Razik Yousfi

New York, New York, United States Contact Info
2K followers 500+ connections

Join to view profile

About

Technology & Engineering leader with strong technical background and comprehensive…

Activity

Join now to see all activity

Experience & Education

  • Paige

View Razik’s full experience

See their title, tenure and more.

or

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

Publications

  • Medical Machine Learning with Razik Yousfi and Leo Grady

    Software Engineering Daily

    Medical imaging is used to understand what is going on inside the human body and prescribe treatment. With new image processing and machine learning techniques, the traditional medical imaging techniques such as CT scans can be enriched to get a more sophisticated diagnosis.

    HeartFlow uses data from a standard CT scan to model a human heart and understand blockages of blood flow using simulations of fluid dynamics. In today’s episode, Razik Yousfi and Leo Grady from HeartFlow describe…

    Medical imaging is used to understand what is going on inside the human body and prescribe treatment. With new image processing and machine learning techniques, the traditional medical imaging techniques such as CT scans can be enriched to get a more sophisticated diagnosis.

    HeartFlow uses data from a standard CT scan to model a human heart and understand blockages of blood flow using simulations of fluid dynamics. In today’s episode, Razik Yousfi and Leo Grady from HeartFlow describe the data processing pipeline for the company and what their technology stack looks like.

    Other authors
    See publication

  • New GPU optimizations for Intensity-based Registration

    SPIE

    The task of registering 3D medical images is very computationally expensive. With CPU-based implementations of registration algorithms it is typical to use various approximations, such as subsampling, to maintain reasonable computation times. This may however result in suboptimal alignments. With the constant increase of capabilities and performances of GPUs (Graphics Processing Unit), these highly vectorized processors have become a viable alternative to CPUs for image related computation…

    The task of registering 3D medical images is very computationally expensive. With CPU-based implementations of registration algorithms it is typical to use various approximations, such as subsampling, to maintain reasonable computation times. This may however result in suboptimal alignments. With the constant increase of capabilities and performances of GPUs (Graphics Processing Unit), these highly vectorized processors have become a viable alternative to CPUs for image related computation tasks. This paper describes new strategies to implement on GPU the computation of image similarity metrics for intensity-based registration, using in particular the latest features of NVIDIA's GeForce 8 architecture and the Cg language. Our experimental results show that the computations are many times faster. In this paper, several GPU implementations of two image similarity criteria for both intra-modal and multi-modal registration have been compared. In particular, we propose a new efficient and flexible solution based on the geometry shader.

    Other authors
    See publication

Patents

  • Systems and methods for visualizing elongated structures and detecting branches therein

    Issued US US20150086100

    Computer implemented methods are disclosed for acquiring, using a processor, digital data of a portion of an elongate object, and identifying, using a processor, a centerline connecting a plurality of points within the portion of the elongate object. The methods also may include defining a first half-plane along the centerline, traversing a predetermined angular distance in a clockwise or counter clockwise direction from the first half-plane to a second half-plane to define an angular wedge…

    Computer implemented methods are disclosed for acquiring, using a processor, digital data of a portion of an elongate object, and identifying, using a processor, a centerline connecting a plurality of points within the portion of the elongate object. The methods also may include defining a first half-plane along the centerline, traversing a predetermined angular distance in a clockwise or counter clockwise direction from the first half-plane to a second half-plane to define an angular wedge, and calculating, using a processor, a view of the angular wedge between the first half-plane and the second half-plane and generating an electronic view of the angular wedge.

    Other inventors
    See patent

  • Multilevel thresholding for mutual information based registration and image registration using a GPU

    Issued US US8731334

    An exemplary embodiment of the present invention includes a method of registering images. The method includes: for each image, determining an optimum intensity threshold set from a plurality of intensity threshold sets that maximizes a variance between classes of each set, segmenting each image using the corresponding determined optimum intensity threshold set, generating mutual information from a joint histogram of at least two of the segmented images, and registering the at least two images…

    An exemplary embodiment of the present invention includes a method of registering images. The method includes: for each image, determining an optimum intensity threshold set from a plurality of intensity threshold sets that maximizes a variance between classes of each set, segmenting each image using the corresponding determined optimum intensity threshold set, generating mutual information from a joint histogram of at least two of the segmented images, and registering the at least two images using the mutual information. The joint histogram may be generated using a geometry shader of a graphical processing unit.

    Other inventors
    See patent

Languages

  • French

    -

  • English

    -

Recommendations received

6 people have recommended Razik

Join now to view

More activity by Razik

View Razik’s full profile

  • See who you know in common
  • Get introduced
  • Contact Razik directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Razik Yousfi

1 other named Razik Yousfi is on LinkedIn

See others named Razik Yousfi

Add new skills with these courses

See all courses