Deep learning system for malignancy risk prediction in cystic renal lesions: a multicenter study.

OBJECTIVES: To develop an interactive, non-invasive artificial intelligence (AI) system for malignancy risk prediction in cystic renal lesions (CRLs). METHODS: In this retrospective, multicenter diagnostic study, we evaluated 715 patients. An interactive geodesic-based 3D segmentation model was created for CRLs segmentation. A CRLs classification model was developed using spatial encoder temporal decoder (SETD) architecture. The classification model combines a 3D-ResNet50 network for extracting spatial features and a gated recurrent unit (GRU) network for decoding temporal features from multi-phase CT images. We assessed the segmentation model using sensitivity (SEN), specificity (SPE), intersection over union (IOU), and dice similarity (Dice) metrics. The classification model's performance was evaluated using the area under the receiver operator characteristic curve (AUC), accuracy score (ACC), and decision curve analysis (DCA). RESULTS: From 2012 to 2023, we included 477 CRLs (median age, 57 [IQR: 48-65]; 173 men) in the training cohort, 226 CRLs (median age, 60 [IQR: 52-69]; 77 men) in the validation cohort, and 239 CRLs (median age, 59 [IQR: 53-69]; 95 men) in the testing cohort (external validation cohort 1, cohort 2, and cohort 3). The segmentation model and SETD classifier exhibited excellent performance in both validation (AUC = 0.973, ACC = 0.916, Dice = 0.847, IOU = 0.743, SEN = 0.840, SPE = 1.000) and testing datasets (AUC = 0.998, ACC = 0.988, Dice = 0.861, IOU = 0.762, SEN = 0.876, SPE = 1.000). CONCLUSION: The AI system demonstrated excellent benign-malignant discriminatory ability across both validation and testing datasets and illustrated improved clinical decision-making utility. CRITICAL RELEVANCE STATEMENT: In this era when incidental CRLs are prevalent, this interactive, non-invasive AI system will facilitate accurate diagnosis of CRLs, reducing excessive follow-up and overtreatment. KEY POINTS: The rising prevalence of CRLs necessitates better malignancy prediction strategies. The AI system demonstrated excellent diagnostic performance in identifying malignant CRL. The AI system illustrated improved clinical decision-making utility.

Value of CT-Based Deep Learning Model in Differentiating Benign and Malignant Solid Pulmonary Nodules ≤ 8 mm.

RATIONALE AND OBJECTIVES: We examined the effectiveness of computed tomography (CT)-based deep learning (DL) models in differentiating benign and malignant solid pulmonary nodules (SPNs) ≤ 8 mm. MATERIALS AND METHODS: The study patients (n = 719) were divided into internal training, internal validation, and external validation cohorts; all had small SPNs and had undergone preoperative chest CTs and surgical resection. We developed five DL models incorporating features of the nodule and five different peri-nodular regions with the Multiscale Dual Attention Network (MDANet) to differentiate benign and malignant SPNs. We selected the best-performing model, which was then compared to four conventional algorithms (VGG19, ResNet50, ResNeXt50, and DenseNet121). Furthermore, another five DL models were constructed using MDANet to distinguish benign tumors from inflammatory nodules and the one performed best was selected out. RESULTS: Model 4, which incorporated the nodule and 15 mm peri-nodular region, best differentiated benign and malignant SPNs. The model had an area under the curve (AUC), accuracy, recall, precision, and F1-score of 0.730, 0.724, 0.711, 0.705, and 0.707 in the external validation cohort. Model 4 also performed better than the other four conventional algorithms. Model 8, which incorporated the nodule and 10 mm peri-nodular region, was the best model for distinguishing benign tumors from inflammatory nodules. The model had an AUC, accuracy, recall, precision, and F1-score of 0.871, 0.938, 0.863, 0.904, and 0.882 in the external validation cohort. CONCLUSION: The study concludes that CT-based DL models built with MDANet can accurately discriminate among small benign and malignant SPNs, benign tumors and inflammatory nodules.

Bubble-like lucency in pulmonary ground glass nodules on computed tomography: a specific pattern of air-containing space for diagnosing neoplastic lesions.

PURPOSE: To investigate the computed tomography (CT) characteristics of air-containing space and its specific patterns in neoplastic and non-neoplastic ground glass nodules (GGNs) for clarifying their significance in differential diagnosis. MATERIALS AND METHODS: From January 2015 to October 2022, 1328 patients with 1,350 neoplastic GGNs and 462 patients with 465 non-neoplastic GGNs were retrospectively enrolled. Their clinical and CT data were analyzed and compared with emphasis on revealing the differences of air-containing space and its specific patterns (air bronchogram and bubble-like lucency [BLL]) between neoplastic and non-neoplastic GGNs and their significance in differentiating them. RESULTS: Compared with patients with non-neoplastic GGNs, female was more common (P < 0.001) and lesions were larger (P < 0.001) in those with neoplastic ones. Air bronchogram (30.1% vs. 17.2%), and BLL (13.0% vs. 2.6%) were all more frequent in neoplastic GGNs than in non-neoplastic ones (each P < 0.001), and the BLL had the highest specificity (93.6%) in differentiation. Among neoplastic GGNs, the BLL was more frequently detected in the larger (14.9 ± 6.0 mm vs. 11.4 ± 4.9 mm, P < 0.001) and part-solid (15.3% vs. 10.7%, P = 0.011) ones, and its incidence significantly increased along with the invasiveness (9.5-18.0%, P = 0.001), whereas no significant correlation was observed between the occurrence of BLL and lesion size, attenuation, or invasiveness. CONCLUSION: The air containing space and its specific patterns are of great value in differentiating GGNs, while BLL is a more specific and independent sign of neoplasms.

Accuracy of solid portion size measured on multiplanar volume rendering images for assessing invasiveness in lung adenocarcinoma manifesting as subsolid nodules.

Background: The solid component of subsolid nodules (SSNs) is closely associated with the invasiveness of lung adenocarcinoma, and its accurate assessment is crucial for selecting treatment method. Therefore, this study aimed to evaluate the accuracy of solid component size within SSNs measured on multiplanar volume rendering (MPVR) and compare it with the dimensions of invasive components on pathology. Methods: A pilot study was conducted using a chest phantom to determine the optimal MPVR threshold for the solid component within SSN, and then clinical validation was carried out by retrospective inclusion of patients with pathologically confirmed solitary SSN from October 2020 to October 2021. The radiological tumor size on MPVR and solid component size on MPVR (RSSm) and on lung window (RSSl) were measured. The size of the tumor and invasion were measured on the pathological section, and the invasion, fibrosis, and inflammation within SSNs were also recorded. The measurement difference between computed tomography (CT) and pathology, inter-observer and inter-measurement agreement were analyzed. Receiver operating characteristic (ROC) analysis and Bland-Altman plot were performed to evaluate the diagnostic efficiency of MPVR. Results: A total of 142 patients (mean age, 54±11 years, 39 men) were retrospectively enrolled in the clinical study, with 26 adenocarcinomas in situ, 92 minimally invasive adenocarcinomas (MIAs), and 24 invasive adenocarcinomas (IAs). The RSSl was significantly smaller than pathological invasion size with fair inter-measurement agreement [intraclass correlation coefficient (ICC) =0.562, P<0.001] and moderate interobserver agreement (ICC =0.761, P<0.001). The RSSm was significantly larger than pathological invasion size with the excellent inter-measurement agreement (ICC =0.829, P<0.001) and excellent (ICC =0.952, P<0.001) interobserver agreement. ROC analysis showed that the cutoff value of RSSm for differentiating adenocarcinoma in situ from MIA and MIA from IA was 1.85 and 6.45 mm (sensitivity: 93.8% and 95.5%, specificity: 85.7% and 88.2%, 95% confidence internal: 0.914-0.993 and 0.900-0.983), respectively. The positive predictive value-and negative predictive value of MPVR in predicting invasiveness were 92.8% and 100%, respectively. Conclusions: Using MPVR to predict the invasive degree of SSN had high accuracy and good inter-observer agreement, which is superior to lung window measurements and helpful for clinical decision-making.

Potential Role of Intrapulmonary Concomitant Lesions in Differentiating Non-Neoplastic and Neoplastic Ground Glass Nodules.

Purpose: To determine the value of intrapulmonary concomitant lesions in differentiating non-neoplastic and neoplastic ground-glass nodules (GGNs). Patients and Methods: From January 2014 to March 2022, 395 and 583 patients with confirmed non-neoplastic and neoplastic GGNs were retrospectively enrolled. Their clinical and chest CT data were evaluated. The CT features of target GGNs and intrapulmonary concomitant lesions in these two groups were analyzed and compared, and the role of intrapulmonary concomitant lesions in improving differentiation was evaluated. Results: The intrapulmonary concomitant lesions were more common in patients with non-neoplastic GGNs than in those with neoplastic ones (87.88% vs 82.18%, P = 0.015). Specifically, patients with non-neoplastic GGNs had a higher incidence of multiple solid nodules (SNs), patchy ground-glass opacity/consolidation, and fibrosis/calcification in any lung fields (each P < 0.05). Logistic regression analysis indicated that patients < 44 years old, diameter < 7.35 mm, irregular shape, and coarse margin or ill-defined boundary for target GGN, pleural thickening, and concomitant SNs in the same lobe and fibrosis or calcification in any lung field were independent indicators for predicting non-neoplastic GGNs. The AUC of the model for predicting non-neoplastic GGNs increased from 0.894 to 0.926 (sensitivity, 83.10%; specificity, 87.10%) after including the concomitant lesions in the patients' clinical characteristics and CT features of target GGNs (P < 0.0001). Conclusion: Besides the patients' clinical characteristics and CT features of target GGNs, the concomitant multiple SNs in the same lobe and fibrosis/calcification in any lung field should be considered in further differentiating non-neoplastic and neoplastic GGNs.

Solitary lung adenocarcinoma: follow-up CT, pathological-molecular characteristics, and surgical prognosis for different morphological classifications.

OBJECTIVE: To investigate the dynamic changes during follow-up computed tomography (CT), histological subtypes, gene mutation status, and surgical prognosis for different morphological presentations of solitary lung adenocarcinomas (SLADC). MATERIALS AND METHODS: This retrospective study compared dynamic tumor changes and volume doubling time (VDT) in 228 patients with SLADC (morphological types I-IV) who had intermittent growth during follow-ups. The correlation between the morphological classification and histological subtypes, gene mutation status, and surgical prognosis was evaluated. RESULTS: Among the 228 patients, 66 (28.9%) were classified as type I, 123 (53.9%) as type II, 16 (7%) as type III, and 23 (10.1%) as type IV. Type I had the shortest VDT (254 days), followed by types IV (381 days) and III (501 days), and then type II (993 days) (p < 0.05 each). Type I had a greater proportion of solid/micropapillary-predominant pattern than type II, and the lepidic-predominant pattern was more common in type II and III than in type I (p < 0.05 each). Furthermore, type II and IV SLADCs were correlated with positive epidermal growth factor receptor mutation (p < 0.05 each). Lastly, the Kaplan-Meier curves showed that the disease-free survival was longest for patients with type II tumors, followed by those with type III and IV tumors, and then those with type I tumors (p < 0.001 each). CONCLUSION: A good understanding of the natural progression and pathological-molecular characteristics of different morphological SLADC types can help make accurate diagnoses, develop individual treatment strategies, and predict patient outcomes. CRITICAL RELEVANCE STATEMENT: A good understanding of the natural progression and pathological-molecular characteristics of different morphological solitary lung adenocarcinoma types can help make accurate diagnoses, develop individual treatment strategies, and predict patient outcomes. KEY POINTS: • Type I-IV solitary lung adenocarcinomas exhibit varying natural progression on serial CT scans. • Morphological classification of solitary lung adenocarcinomas predicts histological subtype, gene status, and surgical prognosis. • This classification of solitary lung adenocarcinomas may help improve diagnostic, therapeutic, and prognosticating abilities.

Differentiation of pulmonary solid nodules attached to the pleura detected by thin-section CT.

BACKGROUND: Pulmonary solid pleura-attached nodules (SPANs) are not very commonly detected and thus not well studied and understood. This study aimed to identify the clinical and CT characteristics for differentiating benign and malignant SPANs. RESULTS: From January 2017 to March 2023, a total of 295 patients with 300 SPANs (128 benign and 172 malignant) were retrospectively enrolled. Between benign and malignant SPANs, there were significant differences in patients' age, smoking history, clinical symptoms, CT features, nodule-pleura interface, adjacent pleural change, peripheral concomitant lesions, and lymph node enlargement. Multivariate analysis revealed that smoking history (odds ratio [OR], 2.016; 95% confidence interval [CI], 1.037-3.919; p = 0.039), abutting the mediastinal pleura (OR, 3.325; 95% CI, 1.235-8.949; p = 0.017), nodule diameter (> 15.6 mm) (OR, 2.266; 95% CI, 1.161-4.423; p = 0.016), lobulation (OR, 8.922; 95% CI, 4.567-17.431; p < 0.001), narrow basement to pleura (OR, 6.035; 95% CI, 2.847-12.795; p < 0.001), and simultaneous hilar and mediastinal lymph nodule enlargement (OR, 4.971; 95% CI, 1.526-16.198; p = 0.008) were independent predictors of malignant SPANs, and the area under the curve (AUC) of this model was 0.890 (sensitivity, 82.0%, specificity, 77.3%) (p < 0.001). CONCLUSION: In patients with a smoking history, SPANs abutting the mediastinal pleura, having larger size (> 15.6 mm in diameter), lobulation, narrow basement, or simultaneous hilar and mediastinal lymph nodule enlargement are more likely to be malignant. CRITICAL RELEVANCE STATEMENT: The benign and malignant SPANs have significant differences in clinical and CT features. Understanding the differences between benign and malignant SPANs is helpful for selecting the high-risk ones and avoiding unnecessary surgical resection. KEY POINTS: • The solid pleura-attached nodules (SPANs) are closely related to the pleura. • Relationship between nodule and pleura and pleural changes are important for differentiating SPANs. • Benign SPANs frequently have broad pleural thickening or embed in thickened pleura. • Smoking history and lesions abutting the mediastinal pleura are indicators of malignant SPANs. • Malignant SPANs usually have larger diameters, lobulation signs, narrow basements, and lymphadenopathy.

Significance of marginal vessels in differentiating peripheral small-cell lung cancer and benign lung tumor.

BACKGROUND: Some peripheral small cell lung cancers (pSCLCs) and benign lung tumors (pBLTs) have similar morphological features but different treatment and prognosis. PURPOSE: To determine the significance of marginal vessels in differentiating pSCLCs and pBLTs. MATERIAL AND METHODS: A total of 57 and 95 patients with pathological confirmed nodular (≤3 cm) pSCLC and pBLT with similar morphological features were enrolled in this study retrospectively. The patients' clinical characteristics and computed tomography (CT) features of tumors and marginal vessels (vessels connecting with tumors) were analyzed and compared. RESULTS: Compared with pBLTs, pSCLCs had a larger diameter (P = 0.001) but lower enhancement (P = 0.015) and fewer had calcification (P = 0.013). Compared with pBLTs, more lesions had proximal (70.2% vs. 22.1%) and distal (59.6% vs. 4.2%) marginal vessels in pSCLCs (each P < 0.0001). In addition, in pSCLCs, the numbers of proximal (1.3 ± 1.4 vs. 0.3 ± 0.6), distal (2.4 ± 3.1 vs. 0.1 ± 0.5), and total (3.6 ± 3.5 vs. 0.4 ± 1.0) marginal vessels were all more than those in pBLTs (each P < 0.001). Receiver operating characteristic curve analysis revealed the positive distal marginal vessel sign had the highest specificity (95.8%), and the number of total marginal vessels had the best performance in discriminating pSCLC from pBLT (cutoff value = 1.5, AUC = 0.80, 95% CI = 0.72-0.89, sensitivity = 70.2%, and specificity = 91.6%). CONCLUSION: For peripheral solid nodules similar to pBLTs but without any calcification, the possibility of pSCLC should be considered if they have multiple marginal vessels (≥2), especially the distal ones.

Comparison of different noncontrast computed tomographic markers for predicting early perihematomal edema expansion in patients with intracerebral hemorrhage.

OBJECTIVES: Noncontrast computed tomography (NCCT) imaging markers are associated with early perihematomal edema (PHE) growth. The aim of this study was to compare the predictive value of different NCCT markers in predicting early PHE expansion. METHODS: ICH patients who underwent baseline CT scan within 6 h of symptoms onset and follow-up CT scan within 36 h between July 2011 and March 2017 were included in this study. The predictive value of hypodensity, satellite sign, heterogeneous density, irregular shape, blend sign, black hole sign, island sign and expansion-prone hematoma for early perihematomal edema expansion were assessed, separately. RESULTS: 214 patients were included in our final analysis. After adjusting for ICH characteristics, hypodensity, blend sign, island sign and expansion-prone hematoma are still predictors of early perihematomal edema expansion in multivariable logistics regression analysis (all P < 0.05). The area under the receiver operating characteristic (ROC) curve of expansion-prone hematoma was significantly larger than the area under the ROC curve of hypodensity, blend sign and island sign in predicting PHE expansion (P = 0.003, P < 0.001 and P = 0.002, respectively). CONCLUSION: Compared with single NCCT imaging markers, expansion-prone hematoma seems to be optimal predictor for early PHE expansion than any single NCCT imaging marker.

Reticulation Sign on Thin-Section CT: Utility for Predicting Invasiveness of Pure Ground-Glass Nodules.

BACKGROUND. Pure ground-glass nodules (pGGNs) may represent a diverse range of histologic entities of varying aggressiveness. OBJECTIVE. The purpose of this study was to evaluate the use of the reticulation sign on thin-section CT images for predicting the invasiveness of pGGNs. METHODS. This retrospective study included 795 patients (mean age, 53.4 ± 11.1 [SD] years; 254 men, 541 women) with a total of 876 pGGNs on thin-section CT that underwent resection between January 2015 and April 2022. Two fellowship-trained thoracic radiologists independently reviewed unenhanced CT images to assess the pGGNs for a range of features, including diameter, attenuation, location, shape, air bronchogram, bubble lucency, vascular change, lobulation, spiculation, margins, pleural indentation, and the reticulation sign (defined as multiple small linear opacities resembling a mesh or a net); differences were resolved by consensus. The relationship between the reticulation sign and lesion invasiveness on pathologic assessment was evaluated. RESULTS. On pathologic assessment, the 876 pGGNs included 163 nonneoplastic and 713 neoplastic pGGNs (323 atypical adenomatous hyperplasias [AAHs] or adenocarcinomas in situ [AISs], 250 minimally invasive adenocarcinomas [MIAs], and 140 invasive adenocarcinomas [IACs]). Interobserver agreement for the reticulation sign, expressed as kappa, was 0.870. The reticulation sign was detected in 0.0% of nonneoplastic lesions, 0.0% of AAHs/AISs, 6.8% of MIAs, and 54.3% of IACs. The reticulation sign had sensitivity of 24.0% and specificity of 100.0% for a diagnosis of MIA or IAC and sensitivity of 54.3% and specificity of 97.7% for a diagnosis of IAC. In multivariable regression analyses including all of the assessed CT features, the reticulation sign was a significant independent predictor of IAC (OR, 3.64; p = .001) but was not a significant independent predictor of MIA or IAC. CONCLUSION. The reticulation sign, when observed in a pGGN on thin-section CT, has high specificity (albeit low sensitivity) for invasiveness and is an independent predictor of IAC. CLINICAL IMPACT. Those pGGNs that show the reticulation sign should be strongly suspected to represent IAC; this suspicion may guide risk assessments and follow-up recommendations.

Correlations Between Inflammatory Cell Infiltration and Relative Density and the Boundary Manifestation of Pulmonary Non-Neoplastic Ground Glass Nodules.

Purpose: To investigate the influence factors for the various boundary manifestations of pulmonary non-neoplastic ground glass nodules (GGNs) on computed tomography (CT). Materials and Methods: From January 2015 to March 2022, a total of 280 patients with 318 non-neoplastic GGNs were enrolled. The correlations between degree of inflammatory cell infiltration and relative density (ΔCT) and the boundary manifestations of lesions were evaluated, respectively. Results: Nongranulomatous nodules (283, 89.0%) with fibrous tissue proliferation and/or inflammatory cells as the predominant pathological findings were the most common non-neoplastic GGNs, followed by granulomatous nodules (28, 8.8%). Among nongranulomatous GGNs, cases with more and less/no inflammatory cells were 15 (10.9%) and 122 (89.1%) in 137 well-defined ones with smooth margin, 16 (24.6%) and 49 (75.4%) in 65 well-defined ones with coarse margin, 43 (91.5%) and 4 (8.5%) in 47 ill-defined ones with higher ΔCT (>151HU), and 4 (11.8%) and 30 (88.2%) in 34 ill-defined ones with lower ΔCT (< 151HU). The proportion of cases with more inflammatory cells in well-defined nodules was similar to that in ill-defined ones with lower ΔCT (P = 0.587) but significantly lower than that in ill-defined ones with higher ΔCT (P < 0.001). Among the granulomatous nodules, ill-defined cases with higher ΔCT (16, 57.1%) were the most common, and they (7/8, 87.5%) frequently had changes during short-term follow-up. Conclusion: Nongranulomatous nodules are the most common non-neoplastic GGNs, their diverse boundary manifestations closely correlate with degree of inflammatory cell infiltration and density difference.

Prediction of Early Perihematomal Edema Expansion Based on Noncontrast Computed Tomography Radiomics and Machine Learning in Intracerebral Hemorrhage.

OBJECTIVES: To investigate the predictive value of noncontrast computed tomography (NCCT) models based on radiomics features and machine learning for early perihematomal edema (PHE) expansion in patients with spontaneous intracerebral hemorrhage (ICH). METHODS: We retrospectively reviewed NCCT data from 214 patients with spontaneous ICH. All radiomics features were extracted from volume of interest of hematomas on admission scans. A total of 8 machine learning methods were applied for constructing models in the training and the test set. Receiver operating characteristic analysis and the areas under the curve were used to evaluate the predictive value. RESULTS: A total of 23 features were finally selected to establish models of early PHE expansion after feature screening. Patients were randomly assigned into training (n = 171) and test (n = 43) sets. The accuracy, sensitivity, and specificity in the test set were 72.1%, 90.0%, and 66.7% for the support vector machine model; 79.1%, 70.0%, and 84.4% for the k-nearest neighbor model; 88.4%, 90.0%, and 87.9% for the logistic regression model; 74.4%, 90.0%, and 69.7% for the extra tree model; 74.4%, 90.0%, and 69.7% for the extreme gradient boosting model; 83.7%, 100%, and 78.8% for the multilayer perceptron (MLP) model; 72.1%, 100%, and 65.6% for the light gradient boosting machine model; and 60.5%, 90.0%, and 53.1% for the random forest model, respectively. CONCLUSIONS: The MLP model seemed to be the best model for prediction of PHE expansion in patients with ICH. NCCT models based on radiomics features and machine learning could predict early PHE expansion and improve the discrimination of identify spontaneous intracerebral hemorrhage patients at risk of early PHE expansion.

A combined non-enhanced CT radiomics and clinical variable machine learning model for differentiating benign and malignant sub-centimeter pulmonary solid nodules.

BACKGROUND: Radiomics has been used to predict pulmonary nodule (PN) malignancy. However, most of the studies focused on pulmonary ground-glass nodules. The use of computed tomography (CT) radiomics in pulmonary solid nodules, particularly sub-centimeter solid nodules, is rare. PURPOSE: This study aims to develop a radiomics model based on non-enhanced CT images that can distinguish between benign and malignant sub-centimeter pulmonary solid nodules (SPSNs, <1 cm). METHODS: The clinical and CT data of 180 SPSNs confirmed by pathology were analyzed retrospectively. All SPSNs were divided into two groups: training set (n = 144) and testing set (n = 36). From non-enhanced chest CT images, over 1000 radiomics features were extracted. Radiomics feature selection was performed using the analysis of variance and principal component analysis. The selected radiomics features were fed into a support vector machine (SVM) to develop a radiomics model. The clinical and CT characteristics were used to develop a clinical model. Associating non-enhanced CT radiomics features with clinical factors were used to develop a combined model using SVM. The performance was evaluated using the area under the receiver-operating characteristic curve (AUC). RESULTS: The radiomics model performed well in distinguishing between benign and malignant SPSNs, with an AUC of 0.913 (95% confidence interval [CI], 0.862-0.954) in the training set and an AUC of 0.877 (95% CI, 0.817-0.924) in the testing set. The combined model outperformed the clinical and radiomics models with an AUC of 0.940 (95% CI, 0.906-0.969) in the training set and an AUC of 0.903 (95% CI, 0.857-0.944) in the testing set. CONCLUSIONS: Radiomics features based on non-enhanced CT images can be used to differentiate SPSNs. The combined model, which included radiomics and clinical factors, had the best discrimination power between benign and malignant SPSNs.

Quantitative evaluation of density variability in the lesion-lung boundary zone to differentiate pulmonary subsolid nodules.

Background: Transition of the CT values from nodule to peripheral normal lung is related to pathological changes and may be a potential indicator for differential diagnosis. This study investigated the significance of the standard deviation (SD) values in the lesion-lung boundary zone when differentiating between benign and neoplastic subsolid nodules (SSNs). Methods: From January 2012 to July 2021, a total of 229 neoplastic and 84 benign SSNs confirmed by pathological examination were retrospectively and nonconsecutively enrolled in this study. The diagnostic study was not registered with a clinical trial platform, and the study protocol was not published. Computed tomography (CT) values of the ground-glass component (CT1), adjacent normal lung tissue (CT2), and lesion-lung boundary zone (CT3) were measured consecutively. The SD of CT3 was recorded to assess density variability. The CT1, CT2, CT3, and SD values were compared between benign and neoplastic SSNs. Results: No significant differences in CT1 and CT2 were observed between benign and neoplastic SSNs (each P value >0.05). CT3 (-736.1±51.0 vs. -792.6±73.9; P<0.001) and its SD (135.6±29.6 vs. 83.6±20.6; P<0.001) in neoplastic SSNs were significantly higher than those in benign SSNs. Moreover, the SD increased with the invasiveness degree of neoplastic SSNs (r=0.657; P<0.001). The receiver operating characteristic (ROC) curve revealed that the area under the curve was 0.927 (95% CI: 0.896-0.959) when using the SD (cutoff value =106.98) as a factor to distinguish SSNs, which increased to 0.966 (95% CI: 0.934-0.985) when including nodules with a CT1 of ≥-715 Hounsfield units (HU) only (cutoff of SD 109.9, sensitivity 0.930, and specificity 0.914). Conclusions: The SD as an objective index is valuable for differentiating SSNs, especially for those with a CT1 of ≥-715 HU, which have a higher possibility of neoplasm if the SD is >109.9.

Deep learning and radiomic feature-based blending ensemble classifier for malignancy risk prediction in cystic renal lesions.

BACKGROUND: The rising prevalence of cystic renal lesions (CRLs) detected by computed tomography necessitates better identification of the malignant cystic renal neoplasms since a significant majority of CRLs are benign renal cysts. Using arterial phase CT scans combined with pathology diagnosis results, a fusion feature-based blending ensemble machine learning model was created to identify malignant renal neoplasms from cystic renal lesions (CRLs). Histopathology results were adopted as diagnosis standard. Pretrained 3D-ResNet50 network was selected for non-handcrafted features extraction and pyradiomics toolbox was selected for handcrafted features extraction. Tenfold cross validated least absolute shrinkage and selection operator regression methods were selected to identify the most discriminative candidate features in the development cohort. Feature's reproducibility was evaluated by intra-class correlation coefficients and inter-class correlation coefficients. Pearson correlation coefficients for normal distribution and Spearman's rank correlation coefficients for non-normal distribution were utilized to remove redundant features. After that, a blending ensemble machine learning model were developed in training cohort. Area under the receiver operator characteristic curve (AUC), accuracy score (ACC), and decision curve analysis (DCA) were employed to evaluate the performance of the final model in testing cohort. RESULTS: The fusion feature-based machine learning algorithm demonstrated excellent diagnostic performance in external validation dataset (AUC = 0.934, ACC = 0.905). Net benefits presented by DCA are higher than Bosniak-2019 version classification for stratifying patients with CRL to the appropriate surgery procedure. CONCLUSIONS: Fusion feature-based classifier accurately distinguished malignant and benign CRLs which outperformed the Bosniak-2019 version classification and illustrated improved clinical decision-making utility.

Prehospital Ultra-Early Neurological Deterioration in Intracerebral Hemorrhage: Definition, Prevalence, and Association with Outcomes.

INTRODUCTION: The objective of this study was to define prehospital ultra-early neurological deterioration (UND) and to investigate the association with functional outcomes in patients with intracerebral hemorrhage (ICH). METHODS: We conducted a prospective cohort study of consecutive acute ICH patients. The stroke severity at onset and hospital admission was assessed using the Chongqing Stroke Scale (CQSS), and prehospital UND was defined as a CQSS increase of ≥2 points between symptoms onset and admission. Early neurological deterioration (END) was defined as the increase of ≥4 points in NIHSS score within the first 24 h after admission. Poor outcome was defined as a modified Rankin Scale (mRS) of 4-6 at 3 months. RESULTS: Prehospital UND occurred in 29 of 169 patients (17.2%). Patients with prehospital UND had a median admission NIHSS score of 17.0 as opposed to those without prehospital UND with a median NIHSS score of 8.5. There were three patterns of neurological deterioration: prehospital UND only in 21 of 169 patients (12.4%), END but without prehospital UND in 20 of 169 patients (11.8%), and continuous neurological deterioration in both phases in 8 patients (4.7%). Prehospital UND was associated with worse 3-month outcomes (median mRS score, 4.0 vs. 2.0, p = 0.002). After adjusting for age, time from onset to admission, END, and systolic blood pressure, prehospital UND was an independent predictor of poor outcome (odds ratio [OR] 3.27, 95% confidence interval [CI] 1.26-8.48, p = 0.015). CONCLUSION: Prehospital UND occurs in approximately 1 in 7 patients between symptom onset and admission and is associated with poor functional outcome in patients with ICH. Further research is needed to investigate the prehospital UND in the prehospital phase in the triage of patients with ICH.

Differential diagnosis of benign and malignant patchy ground-glass opacity by thin-section computed tomography.

BACKGROUND: Previous studies confirmed that ground-glass nodules (GGNs) with certain CT manifestations had a higher probability of malignancy. However, differentiating patchy ground-glass opacities (GGOs) and GGNs has not been discussed solely. This study aimed to investigate the differences between the CT features of benign and malignant patchy GGOs to improve the differential diagnosis. METHODS: From January 2016 to September 2021, 226 patients with 247 patchy GGOs (103 benign and 144 malignant) confirmed by postoperative pathological examination or follow-up were retrospectively enrolled. Their clinical and CT data were reviewed, and their CT features were compared. A binary logistic regression analysis was performed to reveal the predictors of malignancy. RESULTS: Compared to patients with benign patchy GGOs, malignant cases were older (P <  0.001), had a lower incidence of malignant tumor history (P = 0.003), and more commonly occurred in females (P = 0.012). Based on CT images, there were significant differences in the location, distribution, density pattern, internal bronchial changes, and boundary between malignant and benign GGOs (P <  0.05). The binary logistic regression analysis revealed that the independent predictors of malignant GGOs were the following: patient age ≥ 58 years [odds ratio (OR), 2.175; 95% confidence interval (CI), 1.135-6.496; P = 0.025], locating in the upper lobe (OR, 5.481; 95%CI, 2.027-14.818; P = 0.001), distributing along the bronchovascular bundles (OR, 12.770; 95%CI, 4.062-40.145; P < 0.001), centrally distributed solid component (OR, 3.024; 95%CI, 1.124-8.133; P = 0.028), and well-defined boundary (OR, 5.094; 95%CI, 2.079-12.482; P < 0.001). CONCLUSIONS: In older patients (≥58 years), well-defined patchy GGOs with centric solid component, locating in the upper lobe, and distributing along the bronchovascular bundles should be highly suspected as malignancy.

Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm.

Using nephrographic phase CT images combined with pathology diagnosis, we aim to develop and validate a fusion feature-based stacking ensemble machine learning model to distinguish malignant renal neoplasms from cystic renal lesions (CRLs). This retrospective research includes 166 individuals with CRLs for model training and 47 individuals with CRLs in another institution for model testing. Histopathology results are adopted as diagnosis criterion. Nephrographic phase CT scans are selected to build the fusion feature-based machine learning algorithms. The pretrained 3D-ResNet50 CNN model and radiomics methods are selected to extract deep features and radiomics features, respectively. Fivefold cross-validated least absolute shrinkage and selection operator (LASSO) regression methods are adopted to identify the most discriminative candidate features in the development cohort. Intraclass correlation coefficients and interclass correlation coefficients are employed to evaluate feature's reproducibility. Pearson correlation coefficients for normal distribution features and Spearman's rank correlation coefficients for non-normal distribution features are used to eliminate redundant features. After that, stacking ensemble machine learning models are developed in the training cohort. The area under the receiver operator characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) are adopted in the testing cohort to evaluate the performance of each model. The stacking ensemble machine learning algorithm reached excellent diagnostic performance in the testing dataset. The calibration plot shows good stability when using the stacking ensemble model. Net benefits presented by DCA are higher than the Bosniak 2019 version classification when employing any machine learning algorithm. The fusion feature-based machine learning algorithm accurately distinguishes malignant renal neoplasms from CRLs, which outperformed the Bosniak 2019 version classification, and proves to be more applicable for clinical decision-making.

3D island sign on computed tomography predicts early perihematomal edema expansion and poor outcome in patients with intracerebral hemorrhage.

BACKGROUND AND PURPOSE: To determine the prognostics significance of the computed tomography (CT) 3D island sign for predicting early perihematomal edema (PHE) expansion and poor functional outcome in patients presenting with intracerebral hemorrhage (ICH). METHODS: Between July 2011 and March 2017, patients with intracerebral hemorrhage who had undergone baseline CT within 6 h after ICH symptom onsets and follow-up CT in our hospital were included. Two different readers independently assessed the presence of 3D island sign on admission CT scan of each patient. Multivariable logistic regression analysis was used to analyze association between 3D island sign and early perihematomal edema expansion and poor functional outcome, separately. RESULTS: A total of 214 patients who met the inclusion criteria were included in our study, 3D island sign was observed in 60 patients (28.0 %) on admission CT scan. The multivariate logistic regression analysis demonstrated that baseline hematoma volume, time to baseline and follow-up CT scans and the presence of 3D island sign were predictors of early PHE expansion. After adjusting for age, baseline hematoma and edema volume, time to baseline and follow-up CT scans, GCS on admission, presence of intraventricular hemorrhage (IVH) and systolic blood pressure, the 3D island sign was an independently imaging marker for poor outcome (OR, 2.803; 95 % confidence interval, 1.189-6.609; P = 0.018). CONCLUSION: The 3D island sign in patients with intracerebral hemorrhage was a reliable predictor for early perihematomal edema expansion and poor functional outcome. It may serve as a potential therapeutic target for intervention.

Clinical and Computed Tomography Characteristics of Solitary Pulmonary Nodules Caused by Fungi: A Comparative Study.

Purpose: To clarify the clinical and computed tomography (CT) indicators in distinguishing pulmonary nodules caused by fungal infection from lung cancers. Methods: From January 2013 to April 2022, 68 patients with solitary fungal nodules (64 were solid and 4 were mixed ground-glass nodules) and 140 cases with solid cancerous nodules with similar size were enrolled. Their clinical characteristics and CT manifestations of the solid nodules were summarized and compared, respectively. Results: Compared with patients with lung cancers, cases were younger (51.2 ± 11.5 vs 61.3 ± 10.2 years) and non-smokers (72.1% vs 57.9%) and immunocompromised (44.1% vs 17.9%) individuals were more common in patients with fungal nodules (each P < 0.05). The air crescent sign (ACS) (34.4% vs 0%), halo sign (HS) (23.4% vs 4.3%), and satellite lesions (45.3% vs 2.9%) were more frequently detected in fungal nodules than in cancerous ones (each P < 0.05). Air bronchogram similarly occurred in fungal and cancerous nodules, whereas the natural ones were more common in the former (100% vs 16.7%, P = 0.000). However, the fungal nodules had a lower enhancement degree (29.0 ± 19.2 HU vs 40.3 ± 28.3 HU, P = 0.038) and frequency of hilar and/or mediastinal lymph node enlargement (2.9% vs 14.3%, P = 0.013) compared with the cancerous nodules. Conclusion: In the younger, non-smoking and immunocompromised patients, a solitary pulmonary solid nodule with ACS, HS, satellite lesions and/or natural air bronchogram but without significant enhancement, fungal infection is a probable diagnosis.