How Artificial Intelligence is Revolutionizing Opportunistic Detection on CT scan?

CINA-iPE-output

Opportunistic findings are those that are unexpected or incidental and discovered on medical imaging studies performed for other reasons. Artificial intelligence (AI) can help detect these small, and sometimes subtle, findings, leading to earlier treatment of potentially serious conditions.

Harnessing AI for Opportunistic Medical Findings Detection

Opportunistic detection of pulmonary embolism (PE) is one example among many. The frequency of incidental detection of PE among oncology patients is approximately 3.4%.1 Up to 45% of PEs are missed by radiologists when “off-search” for the exam’s primary purpose.Undetected PE is associated with poorer outcomes; thus, prompt management is essential.

Oncology studies may be reviewed anywhere from hours to days after they have been acquired. This is particularly true of late, with the growing backlog of examinations associated with rising case volumes and staffing limitations.

Capable AI can work in the background, leveraging computer vision as an always-on assistant, unfettered by indication-related expectations, and ensuring that opportunistic findings are promptly identified, called to the radiologists’ attention, and reported.

Detecting Pulmonary Embolism and Beyond

Incidental detection of disease on common examinations like CTs can also have a significant impact on health. For example, using AI to scrutinize CT scans acquired for other reasons can help identify unsuspected vertebral compression fractures (VCFs). These fractures can be difficult to detect, especially in patients who are not experiencing severe pain. AI-based screening of CT scans can lead to earlier treatment, preventing complete vertebral collapse, and improving patient quality of life.3,4

AI algorithms can also be used with CT to quantify visceral fat when evaluating for metabolic syndrome; to assess muscle bulk and density for sarcopenia diagnosis; to quantify liver fat in assessing hepatic steatosis; and to quantify aortic and coronary calcium for cardiovascular risk.5,7

These algorithms provide reproducible and reliable measurements to assess the hidden condition and help personalize patient management. Early studies also show their potential to predict treatment response and future adverse events.8,9

The American College of Radiology’s Incidental Findings Committee, supports opportunistic identification and quantification of coronary calcium on routine CT scans of the chest as well as CT performed at low dose for lung cancer screening.10

AI's Role in Early Disease Detection and Personalized Patient Care

Although these applications of AI have the potential to improve patient outcomes and increase efficiency, they also have drawbacks. It is true that some findings can be beneficial, but others may be clinically insignificant and yet lead to additional imaging, testing, and higher costs, as well as psychological distress, for patients. Convenient methods of informing the patient about the opportunistic finding and ensuring adequate follow-up are necessary for the appropriate use of such capabilities.

At present, only a limited number of AI-fueled applications are available for screening, particularly for diseases with low incidence. But more are expected in the coming years, and they may be able to weigh patient risk factors and contribute to disease prediction and prevention.

References

1.Meyer HJ, Wienke A, Surov A. Incidental pulmonary embolism in oncologic patients—a systematic review and meta-analysis. Support Care Cancer. 2021;29(3):1293–1302.

2. Topff L, Ranschaert, ER, Bartels-Rutten A, Negoita A, Menezes R, Beets-Tan RG, Visser JJ. Artificial intelligence tool for detection and worklist prioritization reduces time to diagnosis of incidental pulmonary embolism at ct radiology. Cardiothoracic Imaging. 2023; 5(2):e220163.

3. Chen HY, Wu T, Tseng SP, Lin CY, Chen CW, Wong TH, Wei YF, Chen YF. Application of tomosynthesis for vertebral compression fracture diagnosis and bone healing assessment in fracture liaison services. Front Med (Lausanne). 2022 Sep 16;9:910130.

4. Lopes JB, Fung LK, Cha CC, Gabriel GM, Takayama L, Figueiredo CP, Pereira RM. The impact of asymptomatic vertebral fractures on quality of life in older community-dwelling women: The São Paulo Ageing & Health Study. Clinics (Sao Paulo). 2012 Dec;67(12):1401-6. 

5. Huang YT, Tsai YS, Lin PC, Yeh YM, Hsu YT, Wu PY, Shen MR. The value of artificial intelligence-assisted imaging in identifying diagnostic markers of sarcope- nia in patients with cancer. Dis Markers. 2022 Mar 29;2022:1819841.

6. Graffy PM, Liu J, O’Connor S, Summers RM, Pickhardt PJ. Automated segmentation and quantification of aortic calcification at abdominal CT: application of a deep learning-based algorithm to a longitudinal screening cohort. Abdom Radiol (NY). 2019 Aug;44(8):2921-2928.

7. Jairam PM, van der Graaf Y, Lammers JW. J, Willem PT. M, de Jong, PA. Incidental findings on chest CT imaging are associated with increased COPD exacerba- tions and mortality. Thorax. 2015;70(8): 725-731.

8. Xu X, Zhang HL, Liu QP, Sun SW, Zhang J, Zhu FP, Yang G, Yan X, Zhang YD, Liu XS. Radiomic analysis of contrast-enhanced CT predicts microvascular inva- sion and outcome in hepatocellular carcinoma. J Hepatol. 2019 Jun;70(6):1133-1144.

9. Trebeschi S, Drago SG, Birkbak NJ, Kurilova I, Cǎlin AM, Delli Pizzi A, Lalezari F, Lambregts DMJ, Rohaan MW, Parmar C, Rozeman EA, Hartemink KJ, Swan- ton C, Haanen JBAG, Blank CU, Smit EF, Beets-Tan RGH, Aerts HJWL. Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers. Ann Oncol. 2019 Jun 1;30(6):998-1004.

10. Munden RF, Carter BW, Chiles C, et al. Managing incidental findings on thoracic CT: mediastinal and cardiovascular findings. A White Paper of the ACR Incidental Findings Committee. J Am Coll Radiol. 2018 Aug;15(8):1087-1096.

AI triage solution for deadly vascular conditions receives FDA clearance and CE Mark

CINA-LVO

Avicenna.AI announces the introduction of CINA-PE and CINA-AD, including AI tools for detection and emergency triage of pulmonary embolism and aortic dissection

Marseille, FRANCE – June 2, 2021 – Medical imaging AI specialist Avicenna.AI today announced that it has received certification in the United States and European Union for CINA-PE and CINA-AD, the new AI solutions that leverages deep learning algorithms for emergency triage of deadly vascular conditions.

In addition to securing a CE Mark in the EU, CINA-PE and CINA-AD have also received 510(k) clearance from the US Food and Drug Administration for its automatic detection and triage capabilities for both pulmonary embolism (PE) and aortic dissection (AD) from CT-scan imaging.our CINA solution.

Pulmonary embolism is the blockage of an artery in the lungs and is one of the major causes of death, morbidity, and hospitalization worldwide. It is difficult to diagnose PE as it manifests in diverse ways and can be mimicked by a range of other conditions. CINA CHEST provides rapid automatic PE detection on CT chest angiography, providing clinicians with accurate and rapid real-time alerts on the disease.  

Aortic dissection is a tear in the inner layer of the aorta, allowing blood to flow between the layers. Although relatively rare, AD has a high mortality rate and is often not diagnosed when it first appears. Patients who receive the appropriate treatment in a timely manner have a high survival rate, so the importance of a quick and accurate diagnosis is critical. CINA CHEST identifies acute AD cases that require urgent intervention, providing accurate, real-time alerts on thoraco-abdominal CT angiography.

CINA CHEST is part of Avicenna’s CINA family of AI tools that support the treatment of emergencies, including CINA HEAD, its FDA-cleared and CE-Marked solution that supports the detection and triage of stroke and neurovascular emergencies.

“At Avicenna, we specialize in the development of AI algorithms that can identify acute abnormalities, and CINA CHEST is the latest application we’ve developed to enhance emergency room radiology,” said Cyril Di Grandi, co-founder and CEO of Avicenna.AI. “Our PE and AD triage tools are the third and fourth algorithms we’ve released in less than 12 months, demonstrating our ambition to create AI applications that support detection and triage of emergencies throughout the entire body.”

Avicenna.AI receives CE Mark for stroke severity assessment AI tool

ai tools for neuro

Medical imaging AI innovator secures EU certification for CINA-ASPECTS, which helps quantify the severity of a stroke from a brain CT scan.

Marseille, FRANCE – May 27, 2021 – Medical imaging AI specialist Avicenna.AI today announced that it has received CE Mark certification for its CINA-ASPECTS AI tool for stroke severity assessment. CINA-ASPECTS automatically processes non-contrast CT scans and calculates the “ASPECT”score, assisting the radiologist within their existing systems and workflow.

ASPECTS, which stands for “Alberta Stroke Program Early CT Score” is a topographic scoring system used to quantify the severity of a stroke from a CT scan of the brain. It divides the brain territory affected by a stroke into 10 areas of interest and provides a score between zero and 10, where 10 is normal and zero indicates widespread ischemic damage throughout the affected area.

CINA-ASPECTS computes a heat map indicating the probability of hypodensity and/or sulcal effacement in the brain, and displays a list of infarcted regions. It also provides tilted and resliced CT images to allow easy comparison of the right and left hemispheres.

In addition to assisting clinicians to evaluate the ASPECT score from CT scans, CINA-ASPECTS also helps improve the reproducibility of the score, which often varies depending on the radiologist reading the scan.

CINA-ASPECTS is part of Avicenna.AI’s CINA Head family of AI tools that support the treatment of stroke and neurovascular emergencies. CINA Head also includes FDA-cleared and CE-Marked tools for detecting intracranial hemorrhages (ICHs) and large vessel occlusions (LVOs) from CT-scan imaging.

“CINA-ASPECTS supports stroke physicians and radiologists in the assessment and characterization of early ischemic brain tissue injury using CT image data,” said Cyril Di Grandi, co-founder, and CEO of Avicenna.AI.

“This new tool demonstrates our commitment to providing radiologists with AI solutions that can enhance their capabilities. Securing a CE Mark is a key milestone and we are delighted to be able to start offering the benefits of CINA-ASPECTS to our European customers – we look forward to FDA clearance in due course.”

Stroke Detection AI Tool Approved for Medicare NTAP

Triage tool for CT Scan

Paris, FRANCE – November 24th, 2020 – Medical imaging AI specialist Avicenna.AI today announced that its CINA Head software qualifies for the new technology add-on payment (NTAP) recently approved by the Centers for Medicare & Medicaid Services (CMS).

The NTAP is available for radiological computer-assisted triage and notification software systems like CINA Head, which analyzes computed tomography angiogram (CTA) images and urgently notifies clinical team members when a suspected large vessel occlusion (LVO) has been identified to reduce time to treatment.

Dr Peter Chang, radiologist and co-founder of Avicenna.AI, said, “AI-enabled CT stroke triage, specifically with LVO detection, is the first deep learning tool to receive the CMS NTAP designation and is eligible for up to $1040 of reimbursement. CMS only grants NTAP designation to promote the adoption of new technology that provides substantial clinical improvement over standard of care. This will help accelerate the innovation and adoption of deep learning technology by aligning the incentives of both software developers and clinical providers.”

In addition to LVO detection, Avicenna’s FDA-approved CINA Head triage AI solution for neurovascular emergencies also detects intracranial hemorrhages (ICHs). Using a combination of deep learning and machine learning technologies, CINA Head automatically detects and prioritizes acute ICH and LVO cases from CT-scan imaging within 20 seconds, seamlessly alerting the radiologist within their existing systems and workflow.

Avicenna.ai: NTAP information for customers

Avicenna.AI believes that there is a strong argument that the CINA Head triage solution is substantially similar to the applicant technology and that the same ICD-10-PCS code may be used to describe the use of CINA Head.

Avicenna.AI secures FDA clearance for its CINA neurovascular imaging Tool

Brain CT scan

CINA supports emergency room triage for intracranial hemorrhages and large vessel occlusions.

Paris, FRANCE – July 14, 2020 – Medical imaging AI specialist Avicenna.AI today announced it has received 510(k) clearance from the US Food and Drug Administration (FDA) for its CINA triage AI solution for neurovascular emergencies. The FDA’s decision covers CINA’s automatic detection capabilities for both intracranial hemorrhage (ICH) and large vessel occlusion (LVO) from CT-scan imaging.

Stroke is a leading cause of death in the US, with more than 795,000 strokes resulting in more than 100,000 deaths each year. It is estimated that up to a third of the most common type of stroke are caused by LVO, when a clot blocks the circulation of the blood in the brain. Around 1 in 10 strokes are thought to be caused by ICH, or bleeding that occurs inside the skull. Using a combination of deep learning and machine learning technologies, CINA automatically detects and prioritizes acute ICH and LVO cases within 20 seconds, seamlessly alerting the radiologist within their existing systems and workflow.

Dr. Peter Chang, radiologist and co-founder of Avicenna.AI, said, “When dealing with a stroke, time is of the essence and being able to prioritize effectively is critical to saving lives and improving outcomes. Not only does CINA helps radiologists to identify pathologies quickly, but also to highlight those that require the most urgent care.”

CINA’s ICH detection capability was validated using data from 814 cases conducted at more than 250 imaging centers across the United States, with 96% accuracy, 91.4% sensitivity, and 97.5% specificity. The product’s LVO detection capability was validated based on 476 cases, with 97.7% accuracy 97.9% sensitivity, and 97.6% specificity.

Cyril Di Grandi, co-founder, and CEO of Avicenna.AI, said, “We’re excited to have received FDA clearance for CINA and we are looking forward to working with emergency departments and stroke centers across the United States to help improve detection, decision-making and patient outcomes. As a triage AI tool that identifies multiple pathologies, we believe that CINA delivers more value than AI tools or algorithms that only target a single condition.”

CINA is the first in a family of AI tools for emergency radiology being developed by  Avicenna.AI. Subsequent products spanning the trauma and vascular fields are expected to be unveiled in the next 12 months.