Welcome | Publications | Research | Industry | Teaching | Biography
UofT Logo (Small)
Mahdi Marsousi
Academic Affiliation:
Multimedia Processing Lab, 
Electrical and Computer Eng. Dept., 
University of Toronto,
Toronto, ON, Canada
Industrial Affiliation:
Research Engineer,
Research and Development Department,
Magna Electronics Inc.,
1 Kenview Blvd, Suite 200,
Brampton, ON, L6T 5E6, Canada
Contact Information:
Academic email:
Work email: 
Email: marsousi@gmail.com
Cell-phone: (647) 967-1585

Computer-assisted medical diagnosis for trauma patients:

Due to the limitations of healthcare services in emergency situations, blunt abdominal bleeding causes a large number of preventable deaths each year around the world. Saving a trauma patient's life requires rapid diagnosis, which is not always available in emergency situations. This is the thesis of this line of research that a computer-assisted algorithm based on 3D ultrasound imagery can provide a systematic solution to facilitate rapid diagnosis of trauma patients in emergency situations by first responders (ie. paramedics).

Right picture shows an anatomical illustration of a typical internal blood between liver and right kidney [Ref], and left picture shows a trauma patient in a battle field [Ref].

The use of ultrasound imagery is the key to success in designing the computer-assisted trauma diagnostic tool, because ultrasound imagery is a portable imaging system which can be carried to the emergency location, and eliminates the need to move an unstable patient to an imaging room. Despite two-dimensional (2D) ultrasound imagery is the popular tool for trauma diagnosis by experts, designing a computer-assisted trauma diagnostic system is only possible using 3D ultrasound imagery, becuase:

  1. automated detection and localization of internal organs and strcurures, which is essential for computer-assisted probe placement for trauma diagnosis, are only possible using 3D ultrasound imagery. This is essential, because ultrasonographers are not always present at emergency situations, and a computer-assisted solution is needed to guide paramedics to conduct ultrasound scan needed for trauma diagnosis.

  2. 3D ultrasound imagery provides more detectability of abdominal bleeding than 2D ultrasound imagery, becaus it visualizes internal views that cannot be viewed by 2D ultrasound imagery.

  3. 3D ultrasound imagery facilitates measuring the volume of internal bleeding, which is not doable by 2D ultrasound imagery.

Comparing utility of imaging systems for computer-assisted trauma diagnosis.

An abdominal bleeding has a high tendency to align around the right kidney. The right-upperquadrant view of sonography shows the entire kidney shape, and therefore, it is considered as the most relevant internal view to trauma diagnosis. Paramedics usually lack proper knowledge to find the right-upper-quadrant view, to detect the kidney shape, and to detect an internal bleeding using an ultrasound imaging device. Hence, computer-assisted algorithms are required to perform these tasks. On major focus of this research is on developing automated methods to detect and segment the kidney shape in three dimensional ultrasound imagery. The detected kidney shape will be used for two purposes: (a) it is used to calculate the ultrasound probe's misalignment with respect to the right-upper-quadrant view, which is used to guide the operator to move the probe toward the correct alignment on the patient's body; (b) the detected kidney shape is used to initialize the kidney segmentation process, and thereby, an automated kidney segmentation approach is achieved. The kidney segmentation output can be used to automatically detect an internal bleeding. The processing pipeline of the computer-assisted trauma dianostic system is shown in the figure below.

Processing pipeline of computer-assisted diagnostic system for trauma patients.

Additional resources:

Download my PhD defence slides here.

2016 (c) Copy-right preserved, Welcome | Publications | Research | Industry | Biography