were built to classify calcifications into malignant and benign groups. The diagnostic matrices were also evaluated by combing ML models with subjective reading. RESULTS: Models for LE (significant features: wavelet-LLL_glcm_Imc2_MLO; wavelet-HLL_firstorder_Entropy_MLO; wavelet-LHH_glcm_DifferenceVariance_CC; wavelet-HLL_glcm_SumEntropy_MLO;wavelet-HLH_glrlm_ShortRunLowGray LevelEmphasis_MLO; original_firstorder_Entropy_MLO; original_shape_Elongation_MLO) and RC (significant features: wavelet-HLH_glszm_GrayLevelNonUniformityNormalized_MLO; wavelet-LLH_firstorder_10Percentile_CC; original_firstorder_Maximum_MLO; wavelet-HHH_glcm_Autocorrelation_MLO; original_shape_Elongation_MLO; wavelet-LHL_glszm_GrayLevelNonUniformityNormalized_MLO; wavelet-LLH_firstorder_RootMeanSquared_MLO) images were set up with 7 features. Areas under the curve (AUCs) of RC models are significantly better than those of LE models with compact and expanded boundary (RC v.s. LE, compact: 0.81 v.s. 0.73, p <  0.05; expanded: 0.89 v.s. 0.81, p <  0.05) and RC models with 3 mm boundary extension yielded the best performance compared to those with other sizes (AUC = 0.89). Combining with radiologists' reading, the 3mm-boundary RC model achieved a sensitivity of 0.871 and negative predictive value of 0.937 with similar accuracy of 0.843 in predicting malignancy. CONCLUSIONS: The machine learning model integrating intra- and peri-calcification regions on CEM has the potential to aid radiologists' performance in predicting malignancy of suspicious breast calcifications.

Radiomics for differentiating tumor deposits from lymph node metastasis in rectal cancer.

BACKGROUND: Tumor deposits (TDs) are not equivalent to lymph node (LN) metastasis (LNM) but have become independent adverse prognostic factors in patients with rectal cancer (RC). Although preoperatively differentiating TDs and LNMs is helpful in designing individualized treatment strategies and achieving improved prognoses, it is a challenging task. AIM: To establish a computed tomography (CT)-based radiomics model for preoperatively differentiating TDs from LNM in patients with RC. METHODS: This study retrospectively enrolled 219 patients with RC [TDs+LNM- (n = 89); LNM+ TDs- (n = 115); TDs+LNM+ (n = 15)] from a single center between September 2016 and September 2021. Single-positive patients (i.e., TDs+LNM- and LNM+TDs-) were classified into the training (n = 163) and validation (n = 41) sets. We extracted numerous features from the enhanced CT (region 1: The main tumor; region 2: The largest peritumoral nodule). After deleting redundant features, three feature selection methods and three machine learning methods were used to select the best-performing classifier as the radiomics model (Rad-score). After validating Rad-score, its performance was further evaluated in the field of diagnosing double-positive patients (i.e., TDs+LNM+) by outlining all peritumoral nodules with diameter (short-axis) > 3 mm. RESULTS: Rad-score 1 (radiomics signature of the main tumor) had an area under the curve (AUC) of 0.768 on the training dataset and 0.700 on the validation dataset. Rad-score 2 (radiomics signature of the largest peritumoral nodule) had a higher AUC (training set: 0.940; validation set: 0.918) than Rad-score 1. Clinical factors, including age, gender, location of RC, tumor markers, and radiological features of the largest peritumoral nodule, were excluded by logistic regression. Thus, the combined model was comprised of Rad-scores of 1 and 2. Considering that the combined model had similar AUCs with Rad-score 2 (P = 0.134 in the training set and 0.594 in the validation set), Rad-score 2 was used as the final model. For the diagnosis of double-positive patients in the mixed group [TDs+LNM+ (n = 15); single-positive (n = 15)], Rad-score 2 demonstrated moderate performance (sensitivity, 73.3%; specificity, 66.6%; and accuracy, 70.0%). CONCLUSION: Radiomics analysis based on the largest peritumoral nodule can be helpful in preoperatively differentiating between TDs and LNM.

Deep Learning Radiomics Nomogram to Predict Lung Metastasis in Soft-Tissue Sarcoma: A Multi-Center Study.

Objectives: To build and evaluate a deep learning radiomics nomogram (DLRN) for preoperative prediction of lung metastasis (LM) status in patients with soft tissue sarcoma (STS). Methods: In total, 242 patients with STS (training set, n=116; external validation set, n=126) who underwent magnetic resonance imaging were retrospectively enrolled in this study. We identified independent predictors for LM-status and evaluated their performance. The minimum redundancy maximum relevance (mRMR) method and least absolute shrinkage and selection operator (LASSO) algorithm were adopted to screen radiomics features. Logistic regression, decision tree, random forest, support vector machine (SVM), and adaptive boosting classifiers were compared for their ability to predict LM. To overcome the imbalanced distribution of the LM data, we retrained each machine-learning classifier using the synthetic minority over-sampling technique (SMOTE). A DLRN combining the independent clinical predictors with the best performing radiomics prediction signature (mRMR+LASSO+SVM+SMOTE) was established. Area under the receiver operating characteristics curve (AUC), calibration curves, and decision curve analysis (DCA) were used to assess the performance and clinical applicability of the models. Result: Comparisons of the AUC values applied to the external validation set revealed that the DLRN model (AUC=0.833) showed better prediction performance than the clinical model (AUC=0.664) and radiomics model (AUC=0.799). The calibration curves indicated good calibration efficiency and the DCA showed the DLRN model to have greater clinical applicability than the other two models. Conclusion: The DLRN was shown to be an accurate and efficient tool for LM-status prediction in STS.

Radiomics for predicting perineural invasion status in rectal cancer.

BACKGROUND: Perineural invasion (PNI), as a key pathological feature of tumor spread, has emerged as an independent prognostic factor in patients with rectal cancer (RC). The preoperative stratification of RC patients according to PNI status is beneficial for individualized treatment and improved prognosis. However, the preoperative evaluation of PNI status is still challenging. AIM: To establish a radiomics model for evaluating PNI status preoperatively in RC patients. METHODS: This retrospective study enrolled 303 RC patients in a single institution from March 2018 to October 2019. These patients were classified as the training cohort (n = 242) and validation cohort (n = 61) at a ratio of 8:2. A large number of intra- and peritumoral radiomics features were extracted from portal venous phase images of computed tomography (CT). After deleting redundant features, we tested different feature selection (n = 6) and machine-learning (n = 14) methods to form 84 classifiers. The best performing classifier was then selected to establish Rad-score. Finally, the clinicoradiological model (combined model) was developed by combining Rad-score with clinical factors. These models for predicting PNI were compared using receiver operating characteristic curve (ROC) analysis and area under the ROC curve (AUC). RESULTS: One hundred and forty-four of the 303 patients were eventually found to be PNI-positive. Clinical factors including CT-reported T stage (cT), N stage (cN), and carcinoembryonic antigen (CEA) level were independent risk factors for predicting PNI preoperatively. We established Rad-score by logistic regression analysis after selecting features with the L1-based method. The combined model was developed by combining Rad-score with cT, cN, and CEA. The combined model showed good performance to predict PNI status, with an AUC of 0.828 [95% confidence interval (CI): 0.774-0.873] in the training cohort and 0.801 (95%CI: 0.679-0.892) in the validation cohort. For comparison of the models, the combined model achieved a higher AUC than the clinical model (cT + cN + CEA) achieved (P < 0.001 in the training cohort, and P = 0.045 in the validation cohort). CONCLUSION: The combined model incorporating Rad-score and clinical factors can provide an individualized evaluation of PNI status and help clinicians guide individualized treatment of RC patients.

Prediction efficacy of feature classification of solitary pulmonary nodules based on CT radiomics.

OBJECTIVE: To investigate the relationship between CT radiomic features, pathological classification of pulmonary nodules, and evaluate the prediction effect of different stratified progressive radiomic models on the pathological classification of pulmonary nodules. METHODS: Altogether, 189 patients pathologically confirmed with pulmonary nodules from July 2017 to August 2019 who had complete data were enrolled, including 71 patients with benign nodules, 51 with malignant non-invasive nodules, and 67 with invasive nodules. Three CT radiomic models were established respectively. Model 1 classified benign and malignant nodules (including malignant non-invasive and invasive nodules). Model 2 classified malignant non-invasive and invasive nodules. Model 3 classified benign, malignant non-invasive, and invasive nodules. High-throughput feature collection was carried out for all delineated regions of interest (ROIs), and the best models were established by screening features and classifiers using intelligent methods. ROC curves and areas under the curve (AUCs) were used to evaluate the prediction efficacy of the models by calculating the sensitivity, specificity, accuracies, positive predictive values, and negative predictive values. RESULTS: Through Models 1, 2, and 3, we screened out 20, 2, and 20 radiomic features, respectively, and plotted the ROC curves. In the test group, the AUC values were 0.85, 0.89, and 0.84, respectively; the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 79.66 %, 70.42 %, 84.59 %, and 81.74 % and 67.57％ for Model 1, 88.06 %, 74.51 %, 82.2 %, 81.94 %, and 82.61 % for Model 2, and 71.34 %, 85.05 %, 70.37 %, 83.2 %, and 76.3 % for Model 3. CONCLUSION: The radiomic feature models based on CT images could well reflect the differences between benign nodules, malignant non-invasive nodules, and invasive nodules, and assist in their classification.

Systemic effect of dietary lipid levels and α-lipoic acid supplementation on nutritional metabolism in zebrafish (Danio rerio): focusing on the transcriptional level.

Considering the excessive lipid accumulation status caused by the increased dietary lipid intake in farmed fish, this study aimed to investigate the systemic effect of dietary lipid levels and α-lipoic acid supplementation on nutritional metabolism in zebrafish. A total of 540 male zebrafish (0.17 g) were fed with normal (CT) and high lipid level (HL) diets for 6 weeks, then fed on 1000 mg/kg α-lipoic acid supplementation diets for the second 6 weeks. HL diets did not affect whole fish protein content, but increased ASNS expression (P < 0.05). Dietary α-lipoic acid increased whole fish protein content, and decreased the expressions of protein catabolism-related genes in muscle of high lipid level groups (P < 0.05). Furthermore, HL diets increased the whole fish lipid content and the expressions of gluconeogenesis and lipogenesis-related genes (P < 0.05), and α-lipoic acid counteracted these effects and decreased the whole fish triglyceride and cholesterol contents and expressions of lipogenesis-related genes, with the enhanced expressions of lipolytic genes, especially in high lipid groups (P < 0.05). HL diets did not affect hepatocyte mitochondrial quantity or the mRNA expressions of mitochondrial biogenesis and electron transport chain-related genes; they were significantly increased by dietary α-lipoic acid (P < 0.05). These results indicated that high dietary lipid promotes lipid accumulation, while α-lipoic acid increases protein content in association of enhanced lipid catabolism. Thus, dietary α-lipoic acid supplementation could reduce lipid accumulation under high lipid, which provides a promising new approach in solving the problem of lipid accumulation in farmed fish.

Molecular characterization and tissue distribution of SREBP-1 and PPARα in Onychostoma macrolepis and their mRNA expressions in response to thermal exposure.

Fatty acid metabolism is crucial for maintaining energy homeostasis in aquatic vertebrates experiencing environmental stress. Both sterol regulatory element-binding protein 1 (SREBP-1) and peroxisome proliferator-activated receptor α (PPARα) are the key regulators of fatty acid metabolism. In this study, the coding sequences (CDS) of SREBP-1 and PPARα were firstly identified and characterized from Onychostoma macrolepis, encoding peptides of 1136 and 470 amino acids, respectively. The functional domains in O. macrolepis SREBP-1 and PPARα proteins retained the high similarity with those of other animals, at 74.69% and 77.29%, respectively. The mRNA encoding SREBP-1 was primarily expressed in the muscle and PPARα was highly expressed in the liver and intestine. Under thermal exposure, the content of non-esterified fatty acid (NEFA) decreased gradually after 1 h in the liver and muscle of O. macrolepis, which might be due to that the organism meet more energy expenditure via fatty acid ß-oxidation. Furthermore, the mRNA expression level of SREBP-1 decreased, while the mRNA expression level of PPARα increased from 0 h to 6 h in the liver. And we found that the mRNA expression levels of both SREBP-1 and PPARα decreased significantly at 48 h (P < .05) in the muscle, which was in accordance with the significant decrease of target gene FAS and CPT1A mRNA expression levels, respectively. It might be the physiological adjustment that the fish adapted to thermal exposure at the end of experiment. These results illustrate that O. macrolepis SREBP-1 and PPARα-mediated fatty acid metabolism is a fundamental requirement for thermal adaptation.