Posts Tagged :

imaging biomarker

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.

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

025-FEDER2-declaracion14-20

El proyecto QUIBIM recibe el apoyo del FONDO EUROPEO DE DESARROLLO FEDER

QUIBIM es un proyecto empresarial de alto impacto social y sanitario, que extrae información cuantitativa de las imágenes médicas radiológicas, mediante técnicas innovadoras y avanzadas de procesado computacional, con el objetivo de mejorar los procesos de diagnóstico de enfermedades con alta incidencia y evaluar adecuadamente los cambios que producen los tratamientos farmacológicos en el organismo.

Durante 2016 el proyecto de internacionalización QUIBIM ha recibido la ayuda IVACE (ITAPIN IT16 PLANES DE INTERNACIONALIZACIÓN PYME CV 2016) con el apoyo del Fondo Europeo de Desarrollo Regional (FEDER) con el objetivo de presentar nuestros servicios de diagnóstico y análisis avanzado de imagen médica y dar a conocer nuestra plataforma de análisis QUIBIM Precision® para el análisis de Biomarcadores de Imagen.

quibim map

Visit of the group of Dr. Regina Beets-Tan and Dr. Erik Ranschaert to QUIBIM headquarters

The satisfaction of bringing together the best experts in the world at home

Dr. Luis Martí-Bonmatí (QUIBIM co-founder and director of advisory board) and myself had been locally organising the joint congress of the European Society of Oncological Imaging (ESOI) and the European Society of Medical Imaging Informatics (EuSoMII) for approximately 1 year, and the event finally took place past October from 6th to 8th at our home. The Venue was our hospital: La Fe Polytechnics and University Hospital, where we develop our professional activity and where QUIBIM headquarters are placed, since QUIBIM is a spin-off Company of La Fe Health Research Institute, the institutional arm of the hospital to perform research.

The topic of the congress was “Imaging Informatics in Oncology” and it was the result of joining both Societies fields like Oncology and Medical Imaging Informatics from ESOI and EUSOMII, respectively. The congress program combined workshops with plenary sessions. The workshops covered different concrete areas like Response to treatment, Tumor Boards, 3D printing, and Imaging Informatics for clinicians and computer scientists. The complete program can be found here.

I had the opportunity to present on our stepwise development of Imaging Biomarkers process and the associated bottlenecks for validation. Here you can find the slides of the presentation.

Our group had a really active participation, either from the Biomedical Imaging Research Group (GIBI230) from our Hospital and from QUIBIM.

The main scientific presentations were:

  1. ProstateChecker, a tool for the multi-variate analysis of Prostate Cancer from T2, diffusion and perfusion MR sequences, by David García-Juan, post-processing biomedical engineer at QUIBIM
  2. Cloud architecture for Imaging Biomarkers analysis, by Rafael Hernández, CTO at QUIBIM
  3. Spatial registration on PET-CT scans and quantitative structured report for treatment response evaluation on lymphoma patients, by Fabio García-Castro, post-processing biomedical engineer at QUIBIM
  4. Web application for PI-RADS 2.0 Structured Reporting, by Enrique Ruiz-Martínez, CTO at GIBI230 group
  5. Business analytic, metric, key performance indicator. Automating the monitorization of performance indicators in Radiology departments, by Enrique Ruiz-Martinez, CTO at GIBI230 group
  6. Platform for the integration of Imaging Biomarkers in Radiology Departments, by Enrique Ruiz-Martinez, CTO at GIBI230 group
  7. Integration of Redmine as a tool to manage Clinical Trials in Radiology, by Amadeo Ten-Esteve, Clinical Trial Manager at GIBI230 group.
  8. Artificial intelligence techniques applied to medical imaging. Deep learning applied to automated chest X-ray screening, by Belén Fos-Guarinos, internship biomedical engineering student at GIBI230 group.
  9. Automatic vertebrae localization in pathological spine CT using Decision Forests, by Ana Jiménez Pastor, internship telecommunications engineering student at QUIBIM.
  10. Automated segmentation of muscle using Neural Networks, by Sara Rocher, internship biomedical engineering student at GIBI230 group.
  11. Automatic classification of intensity-vs-time curves in breast DCE-MRI by K-means clustering and Dynamic Time Warping curve matching, by Fabio García-Castro, post-processing biomedical engineer at QUIBIM

In the meantime, the QUIBIM stand was boiling! With several experts interested…

QUIBIM CEO, Angel Alberich-Bayarri explaining QUIBIM advantages to interested attendees to EUSOMII - ESOI congress

QUIBIM CEO, Angel Alberich-Bayarri explaining QUIBIM advantages to interested attendees to EUSOMII – ESOI congress

Besides the opportunity to present the work of our group, we had some remarkable visits to our headquarters, like the visit of Dr. Regina Beets-Tan group together with Dr. Erik Ranschaert (see photo).

Visit of the group of Dr. Regina Beets-Tan and Dr. Erik Ranschaert to QUIBIM headquarters

Visit of the group of Dr. Regina Beets-Tan and Dr. Erik Ranschaert to QUIBIM headquarters

Industry also visited us, in this case it was Agfa Healthcare. The Global Senior Solution Manager, Mr. Chris Townend and the National Sales Manager, José Vicente Puig visited our headquarters and attended the demo of our solution.

Visit of José Vicente Puig (National Sales Manager at Agfa Healthcare) and Chris Townend (Global Senior Solution Manager at Agfa Healthcare)

Visit of José Vicente Puig (National Sales Manager at Agfa Healthcare) and Chris Townend (Global Senior Solution Manager at Agfa Healthcare)

 

The last day we were lucky to have Regina Beets-Tan and Sergey Mozorov, new presidents of ESOI and EUSOMII, respectively, at our headquarters.

 

Visit of Sergey Morozov and Regina Beets-Tan. Photo with QUIBIM founders

Visit of Sergey Morozov and Regina Beets-Tan. Photo with QUIBIM founders

 

The experience speaks by itself.