Search

Purpose: To evaluate the clinical performance of a Protocol Recommendation System (PRS) automatic protocolling of chest CT imaging requests. Materials and Methods: 322 387 consecutive historical imaging requests for chest CT between 2017 and 2022 were extracted from a radiology information system (RIS) database containing 16 associated patient information values. Records with missing fields and protocols with <100 occurrences were removed, leaving 18 protocols for training. After freetext pre-processing and applying CLEVER terminology word replacements, the features of a bag-of-words model were used to train a multinomial logistic regression classifier. Four readers protocolled 300 clinically executed protocols (CEP) based on all clinically available information. After their selection was made, the PRS and CEP were unblinded, and the readers were asked to score their agreement (1 = severe error, 2 = moderate error, 3 = disagreement but acceptable, 4 = agreement). The ground truth was established by the readers' majority selection, a judge helped break ties. For the PRS and CEP, the accuracy and clinical acceptability (scores 3 and 4) were calculated. The readers' protocolling reliability was measured using Fleiss' Kappa. Results: Four readers agreed on 203/300 protocols, 3 on 82/300 cases, and in 15 cases, a judge was needed. PRS errors were found by the 4 readers in 1%, 2.7%, 1%, and 0.7% of the cases, respectively. The accuracy/clinical acceptability of the PRS and CEP were 84.3%/98.6% and 83.0%/99.3%, respectively. The Fleiss' Kappa for all readers and all protocols was 0.805. Conclusion: The PRS achieved similar accuracy to human performance and may help radiologists master the ever-increasing workload., Competing Interests: Declaration of Conflicting InterestsThe author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Purpose: MRI-based radiomics models can predict genetic markers in pediatric low-grade glioma (pLGG). These models usually require tumour segmentation, which is tedious and time consuming if done manually. We propose a deep learning (DL) model to automate tumour segmentation and build an end-to-end radiomics-based pipeline for pLGG classification. Methods: The proposed architecture is a 2-step U-Net based DL network. The first U-Net is trained on downsampled images to locate the tumour. The second U-Net is trained using image patches centred around the located tumour to produce more refined segmentations. The segmented tumour is then fed into a radiomics-based model to predict the genetic marker of the tumour. Results: Our segmentation model achieved a correlation value of over 80% for all volume-related radiomic features and an average Dice score of .795 in test cases. Feeding the auto-segmentation results into a radiomics model resulted in a mean area under the ROC curve (AUC) of .843, with 95% confidence interval (CI) [.78-.906] and .730, with 95% CI [.671-.789] on the test set for 2-class (BRAF V600E mutation BRAF fusion) and 3-class (BRAF V600E mutation BRAF fusion and Other) classification, respectively. This result was comparable to the AUC of .874, 95% CI [.829-.919] and .758, 95% CI [.724-.792] for the radiomics model trained and tested on the manual segmentations in 2-class and 3-class classification scenarios, respectively. Conclusion: The proposed end-to-end pipeline for pLGG segmentation and classification produced results comparable to manual segmentation when it was used for a radiomics-based genetic marker prediction model., Competing Interests: Declaration of Conflicting of InterestsThe authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Deep learning techniques using convolutional neural networks (CNNs) have been successfully developed for various medical image analysis tasks. However, the skills to understand and develop deep learning models are not usually taught during radiology training, which constitutes a barrier for radiologists looking to integrate machine learning (ML) into their research or clinical practice. In this work, we developed and evaluated an educational graphical user interface (GUI) to construct CNNs for teaching deep learning concepts to radiology trainees. The GUI was developed in Python using the PyQt and PyTorch frameworks. The functionality of the GUI was demonstrated through a binary classification task on a dataset of MR images of the brain. The usability of the GUI was assessed through 45-min user testing sessions with 5 neuroradiologists and neuroradiology fellows, assessing mean task completion times, the System Usability Scale (SUS), and a qualitative questionnaire as metrics. Task completion times were compared against a ML expert who performed the same tasks. After a 20-min introduction to CNNs and a walkthrough of the GUI, users were able to perform all assigned tasks successfully. There was no significant difference in task completion time compared to a ML expert. The educational GUI achieved a score of 82.5 on the SUS, suggesting that the system is highly usable. Users indicated that the GUI seems useful as an educational tool to teach ML topics to radiology trainees. An educational GUI allows interactive teaching in ML that can be incorporated into radiology training.

Purpose: Biopsy-based assessment of H3 K27 M status helps in predicting survival, but biopsy is usually limited to unusual presentations and clinical trials. We aimed to evaluate whether radiomics can serve as prognostic marker to stratify diffuse intrinsic pontine glioma (DIPG) subsets. Methods: In this retrospective study, diagnostic brain MRIs of children with DIPG were analyzed. Radiomic features were extracted from tumor segmentations and data were split into training/testing sets (80:20). A conditional survival forest model was applied to predict progression-free survival (PFS) using training data. The trained model was validated on the test data, and concordances were calculated for PFS. Experiments were repeated 100 times using randomized versions of the respective percentage of the training/test data. Results: A total of 89 patients were identified (48 females, 53.9%). Median age at time of diagnosis was 6.64 years (range: 1-16.9 years) and median PFS was 8 months (range: 1-84 months). Molecular data were available for 26 patients (29.2%) (1 wild type, 3 K27M-H3.1, 22 K27M-H3.3). Radiomic features of FLAIR and nonenhanced T1-weighted sequences were predictive of PFS. The best FLAIR radiomics model yielded a concordance of .87 [95% CI: .86-.88] at 4 months PFS. The best T1-weighted radiomics model yielded a concordance of .82 [95% CI: .8-.84] at 4 months PFS. The best combined FLAIR + T1-weighted radiomics model yielded a concordance of .74 [95% CI: .71-.77] at 3 months PFS. The predominant predictive radiomic feature matrix was gray-level size-zone. Conclusion: MRI-based radiomics may predict progression-free survival in pediatric diffuse midline glioma/diffuse intrinsic pontine glioma.

Background: Radiomic features in pancreatic ductal adenocarcinoma (PDAC) often lack validation in independent test sets or are limited to early or late stage disease. Given the lethal nature of PDAC it is possible that there are similarities in radiomic features of both early and advanced disease reflective of aggressive biology., Purpose: To assess the performance of prognostic radiomic features previously published in patients with resectable PDAC in a test set of patients with unresectable PDAC undergoing chemotherapy., Methods: The pre-treatment CT of 108 patients enrolled in a prospective chemotherapy trial were used as a test cohort for 2 previously published prognostic radiomic features in resectable PDAC (Sum Entropy and Cluster Tendency with square-root filter[Sqrt]). We assessed the performance of these 2 radiomic features for the prediction of overall survival (OS) and time to progression (TTP) using Cox proportional-hazard models., Results: Sqrt Cluster Tendency was significantly associated with outcome with a hazard ratio (HR) of 1.27(for primary pancreatic tumor plus local nodes), (Confidence Interval(CI):1.01 -1.6, P -value = 0.039) for OS and a HR of 1.25(CI:1.00 -1.55, P -value = 0.047) for TTP. Sum entropy was not associated with outcomes. Sqrt Cluster Tendency remained significant in multivariate analysis., Conclusion: The CT radiomic feature Sqrt Cluster Tendency, previously demonstrated to be prognostic in resectable PDAC, remained a significant prognostic factor for OS and TTP in a test set of unresectable PDAC patients. This radiomic feature warrants further investigation to understand its biologic correlates and CT applicability in PDAC patients.