To compare WB-MRI with an [18F]FDG-PET/CT-based reference for early response assessment and restaging in children with Hodgkin’s lymphoma (HL). Fifty-one children (ages 10–17) with HL were included in this prospective, multicentre study. All participants underwent WB-MRI and [18F]FDG-PET/CT at early response assessment. Thirteen of the 51 patients also underwent both WB-MRI and [18F]FDG-PET/CT at restaging. Two radiologists independently evaluated all WB-MR images in two separate readings: witho...
#1Valeria Romeo(University of Naples Federico II)H-Index: 10
#2Renato Cuocolo(University of Naples Federico II)H-Index: 13
Last. Arturo Brunetti(University of Naples Federico II)H-Index: 40
view all 17 authors...
We aimed to assess the performance of radiomics and machine learning (ML) for classification of non-cystic benign and malignant breast lesions on ultrasound images, compare ML’s accuracy with that of a breast radiologist, and verify if the radiologist’s performance is improved by using ML. Our retrospective study included patients from two institutions. A total of 135 lesions from Institution 1 were used to train and test the ML model with cross-validation. Radiomic features were extracted from ...
#2Jason Chan(U of O: University of Ottawa)H-Index: 3
Last. Nicola Schieda(U of O: University of Ottawa)H-Index: 24
view all 7 authors...
OBJECTIVE To evaluate Bosniak Classification v2019 definitions in pathologically confirmed cystic renal masses. MATERIALS AND METHODS Seventy-three cystic (≤ 25% solid) masses with histological confirmation (57 malignant, 16 benign) imaged by CT (N = 28) or CT+MRI (N = 56) between 2009 and 2019 were independently evaluated by three blinded radiologists using Bosniak v2019 and original classifications. Discrepancies were resolved by consensus with a fourth blinded radiologist. Overall class and v...
To evaluate the association between a sign and visceral pleural invasion (VPI) of peripheral non–small-cell lung cancer (NSCLC) that does not appear touching the pleural surface. A total of 221 consecutive patients with NSCLC that did not appear touching the pleural surface, ≤ 3 cm in solid tumor diameter, and was surgically resected between January 2009 and December 2015 were included. We focused on the flat distortion of the tumor caused by an arch-shaped linear tag between the tumor and the p...
Different machine learning algorithms (MLAs) for automated segmentation of gliomas have been reported in the literature. Automated segmentation of different tumor characteristics can be of added value for the diagnostic work-up and treatment planning. The purpose of this study was to provide an overview and meta-analysis of different MLA methods. A systematic literature review and meta-analysis was performed on the eligible studies describing the segmentation of gliomas. Meta-analysis of the per...
Last. Y.-C. Liu(Capital Medical University)H-Index: 1
view all 8 authors...
OBJECTIVES To evaluate the diagnostic accuracy of super-selective pseudo-continuous arterial spin labeling (ss-pCASL) at depicting external carotid artery (ECA) perfusion territory in moyamoya disease (MMD). METHODS In total, 103 patients with MMD who underwent both ss-pCASL and digital subtraction angiography (DSA, the reference standard) were included. There were 3, 184, and 19 normal, preoperative, and postoperative MMD hemispheres, respectively. The ss-pCASL results were interpreted by two d...
#1Yunchao Yin(UMCG: University Medical Center Groningen)
#2Derya Yakar(UMCG: University Medical Center Groningen)H-Index: 9
Last. Robbert J. de Haas(UMCG: University Medical Center Groningen)H-Index: 9
view all 6 authors...
Objectives Deep learning has been proven to be able to stage liver fibrosis based on contrast-enhanced CT images. However, until now, the algorithm is used as a black box and lacks transparency. This study aimed to provide a visual-based explanation of the diagnostic decisions made by deep learning. Methods The liver fibrosis staging network (LFS network) was developed at contrast-enhanced CT images in the portal venous phase in 252 patients with histologically proven liver fibrosis stage. To gi...
Last. Zhiqiang Zhang(Southern Medical University)H-Index: 3
view all 14 authors...
OBJECTIVES Although Rolandic epilepsy (RE) has been regarded as a brain developmental disorder, neuroimaging studies have not yet ascertained whether RE has brain developmental delay. This study employed deep learning-based neuroanatomic biomarker to measure the changed feature of "brain age" in RE. METHODS The study constructed a 3D-CNN brain age prediction model through 1155 cases of typically developing children's morphometric brain MRI from open-source datasets and further applied to a local...
#1Beatriu Reig(NYU: New York University)H-Index: 7
KEY POINTS • The use of screening breast MRI is expanding beyond high-risk women to include intermediate- and average-risk women.• The study by Potsch et al uses a radiomics-based method to decrease the number of benign biopsies while maintaining high sensitivity.• Future studies will likely increasingly focus on deep learning methods and abbreviated MRI data.
#1Yusuhn Kang(Seoul National University Bundang Hospital)H-Index: 13
#2Dongjun Choi(Seoul National University Bundang Hospital)H-Index: 2
Last. Joong Mo Ahn(Seoul National University Bundang Hospital)H-Index: 19
view all 6 authors...
OBJECTIVE To develop a deep learning algorithm capable of evaluating subscapularis tendon (SSC) tears based on axillary lateral shoulder radiography. METHODS A total of 2,779 axillary lateral shoulder radiographs (performed between February 2010 and December 2018) and the patients' corresponding clinical information (age, sex, dominant side, history of trauma, and degree of pain) were used to develop the deep learning algorithm. The radiographs were labeled based on arthroscopic findings, with t...