Automatic Segmentation of Polycystic Liver

Liver Injury Clinical Trial

— ASEPOL  

Official title:

Automatic Segmentation by a Convolutional Neural Network (Artificial Intelligence - Deep Learning) of Polycystic Livers, as a Model of Multi-lesional Dysmorphic Livers

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT03960710
• Other study ID #: ASEPOL
• Status: Recruiting
• Start date: April 1, 2019
• Est. completion date: September 2019

Study information

• Verified date: May 2019
• Source: Hospices Civils de Lyon
• Contact: Bénédicte CAYOT
• Phone: 472110400
• Email: benedicte.cayot[@]chu-lyon.fr
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Assessing the volume of the liver before surgery, predicting the volume of liver remaining after surgery, detecting primary or secondary lesions in the liver parenchyma are common applications that require optimal detection of liver contours, and therefore liver segmentation.

Several manual and laborious, semi-automatic and even automatic techniques exist.

However, severe pathology deforming the contours of the liver (multi-metastatic livers...), the hepatic environment of similar density to the liver or lesions, the CT examination technique are all variables that make it difficult to detect the contours. Current techniques, even automatic ones, are limited in this type of case (not rare) and most often require readjustments that make automatisation lose its value.

All these criteria of segmentation difficulties are gathered in the livers of hepatorenal polycystosis, which therefore constitute an adapted study model for the development of an automatic segmentation tool.

To obtain an automatic segmentation of any lesional liver, by exceeding the criteria of difficulty considered, investigators have developed a convolutional neural network (artificial intelligence - deep learning) useful for clinical practice.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 120
• Est. completion date: September 2019
• Est. primary completion date: July 2019
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

• Patients = 18 years old

• Patients with hepato-renal polycystosis, with or without surgery

• Patients with at least one abdominal-pelvic CT scan without injection or with injection between January 1, 2016 and August 2018

• Patients with good quality and available images

Exclusion Criteria:

• Patients with no CT scan images available

• Patients with bad quality of CT scan images

Related Conditions & MeSH terms

• Cysts
• Liver Diseases
• Liver Injury
• Polycystic Hepatorenal Disease
• Polycystic Liver Disease

Intervention

Other:
• Anonymized CT examinations
The anonymized CT examinations will be reviewed in Lyon, in the imaging department of Edouard Herriot Hospital, by an expert radiologist and an intern from the Lyon hospitals.
• Training (1)
An initial training phase of the artificial intelligence network will be carried out : - Segmentation of the livers of a first part of the CT examination, by an intern of the Lyon hospitals
• Training (2)
An initial training phase of the artificial intelligence network will be carried out : - Use of computer data to drive the artificial intelligence network.
• Validation (1)
A validation phase of the artificial intelligence tool will be carried out with segmentation of the livers of the second part of the CT examinations : - Carried out by an intern at the Lyon hospitals
• Validation (2)
A validation phase of the artificial intelligence tool will be carried out with segmentation of the livers of the second part of the CT examinations : - Carried out by the neural network

Locations

Country	Name	City	State
France	Service de radiologie - Pavillon B - Cellule Recherche imagerie, Hôpital Edouard Herriot (HCL)	Lyon

Sponsors (1)

Lead Sponsor	Collaborator
Hospices Civils de Lyon

Country where clinical trial is conducted

France, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Test of automatic segmentation by the convolutional neural network on these group and collection of data set	Development of an automatic segmentation tool for highly dysmorphic polycystic livers as a prerequisite for segmentation of any type of multi-lesional livers that are difficult to segment, in order to facilitate lesion detection and volume measurement in clinical practice.; Randomisation of the patient into two data groups, one for training the other for Validating the convolutional neural network (artificial intelligence); Manual segmentation of polycystic livers of the 1st training group and deep learning of convolutional neural network; Manual segmentation of polycystic livers of 2nd validation group; Test of automatic segmentation by the convolutional neural network on these group and collection of data set	At 4 months after randomization