Automated Critical Test Findings Identification and Online Notification System Using Artificial Intelligence in Imaging

Abstract

Purpose To evaluate the performance of an artificial intelligence (AI) tool using a deep learning algorithm for detecting hemorrhage, mass effect, or hydrocephalus (HMH) at non-contrast material-enhanced head computed tomographic (CT) examinations and to determine algorithm performance for detection of suspected acute infarct (SAI). Materials and Methods This HIPAA-compliant retrospective study was completed after institutional review board approval. A training and validation dataset of noncontrast-enhanced head CT examinations that comprised 100 examinations of HMH, 22 of SAI, and 124 of noncritical findings was obtained resulting in 2583 representative images. Examinations were processed by using a convolutional neural network (deep learning) using two different window and level configurations (brain window and stroke window). AI algorithm performance was tested on a separate dataset containing 50 examinations with HMH findings, 15 with SAI findings, and 35 with noncritical findings. Results Final algorithm performance for HMH showed 90% (45 of 50) sensitivity (95% confidence interval [CI]: 78%, 97%) and 85% (68 of 80) specificity (95% CI: 76%, 92%), with area under the receiver operating characteristic curve (AUC) of 0.91 with the brain window. For SAI, the best performance was achieved with the stroke window showing 62% (13 of 21) sensitivity (95% CI: 38%, 82%) and 96% (27 of 28) specificity (95% CI: 82%, 100%), with AUC of 0.81. Conclusion AI using deep learning demonstrates promise for detecting critical findings at noncontrast-enhanced head CT. A dedicated algorithm was required to detect SAI. Detection of SAI showed lower sensitivity in comparison to detection of HMH, but showed reasonable performance. Findings support further investigation of the algorithm in a controlled and prospective clinical setting to determine whether it can independently screen noncontrast-enhanced head CT examinations and notify the interpreting radiologist of critical findings. RSNA, 2017 Online supplemental material is available for this article.

Intracranial Hemorrhage Segmentation Using a Deep Convolutional Model

“…Much interesting work has been performed for the automated ICH diagnosis. The majority of this work has focused either on a two-class detection problem where the method detects the presence of an ICH [6][7][8][9][10][11][12][13][14][15][16][16][17][18][19] or as a multi-class classification problem, where the goal is to detect the ICH sub-types [6,8,11,15,[17][18][19]. Some researchers have extended the scope and performed the ICH segmentation to identify the region of ICH [7,11,15,17,[19][20][21][22][23][24][25][26].…”

“…Some researchers have extended the scope and performed the ICH segmentation to identify the region of ICH [7,11,15,17,[19][20][21][22][23][24][25][26]. Most researchers validated their algorithms using small datasets [7][8][9][10][11][12][13]17,[20][21][22][24][25][26], while a few used large datasets for testing and validating [6,[14][15][16]18,19,23]. We provide a comprehensive review of the published papers for the ICH detection and segmentation ( Figure 1) in this section.…”

“…Other approaches were 1-stage , meaning that they did not consider the spatial dependency between the slices [12,19,23]. Prevedello and colleagues proposed two algorithms based on CNN [12]. One of their algorithms was focused on detecting ICH, mass effect, and hydrocephalus at the CT scans while their other algorithm was developed to detect the suspected acute infarcts.…”

Deep Learning Lends a Hand to Pediatric Radiology

“…Such examples may be highly specific, for example bone age assessment as in this study. Or they could be more comprehensive, attempting to diagnose two or more diseases in the same image or threedimensional volume (6,10). Many data sets of radiology images and accompanying reference standards have been collected over the years and new ones are appearing (1,11).…”

“…The benefits of these machine learning systems for their intended use in the clinic will also need to be assessed with appropriate observer trials. colitis on abdominopelvic CT images; and tuberculosis on chest radiographs (6)(7)(8). Third, the authors outlined an approach that with limited modification could be adapted to develop computer models that learn how to perform other quantitative radiology analyses given sufficient training data.…”