Posts Tagged :

AI

Lung texture outcomes in Chest Xray

Imaging, AI and radiomics to understand and fight coronavirus Covid-19
  • There is currently no effective cure for this virus and there is an urgent need to increase global knowledge in its mechanisms of infection, lung parenchyma damage distribution and associated patterns.
  • Artificial Intelligence and radiomics applied to X-Ray and Computed Tomography are useful tools in the detection and follow-up of the disease.

In December 2019 the city of Wuhan (China) became the center of a pneumonia outbreak of an unknown cause with global implications. In early 2020, Chinese scientists isolated a novel coronavirus (CoV), from patients in Wuhan, formerly  known as 2019-nCoV 1 and now renamed as Covid-19 by the World Health Organization (WHO). Patients infected with this strain present a wide range of symptoms 2, most seem to have mild disease, with about 20% appear to progress to severe disease, including pneumonia, respiratory failure and in around 2% of cases death 3. Common signs of infection include respiratory symptoms, shortness of breath and breathing difficulties, fever and cough 4.

Coronaviruses (CoV) are a large family of viruses that cause illness ranging from the common cold to more severe diseases such as Middle East Respiratory Syndrome (MERS-CoV) and Severe Acute Respiratory Syndrome (SARS-CoV). This novel coronavirus (nCoV) is a new strain not previously identified in humans. Although this outbreak had its start in China, today there are several countries around the world with identified cases, making it a worldwide public health concern.

Confirmed cases of COVID-19 acute respiratory disease reported by provinces, regions and cities in China, 13 February 2020*

Table 1. Confirmed cases of COVID-19 acute respiratory disease reported by provinces, regions and cities in China, 13 February 2020*

How could AI and imaging biomarkers aid to fight against this emerging zoonotic illness?

There is currently no effective cure for this virus and there is an urgent need to increase global knowledge in its mechanisms of infection, lung parenchyma damage distribution and associated patterns, not only for disease detection or to complement the diagnosis, but also to support the design of a curative therapy. AI and radiomics applied to X-Ray and Computed Tomography are useful tools in the detection and follow-up of the disease. As stated in 5, conspicuous ground grass opacity lesions in the peripheral and posterior lungs on CT images are indicative of Covid-19 pneumonia. Therefore, CT can play an important role in the diagnosis of Covid-19 as an advanced imaging evidence once findings in chest radiographs are indicative of coronavirus. AI algorithms and radiomics features derived from Chest X-rays would be of huge help to undertake massive screening programs that could take place in any country with access to X-ray equipment and aid in the diagnosis of Covid-19 6.

QUIBIM_StructuredReport_Chest-X-Ray-Classifier

FIGURE 1: QUIBIM – Quantitative Structured Report – Chest X-Ray Classifier

In order to speed up the discovery of disease mechanisms, QUIBIM’s Chest X-Ray Classifier (Figure 1) can be used to detect abnormalities and extract textural features of the altered lung parenchima that could be related to specific signatures of the Covid-19 virus. We have combined all our knowledge in AI and radiomics in this novel analysis pipeline specifically designed to extract disease patterns. First, the Chest X-Ray is automatically analyzed using a deep learning classifier to provide an abnormality score between 0 and 1. Any abnormality score above 0.3 is considered as an abnormal case. After this initial analysis, lungs are automatically segmented using a Mask R-CNN like convolutional neural network architecture and finally, a massive extraction of texture features is applied (figure header). This pipeline has been completely automated and will serve to provide additional information to the diagnosis of Covid-19.

QUIBIM is committed to provide access to our existing AI technology to find new diagnostic tools and ways to understand the mechanisms and aggressiveness of the disease, contributing to the efforts to find a cure.  Any clinician can fill this form created by QUIBIM to get free credentials for the use of the AI Chest X-Ray classification analysis technology available in the QUIBIM Precision Cloud platform. This research tool is offered to any doctor worldwide with the need of analyzing Chest X-Rays with suspicion of Covid-19.

References:

  1. https://reference.medscape.com/slideshow/2019-novel-coronavirus-6012559
  2. https://www.ncbi.nlm.nih.gov/pubmed/31978945
  3. https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200128-sitrep-8-ncov-cleared.pdf
  4. https://www.who.int/health-topics/coronavirus
  5. https://pubs.rsna.org/doi/10.1148/radiol.2020200274
  6. https://www.auntminnie.com/index.aspx?sec=sup&sub=xra&pag=dis&ItemID=127983

Authors:

 

Rafael López González – R&D Engineer

 

NVIDIA QUIBIM

QUIBIM Brings AI to Radiology Workflows with NVIDIA EGX

Artificial intelligence is becoming a reality in radiology as new AI solutions are moving from research to clinical validation and daily clinical workflow.

QUIBIM (Valencia, Spain) has a proprietary software platform and develops AI algorithms across imaging modalities for quantitative imaging biomarkers used in hospitals, radiology centers and clinical trials focusing on body ( liver, prostate) and musculoskeletal analysis algorithms.

QUIBIM’s solutions have already demonstrated a major impact in partner hospitals and radiology centers with a 70% reduction in reporting time of multiple sclerosis cases of the brain using QUIBIM’s White Matter Lesions algorithm. In addition, a large hospital in Valencia, Spain, has experienced significant cost savings using QUIBIM’s Chest X-ray classifier product.

By being able to seamlessly integrate AI solutions in the radiology workflows, QUIBIM helps healthcare providers stay ahead of increasing amounts of data needed for patient care. For example: with the QUIBIM Precision® data mining tool, it is possible to obtain new disease phenotypes based on non-supervised AI clustering. The combined power of AI and edge computing can retain critical processing tasks on devices at the point of care to help in earlier diagnosis of disease and eliminating manual tasks of the radiologists, thereby enabling them to optimize reporting and interpretation.

QUIBIM Precision® and NVIDIA EGX

Delivering AI at the edge minimizes data privacy concerns and enables real-time AI for clinical decisions. QUIBIM and NVIDIA are bringing AI to the edge of medical imaging, the most important healthcare tool in early detection, with the NVIDIA EGX Intelligent Edge Computing Platform. Having the possibility to containerize algorithms on NGC, which is optimized on EGX systems, QUIBIM is able to expand its reach, which helps in the democratization of AI and the ability to provide access to care using AI even in the remote regions of the world.

By delivering new diagnostic and operational capabilities that enhance patient care, QUIBIM and NVIDIA EGX are ushering in a new generation of smart hospitals and radiology departments.

RSNA 2019

QUIBIM at RSNA 2019
with new features!

For the third consecutive year, and coinciding with our business expansion, currently installed in more than 60 hospitals and used by more than 20 clinical trials worldwide, QUIBIM attends this RSNA 2019 edition with new solutions based on artificial intelligence.

Located at the AI Showcase booth #10418, QUIBIM has set up three demo points where participants can interact and navigate the platform testing their main features:

  • AI app’s for quantitative analysis and workflow optimization
  • Radiomics Data Miner tool.
  • Quantitative and radiological structured reporting.
  • Vendor-agnostic system compatible with all PACS vendors and equipment manufacturers.
  • Head-to toe solution (neurology, chest, body, and musculoskeletal).
  • Advanced visualization tools: Zero-footprint DICOM viewer. 

map-01

Seamless AI for Radiologists

QUIBIM Precision® platform integrates AI algorithms into the radiology department workflow with no clicks, making it an efficient system that provides a complete radiology solution covering the AI and quantitative needs.

In our strategy of providing value-driven solutions, QUIBIM uses AI as a tool for organ segmentation (prostate, liver, vertebraes, fat) using Deep Learning, lesions detection (white matter lesions), and classification (chest X-ray). These AI solutions are seamlessly integrated with PACS and RIS making them a part of daily clinical practice, by activating smart back-end rules engine to schedule post-processing tasks.

Discover how QUIBIM empowers radiologists’ workflow at booth #10418 – AI Showcase in the North Hall Level 2.

RSNA_schedule a meeting

In addition, as an advanced research tool QUIBIM has integrated a prostate nosological imaging module based on a non-supervised AI algorithm using quantitative data obtained from multiparametric magnetic resonance (mp-MR) images. This method could serve as a pipeline for the development of nosologic maps and speed up the case assessment and reporting time. This tool helps radiologists’ daily work leading them focus on small zones with malignant features that would be undetected in most of the cases.

More at RSNA 2019

AI THEATER PRESENTATION

Discover at the AI Theater our presentation AI Integrated in Daily Workflow with QUIBIM Precision: Visualize, Annotate, Quantify, Report and Discover how QUIBIM Precision® is providing a seamless solution for AI in radiology, with a complete integration in clinical routine and a completely automated rules engine to get all results before reporting. Special analysis modules for brain, musculoskeletal, lung and body-oncology applications. Presented by Angel Alberich-Bayarri, PhD, our CEO and Founder.

Monday 12:00-12:20 PM | AI24 | Room: AI Showcase, North Building, Level 2.  ADD TO YOUR CALENDAR

AI WORKSHOP

Also, we have organized a special workshop for those interested in a Head-to-Toe Hands-on with AI and Imaging Biomarkers Integrated in PACS. QUIBIM Precision. We will show how to empower radiologists’ daily practice by offering full control over our AI solutions. We will show how AI solutions are seamlessly integrated with PACS and RIS on a daily practice and how to interpret quantitative imaging and AI results.  Presented by Angel Alberich-Bayarri, PhD | Fabio Garcia-Castro | Mar Roca-Sogorb, PhD

Tuesday 1:00-2:30 PM | HW32 | Room: AI Showcase, North Building, Level 2

Interested?  PLACES ARE LIMITED!

Register now

In order to get the best experience for this workshop, it is highly recommended that attendees bring a laptop with a keyboard and decent-sized screen.

Join us at RSNA 2019!

 

 

2019-06-26

QUIBIM to develop platform in leading research project to fight pediatric cancer

QUIBIM is helping to advance knowledge of the most lethal pediatric tumors through EU-funded program PRIMAGE, which exploits precision information from medical imaging to establish tumor prognosis, and expected treatment response using radiomics, imaging biomarkers and artificial intelligence (AI).

Pediatric cancer is a rare disease, but treatment remains challenging. Improving knowledge is key to adequately plan therapy and boost survival, and the latest AI techniques have the potential to harness unprecedented information from medical images.

A few months ago, the European Commission funded the PRIMAGE (1) project with over €10M, to help identify the most efficient treatment and a tumor’s main characteristics without the need for biopsy, by using computational processing of medical images on the cloud.

The PRIMAGE consortium will create a bank of images obtained through AI, using an open cloud-based platform to support decision-making in the clinical management of Neuroblastoma (NB), the most frequent solid cancer of early childhood, and Diffuse Intrinsic Pontine Glioma (DIPG), the leading cause of brain tumor-related death in children. The PRIMAGE platform will implement the latest advancement of in-silico imaging biomarkers and modeling of tumor growth towards a personalized diagnosis, prognosis and therapies follow-up.
The project involves 16 European partners, including internationally recognized institutions, and four leading industrial partners, including Spanish biotechnology company QUIBIM, all working under the aegis of the Imaging Biomedical Research Group (GIBI230) based in La Fe Hospital, Valencia.

181220_IISLAFE PRIMAGE kick offprimage-logo-transparent
Sharing high-end knowledge of AI tools

QUIBIM is responsible for the central task of developing the PRIMAGE platform’s architecture, adaptation and design. The company recently obtained CE mark for its Chest X-Ray Classification AI-Tool and its imaging biomarker analysis algorithms, zero footprint DICOM viewer and platform within the QUIBIM Precision platform.

QUIBIM researchers are now bringing their expertise in medical image post processing and management to PRIMAGE, by passing on their knowledge of clinical trials design and validation, imaging biomarkers extraction and validation, radiomics, data clustering and visualization, and development of AI-fueled tools, such as organ segmentation models.
“Much work remains to be done to improve our knowledge of pediatric brain cancer. NB and DIPG have a complex therapeutic approach and we need proper tools to improve survival. Extracting quantitative information from medical images with AI can help visualize tumor growth with extreme precision, and help to tailor therapy to each individual patient,” Ángel Alberich-Bayarri  said.

QUIBIM’s input will also help to define the methodologies and standards to be used in the different development areas, to facilitate interoperability between the platform ́s modules and for future interoperability with their cloud-based platforms for functionality add-ons.

Transferrable knowledge to other cancers

Cancer has a very low incidence among children and experts estimate that 500,000 EU citizens will be pediatric cancer survivors by 2020. Nonetheless, cancer remains the first cause of non-traumatic death among children.

Neuroblastoma is the most common extracraneal tumor in children, representing 8-10% of all pediatric cancers. In Europe, 35,000 new cases are diagnosed each year, 1,000 in Spain alone.

Diffuse Intrinsic Pontine Glioma is a very rare disease in childhood and is associated with low survival (10%), despite many existing treatments and on-going research. Treatment is not curative, only palliative, i.e. radiotherapy to improve the patient’s life. 16 new cases are diagnosed each year in Spain, accounting for 2.5% of oncological pediatric patients and 13% of pediatric tumors of the central nervous system.

Because of the peculiarities of computational approximation in these two types of tumors that are proper to childhood, investigation done in that area will also be applicable to other types of tumors. Because it will gather considerable scientific effort, PRIMAGE should also help advance research on other types of cancer.
(1): PRedictive In-silico Multiscale Analytics to support cancer personalized diaGnosis and prognosis, Empowered by imaging biomarkers (PRIMAGE)

QUIBIM_Symbiosis of Radiology and AI

QUIBIM at RSNA 2018!

We are happy to announce that QUIBIM will be attending this year’s annual meeting of the Radiological Society of North America – RSNA 2018. From November 25 to 29, many of our Quibimers will be in Chicago demoing, sharing and showing our Radiomic solution for Hospitals and Radiology departments.

This year, QUIBIM developments are focused on the Symbiosis of Radiology and Artificial Intelligence to seamlessly integrate imaging biomarkers into radiology workflows.

QUIBIM_RSNA BOOTH 7367G

Attendees can find us at the Machine Learning Showcase – Booth #7367G  (North Building Level 3), where anyone is welcome to come over and explore the latest version of our QUIBIM Precision® Platform for medical images processing and imaging biomarkers analysis.

WANT TO DISCOVER OUR PLATFORM?

demo

image2

QUIBIM will be also taking part in the Machine Learning Showcase through a communication from our CEO and Founder, Ángel Alberich-Bayarri, on November 25 at 12:30 pm. The communication is entitled “QUIBIM Precision 3.0: AI as a Means, Not an End, for Imaging Biomarkers Integration in Clinical Practice” and shares QUIBIM insights about the role of AI on imaging biomarkers integration.

RSNA 2018_AAB_QUIBIM

Furthermore, as members of the NVIDIA Inception Program, QUIBIM will be demoing at the NVIDIA booth #6568 on November 26 at 10:00 am. Don’t miss it!

nvidia banner

It is a great opportunity for QUIBIM to be engaged in such a recognised event and get in touch with professionals in the fields of radiology and medical imaging.

MEET US!

QUIBIM_chest_xray_classifier_logo3

New Chest X-Ray Classification Tool

Despite the technological evolution of imaging modalities like CT, US and MRI, conventional X-ray remains the most performed examination in radiology departments, and remains a fundamental tool for anatomical analysis in the detection and diagnosis of respiratory diseases and bone tissue alterations. However, radiology departments have limitations in reporting the X-Rays due to the limited resources available (link).

QUIBIM has developed a Chest X-Ray Classification Tool that offers a solution to this problem which can help radiology departments become even more efficient. This classifier developed in collaboration with Hospital Universitario y Politécnico La Fe, estimates the probability of chest X-Rays of having a pathology using Artificial Intelligence.

How does it work?

This tool makes use of fourteen Convolutional Neural Networks trained with a database of more than 100,000 images (NIH ChestXray14 dataset) to estimate the probability of presence of the following pathologies in chest X-Rays: atelectasis, cardiomegaly, effusion, infiltration, mass, nodule, pneumonia, pneumothorax, consolidation, edema, emphysema, fibrosis, pleural thickening and hernia. Afterwards, the probabilities are used by a Fully Connected Neural Network to get the final probability of the X-Ray of being abnormal.

XRAY chest

Because of this AI methodology the classifier understands the visual patterns that are most indicative of the different pathologies using the knowledge extracted from the large dataset of radiographs used to train the networks. QUIBIM’s Chest X-Ray Classification Tool is able to learn further using new images, which means that this system is continually improving and evolving with time.

 What information does it provide?

Once all the quantifications are performed this tool provides an intuitive Structured Report with the patient’s information, the abnormal probability of the radiographs analyzed and the representation of the findings. In addition, if the image is classified as abnormal, the report shows the three pathologies that are more likely to be found and a heatmap that highlights the most abnormal regions. This report is designed to be very user friendly, to assist the user in understanding the tool’s findings at a glance in order to make its usage highly efficient.

Why is this new tool so useful?

Using this technology it is possible to prioritize unreported, potentially pathological radiographs which allows radiologists to focus their efforts on studies that are more likely to have pathologies and thereby become more efficient. This tool essentially ensures that pathological findings, which could have been unreported due to the heavy workload of radiology departments, are correctly reported.

QUIBIM’s goal is to provide the radiology departments with an optimal solution for automatic reading of X-Rays without interfering in the  workflow of the department.

QUIBIM’S Chest X-Ray Analysis Tool is already available at QUIBIM Precision® Depending on the needs of the department, this tool is accessible through the cloud with just a few clicks  or  it can be fully integrated in the radiology department’s workflow as a local solution for  seamless interpretation of  chest X-Rays.

boton try quibim