Phenotyping Liver Cancer Registry

NCT ID: NCT04681274

Last Updated: 2023-05-16

Basic Information

• Recruitment Status: COMPLETED
• Total Enrollment: 2429 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2020-08-31
• Study Completion Date: 2022-12-31

Brief Summary

The purpose of this study is the development of a content-based image retrieval (CBIR) platform, where validation studies will be conducted for liver disease subtyping and hepatocellular carcinoma (HCC) phenotyping on images for use as diagnostic and prognostic markers of outcome in conjunction with large scale data registries and advanced predictive machine learning methodologies. The proposed objectives will deliver one or more fit-for-purpose non-invasive imaging-based methodologies to evaluate the presence, activity and type of HCC in clinical practice.

Detailed Description

The study will advance through two distinct phases.

• Phase 1 has two main stages: The first stage will identify unique tumor phenotypes based on the iBiopsy phenotyping platform which extracts image-based signatures corresponding to each individual phenotype and will assess the analytic/technical performance of the iBiopsy platform. Gaps in characterization of the analytic readout under varying conditions of image acquisition and the repeat variability under identical analytic conditions will be filled by the proposed design. Once a set of suitable tumor phenotypes have been identified they will advance to the characterization phase. This will be done by the evaluation of an initial representative specific dataset (e.g. hundreds of patients) for training (to discover) and validation (to test robustness). The second stage will complete a preliminary biological/clinical validation of the above phenotypes for diagnosis and disease subtyping. This includes the investigation of a large dataset (e.g. thousands of patients) CDR for training and validation, using histopathology data as the reference standard and the optimization of the imaging signatures using AI based learning methodologies.
• Phase 2 also has two stages. The first stage of Phase 2 is to rigorously validate the candidate phenotypes emerging from Phase 1 for the diagnosis of subjects with HCC. The second stage of Phase 2 is to validate these select candidate phenotypes for prediction of outcome. These rigorous validations include using large CDR of patients with HCC (late stage biological/clinical validation).

Traditional medical image retrieval systems such as Picture Archival Systems (PACS) use structured data (metadata) or unstructured text annotations (physician reports) to retrieve the images. However, the content of the images cannot be completely described by words, and the understanding of images is different from person to person, therefore text-based image retrieval system cannot meet the requirements for massive images retrieval. In response to these limitations, CBIR systems using visual features extracted from the images in lieu of keywords have been developed. An important and useful outcome of these CBIR is the possibility to bridge the semantic gap, allowing users to search an image repository for high-level image features allowing the matching of image-based phenotype signatures extracted directly from the query medical image with phenotype signatures indexed in a registry.

The Median Technologies CBIR system uses patented algorithms and processes to decode the images by automatically extracting hundreds of imaging features as well as highly compact signatures from tens of thousands of 3D image patches computed across the entire image without the need for any prior segmentation. In addition to detailed phenotypic profiles which can be correlated with histopathology and genomic and plasmatic profiles, the system generates a unique signature for each tile providing a fingerprint of the "image-based phenotype" of the corresponding tissue. Using massively parallel computing methods, imaging biomarkers and phenotype signatures are extracted from a target image are then organized into clusters of similar signatures and indexed for real-time search and retrieval into schema-less (NoSQL) databases.

Conditions

Hepatocellular Carcinoma

Study Design

• Observational Model Type: OTHER
• Study Time Perspective: RETROSPECTIVE

Study Groups

patient with hepatocellular carcinoma

Phenotype signature database building Image features extraction and clustering

Image features extraction and clustering

Intervention Type: DEVICE

The image processing operations required for local content-based image feature extraction consist of two main tasks: 1) tiling the images in smaller VOIs, typically a small cube, whose size depends on the modality, on the image resolution and on the purpose of the content-based query, and 2) performing feature extraction operations on the VOIs.

The Feature Extraction Engine performs totally unsupervised, automatic and asynchronous extractions of features from the images, organizes and indexes them in a no-SQL database based on unique similarity metric. The results of this phase are a series of clusters of phenotype signatures.

Phenotype signature database building

Intervention Type: DEVICE

Since the clusters are self-organizing their pathophysiological meaning is not readily apparent and requires further analysis. The characterization of each cluster is performed by analyzing representative samples and their respective correlation with histopathology results. After a series of iterations, the clusters are organized to correlate with distinct tissue subtypes identified by their signature similarity. The final number of clusters is not known a priori and depends on the heterogeneity of the underlying imaging phenotypes.

Interventions

Image features extraction and clustering

The image processing operations required for local content-based image feature extraction consist of two main tasks: 1) tiling the images in smaller VOIs, typically a small cube, whose size depends on the modality, on the image resolution and on the purpose of the content-based query, and 2) performing feature extraction operations on the VOIs.

The Feature Extraction Engine performs totally unsupervised, automatic and asynchronous extractions of features from the images, organizes and indexes them in a no-SQL database based on unique similarity metric. The results of this phase are a series of clusters of phenotype signatures.

Intervention Type: DEVICE

Phenotype signature database building

Since the clusters are self-organizing their pathophysiological meaning is not readily apparent and requires further analysis. The characterization of each cluster is performed by analyzing representative samples and their respective correlation with histopathology results. After a series of iterations, the clusters are organized to correlate with distinct tissue subtypes identified by their signature similarity. The final number of clusters is not known a priori and depends on the heterogeneity of the underlying imaging phenotypes.

Intervention Type: DEVICE

Eligibility Criteria

Inclusion Criteria

Patients with visual liver disease who:

• Have a lesion visualized on CT scans / MRI with histological confirmation (surgical resection, biopsy, transplant).
• With a CT scan / MRI performed within 6 months prior to biopsy, surgical or transplant intervention.

Exclusion Criteria

• Patients that had CT scans / MRI taken more than 6 months prior to surgical intervention

• Minimum Eligible Age: 18 Years
• Maximum Eligible Age: 100 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Assistance Publique - Hôpitaux de Paris

OTHER

Sponsor Role: lead

Responsible Party

Responsibility Role: SPONSOR

Principal Investigators

Olivier Lucidarme, MD

Role: PRINCIPAL_INVESTIGATOR

Assitance Publique - Hôpitaux de Paris

Locations

Assistance Publique - Hôpitaux de Paris (AP-HP) Groupe Hospitalier La Pitié-Salpêtrière

Paris, Île-de-France Region, France

Countries

France

Other Identifiers

APHP191046

Identifier Type: -

Identifier Source: org_study_id