Positive predictive value and stroke workflow outcomes using automated vessel density (RAPID-CTA) in stroke patients: One year experience

Adhya, Julie; Li, Charles; Eisenmenger, Laura; Cerejo, Russell; Tayal, Ashis H; Goldberg, Michael F.; Chang, Warren

doi:10.1177/19714009211012353

Cited by 20 publications

(21 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One limitation of this study is that we did not evaluate the impact of these tools on clinical outcomes. Other studies have previously shown a significant improvement in transfer times of LVO patients ( 10 ), but there are mixed results at comprehensive stroke centers ( 9 , 11 – 13 ). This study included a relatively small sample size at a single institution which may limit generalizability.…”

Section: Discussionmentioning

confidence: 95%

See 1 more Smart Citation

Head-to-head comparison of commercial artificial intelligence solutions for detection of large vessel occlusion at a comprehensive stroke center

Schlossman

Salehi

et al. 2022

Front. Neurol.

View full text Add to dashboard Cite

PurposeDespite the availability of commercial artificial intelligence (AI) tools for large vessel occlusion (LVO) detection, there is paucity of data comparing traditional machine learning and deep learning solutions in a real-world setting. The purpose of this study is to compare and validate the performance of two AI-based tools (RAPID LVO and CINA LVO) for LVO detection.Materials and methodsThis was a retrospective, single center study performed at a comprehensive stroke center from December 2020 to June 2021. CT angiography (n = 263) for suspected stroke were evaluated for LVO. RAPID LVO is a traditional machine learning model which primarily relies on vessel density threshold assessment, while CINA LVO is an end-to-end deep learning tool implemented with multiple neural networks for detection and localization tasks. Reasons for errors were also recorded.ResultsThere were 29 positive and 224 negative LVO cases by ground truth assessment. RAPID LVO demonstrated an accuracy of 0.86, sensitivity of 0.90, specificity of 0.86, positive predictive value of 0.45, and negative predictive value of 0.98, while CINA demonstrated an accuracy of 0.96, sensitivity of 0.76, specificity of 0.98, positive predictive value of 0.85, and negative predictive value of 0.97.ConclusionBoth tools successfully detected most anterior circulation occlusions. RAPID LVO had higher sensitivity while CINA LVO had higher accuracy and specificity. Interestingly, both tools were able to detect some, but not all M2 MCA occlusions. This is the first study to compare traditional and deep learning LVO tools in the clinical setting.

show abstract

Section: Discussionmentioning

confidence: 95%

“…There are ways for both tools to improve their detection and increase their PPV. A previous paper demonstrated RAPID's PPV could be improved by incorporating a relative vessel density threshold ( 9 ). No similar paper has demonstrated this for CINA LVO to the authors' knowledge and remains a potential opportunity for study.…”

Section: Discussionmentioning

confidence: 99%

Head-to-head comparison of commercial artificial intelligence solutions for detection of large vessel occlusion at a comprehensive stroke center

Schlossman

Salehi

et al. 2022

Front. Neurol.

View full text Add to dashboard Cite

show abstract

“…Radiology AI classification often focuses on the detection of abnormalities on a single scan, but we often care about the difference between successive scans. AI-based classification has hitherto focused largely on classification that distinguishes on a single scan between normal and abnormal/disease states [5,6,7]. While this is helpful to prioritize scans that need further urgent evaluation in the community and emergency room setting, most patients will have essentially normal scans.…”

Section: Discussionmentioning

confidence: 99%

Direct evaluation of progression or regression of disease burden in brain metastatic disease with Deep Neuroevolution

Stember¹,

Young²,

Shalu³

2022

Preprint

View full text Add to dashboard Cite

Purpose A core component of advancing cancer treatment research is assessing response to therapy. Doing so by hand, for example as per RE-CIST or RANO criteria, is tedious, time-consuming, and can miss important tumor response information; most notably, such criteria often exclude lesions, the non-target lesions, altogether. We wish to assess change in a holistic fashion that includes all lesions, obtaining simple, informative, and automated assessments of tumor progression or regression. Because genetic sub-types of cancer can be fairly specific and patient enrollment in therapy trials is often limited in number and accrual rate, we wish to make response assessments with small training sets. deep neuroevolution (DNE) can produce radiology artificial intelligence (AI) that performs well on small training sets. Following recent work in which we used DNE to train the parameters of a small convolutional neural network (CNN) for MRI sequence identification, we have now used a DNE parameter search to optimize a CNN that predicts progression versus regression of metastatic brain disease.Methods We analyzed 50 pairs of MRI contrast-enhanced images as our training set. Half of these pairs, separated in time, qualified as disease progression, while the other 25 images constituted regression. We trained the parameters of a relatively small CNN via "mutations" that consisted of random CNN weight adjustments and mutation "fitness." We then incorporated the best mutations into the next generation's CNN, repeating

show abstract

“…Three studies assessed detection of tissue ischemia (all Brainomix, all retrospective, 2 independent of the company, 32,39 total patients n=367), 32,39,40 with sensitivities of 44% to 83% and specificities of 57% to 93% (Table 2). Six studies assessed detection of large vessel occlusion (LVO; 3 vendors, all retrospective, 1 independent of the vendor, 41 total n=2635) 38,[41][42][43][44][45] with sensitivities of 80% to 96% and specificities of 90% to 98%. Only 1 study each assessed hemorrhage detection 46 and MRI diffusion or perfusion imaging.…”

Section: Accuracy Of Ai In Strokementioning

confidence: 99%

Accuracy of Automated Computer-Aided Diagnosis for Stroke Imaging: A Critical Evaluation of Current Evidence

Mair

Kummer

Williams

et al. 2022

Stroke

View full text Add to dashboard Cite

There is increasing interest in computer applications, using artificial intelligence methodologies, to perform health care tasks previously performed by humans, particularly in medical imaging for diagnosis. In stroke, there are now commercial artificial intelligence software for use with computed tomography or MR imaging to identify acute ischemic brain tissue pathology, arterial obstruction on computed tomography angiography or as hyperattenuated arteries on computed tomography, brain hemorrhage, or size of perfusion defects. A rapid, accurate diagnosis may aid treatment decisions for individual patients and could improve outcome if it leads to effective and safe treatment; or conversely, to disaster if a delayed or incorrect diagnosis results in inappropriate treatment. Despite this potential clinical impact, diagnostic tools including artificial intelligence methods are not subjected to the same clinical evaluation standards as are mandatory for drugs. Here, we provide an evidence-based review of the pros and cons of commercially available automated methods for medical imaging diagnosis, including those based on artificial intelligence, to diagnose acute brain pathology on computed tomography or magnetic resonance imaging in patients with stroke.

show abstract

Positive predictive value and stroke workflow outcomes using automated vessel density (RAPID-CTA) in stroke patients: One year experience

Cited by 20 publications

References 49 publications

Head-to-head comparison of commercial artificial intelligence solutions for detection of large vessel occlusion at a comprehensive stroke center

Head-to-head comparison of commercial artificial intelligence solutions for detection of large vessel occlusion at a comprehensive stroke center

Direct evaluation of progression or regression of disease burden in brain metastatic disease with Deep Neuroevolution

Accuracy of Automated Computer-Aided Diagnosis for Stroke Imaging: A Critical Evaluation of Current Evidence

Contact Info

Product

Resources

About