Automated detection and segmentation of intracranial hemorrhage suspect hyperdensities in non-contrast-enhanced CT scans of acute stroke patients

Abstract Objectives Artif icial intelligence (AI)–based image analysis is increasingly applied in the acute stroke field. Its implementation for the detection and quantification of hemorrhage suspect hyperdensities in non-contrast-enhanced head CT (NCCT) scans may facilitate clinical decision-making and accelerate stroke management. Methods NCCTs of 160 patients with suspected acute stroke were analyzed regarding the presence or absence of acute intracranial hemorrhages (ICH) using a novel AI-based algorithm. Read was performed by two blinded neuroradiology residents (R1 and R2). Ground truth was established by an expert neuroradiologist. Specificity, sensitivity, and area under the curve were calculated for ICH and intraparenchymal hemorrhage (IPH) detection. IPH-volumes were segmented and quantified automatically by the algorithm and semi-automatically. Intraclass correlation coefficient (ICC) and Dice coefficient (DC) were calculated. Results In total, 79 of 160 patients showed acute ICH, while 47 had IPH. Sensitivity and specificity for ICH detection were 0.91 and 0.89 for the algorithm; 0.99 and 0.98 for R1; and 1.00 and 0.98 for R2. Sensitivity and specificity for IPH detection were 0.98 and 0.89 for the algorithm; 0.83 and 0.99 for R1; and 0.91 and 0.99 for R2. Interreader reliability for ICH and IPH detection showed strong agreements for the algorithm (0.80 and 0.84), R1 (0.96 and 0.84), and R2 (0.98 and 0.92), respectively. ICC indicated an excellent (0.98) agreement between the algorithm and the reference standard of the IPH-volumes. The mean DC was 0.82. Conclusion The AI-based algorithm reliably assessed the presence or absence of acute ICHs in this dataset and quantified IPH volumes precisely. Key Points • Artificial intelligence (AI) is able to detect hyperdense volumes on brain CTs reliably. • Sensitivity and specificity are highest for the detection of intraparenchymal hemorrhages. • Interreader reliability for hemorrhage detection shows strong agreement for AI and human readers.

Download Full-text

Machine Learning for Detecting Early Infarction in Acute Stroke with Non–Contrast-enhanced CT

Radiology ◽

10.1148/radiol.2020191193 ◽

2020 ◽

Vol 294 (3) ◽

pp. 638-644 ◽

Cited By ~ 13

Author(s):

Wu Qiu ◽

Hulin Kuang ◽

Ericka Teleg ◽

Johanna M. Ospel ◽

Sung Il Sohn ◽

...

Keyword(s):

Machine Learning ◽

Acute Stroke ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct ◽

Early Infarction

Download Full-text

Development and Validation of a Contrast-Enhanced CT-Based Radiomics Nomogram for Prediction of Therapeutic Efficacy of Anti-PD-1 Antibodies in Advanced HCC Patients

Frontiers in Immunology ◽

10.3389/fimmu.2020.613946 ◽

2021 ◽

Vol 11 ◽

Author(s):

Guosheng Yuan ◽

Yangda Song ◽

Qi Li ◽

Xiaoyun Hu ◽

Mengya Zang ◽

...

Keyword(s):

Treatment Efficacy ◽

Multivariate Logistic Regression Analysis ◽

Area Under The Curve ◽

Clinical Factors ◽

Advanced Hcc ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct ◽

Line Of Therapy ◽

Enhanced Computed Tomography

BackgroundThere is no study accessible now assessing the prognostic aspect of radiomics for anti-PD-1 therapy for patients with HCC.AimThe aim of this study was to develop and validate a radiomics nomogram by incorporating the pretreatment contrast-enhanced Computed tomography (CT) images and clinical risk factors to estimate the anti-PD-1 treatment efficacy in Hepatocellular Carcinoma (HCC) patients.MethodsA total of 58 patients with advanced HCC who were refractory to the standard first-line of therapy, and received PD-1 inhibitor treatment with Toripalimab, Camrelizumab, or Sintilimab from 1st January 2019 to 31 July 2020 were enrolled and divided into two sets randomly: training set (n = 40) and validation set (n = 18). Radiomics features were extracted from non-enhanced and contrast-enhanced CT scans and selected by using the least absolute shrinkage and selection operator (LASSO) method. Finally, a radiomics nomogram was developed based on by univariate and multivariate logistic regression analysis. The performance of the nomogram was evaluated by discrimination, calibration, and clinical utility.ResultsEight radiomics features from the whole tumor and peritumoral regions were selected and comprised of the Fusion Radiomics score. Together with two clinical factors (tumor embolus and ALBI grade), a radiomics nomogram was developed with an area under the curve (AUC) of 0.894 (95% CI, 0.797–0.991) and 0.883 (95% CI, 0.716–0.998) in the training and validation cohort, respectively. The calibration curve and decision curve analysis (DCA) confirmed that nomogram had good consistency and clinical usefulness.ConclusionsThis study has developed and validated a radiomics nomogram by incorporating the pretreatment CECT images and clinical factors to predict the anti-PD-1 treatment efficacy in patients with advanced HCC.

Download Full-text

Deep learning based classification of solid lipid-poor contrast enhancing renal masses using contrast enhanced CT

British Journal of Radiology ◽

10.1259/bjr.20200002 ◽

2020 ◽

Vol 93 (1111) ◽

pp. 20200002

Author(s):

Assad Oberai ◽

Bino Varghese ◽

Steven Cen ◽

Tomas Angelini ◽

Darryl Hwang ◽

...

Keyword(s):

Confidence Interval ◽

Area Under The Curve ◽

Neural Nets ◽

Renal Masses ◽

Renal Lesions ◽

Solid Lipid ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct ◽

Segmented Images

Objective: Establish a workflow that utilizes convolutional neural nets (CNN) to classify solid, lipid-poor, contrast enhancing renal masses using multiphase contrast enhanced CT (CECT) images and to assess the performance of the resulting network. Methods: In this institutional review board approved study of 143 patients with predominantly solid, lipid-poor, contrast enhancing renal lesions (46 benign and 97 malignant), patients with a pre-operative multiphase CECT of the abdomen and pelvis obtained between June 2009 and June 2015 were retrospectively queried. Benign renal masses included oncocytoma and lipid-poor angiomyolipoma and the malignant group included clear cell, papillary, and chromophobe carcinomas. Region of interests of whole tumor volumes were manually segmented, and CT phase images with the largest cross-section of the segmented tumor in the axial plane were used for assessment. Post-surgical pathological evaluation was used to establish diagnosis. The segmented images of renal masses were used as input to a CNN. The data were augmented and split into training (83.9%) and validation sets (16.1%) to determine the hyperparameters of the CNN. Thereafter. the performance of the resulting CNN was quantified using eightfold cross-validation. Results: The CNN-based classifier demonstrated an overall accuracy of 78% (95% confidence interval: 76–80%), sensitivity of 70% (95% confidence interval: 66–74%), specificity of 81% (79–83%) and an area under the curve of 0.82. Conclusion: A CNN-based classifier to diagnose solid enhancing malignant renal masses based on multiphase CECT images was developed. Advances in knowledge: It was established that a CNN-based classifier could be trained to accurately distinguish malignant renal lesions.

Download Full-text