Distinguishing common renal cell carcinomas from benign renal tumors based on machine learning: comparing various CT imaging phases, slices, tumor sizes, and ROI segmentation strategies.

OBJECTIVES: To determine whether a CT-based machine learning (ML) can differentiate benign renal tumors from renal cell carcinomas (RCCs) and improve radiologists' diagnostic performance, and evaluate the impact of variable CT imaging phases, slices, tumor sizes, and region of interest (ROI) segmentation strategies. METHODS: Patients with pathologically proven RCCs and benign renal tumors from our institution between 2008 and 2020 were included as the training dataset for ML model development and internal validation (including 418 RCCs and 78 benign tumors), and patients from two independent institutions and a public database (TCIA) were included as the external dataset for individual testing (including 262 RCCs and 47 benign tumors). Features were extracted from three-phase CT images. CatBoost was used for feature selection and ML model establishment. The area under the receiver operating characteristic curve (AUC) was used to assess the performance of the ML model. RESULTS: The ML model based on 3D images performed better than that based on 2D images, with the highest AUC of 0.81 and accuracy (ACC) of 0.86. All three radiologists achieved better performance by referring to the classifier's decision, with accuracies increasing from 0.82 to 0.87, 0.82 to 0.88, and 0.76 to 0.87. The ML model achieved higher negative predictive values (NPV, 0.82-0.99), and the radiologists achieved higher positive predictive values (PPV, 0.91-0.95). CONCLUSIONS: A ML classifier based on whole-tumor three-phase CT images can be a useful and promising tool for differentiating RCCs from benign renal tumors. The ML model also perfectly complements radiologist interpretations. KEY POINTS: • A machine learning classifier based on CT images could be a reliable way to differentiate RCCs from benign renal tumors. • The machine learning model perfectly complemented the radiologists' interpretations. • Subtle variances in ROI delineation had little effect on the performance of the ML classifier.

Detecting Muscle Invasion of Bladder Cancer Using a Proposed Magnetic Resonance Imaging Strategy.

BACKGROUND: Accurate evaluation of the invasion depth of tumors with a Vesical Imaging-Reporting and Data System (VI-RADS) score of 3 is difficult. PURPOSE: To evaluate the diagnostic performance of a new magnetic resonance imaging (MRI) strategy based on the integration of the VI-RADS and tumor contact length (TCL) for the diagnosis of muscle-invasive bladder cancer (MIBC). STUDY TYPE: Single center, retrospective. SUBJECTS: A group of 179 patients with a mean age of 67 years (range, 24.0-96.0) underwent multiparametric MRI (mpMRI) before surgery, including 147 (82.1%) males and 32 (17.9%) females. Twenty-four (13.4%), 90 (50.3%), 43 (24.0%), 15 (8.4%), and 7 (3.9%) cases were Ta, T1, T2, T3, and T4, respectively. FIELD STRENGTH/SEQUENCE: A 1.5 T and 3.0 T, T2-weighted turbo spin-echo (TSE), single-shot echo-planar (SS-EPI), diffusion-weighted imaging (DWI), and T1-weighted volumetric interpolated breath-hold examination (T1-VIBE). ASSESSMENT: Three radiologists independently graded the VI-RADS score and measured the TCL on index lesion images. A proposed MRI strategy called VI-RADS_TCL was introduced by modifying the VI-RADS score, which was downgraded to VI-RADS 3F (equal to a VI-RADS score of 2) if VI-RADS = 3 and TCL < 3 cm. STATISTICAL TESTS: Intraclass correlation coefficients (ICCs), Mann-Whitney U test, chi-square tests, receiver operating characteristic (ROC) curves, and 2 × 2 contingency tables were applied. RESULTS: Inter-reader agreement values were 0.941 (95% CI, 0.924-0.955) and 0.934 (95% CI, 0.916-0.948) for the TCL and VI-RADS score. The TCL was significantly increased in the MIBC group (6.40-6.85 cm) compared with the NMIBC group (1.98-2.45 cm) (P < 0.05). The specificity and positive predictive values (PPV) of VI-RADS_TCL were 82.46%-87.72% and 90.91%-91.59%, which were significantly greater than VI-RADS score (P < 0.05). Additionally, 52.17%-55.88% NMIBC lesions with VI-RADS 3 were downgraded to 3F by using VI-RADS_TCL. DATA CONCLUSION: The proposed MRI strategy could reduce the false-positive rate of lesions with a VI-RADS score of 3 while retaining sensitivity. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: 2.

Performance of Dual-Source CT in Calculi Component Analysis: A Systematic Review and Meta-Analysis of 2151 Calculi.

OBJECTIVE: To evaluate the performance of dual-source computed tomography (DSCT) in the component analysis of all types of calculi by doing a systematic review and meta-analysis. METHODS: We searched MEDLINE, Embase, Scopus, and CNKI up to February 28, 2020, for in vivo studies investigating the performance of DSCT in the component analysis of calculi. We pooled the sensitivity, specificity, and areas under the summary receiver operating characteristic (AUROC) curves using a random-effect model in the meta-analysis. Publication bias was evaluated using Deek's funnel plot asymmetry test. RESULTS: This analysis included a total of 37 studies in 1840 patients with 2151 calculi (462 uric acid [UA], 1383 calcium oxalate [CaOx], 55 cystine [Cys], 197 hydroxyapatite [HA], and 54 struvite [SV]). Using DSCT, the pooled accuracy for diagnosing UA (sensitivity, 0.95; specificity, 0.99), CaOx (0.98; 0.93), Cys (0.99; 0.99), HA (0.91; 0.99), and SV (0.42; 0.98) was calculated, respectively. The AUROC value was 0.99, 0.99, 1.00, 0.99, and 0.93, respectively. The P values for publication bias test were .49, .70, .07, .04, and .19, respectively. CONCLUSION: Dual-source computed tomography has high sensitivity and specificity for the component analysis of UA, CaOx, Cys, and HA calculi in vivo. This tool may have the potential to replace the current analysis tool in vitro in diagnosing calculi.

Predicting the ISUP grade of clear cell renal cell carcinoma with multiparametric MR and multiphase CT radiomics.

OBJECTIVE: To investigate externally validated magnetic resonance (MR)-based and computed tomography (CT)-based machine learning (ML) models for grading clear cell renal cell carcinoma (ccRCC). MATERIALS AND METHODS: Patients with pathologically proven ccRCC in 2009-2018 were retrospectively included for model development and internal validation; patients from another independent institution and The Cancer Imaging Archive dataset were included for external validation. Features were extracted from T1-weighted, T2-weighted, corticomedullary-phase (CMP), and nephrographic-phase (NP) MR as well as precontrast-phase (PCP), CMP, and NP CT. CatBoost was used for ML-model investigation. The reproducibility of texture features was assessed using intraclass correlation coefficient (ICC). Accuracy (ACC) was used for ML-model performance evaluation. RESULTS: Twenty external and 440 internal cases were included. Among 368 and 276 texture features from MR and CT, 322 and 250 features with good to excellent reproducibility (ICC ≥ 0.75) were included for ML-model development. The best MR- and CT-based ML models satisfactorily distinguished high- from low-grade ccRCCs in internal (MR-ACC = 73% and CT-ACC = 79%) and external (MR-ACC = 74% and CT-ACC = 69%) validation. Compared to single-sequence or single-phase images, the classifiers based on all-sequence MR (71% to 73% in internal and 64% to 74% in external validation) and all-phase CT (77% to 79% in internal and 61% to 69% in external validation) images had significant increases in ACC. CONCLUSIONS: MR- and CT-based ML models are valuable noninvasive techniques for discriminating high- from low-grade ccRCCs, and multiparameter MR- and multiphase CT-based classifiers are potentially superior to those based on single-sequence or single-phase imaging. KEY POINTS: • Both the MR- and CT-based machine learning models are reliable predictors for differentiating high- from low-grade ccRCCs. • ML models based on multiparameter MR sequences and multiphase CT images potentially outperform those based on single-sequence or single-phase images in ccRCC grading.

Preoperative prediction of lymphovascular invasion in invasive breast cancer with dynamic contrast-enhanced-MRI-based radiomics.

BACKGROUND: Lymphovascular invasion (LVI) status facilitates the selection of optimal therapeutic strategy for breast cancer patients, but in clinical practice LVI status is determined in pathological specimens after resection. PURPOSE: To explore the use of dynamic contrast-enhanced (DCE)-magnetic resonance imaging (MRI)-based radiomics for preoperative prediction of LVI in invasive breast cancer. STUDY TYPE: Prospective. POPULATION: Ninety training cohort patients (22 LVI-positive and 68 LVI-negative) and 59 validation cohort patients (22 LVI-positive and 37 LVI-negative) were enrolled. FIELD STRENGTH/SEQUENCE: 1.5 T and 3.0 T, T1 -weighted DCE-MRI. ASSESSMENT: Axillary lymph node (ALN) status for each patient was evaluated based on MR images (defined as MRI ALN status), and DCE semiquantitative parameters of lesions were calculated. Radiomic features were extracted from the first postcontrast DCE-MRI. A radiomics signature was constructed in the training cohort with 10-fold cross-validation. The independent risk factors for LVI were identified and prediction models for LVI were developed. Their prediction performances and clinical usefulness were evaluated in the validation cohort. STATISTICAL TESTS: Mann-Whitney U-test, chi-square test, kappa statistics, least absolute shrinkage and selection operator (LASSO) regression, logistic regression, receiver operating characteristic (ROC) analysis, DeLong test, and decision curve analysis (DCA). RESULTS: Two radiomic features were selected to construct the radiomics signature. MRI ALN status (odds ratio, 10.452; P < 0.001) and the radiomics signature (odds ratio, 2.895; P = 0.031) were identified as independent risk factors for LVI. The value of the area under the curve (AUC) for a model combining both (0.763) was higher than that for MRI ALN status alone (0.665; P = 0.029) and similar to that for the radiomics signature (0.752; P = 0.857). DCA showed that the combined model added more net benefit than either feature alone. DATA CONCLUSION: The DCE-MRI-based radiomics signature in combination with MRI ALN status was effective in predicting the LVI status of patients with invasive breast cancer before surgery. LEVEL OF EVIDENCE: 1 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019;50:847-857.

CT texture analysis in the differentiation of major renal cell carcinoma subtypes and correlation with Fuhrman grade.

OBJECTIVE: CT texture analysis (CTTA) using filtration-histogram-based parameters has been associated with tumor biologic correlates such as glucose metabolism, hypoxia, and tumor angiogenesis. We investigated the utility of these parameters for differentiation of clear cell from papillary renal cancers and prediction of Fuhrman grade. METHODS: A retrospective study was performed by applying CTTA to pretreatment contrast-enhanced CT scans in 290 patients with 298 histopathologically confirmed renal cell cancers of clear cell and papillary types. The largest cross section of the tumor on portal venous phase axial CT was chosen to draw a region of interest. CTTA comprised of an initial filtration step to extract features of different sizes (fine, medium, coarse spatial scales) followed by texture quantification using histogram analysis. RESULTS: A significant increase in entropy with fine and medium spatial filters was demonstrated in clear cell RCC (p = 0.047 and 0.033, respectively). Area under the ROC curve of entropy at fine and medium spatial filters was 0.804 and 0.841, respectively. An increased entropy value at coarse filter correlated with high Fuhrman grade tumors (p = 0.01). The other texture parameters were not found to be useful. CONCLUSION: Entropy, which is a quantitative measure of heterogeneity, is increased in clear cell renal cancers. High entropy is also associated with high-grade renal cancers. This parameter may be considered as a supplementary marker when determining aggressiveness of therapy. KEY POINTS: • CT texture analysis is easy to perform on contrast-enhanced CT. • CT texture analysis may help to separate different types of renal cancers. • CT texture analysis may enhance individualized treatment of renal cancers.

Whole-Lesion Computed Tomography-Based Entropy Parameters for the Differentiation of Minimally Invasive and Invasive Adenocarcinomas Appearing as Pulmonary Subsolid Nodules.

OBJECTIVE: The aim of this study was to investigate the differentiation of computed tomography (CT)-based entropy parameters between minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC) lesions appearing as pulmonary subsolid nodules (SSNs). METHODS: This study was approved by the institutional review board in our hospital. From July 2015 to November 2018, 186 consecutive patients with solitary peripheral pulmonary SSNs that were pathologically confirmed as pulmonary adenocarcinomas (74 MIA and 112 IAC lesions) were included and subdivided into the training data set and the validation data set. Chest CT scans without contrast enhancement were performed in all patients preoperatively. The subjective CT features of the SSNs were reviewed and compared between the MIA and IAC groups. Each SSN was semisegmented with our in-house software, and entropy-related parameters were quantitatively extracted using another in-house software developed in the MATLAB platform. Logistic regression analysis and receiver operating characteristic analysis were performed to evaluate the diagnostic performances. Three diagnostic models including subjective model, entropy model, and combined model were built and analyzed using area under the curve (AUC) analysis. RESULTS: There were 119 nonsolid nodules and 67 part-solid nodules. Significant differences were found in the subjective CT features among nodule type, lesion size, lobulated shape, and irregular margin between the MIA and IAC groups. Multivariate analysis revealed that part-solid type and lobulated shape were significant independent factors for IAC (P < 0.0001 and P < 0.0001, respectively). Three entropy parameters including Entropy-0.8, Entropy-2.0-32, and Entropy-2.0-64 were identified as independent risk factors for the differentiation of MIA and IAC lesions. The median entropy model value of the MIA group was 0.266 (range, 0.174-0.590), which was significantly lower than the IAC group with value 0.815 (range, 0.623-0.901) (P < 0.0001). Multivariate analysis revealed that the combined model had an excellent diagnostic performance with sensitivity of 88.2%, specificity of 73.0%, and accuracy of 82.1%. The AUC value of the combined model was significantly higher (AUC, 0.869) than that of the subjective model (AUC, 0.809) or the entropy model alone (AUC, 0.836) (P < 0.0001). CONCLUSIONS: The CT-based entropy parameters could help assess the aggressiveness of pulmonary adenocarcinoma via quantitative analysis of intratumoral heterogeneity. The MIA can be differentiated from IAC accurately by using entropy-related parameters in peripheral pulmonary SSNs.

Can functional parameters from hepatobiliary phase of gadoxetate MRI predict clinical outcomes in patients with cirrhosis?

OBJECTIVES: To determine the value of quantitative parameters of gadoxetate-enhanced magnetic resonance imaging (MRI) in predicting prognosis in patients with cirrhosis. METHODS: A cohort of 63 cirrhotic patients who had gadoxetate MRI and 2-year clinical follow-up was enrolled. Enhancement ratio (ER), contrast enhancement index (CEI) and contrast enhancement spleen index (CES) were calculated. The usefulness of these parameters and clinical scores, such as Child-Pugh score (CPS) and model for end stage liver disease (MELD), in predicting adverse outcomes, such as variceal bleeding (VB), hepatic encephalopathy (HE) and mortality at 2 years were evaluated. RESULTS: Fifteen, 31 and 27 patients, respectively, had VB, HE and mortality within 2 years. The ER at 15 min (ER 15) and CES at 20 min (CES 20) were found to be the best MRI predictors. Areas under the receiver operating characteristic curve (AUC) for predicting VB were 0.785, 0.729, 0.673, 0.714, respectively, for ER 15, CES 20, CPS and MELD scores. ER 15 of less than 48 had sensitivity of 96% and specificity of 84% for predicting onset of HE within 2 years. CONCLUSIONS: In patients with cirrhosis, ER 15 or CES 20 were equivalent or better predictors of major morbidity and mortality compared with commonly used clinical scores. KEY POINTS: • Gadoxetate parameters may identify cirrhotic patients at risk of adverse events. • Gadoxetate parameters usually show superior predictive values compared to clinical scores. • CES 20 score is associated with risk of mortality within 2 years.

Quantitative MR Evaluation of Chronic Pancreatitis: Extracellular Volume Fraction and MR Relaxometry.

OBJECTIVE: The purpose of this study was to determine if extracellular volume fraction and T1 mapping can be used to diagnose chronic pancreatitis (CP). MATERIALS AND METHODS: This HIPAA-compliant study analyzed 143 consecutive patients with and without CP who underwent MR imaging between May 2016 and February 2017. Patients were selected for the study according to inclusion and exclusion criteria that considered history and clinical and laboratory findings. Eligible patients (n = 119) were grouped as normal (n = 60) or with mild (n = 22), moderate (n = 27), or severe (n = 10) CP on the basis of MRCP findings using the Cambridge classification as the reference standard. T1 maps were acquired in unenhanced and late contrast-enhanced phases using a 3D dual flip-angle gradient-echo sequence. All patients were imaged on the same 3-T scanner using the same imaging parameters, contrast agent, and dosage. RESULTS: Mean extracellular volume fractions and T1 relaxation times were significantly different within the study groups (one-way ANOVA, p < 0.001). Using the AUC curve analysis, extracellular volume fraction of > 0.27 showed 92% sensitivity (54/59) and 77% specificity (46/60) for the diagnosis of CP (AUC = 0.90). A T1 relaxation time of > 950 ms revealed 64% sensitivity (38/59) and 88% specificity (53/60) (AUC = 0.80). Combining extracellular volume fraction and T1 mapping yielded sensitivity of 85% (50/59) and specificity of 92% (55/60) (AUC = 0.94). CONCLUSION: Extracellular volume fraction and T1 mapping may provide quantitative metrics for determining the presence and severity of acinar cell loss and aid in the diagnosis of CP.

Development and validation of a predictor of insufficient enhancement during the hepatobiliary phase of Gd-EOB-DTPA-enhanced magnetic resonance imaging.

Background Insufficient enhancement of liver parenchyma negatively affects diagnostic accuracy of Gd-EOB-DTPA-enhanced magnetic resonance imaging (MRI). Currently, there is no reliable method for predicting insufficient enhancement during the hepatobiliary phase (HBP) in Gd-EOB-DTPA-enhanced MRI. Purpose To develop a predictor for insufficient enhancement of liver parenchyma during HBP in Gd-EOB-DTPA-enhanced MRI. Material and Methods In order to formulate a HBP enhancement test (HBP-ET), clinical factors associated with relative enhancement ratio (RER) of liver parenchyma were retrospectively determined from the datasets of 156 patients (Development group) who underwent Gd-EOB-DTPA-enhanced MRI between November 2012 and May 2015. The independent clinical factors were identified by Pearson's correlation and multiple stepwise regression analysis; the performance of HBP-ET was compared to Child-Pugh score (CPS), Model for End-stage Liver Disease score (MELD), and total bilirubin (TBIL) using receiver operating characteristic (ROC) curve analysis. The datasets of 52 patients (Validation group), which were examined between June 2015 and Oct 2015, were applied to validate the HBP-ET. Results Six biochemical parameters independently influenced RER and were used to develop HBP-ET. The mean HBP-ET score of patients with insufficient enhancement was significantly higher than that of patients with sufficient enhancement ( P < 0.001) in both the Development and Validation groups. HBP-ET (area under the curve [AUC] = 0.895) had better performance in predicting insufficient enhancement than CPS (AUC = 0.707), MELD (AUC = 0.798), and TBIL (AUC = 0.729). Conclusion The HBP-ET is more accurate than routine indicators in predicting insufficient enhancement during HBP, which is valuable to aid clinical decisions.

Enhancing preoperative diagnosis of microvascular invasion in hepatocellular carcinoma: domain-adaptation fusion of multi-phase CT images.

Objectives: In patients with hepatocellular carcinoma (HCC), accurately predicting the preoperative microvascular invasion (MVI) status is crucial for improving survival rates. This study proposes a multi-modal domain-adaptive fusion model based on deep learning methods to predict the preoperative MVI status in HCC. Materials and methods: From January 2008 to May 2022, we collected 163 cases of HCC from our institution and 42 cases from another medical facility, with each case including Computed Tomography (CT) images from the pre-contrast phase (PCP), arterial phase (AP), and portal venous phase (PVP). We divided our institution's dataset (n=163) into training (n=119) and test sets (n=44) in an approximate 7:3 ratio. Additionally, we included cases from another institution (n=42) as an external validation set (test1 set). We constructed three single-modality models, a simple concatenated multi-modal model, two current state-of-the-art image fusion model and a multi-modal domain-adaptive fusion model (M-DAFM) based on deep learning methods. We evaluated and analyzed the performance of these constructed models in predicting preoperative MVI using the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), and net reclassification improvement (NRI) methods. Results: In comparison with all models, M-DAFM achieved the highest AUC values across the three datasets (0.8013 for the training set, 0.7839 for the test set, and 0.7454 for the test1 set). Notably, in the test set, M-DAFM's Decision Curve Analysis (DCA) curves consistently demonstrated favorable or optimal net benefits within the 0-0.65 threshold probability range. Additionally, the Net Reclassification Improvement (NRI) values between M-DAFM and the three single-modal models, as well as the simple concatenation model, were all greater than 0 (all p < 0.05). Similarly, the NRI values between M-DAFM and the two current state-of-the-art image fusion models were also greater than 0. These findings collectively indicate that M-DAFM effectively integrates valuable information from multi-phase CT images, thereby enhancing the model's preoperative predictive performance for MVI. Conclusion: The M-DAFM proposed in this study presents an innovative approach to improve the preoperative predictive performance of MVI.

Predicting microvascular invasion in hepatocellular carcinoma with a CT- and MRI-based multimodal deep learning model.

PURPOSE: To investigate the value of a multimodal deep learning (MDL) model based on computed tomography (CT) and magnetic resonance imaging (MRI) for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC). METHODS: A total of 287 patients with HCC from our institution and 58 patients from another individual institution were included. Among these, 119 patients with only CT data and 116 patients with only MRI data were selected for single-modality deep learning model development, after which select parameters were migrated for MDL model development with transfer learning (TL). In addition, 110 patients with simultaneous CT and MRI data were divided into a training cohort (n = 66) and a validation cohort (n = 44). We input the features extracted from DenseNet121 into an extreme learning machine (ELM) classifier to construct a classification model. RESULTS: The area under the curve (AUC) of the MDL model was 0.844, which was superior to that of the single-phase CT (AUC = 0.706-0.776, P < 0.05), single-sequence MRI (AUC = 0.706-0.717, P < 0.05), single-modality DL model (AUCall-phase CT = 0.722, AUCall-sequence MRI = 0.731; P < 0.05), clinical (AUC = 0.648, P < 0.05), but not to that of the delay phase (DP) and in-phase (IP) MRI and portal venous phase (PVP) CT models. The MDL model achieved better performance than models described above (P < 0.05). When combined with clinical features, the AUC of the MDL model increased from 0.844 to 0.871. A nomogram, combining deep learning signatures (DLS) and clinical indicators for MDL models, demonstrated a greater overall net gain than the MDL models (P < 0.05). CONCLUSION: The MDL model is a valuable noninvasive technique for preoperatively predicting MVI in HCC.

Deep learning vs. robust federal learning for distinguishing adrenal metastases from benign lesions with multi-phase CT images.

Background: Differentiating adrenal adenomas from metastases poses a significant challenge, particularly in patients with a history of extra-adrenal malignancy. This study investigates the performance of three-phase computed tomography (CT) based robust federal learning algorithm and traditional deep learning for distinguishing metastases from benign adrenal lesions. Material and methods: This retrospective analysis includes 1187 instances who underwent three-phase CT scans between January 2008 and March 2021, comprising 720 benign lesions and 467 metastases. Utilizing the three-phase CT images, both a Robust Federal Learning Signature (RFLS) and a traditional Deep Learning Signature (DLS) were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression. Their diagnostic capabilities were subsequently validated and compared using metrics such as the Areas Under the Receiver Operating Curve (AUCs), Net Reclassification Improvement (NRI), and Decision Curve Analysis (DCA). Results: Compared with DLS, the RFLS showed better capability in distinguishing metastases from benign adrenal lesions (average AUC: 0.816 vs.0.798, NRI = 0.126, P < 0.072; 0.889 vs.0.838, NRI = 0.209, P < 0.001; 0.903 vs.0.825, NRI = 0.643, p < 0.001) in the four-testing cohort, respectively. DCA showed that the RFLS added more net benefit than DLS for clinical utility. Moreover, Comparison with state-of-the-art federal learning methods, the results once again confirmed that the RFLS significantly improved the diagnostic performance based on three-phase CT (AUC: AP, 0.727 vs. 0.757 vs. 0.739 vs. 0.796; PCP, 0.781 vs. 0.851 vs. 0.790 vs. 0.882; VP, 0.789 vs. 0.814 vs. 0.779 vs. 0.886). Conclusion: RFLS was superior to DLS for preoperative distinguishing metastases from benign adrenal lesions with multi-phase CT Images.

Robustly federated learning model for identifying high-risk patients with postoperative gastric cancer recurrence.

The prediction of patient disease risk via computed tomography (CT) images and artificial intelligence techniques shows great potential. However, training a robust artificial intelligence model typically requires large-scale data support. In practice, the collection of medical data faces obstacles related to privacy protection. Therefore, the present study aims to establish a robust federated learning model to overcome the data island problem and identify high-risk patients with postoperative gastric cancer recurrence in a multicentre, cross-institution setting, thereby enabling robust treatment with significant value. In the present study, we collect data from four independent medical institutions for experimentation. The robust federated learning model algorithm yields area under the receiver operating characteristic curve (AUC) values of 0.710, 0.798, 0.809, and 0.869 across four data centres. Additionally, the effectiveness of the algorithm is evaluated, and both adaptive and common features are identified through analysis.

Differentiating adrenal metastases from benign lesions with multiphase CT imaging: Deep learning could play an active role in assisting radiologists.

OBJECTIVES: To develop and externally validate multiphase CT-based deep learning (DL) models for differentiating adrenal metastases from benign lesions. MATERIALS AND METHODS: This retrospective two-center study included 1146 adrenal lesions from 1059 patients who underwent multiphase CT scanning between January 2008 and March 2021. The study encompassed 564 surgically confirmed adenomas, along with 135 benign lesions and 447 metastases confirmed by observation. DL models based on multiphase CT images were developed, validated and tested. The diagnostic performance of the classification models, imaging phases and radiologists with or without DL were compared using accuracy (ACC) and receiver operating characteristic (ROC) curves. Integrated discrimination improvement (IDI) analysis and the DeLong test were used to compare the area under the curve (AUC) among models. Decision curve analysis (DCA) was used to assess the clinical usefulness of the predictive models. RESULTS: The DL signature based on LASSO (DLSL) had a higher AUC than that of the other classification models (IDI > 0, P < 0.05). Furthermore, the precontrast phase (PCP)-based DLSL performed best in the independent external validation (AUC = 0.881, ACC = 82.9 %) and clinical test cohorts (AUC = 0.790, ACC = 70.4 %), outperforming DLSL based on the other single-phase or three-phase images (IDI > 0, P < 0.05). DCA demonstrated that PCP-based DLSL provided a higher net benefit (0.01-0.95). The diagnostic performance led to statistically significant improvements when radiologists incorporated the DL model, with the AUC improving by 0.056-0.159 and the ACC improving by 0.069-0.178 (P < 0.05). CONCLUSION: The DL model based on PCP CT images performed acceptably in differentiating adrenal metastases from benign lesions, and it may assist radiologists in accurate tumor staging for patients with a history of extra-adrenal malignancy.

Identifying Solitary Granulomatous Nodules from Solid Lung Adenocarcinoma: Exploring Robust Image Features with Cross-Domain Transfer Learning.

PURPOSE: This study aimed to find suitable source domain data in cross-domain transfer learning to extract robust image features. Then, a model was built to preoperatively distinguish lung granulomatous nodules (LGNs) from lung adenocarcinoma (LAC) in solitary pulmonary solid nodules (SPSNs). METHODS: Data from 841 patients with SPSNs from five centres were collected retrospectively. First, adaptive cross-domain transfer learning was used to construct transfer learning signatures (TLS) under different source domain data and conduct a comparative analysis. The Wasserstein distance was used to assess the similarity between the source domain and target domain data in cross-domain transfer learning. Second, a cross-domain transfer learning radiomics model (TLRM) combining the best performing TLS, clinical factors and subjective CT findings was constructed. Finally, the performance of the model was validated through multicentre validation cohorts. RESULTS: Relative to other source domain data, TLS based on lung whole slide images as source domain data (TLS-LW) had the best performance in all validation cohorts (AUC range: 0.8228-0.8984). Meanwhile, the Wasserstein distance of TLS-LW was 1.7108, which was minimal. Finally, TLS-LW, age, spiculated sign and lobulated shape were used to build the TLRM. In all validation cohorts, The AUC ranges were 0.9074-0.9442. Compared with other models, decision curve analysis and integrated discrimination improvement showed that TLRM had better performance. CONCLUSIONS: The TLRM could assist physicians in preoperatively differentiating LGN from LAC in SPSNs. Furthermore, compared with other images, cross-domain transfer learning can extract robust image features when using lung whole slide images as source domain data and has a better effect.

CT-based radiomics signature of visceral adipose tissue for prediction of disease progression in patients with Crohn's disease: A multicentre cohort study.

Background: Visceral adipose tissue (VAT) is involved in the pathogenesis of Crohn's disease (CD). However, data describing its effects on CD progression remain scarce. We developed and validated a VAT-radiomics model (RM) using computed tomography (CT) images to predict disease progression in patients with CD and compared it with a subcutaneous adipose tissue (SAT)-RM. Methods: This retrospective study included 256 patients with CD (training, n = 156; test, n = 100) who underwent baseline CT examinations from June 19, 2015 to June 14, 2020 at three tertiary referral centres (The First Affiliated Hospital of Sun Yat-Sen University, The First Affiliated Hospital of Shantou University Medical College, and The First People's Hospital of Foshan City) in China. Disease progression referred to the development of penetrating or stricturing diseases or the requirement for CD-related surgeries during follow-up. A total of 1130 radiomics features were extracted from VAT on CT in the training cohort, and a machine-learning-based VAT-RM was developed to predict disease progression using selected reproducible features and validated in an external test cohort. Using the same modeling methodology, a SAT-RM was developed and compared with the VAT-RM. Findings: The VAT-RM exhibited satisfactory performance for predicting disease progression in total test cohort (the area under the ROC curve [AUC] = 0.850, 95% confidence Interval [CI] 0.764-0.913, P < 0.001) and in test cohorts 1 (AUC = 0.820, 95% CI 0.687-0.914, P < 0.001) and 2 (AUC = 0.871, 95% CI 0.744-0.949, P < 0.001). No significant differences in AUC were observed between test cohorts 1 and 2 (P = 0.673), suggesting considerable efficacy and robustness of the VAT-RM. In the total test cohort, the AUC of the VAT-RM for predicting disease progression was higher than that of SAT-RM (AUC = 0.786, 95% CI 0.692-0.861, P < 0.001). On multivariate Cox regression analysis, the VAT-RM (hazard ratio [HR] = 9.285, P = 0.005) was the most important independent predictor, followed by the SAT-RM (HR = 3.280, P = 0.060). Decision curve analysis further confirmed the better net benefit of the VAT-RM than the SAT-RM. Moreover, the SAT-RM failed to significantly improve predictive efficacy after it was added to the VAT-RM (integrated discrimination improvement = 0.031, P = 0.102). Interpretation: Our results suggest that VAT is an important determinant of disease progression in patients with CD. Our VAT-RM allows the accurate identification of high-risk patients prone to disease progression and offers notable advantages over SAT-RM. Funding: This study was supported by the National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Nature Science Foundation of Shenzhen, and Young S&T Talent Training Program of Guangdong Provincial Association for S&T. Translation: For the Chinese translation of the abstract see Supplementary Materials section.

Classification of tumor from computed tomography images: A brain-inspired multisource transfer learning under probability distribution adaptation.

Preoperative diagnosis of gastric cancer and primary gastric lymphoma is challenging and has important clinical significance. Inspired by the inductive reasoning learning of the human brain, transfer learning can improve diagnosis performance of target task by utilizing the knowledge learned from the other domains (source domain). However, most studies focus on single-source transfer learning and may lead to model performance degradation when a large domain shift exists between the single-source domain and target domain. By simulating the multi-modal information learning and transfer mechanism of human brain, this study designed a multisource transfer learning feature extraction and classification framework, which can enhance the prediction performance of the target model by using multisource medical data (domain). First, this manuscript designs a feature extraction network that takes the maximum mean difference based on the Wasserstein distance as an adaptive measure of probability distribution and extracts the domain-specific invariant representations between source and target domain data. Then, aiming at the random generation of parameters bringing uncertainties to prediction accuracy and generalization ability of extreme learning machine network, the 1-norm regularization is used to implement sparse constraints of the output weight matrix and improve the robustness of the model. Finally, some experiments are carried out on the data of two medical centers. The experimental results show that the area under curves (AUCs) of the method are 0.958 and 0.929 in the two validation cohorts, respectively. The method in this manuscript can provide doctors with a better diagnostic reference, which has certain practical significance.