Tag: Stroke

Categories
Uncategorized

AI-Based Gaze Deviation Detection to Aid LVO Diagnosis in NCCT

Introduction

Strokes occur when blood supply to the brain is interrupted or reduced, depriving brain tissue of oxygen and nutrients. It is estimated that a patient can lose 1.9 million neurons each minute when a stroke is untreated. So, the treatment of stroke is a medical emergency that requires early intervention to minimize brain damage and complications. Furthermore, a stroke caused by emergent large vessel occlusion (LVO) requires a much more prompt identification to improve clinical outcomes.

Neuro interventionalists need to activate their operating rooms to prepare candidates identified for endovascular therapy (EVT) as soon as possible. As a result, identifying imaging findings on non-contrast computed tomography (NCCT) that are predictive of LVO would aid in identifying potential EVT candidates. We present and validate gaze deviation as an indicator to detect LVO using NCCT. In addition, we offer an Artificial Intelligence (AI) algorithm to detect this indicator.

What is LVO?

Large vessel occlusion (LVO) stroke is caused by a blockage in one of the following brain vessels:

  1. Internal Carotid Artery (ICA) 
  2. ICA terminus (T-lesion; T occlusion) 
  3. Middle Cerebral Artery (MCA) 
  4. M1 MCA 
  5. Vertebral Artery 
  6. Basilar Artery

Image source: Science direct

LVO strokes are considered one of the more severe kinds of strokes, accounting for approximately 24% to 46% of acute ischemic strokes. For this reason, acute LVO stroke patients often need to be treated at comprehensive centers that are equipped to handle LVOs. 

Endovascular Treatment (EVT)

EVT is a treatment given to patients with acute ischemic stroke. Using this treatment, clots in large vessels are removed, helping deliver better outcomes. EVT evaluation needs to be done at the earliest for the patients that meet the criteria and are eligible. Early access to EVT increases better outcomes for patients.  The timeframe to perform is usually between 16 – 24 hours in most acute ischemic cases.

Image Source: PennMedicine

Goal for EVT

Since it is important to perform this procedure as early as possible, how do we get there?

LVO detection on NCCT

There is a 3 point step to consider for this:

  1. Absence of blood
  2. Hyperdense vessel sign or dot sign
  3. Gaze deviation (often overlooked on NCCT) 

Gaze deviation and its relationship with acute stroke

Several studies suggest that gaze deviation is largely associated with the presence of LVO [1,2,3].

Stroke patients with eye deviation on admission CT have higher rates of disability/death and hemorrhagic transformation. Consistent assessment and documentation of radiological eye deviation on acute stroke CT scan may help with prognostication [4].

AI algorithm to identify gaze deviation

We developed an AI algorithm that reports the presence of gaze deviation given an NCCT scan. Such AI algorithms have tremendous potential to aid in this triage process. The AI algorithm was trained using a set of scans to identify gaze direction and midline of the brain. The gaze deviation is calculated by measuring the angle between the gaze direction and the midline of the brain. We used this AI algorithm to identify clinical symptoms of ipsiversive gaze deviation in stroke patients with LVO treated with EVT. The AI algorithm has a sensitivity and specificity of 80.8% and 80.1% to detect LVO using gaze deviation as the sole indicator. The test set had 150 scans with LVO-positive cases where thrombectomy was performed.

Discussion

Ipsiversive Gaze deviation on NCCT is a good predictor of LVO due to proximal vessel occlusions in ICA terminus and M1 occlusions. However, it is a poor predictor of LVO due to M2 occlusion. We report an AI algorithm that can identify this clinical sign on NCCT. These findings can aid in the triage of LVO patients and expedite the identification of EVT candidates. 

We are presenting this AI method at SNIS 2022, Toronto. Please attend our oral presentation on 28th July 2022 at 12:15 PM (Toronto time).

 

Upadhyay, Ujjwal & Golla, Satish & Kumar, Shubham & Szweda, Kamila & Shahripour, Reza & Tarpley, Jason. (2022). Society of NeuroInterventional Surgery SNIS

References

[1] Silva, Ana & Pessoa, Ana & Nogueira, Renato & Araújo, José & Alves, José & Pinho, João & Ferreira, Carla. (2019). Prognostic information of gaze deviation in acute ischemic stroke patients. Neurological Sciences. 41. 10.1007/s10072-019-04140-7.

[2] McCluskey, G., Hunter, A., Best, E., McKee, J., McCarron, M. O., & McVerry, F. (2019). Radiological Eye Deviation as a Predictor of Large Vessel Occlusion in Acute Ischaemic Stroke. Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association, 28(8), 2318–2323. https://doi.org/10.1016/j.jstrokecerebrovasdis.2019.05.029 

[3] Jiang, N. N., Wu, W., Fong, C., Sahlas, D. J., & Larrazabal, R. (2020). Role of Radiological Eye Deviation in Imaging Occult Cases of Acute Large Vessel Occlusion. Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association, 29(5), 104687. https://doi.org/10.1016/j.jstrokecerebrovasdis.2020.104687

[4] Payabvash, S., I. Qureshi, and A. I. Qureshi. “Clinical implications of eye deviation on admission CT examination of acute ischaemic stroke patients." Clinical Radiology 71.12 (2016): 1314-e11.

Categories
Uncategorized

Ultrasound AI for Cardiovascular Disease Prevention

Key Using ultrasound AI to prevent cardiovascular diseases through early detection of atherosclerosis.

Key Highlights

  • Cardiovascular diseases (CVD) cause ~32% of deaths; the leading cause of death globally
  • qVH is the first known solution for AI-guided vascular ultrasound (carotid) that can boost disease prevention using point-of-care-ultrasound (POCUS) devices.  
  • With qVH, high-risk individuals can be screened by any clinician/ remote health worker at any convenient location 
  • Patients can be identified before symptoms appear, allowing for earlier disease management, improved patient outcomes, and reduced costs

Using AI to maximize the potential of POCUS for disease prevention

Qure.ai has developed an AI product for vascular health called qVH. It is the first known solution that guides clinicians during a carotid artery scan. Here’s how qVH’s AI works:

Probe Navigation Guidance: Detects probe location (CCA, ICA etc.) & orientation (long/short axis) and recommends best way to reach next step of protocol.

Plaque Detection & Characterization Guidance: Auto-detects abnormalities in a live scan (video) and quantifies it when a diagnostic quality image is available

Image Quality Guidance: Tracks image quality while scanning, recommends steps to maintain diagnostic quality & auto-captures images.

Device Setting Guidance: Detects common errors in ultrasound device settings in Pulse Wave (PW) mode and recommends changes for accurate PW velocity measurements. Thereby, preventing errors that could lead to misdiagnosis. 

*qVH is not FDA approved/CE marked yet and is currently meant for investigational or research use only.

The need for qVH

~20% of strokes in adults are caused by the narrowing of the carotid artery (see image; bottom). Buildup of plaque (fatty deposits) in the arteries is the root cause for this narrowing; a condition that is known as atherosclerosis (see image; top).

Plaques can develop in different vessels leading to artery narrowing/clots and hence reduced blood flow to various parts of our body. This leads to critical events such as:

  • Stroke (Carotid artery)
  • Heart Attack (Coronary Artery)
  • Renal Ischemia (Renal Artery), etc.

Evidence suggests that ~0-3% of the general population have a severe form of this disease but without any symptoms, while ~35% of diabetic patients have carotid plaques with or without symptoms. 

However, preventive measures to reduce disease burden have been limited due to:

  • Lack of clear guidelines
  • Logistical challenges like hospital visits for USG scan
  • Depending on operator skills for accurate scanning & reporting using USG
  • High cost of vascular USG
  • Lack of sufficiently skilled clinicians to perform vascular USG. 

Significant developments in the last decade 

Price: USG machines have become cheaper (by ~80%), more portable (handheld & wireless) and easily accessible with the arrival of point-of-care ultrasounds (POCUS).

Preference: USG is gradually becoming the preferred modality for disease prevention.

  • American Heart Association (AHA) recommends carotid artery duplex scanning in patients with high-risk features undergoing coronary artery bypass graft (CABG) surgery.
  • European Society of Cardiology (ESC) recommends carotid duplex ultrasound for evaluating the extent and severity of carotid stenosis.

Proof: Real-world evidence suggests benefits in risk-stratification through carotid artery screening.

  • Reduction in mortality rates (~10%), early disease diagnosis (~4.5 yrs), reduction in patient costs (by ~50%). [VIPVIZA]
  • Re-classification of low-risk patients to mid/high-risk based on the presence of carotid plaque. [Swiss AGLA]

Advantages: Govt. backed reimbursements for using advanced ultrasound technology.

  • US Hospitals can claim NTAP reimbursement of ~$1868 per patient diagnosed using ultrasound guidance technology (Caption Guidance) for CVD prevention.
  • American Medical Association (AMA) has introduced 2 new CPT codes for quantitative USG tissue characterization with ACR proposing an additional $82/scan.

What is holding back ultrasound-based CVD prevention programs?

POCUS devices have solved problems related to accessibility and affordability. But they have amplified issues related to operator skills since these ultra-portable POCUS devices can be used in any setting (remote areas, sports ground, battlefield etc.) by most clinicians. The existing issues are:

  • Training is needed to perform the ultrasound scan as per the defined protocol.
  • Training is needed to capture diagnostic quality images from a running video (cine loop).
  • There are chances of misdiagnosis due to errors in:
    • Performing ultrasound measurements manually. Eg: plaque length/area, PW ESV/PDV, Degree of Stenosis etc.
    • Optimizing device settings manually. Ex: gate size/angle/position, box angle.
    • Detecting & quantifying abnormalities (plaques, stenosis, etc.).
  • Inter-operator variability due to operator dependence for probe navigation, abnormality detection, image capture and for optimization of USG device settings. 

In 2020, POCUS accounted for only ~3-5% of the ultrasound market by revenues. However,  global POCUS market revenue is predicted to increase to $4B by 2030 from $2B in 2020.

qVH has been designed to address all of the issues outlined above. qVH validation has begun at 2 sites in India & Argentina and will be expanded to 8 sites across Asia, Europe and North America within the next 3 months. qVH can be used with all existing ultrasound machines. Our beta sites are using Cart and POCUS machines.