AI LUMBAR SPINE
MRI READING AND REPORTING
CoLumbo reads, segments, measures and classifies MRI images to provide suspected pathology description, findings and measurements with pre-populated structured or free text report. The project has European Commission Seal of Excellence and there is USPTO Patent Pending US 63/239,985.
CoLumbo has obtained CE mark and complies with FDA Quality System Regulations and has FDA 510(K) clearance and is cleared for clinical use in Europe and the USA.
BENEFITS OF COLUMBO
CoLumbo can help radiologists to reduce the reading and reporting time by up to 25%. This facilitates an increase in total patients examined and a reduction of the cost per patient examination when radiologist hourly rate is taken into account.
Clinical trials has concluded that CoLumbo can reduce errors of omission up to 15% as this percentage is higher for less experienced radiologists. Radiologist using CoLumbo is more accurate than a radiologist NOT using CoLumbo
CoLumbo brings standardization in reporting practices in the case of multiple hospital chains or medical imaging centers. The fully customizable suspected pathology threshold levels enable setting measurement standardization.
CoLumbo is software for analysis of Lumbar spine images obtained with MRI.
CoLumbo is software for analysis of lumbar spine images obtained with MRI. The purpose of CoLumbo is to assist with the reading of MRI images on the lumbar spine and to provide information on suspected pathologies and abnormality detection, and reduce the time to record the readings. According to the Spine Reporting Survey we conducted, the radiologists think that on average about 17.2 minutes are needed for thorough L-Spine MRI examination in cases without any complications and about 30 minutes for more complex cases, but they have only 13.6 minutes on average for MRI reading in a real clinical situation at the cost of up to 30% errors and omissions.
The key novelty of CoLumbo lies in the unique machine learning algorithm, based on fully convolutional neural networks combined with medical domain knowledge, dropout regularization, and packet normalization which are capable of reading MRI images, to assist qualified clinicians in providing a complete diagnosis. U-Net-like architecture is used to improve the resolution.
The first step is the Segmentation of specific structures which is made on a pixel level and the use of fully convolutional neural networks allows quick segmentation maps to be generated for images of any size. The second is the identification of key points in the MRI images. After this is the measurement of distances, areas and angles. Finally, the combination of segmentation, measurements, and specially applied algorithms provides the qualified clinicians with an asisstance in complete diagnosis according to the parameters described in the scientific medical literature. All findings are presented in a easy-to-use final draft report, which is currently available in three languages – English, German and French. More languages will be added soon.
The main benefits of CoLumbo are lower cost, ease of use and optimal cost-result ratio. CoLumbo holds the potential to alleviate the economic burden imposed on the business as the low cost of the service will render it available to a bigger part of the population, thus helping with the implementation of preventative measures which will lower the number of chronically disabled employees.
FEATURES OF COLUMBO
SUSPECTED PATHOLOGIES AND OTHER FINDINGS:
- HERNIATION AND ITS SIZE, LOCATION AND POSSIBLE DESCENDING AND/OR ASCENDING MIGRATION
- NERVE ROOT IMPINGEMENT
- DURAL SAC COMPRESSION
- CENTRAL STENOSIS
- ANTERO AND RETRO – SPONDYLOLISTHESIS
- SYMMETRICAL AND ASYMMETRICAL BULGING
- HYPO AND HYPER-LORDOSIS
- REDUCED DISK HEIGHT
- REDUCED VERTEBRAL BODY HEIGHT
- INCREASED AORTIC DIAMETER
- AXIAL FORAMINAL SIZE
- LEVEL LABELS
- VERTEBRAL BODY
- OTHER PARTS OF THE VERTEBRA
- HERNIATED PART OF THE DISK
- DURAL SAC
- NERVE ROOTS
- LIGAMENTUM FLAVUM
- SIZE OF HERNIATION
- HERNIATION CIRCUMFERENCE
- HERNIATION LOCATION SCORE
- MIGRATION SIZE
- NERVE ROOT IMPINGEMENT SCORE
- DURAL SAC AREA AND STENOTIC RATIO
- SPINAL CANAL DIAMETER
- LISTHESIS PERCENTAGE AND GRADE
- L1S1, L1L5 AND L1L4 LORDOTIC ANGLES
- AORTIC DIAMETER
- BULGING SIZE
- BULGING CIRCUMFERENCE
- BULGING SYMMETRY SCORE
- DISC HEIGHT (ANTERIOR, MIDDLE, POSTERIOR) AND RATIOS
- VERTEBRAL BODY HEIGHT (ANTERIOR, MIDDLE, POSTERIOR)
- AXIAL FORAMINAL SIZE
- INTERVERTEBRAL ANGLES
WHO CAN BENEFIT FROM COLUMBO
RADIOLOGISTS USING MEASUREMENTS
The biggest time saving from using CoLumbo is attributed to the pre-populated draft report, which includes measurements of all suspected pathologies detected by the software. In addition, related tissues measurements, such as vertebral body and disk heights, are visualised in the user interface.
Less experienced radiologists like generalists will benefit the most from our software. The greates benefit for this user group is the inrease in accuracy due to the reduced errors of omission when using CoLumbo.
HOSPITALS AND IMAGING CENTER CHAINS
An unique feature of CoLumbo is the complete customisation of suspected pathology threshold levels. When multiple hospitals or imaging centers use the same threshold levels standardization in reporting can be achieved.
Low Back Pain has a major economic impact with total costs related to this condition exceeding 100 Billion USD per year only in the United States. Herniated discs, stenosis and spondylolisthesis are major causes for lower back pain and disability and the latter being a significant socio-economic problem all over the world. Annually there are 10 million MRI spine exams in the US alone with radiologist wages of USD 140 per hour and second opinion price of USD 50 per exam.
Population in developed countries is aging and there is an enormous demand for healthcare specialists that leads to the demand for healthcare products that will facilitate the work of the physicians. Trends indicate that in five years half of them will be medical and 50 to 80% will be analyzed by artificial intelligence or deep learning software.
Currently, there are situations when patients may need to wait a very long time for diagnosis and pay a very high price. CoLumbo aims to assist qualified clinicians in offering a reliable and accurate diagnosis of back pain problems for a fraction of the current costs. Furthermore, the platform assist qualified clinicians in offering a completely unbiased diagnosis with no ulterior motives. A blind study indicates up to 30% disagreement between radiologists. With CoLumbo the errors will be reduced by up to 15% and time savings of at least 25% will occur.