Stay Ahead of the Curve in Radiology AI.

RadAI Slice is your weekly intelligence briefing on the most critical developments at the intersection of radiology and artificial intelligence. Stop searching. Start leading.

Your Weekly Slice of Innovation

Each issue is precisely structured to give you exactly what you need. No fluff, just facts and forward-looking insights.

Recent Industry News

The Latest Research

FDA Approvals Database

From the Research Hub

CTDetectionChest

Artificial Intelligence for Low-Dose CT Lung Cancer Screening: Comparison of Utilization Scenarios.

<b>BACKGROUND</b>. Artificial intelligence (AI) tools for evaluating low-dose CT (LDCT) lung cancer screening examinations are used predominantly for assisting radiologists' interpretations. Alternate utilization scenarios (e.g., use of AI as a prescreener or backup) warrant consideration. <b>OBJECTIVE</b>. The purpose of this study was to evaluate the impact of different AI utilization scenarios on diagnostic outcomes and interpretation times for LDCT lung cancer screening. <b>METHODS</b>. This retrospective study included 366 individuals (358 men, 8 women; mean age, 64 years) who underwent LDCT from May 2017 to December 2017 as part of an earlier prospective lung cancer screening trial. Examinations were interpreted by one of five readers, who reviewed their assigned cases in two sessions (with and without a commercial AI computer-aided detection tool). These interpretations were used to reconstruct simulated AI utilization scenarios: as an assistant (i.e., radiologists interpret all examinations with AI assistance), as a prescreener (i.e., radiologists only interpret examinations with a positive AI result), or as backup (i.e., radiologists reinterpret examinations when AI suggests a missed finding). A group of thoracic radiologists determined the reference standard. Diagnostic outcomes and mean interpretation times were assessed. Decision-curve analysis was performed. <b>RESULTS</b>. Compared with interpretation without AI (recall rate, 22.1%; per-nodule sensitivity, 64.2%; per-examination specificity, 88.8%; mean interpretation time, 164 seconds), AI as an assistant showed higher recall rate (30.3%; <i>p</i> < .001), lower per-examination specificity (81.1%), and no significant change in per-nodule sensitivity (64.8%; <i>p</i> = .86) or mean interpretation time (161 seconds; <i>p</i> = .48); AI as a prescreener showed lower recall rate (20.8%; <i>p</i> = .02) and mean interpretation time (143 seconds; <i>p</i> = .001), higher per-examination specificity (90.3%; <i>p</i> = .04), and no significant difference in per-nodule sensitivity (62.9%; <i>p</i> = .16); and AI as a backup showed increased recall rate (33.6%; <i>p</i> < .001), per-examination sensitivity (66.4%; <i>p</i> < .001), and mean interpretation time (225 seconds; <i>p</i> = .001), with lower per-examination specificity (79.9%; <i>p</i> < .001). Among scenarios, only AI as a prescreener demonstrated higher net benefit than interpretation without AI; AI as an assistant had the least net benefit. <b>CONCLUSION</b>. Different AI implementation approaches yield varying outcomes. The findings support use of AI as a prescreener as the preferred scenario. <b>CLINICAL IMPACT</b>. An approach whereby radiologists only interpret LDCT examinations with a positive AI result can reduce radiologists' workload while preserving sensitivity.

Lee M, Hwang EJ, Lee JH, et al.·AJR. American journal of roentgenology
Mixed ModalityLLM Radiology ReportAbdominal

Data Extraction and Curation from Radiology Reports for Pancreatic Cyst Surveillance Using Large Language Models.

Manual curation of radiographic features in pancreatic cyst registries for data abstraction and longitudinal evaluation is time consuming and limits widespread implementation. We examined the feasibility and accuracy of using large language models (LLMs) to extract clinical variables from radiology reports. A single center retrospective study included patients under surveillance for pancreatic cysts. Nine radiographic elements used to monitor cyst progression were included: cyst size, main pancreatic duct (MPD) size (continuous variable), number of lesions, MPD dilation ≥5mm (categorical), branch duct dilation, presence of solid component, calcific lesion, pancreatic atrophy, and pancreatitis. LLMs (GPT) on the OpenAI GPT-4 platform were employed to extract elements of interest with a zero-shot learning approach using prompting to facilitate annotation without any training data. A manually annotated institutional cyst database was used as the ground truth (GT) for comparison. Overall, 3198 longitudinal scans from 991 patients were included. GPT successfully extracted the selected radiographic elements with high accuracy. Among categorical variables, accuracy ranged from 97% for solid component to 99% for calcific lesions. In the continuous variables, accuracy varied from 92% for cyst size to 97% for MPD size. However, Cohen's Kappa was higher for cyst size (0.92) compared to MPD size (0.82). Lowest accuracy (81%) was noted in the multi-class variable for number of cysts. LLM can accurately extract and curate data from radiology reports for pancreatic cyst surveillance and can be reliably used to assemble longitudinal databases. Future application of this work may potentiate the development of artificial intelligence-based surveillance models.

Choubey AP, Eguia E, Hollingsworth A, et al.·Journal of the American College of Surgeons
UltrasoundClassificationCardiac

Predicting Cardiopulmonary Exercise Testing Performance in Patients Undergoing Transthoracic Echocardiography - An AI Based, Multimodal Model

Background and AimsTransthoracic echocardiography (TTE) is a widely available tool for diagnosing and managing heart failure but has limited predictive value for survival. Cardiopulmonary exercise test (CPET) performance strongly correlates with survival in heart failure patients but is less accessible. We sought to develop an artificial intelligence (AI) algorithm using TTE and electronic medical records to predict CPET peak oxygen consumption (peak VO2) [&le;] 14 mL/kg/min. MethodsAn AI model was trained to predict peak VO2 [&le;] 14 mL/kg/min from TTE images, structured TTE reports, demographics, medications, labs, and vitals. The training set included patients with a TTE within 6 months of a CPET. Performance was retrospectively tested in a held-out group from the development cohort and an external validation cohort. Results1,127 CPET studies paired with concomitant TTE were identified. The best performance was achieved by using all components (TTE images, all structured clinical data). The model performed well at predicting a peak VO2 [&le;] 14 mL/kg/min, with an AUROC of 0.84 (development cohort) and 0.80 (external validation cohort). It performed consistently well using higher ([&le;] 18 mL/kg/min) and lower ([&le;] 12 mL/kg/min) cut-offs. ConclusionsThis multimodal AI model effectively categorized patients into low and high risk predicted peak VO2, demonstrating the potential to identify previously unrecognized patients in need of advanced heart failure therapies where CPET is not available.

Alishetti, S., Pan, W., Beecy, A. N., et al.·medRxiv

The Sharpest Insights, Effortlessly

Save Time

We scour dozens of sources so you don't have to. Get all the essential information in a 5-minute read.

Stay Informed

Never miss a critical update. Understand the trends shaping the future of your practice and research.

Gain an Edge

Be the first to know about the tools and technologies that matter, from clinical practice to academic research.

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.