An Introductory Guide to Artificial Intelligence in Interventional Radiology: Part 1 Foundational Knowledge.

Artificial intelligence (AI) is rapidly evolving and has transformative potential for interventional radiology (IR) clinical practice. However, formal training in AI may be limited for many clinicians and therefore presents a challenge for initial implementation and trust in AI. An understanding of the foundational concepts in AI may help familiarize the interventional radiologist with the field of AI, thus facilitating understanding and participation in the development and deployment of AI. A pragmatic classification system of AI based on the complexity of the model may guide clinicians in the assessment of AI. Finally, the current state of AI in IR and the patterns of implementation are explored (pre-procedural, intra-procedural, and post-procedural).

An Introductory Guide to Artificial Intelligence in Interventional Radiology: Part 2: Implementation Considerations and Harms.

The introduction of artificial intelligence (AI) in interventional radiology (IR) will bring about new challenges and opportunities for patients and clinicians. AI may comprise software as a medical device or AI-integrated hardware and will require a rigorous evaluation that should be guided based on the level of risk of the implementation. A hierarchy of risk of harm and possible harms are described herein. A checklist to guide deployment of an AI in a clinical IR environment is provided. As AI continues to evolve, regulation and evaluation of the AI medical devices will need to continue to evolve to keep pace and ensure patient safety.

Impact of Automated Prognostication on Traumatic Brain Injury Care: A Focus Group Study.

BACKGROUND: Prognosticating outcomes for traumatic brain injury (TBI) patients is challenging due to the required specialized skills and variability among clinicians. Recent attempts to standardize TBI prognosis have leveraged machine learning (ML) methodologies. This study evaluates the necessity and influence of ML-assisted TBI prognostication through healthcare professionals' perspectives via focus group discussions. METHODS: Two virtual focus groups included ten key TBI care stakeholders (one neurosurgeon, two emergency clinicians, one internist, two radiologists, one registered nurse, two researchers in ML and healthcare and one patient representative). They answered six open-ended questions about their perceptions and potential ML use in TBI prognostication. Transcribed focus group discussions were thematically analyzed using qualitative data analysis software. RESULTS: The study captured diverse perceptions and interests in TBI prognostication across clinical specialties. Notably, certain clinicians who currently do not prognosticate expressed an interest in doing so independently provided they had access to ML support. Concerns included ML's accuracy and the need for proficient ML researchers in clinical settings. The consensus suggested using ML as a secondary consultation tool and promoting collaboration with internal or external research resources. Participants believed ML prognostication could enhance disposition planning and standardize care regardless of clinician expertise or injury severity. There was no evidence of perceived bias or interference during the discussions. CONCLUSION: Our findings revealed an overall positive attitude toward ML-based prognostication. Despite raising multiple concerns, the focus group discussions were particularly valuable in underscoring the potential of ML in democratizing and standardizing TBI prognosis practices.

Development of a Multimodal Machine Learning-Based Prognostication Model for Traumatic Brain Injury Using Clinical Data and Computed Tomography Scans: A CENTER-TBI and CINTER-TBI Study.

Computed tomography (CT) is an important imaging modality for guiding prognostication in patients with traumatic brain injury (TBI). However, because of the specialized expertise necessary, timely and dependable TBI prognostication based on CT imaging remains challenging. This study aimed to enhance the efficiency and reliability of TBI prognostication by employing machine learning (ML) techniques on CT images. A retrospective analysis was conducted on the Collaborative European NeuroTrauma Effectiveness Research in TBI (CENTER-TBI) data set (n = 1016). An ML-driven binary classifier was developed to predict favorable or unfavorable outcomes at 6 months post-injury. The prognostic performance was assessed using the area under the curve (AUC) over fivefold cross-validation and compared with conventional models that depend on clinical variables and CT scoring systems. An external validation was performed using the Comparative Indian Neurotrauma Effectiveness Research in Traumatic Brain Injury (CINTER-TBI) data set (n = 348). The developed model achieved superior performance without the necessity for manual CT assessments (AUC = 0.846 [95% CI: 0.843-0.849]) compared with the model based on the clinical and laboratory variables (AUC = 0.817 [95% CI: 0.814-0.820]) and established CT scoring systems requiring manual interpretations (AUC = 0.829 [95% CI: 0.826-0.832] for Marshall and 0.838 [95% CI: 0.835-0.841] for International Mission for Prognosis and Analysis of Clinical Trials in TBI [IMPACT]). The external validation demonstrated the prognostic capacity of the developed model to be significantly better (AUC = 0.859 [95% CI: 0.857-0.862]) than the model using clinical variables (AUC = 0.809 [95% CI: 0.798-0.820]). This study established an ML-based model that provides efficient and reliable TBI prognosis based on CT scans, with potential implications for earlier intervention and improved patient outcomes.

Opportunistic Screening of Low Bone Mineral Density From Standard X-Rays.

BACKGROUND: Osteoporosis, characterized by loss of bone mineral density (BMD), is underscreened. Osteoporosis and low bone mass are diagnosed by a BMD T-score ≤ -2.5, and between -1.0 and -2.5, respectively, at the femoral neck or lumbar vertebrae (L1-4), using dual energy x-ray absorptiometry (DXA). The ability to estimate BMD at those anatomic sites from standard radiographs would enable opportunistic screening of low BMD (T-score < -1) in individuals undergoing x-ray for any clinical indication. METHODS: Radiographs of the lumbar spine, thoracic spine, chest, pelvis, hand, and knee, with a paired DXA acquired within 1 year, were obtained from community imaging centers (62,023 x-ray-DXA pairs of patients). A software program called Rho was developed that uses x-ray, age, and sex as inputs, and outputs a score of 1 to 10 that corresponds with the likelihood of low BMD. The program's performance was assessed using receiver-operating characteristic analyses in three independent test sets, as follows: patients from community imaging centers (n = 3,729; 83% female); patients in the Canadian Multicentre Osteoporosis Study (n = 1,780; 71% female); and patients in the Osteoarthritis Initiative (n = 591; 50% female). RESULTS: The areas under the receiver-operating characteristic curves were 0.89 (0.87-0.90), 0.87 (0.85-0.88), and 0.82 (0.79-0.85), respectively, and subset analyses showed similar results for each sex, body part, and race. CONCLUSION: Rho can opportunistically screen patients at risk of low BMD (at femoral neck or L1-4) from radiographs of the lumbar spine, thoracic spine, chest, pelvis, hand, or knee.

Automated screening of computed tomography using weakly supervised anomaly detection.

BACKGROUND: Current artificial intelligence studies for supporting CT screening tasks depend on either supervised learning or detecting anomalies. However, the former involves a heavy annotation workload owing to requiring many slice-wise annotations (ground truth labels); the latter is promising, but while it reduces the annotation workload, it often suffers from lower performance. This study presents a novel weakly supervised anomaly detection (WSAD) algorithm trained based on scan-wise normal and anomalous annotations to provide better performance than conventional methods while reducing annotation workload. METHODS: Based on surveillance video anomaly detection methodology, feature vectors representing each CT slice were trained on an AR-Net-based convolutional network using a dynamic multiple-instance learning loss and a center loss function. The following two publicly available CT datasets were retrospectively analyzed: the RSNA brain hemorrhage dataset (normal scans: 12,862; scans with intracranial hematoma: 8882) and COVID-CT set (normal scans: 282; scans with COVID-19: 95). RESULTS: Anomaly scores of each slice were successfully predicted despite inaccessibility to any slice-wise annotations. Slice-level area under the curve (AUC), sensitivity, specificity, and accuracy from the brain CT dataset were 0.89, 0.85, 0.78, and 0.79, respectively. The proposed method reduced the number of annotations in the brain dataset by 97.1% compared to an ordinary slice-level supervised learning method. CONCLUSION: This study demonstrated a significant annotation reduction in identifying anomalous CT slices compared to a supervised learning approach. The effectiveness of the proposed WSAD algorithm was verified through higher AUC than existing anomaly detection techniques.

Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet?

BACKGROUND: The purpose of this study was to conduct a systematic review for understanding the availability and limitations of artificial intelligence (AI) approaches that could automatically identify and quantify computed tomography (CT) findings in traumatic brain injury (TBI). METHODS: Systematic review, in accordance with PRISMA 2020 and SPIRIT-AI extension guidelines, with a search of 4 databases (Medline, Embase, IEEE Xplore, and Web of Science) was performed to find AI studies that automated the clinical tasks for identifying and quantifying CT findings of TBI-related abnormalities. RESULTS: A total of 531 unique publications were reviewed, which resulted in 66 articles that met our inclusion criteria. The following components for identification and quantification regarding TBI were covered and automated by existing AI studies: identification of TBI-related abnormalities; classification of intracranial hemorrhage types; slice-, pixel-, and voxel-level localization of hemorrhage; measurement of midline shift; and measurement of hematoma volume. Automated identification of obliterated basal cisterns was not investigated in the existing AI studies. Most of the AI algorithms were based on deep neural networks that were trained on 2- or 3-dimensional CT imaging datasets. CONCLUSION: We identified several important TBI-related CT findings that can be automatically identified and quantified with AI. A combination of these techniques may provide useful tools to enhance reproducibility of TBI identification and quantification by supporting radiologists and clinicians in their TBI assessments and reducing subjective human factors.

Quantifying uncertainty in machine learning classifiers for medical imaging.

PURPOSE: Machine learning (ML) models in medical imaging (MI) can be of great value in computer aided diagnostic systems, but little attention is given to the confidence (alternatively, uncertainty) of such models, which may have significant clinical implications. This paper applied, validated, and explored a technique for assessing uncertainty in convolutional neural networks (CNNs) in the context of MI. MATERIALS AND METHODS: We used two publicly accessible imaging datasets: a chest x-ray dataset (pneumonia vs. control) and a skin cancer imaging dataset (malignant vs. benign) to explore the proposed measure of uncertainty based on experiments with different class imbalance-sample sizes, and experiments with images close to the classification boundary. We also further verified our hypothesis by examining the relationship with other performance metrics and cross-checking CNN predictions and confidence scores with an expert radiologist (available in the Supplementary Information). Additionally, bounds were derived on the uncertainty metric, and recommendations for interpretability were made. RESULTS: With respect to training set class imbalance for the pneumonia MI dataset, the uncertainty metric was minimized when both classes were nearly equal in size (regardless of training set size) and was approximately 17% smaller than the maximum uncertainty resulting from greater imbalance. We found that less-obvious test images (those closer to the classification boundary) produced higher classification uncertainty, about 10-15 times greater than images further from the boundary. Relevant MI performance metrics like accuracy, sensitivity, and sensibility showed seemingly negative linear correlations, though none were statistically significant (p [Formula: see text] 0.05). The expert radiologist and CNN expressed agreement on a small sample of test images, though this finding is only preliminary. CONCLUSIONS: This paper demonstrated the importance of uncertainty reporting alongside predictions in medical imaging. Results demonstrate considerable potential from automatically assessing classifier reliability on each prediction with the proposed uncertainty metric.

Artificial intelligence and radiomics in pediatric molecular imaging.

In the past decade, a new approach for quantitative analysis of medical images and prognostic modelling has emerged. Defined as the extraction and analysis of a large number of quantitative parameters from medical images, radiomics is an evolving field in precision medicine with the ultimate goal of the discovery of new imaging biomarkers for disease. Radiomics has already shown promising results in extracting diagnostic, prognostic, and molecular information latent in medical images. After acquisition of the medical images as part of the standard of care, a region of interest is defined often via a manual or semi-automatic approach. An algorithm then extracts and computes quantitative radiomics parameters from the region of interest. Whereas radiomics captures quantitative values of shape and texture based on predefined mathematical terms, neural networks have recently been used to directly learn and identify predictive features from medical images. Thereby, neural networks largely forego the need for so called "hand-engineered" features, which appears to result in significantly improved performance and reliability. Opportunities for radiomics and neural networks in pediatric nuclear medicine/radiology/molecular imaging are broad and can be thought of in three categories: automating well-defined administrative or clinical tasks, augmenting broader administrative or clinical tasks, and unlocking new methods of generating value. Specific applications include intelligent order sets, automated protocoling, improved image acquisition, computer aided triage and detection of abnormalities, next generation voice dictation systems, biomarker development, and therapy planning.

The RSNA Pediatric Bone Age Machine Learning Challenge.

Purpose The Radiological Society of North America (RSNA) Pediatric Bone Age Machine Learning Challenge was created to show an application of machine learning (ML) and artificial intelligence (AI) in medical imaging, promote collaboration to catalyze AI model creation, and identify innovators in medical imaging. Materials and Methods The goal of this challenge was to solicit individuals and teams to create an algorithm or model using ML techniques that would accurately determine skeletal age in a curated data set of pediatric hand radiographs. The primary evaluation measure was the mean absolute distance (MAD) in months, which was calculated as the mean of the absolute values of the difference between the model estimates and those of the reference standard, bone age. Results A data set consisting of 14 236 hand radiographs (12 611 training set, 1425 validation set, 200 test set) was made available to registered challenge participants. A total of 260 individuals or teams registered on the Challenge website. A total of 105 submissions were uploaded from 48 unique users during the training, validation, and test phases. Almost all methods used deep neural network techniques based on one or more convolutional neural networks (CNNs). The best five results based on MAD were 4.2, 4.4, 4.4, 4.5, and 4.5 months, respectively. Conclusion The RSNA Pediatric Bone Age Machine Learning Challenge showed how a coordinated approach to solving a medical imaging problem can be successfully conducted. Future ML challenges will catalyze collaboration and development of ML tools and methods that can potentially improve diagnostic accuracy and patient care. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Siegel in this issue.

Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs.

OBJECTIVES: Convolutional neural networks (CNNs) are a subtype of artificial neural network that have shown strong performance in computer vision tasks including image classification. To date, there has been limited application of CNNs to chest radiographs, the most frequently performed medical imaging study. We hypothesize CNNs can learn to classify frontal chest radiographs according to common findings from a sufficiently large data set. MATERIALS AND METHODS: Our institution's research ethics board approved a single-center retrospective review of 35,038 adult posterior-anterior chest radiographs and final reports performed between 2005 and 2015 (56% men, average age of 56, patient type: 24% inpatient, 39% outpatient, 37% emergency department) with a waiver for informed consent. The GoogLeNet CNN was trained using 3 graphics processing units to automatically classify radiographs as normal (n = 11,702) or into 1 or more of cardiomegaly (n = 9240), consolidation (n = 6788), pleural effusion (n = 7786), pulmonary edema (n = 1286), or pneumothorax (n = 1299). The network's performance was evaluated using receiver operating curve analysis on a test set of 2443 radiographs with the criterion standard being board-certified radiologist interpretation. RESULTS: Using 256 × 256-pixel images as input, the network achieved an overall sensitivity and specificity of 91% with an area under the curve of 0.964 for classifying a study as normal (n = 1203). For the abnormal categories, the sensitivity, specificity, and area under the curve, respectively, were 91%, 91%, and 0.962 for pleural effusion (n = 782), 82%, 82%, and 0.868 for pulmonary edema (n = 356), 74%, 75%, and 0.850 for consolidation (n = 214), 81%, 80%, and 0.875 for cardiomegaly (n = 482), and 78%, 78%, and 0.861 for pneumothorax (n = 167). CONCLUSIONS: Current deep CNN architectures can be trained with modest-sized medical data sets to achieve clinically useful performance at detecting and excluding common pathology on chest radiographs.