Conversion of Ultrasound Images to CT Format Imaging Using Artificial Intelligence-based Learning

NCT04654546 | Unknown

• 1 other identifier: 0177-20-EMC
• Study Type: interventional
• Target: 50
• Locations: 1 country
• Sites: 1

Brief Summary

Background: Ultrasound imaging is an imaging method that uses sound waves to characterize the structure and function of various organs in health and disease conditions. This technique is widely used in clinical day-to-day life and has many advantages, such as real-time imaging, availability for imaging at the patient's bedside, and lack of ionizing radiation. Aside from the mentioned advantages, the ultrasound test also has notable drawbacks. These include the absence of sound wave penetration through a medium containing air such as intestinal loops, dependence on operator skill, and the need for the subject's cooperation during the test. Compared to the ultrasound examination, the CT scan allows for a broader anatomical view and is not limited by physiological factors such as bones and air. on the other hand, the test requires ionizing radiation that inevitably carries a direct and indirect danger to the patient's health, and requires more financial resources. Objectives of the study: Using artificial intelligence to bridge the gap between ultrasound and CT scans, and to create a uniform system that takes advantage of them. This is to allow for better spatial orientation as well as a better characterization of the anatomical structures being scanned. Participants: Women and/or men over the age of 18, who performed an abdominal CT scan during the previous month for the ultrasound examination in the experiment. Methods: The study is a prospective open-label research, in which both the physician and the patient are aware of the manner and purposes of the scan. Participants who meet the threshold conditions will be summoned for examination in the rooms of the Imaging Institute at Haemek medical center, during which the participants will undergo a complete ultrasound scan of the abdominal organs using a clinical ultrasound device. The ultrasound images will be visually coupled to previous CT images of the same patient at the time of the examination, using a Fusion system located in the ultrasound device mentioned above. The conjugated CT and ultrasound images will be encoded and will be sent without identifying details to the SAMPL laboratory, to be used as a learning platform for the artificial intelligence system. The images will be transferred after the subject's personal details have been encoded in an EXCEL file and saved by the principal investigator.

Conditions

Anatomy

Outcome Measures

Primary Outcomes (2)

• Normalized cross-correlation between input CT images and the ultrasound-based algorithm-generated CT images

  The cross-correlation between the input CT images, serving as Ground Truth, and the algorithm-generated CT images will serve as a measure of similarity (Similarity score), normalized to a range \[-1,1\].

  2 year

• Accuracy rate

  System accuracy rate will be evaluated by comparing the aforementioned similarity score to a success rate threshold (T).

  2 year

Study Arms (1)

Abdominal scans

EXPERIMENTAL

Participants who performed an abdominal CT exam up to one month prior to the experimental ultrasound exam.

Other: Ultrasound abdominal scan

Interventions

Ultrasound abdominal scan OTHER

A complete ultrasound scan of the abdominal organs using a clinical ultrasound device in the Imaging Institute at Haemek medical center. The ultrasound images will be visually coupled to previous CT images of the same patient at the time of the examination, using a Fusion system located in the ultrasound device mentioned above. The coupled CT and ultrasound images will be encoded and be sent to the SAMPL laboratory in Weizmann institute, there it will serve as a learning platform for the artificial intelligence system.

Abdominal scans

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Participants who performed an abdominal CT exam up to one month prior to the experimental ultrasound exam.

You may not qualify if:

• Participants who had a change in their medical condition that may have substantial effects on the imaging features of the abdominal organs.
• Pregnant women

Sponsors & Collaborators

• HaEmek Medical Center, Israel: lead
• Weizmann Institute of Science: collaborator

Study Sites (1)

Emek medical center

Afula, 1834111, Israel

RECRUITING

Study Officials

• Israel Aharony, M.D. Ph.D

  Imaging institute, Haemek Medical Center, Afula, Israel.

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Israel Aharony‬, M.D. Ph.D

CONTACT

97246495635; elik.aharony@gmail.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: DIAGNOSTIC
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Radiology resident, Haemek medical center Radiology institute, Principal investigator.

Model Details: Scan of abdominal organs of participants as detailed in the study protocol

Study Record Dates

• First Submitted: November 4, 2020
• First Posted: December 4, 2020
• Study Start: August 24, 2021
• Primary Completion: January 1, 2025
• Study Completion: June 1, 2025
• Last Updated: September 28, 2023

Record last verified: 2023-09

Data Sharing

• IPD Sharing: Will not share

Locations

IL (1)