Research

D3YI165WAAUCunr

Comprehensive solutions will boost AI use in medical imaging

Integrating artificial intelligence (AI) into the radiologist’s workflow is still challenging, but all-inclusive solutions can help unfold algorithms’ power, QUIBIM CEO and founder Angel Alberich-Bayarri explained during the ESR AI Premium Event, which was hosted by the European Society of Radiology (ESR) and the European School of Radiology (ESOR) earlier this month in Barcelona.

Medical imaging AI is a bubbling field but very few solutions are used in daily practice today, Alberich told delegates during the busy meeting, which gathered top researchers in medical imaging AI and thousands of online attendees. “We have a lot of research, AI algorithms and start-ups, but few are really embedded in the radiology workflow,” he said.

A main obstacle to AI integration is a lack of knowledge of utilities. For most imaging biomarkers, the real application relationship with clinical endpoints on a large scale – diagnostic, prognostic and treatment response – remains unknown. Clinicians don’t want to integrate biomarkers that have not been validated, but if they don’t gather information massively and try to understand how biomarkers relate to the disease, they will never help advance healthcare, Alberich explained.

“We have to change our minds and not wait for biomarkers to be validated before they can be extracted on a daily basis. Similarly to genomics: we have to do sequencing and study diseases to detect unknown mutations by ourselves,” he said.

The lack of annotated data is another challenge. Radiology reports are not filled with a focus on data annotation, but on descriptive language that needs to be processed by natural language processing (NLP). However they would be an ideal source of knowledge, and not just for the clinicians.

One-stop-shop platform using biomarkers

QUIBIM was created in 2015 as a spinoff company of La Fe Hospital in Valencia, Spain, to help radiologists make the most of AI in their everyday practice, by providing a one-stop-shop solution using imaging biomarkers and powerful algorithms.

“Offering a single solution embedded in workflows is key because radiologists will not buy all start-up micro developments but the best platform,” he said.

The very name of the company is an acronym and stands for Quantitative Imaging Biomarkers in Medicine. Imaging biomarkers enable to measure everything happening in the body to extract parameters that can provide information on the tissue of the lesion type beyond classification. Fuelled by AI, these biomarkers can deliver unprecedented information on disease.

“Many different imaging pipelines have dramatically changed thanks to AI integration. For example, we used to have lots of problems doing segmentation with traditional algorithms in tissues and organs such as the liver in MRI. Thanks to AI, segmentation has improved and with it our knowledge of liver disease,” he said.

A prerequisite is to integrate data mining solutions to make radiomics easy to everyone. This means it must be embedded in the same platform, as current solutions are not able to treat this amount of quantitative data from patient cohorts. “A lot of parameters are quantified in daily routine, but there is still no way to store and process them massively. Our current PACS systems are simply not prepared for quantitative data,” Alberich said.

There is a lot of sense in working within a structured report (SR), as it enables to annotate data that will further advance research. Prospectively the studies can be very well annotated if AI imaging biomarkers are integrated in the fields of the SR. Working with the SR would tremendously facilitate communication between clinicians and with patients.

“We are building the radiology report of the future, only we’re doing it now. Patients do not understand radiology reports, so we have to change the way we communicate. We are very much aligned with the standardized way blood test findings are reported, everyone understands whether findings are in or out of range and if there is any abnormality. We have to be more intuitive in our communication,” Alberich said.

QUIBIM is developing quantitative, one-page long structured reports that are actionable, quantitative and automated. The reports are designed with KOLs in each speciality, to make sure they reflect the reality of clinical practice.

Clinical input and powerful technology

Cooperation with clinicians is a key axis for the company, which uses a stepwise model to create new solutions with clinicians in the loop.

The company develops highly performing AI algorithms using unprecedented network architectures, for instance, multiscale convolutional networks ensemble in brain MR, 2.5D network in liver MR and referee network in chest x-ray, and hundreds of thousands of annotated images that have been acquired through cooperation with researchers and university hospitals.

QUIBIM has launched algorithms in different product areas to provide a head to toe imaging biomarker solution; in neuro for Alzheimer, ALS, MS, stroke and cerebrovascular events; in MSK for articulations; in chest for screening, COPD and fibrosis; and in breast for screening. More products will soon be released that will focus on other body areas.

More than 60 hospitals worldwide currently use QUIBIM tools, most of which have received CE marks and/or are FDA pending. The company has notably developed the new ESOR teaching platform and has supplied its QUIBIM Precision® image analysis platform to the AI Precision Health Institute at the University of Hawai‘i Cancer Center in Honolulu. QUIBIM has received €3.5m funding ever since its creation and has offices in Spain and the U.S.

MRS QUIBIM Analysis_2

QUIBIM now offering advanced MR spectroscopy analysis including 2-HG for IDH1 mutation detection

Continuing its focus in the field of Oncology, QUIBIM is proud to offer an advanced MR Spectroscopy analysis tool. This tool developed in house by QUIBIM will help oncologists to improve diagnosis and treatment of brain gliomas, a disease that has an incidence of 22.6 per 100.000 population in United States.

In order to have reproducible, reliable and accurate information from tumors, we provide physicians with quantification of the metabolite by analyzing Magnetic Resonance Spectroscopy (MRS) images. MRS is a non-invasive imaging technique widely used to obtain chemical information by detecting relevant metabolites concentration from a spectrum.

Even though it is possible to detect almost any metabolite in the body, QUIBIM is currently focusing on the detection of the 2-Hydroxyglurate (2HG) because of its influence in the prediction of low-grade brain gliomas. 2HG is a metabolite, normally present at very low levels in healthy cells and tissues because of the reduction of α-ketoglutarate (α-KG) catalyzed by isocitrate dehydrogenase (IDH) protein. The IDH enzyme mutation in low-grade brain gliomas produces an accumulation of 2-HG which makes the measurement of this oncometabolite crucial to distinguish IDH-mutant gliomas from other brain mass (Stefan, et al., 2010).

MRI quality assurance

The quality assurance of the Magnetic Resonance Imaging (MRI) images is important and mandatory to ensure consequent and reliable results from the MR analysis. For that reason, a qualitative evaluation of the images is performed by QUIBIM to guarantee a strict and standard control of the images by checking the accomplishment of the MRI acquisition protocol set and the absence of artifacts.

MRS quality assurance

The first technical information QUIBIM provides with, is the graphical representation of the voxel placement in the sagittal, axial and coronal view depicted in a structural image. This quality review is important in order to assure the correct position of the voxel in the MRS acquisition avoiding necrotic tissue or non-tumor substances what can affect MRS results.

MRS quantification

Once the quality check of the MRS acquisition is done, QUIBIM produces a technical structured report, quantitative and graphical information about the MRS analysis.

QUIBIM_MRS Structured report

The report, apart from the main images and quantitative information, includes a spectrum graph and the voxel placement. Each peak of the spectrum corresponds to a different substance or metabolite with a different resonance frequency. This difference is usually measured in an independent scale besides the principal magnetic field (parts per million). The intensity of each peak is related to the concentration of the substances in the studied volume (Sánchez, et al., 2001).

To perform the analysis, the voxel in the tumor area and a reference acquisition corresponding to water are required. An automatic analysis of the spectrum is done providing this information and setting the up and down boundary value in ppm according to the metabolite searched. Then, we automatically process the spectrum filtering the water peak in the time domain, reducing the spectrum noise, adjusting the ppm scale according to Creatine and Choline position, and correcting the phase of the signal in order to also correct the baseline offset level to ensure the reliability and accuracy of metabolites’ concentration (Martí-Bonmatí & Alberich-Bayarri, 2013).

Therefore, it is possible to obtain from the studied metabolite its absolute concentration, the percentage of standard deviation (%SD) and its relative concentration using Creatine as a reference value (/Cr), sometimes adding other reference metabolites like PCr as the example of Figure 1 (/Cr+PCr).

The information provided by the standard deviation is essential to read MRS results because absolute concentration reliability depends on them: metabolites with a %SD less than 50 are practically undetectable with this data whereas a %SD<20 is a rough criterion for estimates of acceptable reliability. In addition, the third column indicates ratio relative to /Cr. This quantitative information will appear in the lower part of the report followed by a space for the signature of the scientist from QUIBIM once the analysis is done.

MRS analysis is now available in QUIBIM Precision® Platform to support oncologists and radiologists in brain gliomas treatment and diagnosis.

boton try quibim

References

  • Francesca Branzoli, *. A. (2018). Highly specific determination of IDH status using edited in vivo magnetic resonance spectroscopy. Neuro-Oncology, 907-916.
  • Martí-Bonmatí, L., & Alberich-Bayarri, Á. (2013). Disease Biomarkers: Modelling MR Spectroscopy and Clinical Applications in Bioinformatics of Human Proteomics. Valencia: Springer.
  • Min Zhou, *. Y. (2018). Diagnostic accuracy of 2-hydroxyglutarate magnetic resonance spectroscopy in newly diagnosed brain mass and suspected recurrent gliomas. Neuro-Oncology, 1262-1271.
  • Sánchez, J., Santos, A., SantaMarta, C., Benito, C., Benito, M., & Desco, M. (2001). Herramienta de Análisis de Espectros de RM. CASEIB. Madrid.
  • Stefan, G., Rob A., C., Mark D., M., Edward M., D., Mark A., B., Hyun Gyung, J., . . . David P., S. (2010). Cancer-associated metabolite 2-hydroxyglutarate accumulates in acute myelogenous leukemia with isocitrate dehydrogenase 1 and 2 mutations. Journal of experimental Medicine, 207(2), 339–344.