Philips Healthcare France Company newsroom

Hospices Civils de Lyon (HCL)

The radiology team wanted to automate time-consuming image analysis tasks so radiologists could spend less time drawing contours and more time with patients, while also using image classification to narrow CT scan coverage and reduce unnecessary X-ray exposure.

Reducing the margin could reduce the X-ray dose on average by 20 per cent.
The radiology department of Hôpital de la Croix-Rousse has over 100 staff members, diagnosing more than 100,000 annually.
This means we can spend over twice as much time with our patients.
Using AI, we can now quantify the decay of the lung in a matter of seconds. By hand, it takes several hours per patient.

Reported impact

Business outcome

HCL reduced manual contouring and quantification work, enabling radiologists to spend more time with patients; the team also reported lower CT radiation exposure through better scan targeting and faster longitudinal assessment of lung disease.

  • Customer Experience
  • Productivity Improvement
  • Risk Reduction

Solution

Hospices Civils de Lyon (HCL) worked with Philips to embed AI into radiology workflows inside Philips Advanced Visualization Workspace, the post-processing platform used by radiologists. CT studies are brought into the workspace, where co-developed algorithms first classify the relevant anatomy so technicians can limit scans to the needed region, then segment structures and disease burden for follow-up and reporting. The source says applications created through the partnership were productized in Advanced Visualization Workspace, including CT Pulmo Auto Results, CT Scanner Console, and CT Liver Analysis. HCL also used lung segmentation together with a dedicated lung parenchyma analysis module to quantify emphysema and COVID-19 lesions, and used AI to quantify pulmonary fibrosis progression in seconds rather than manual multi-hour review. Results are returned to clinicians inside the Philips software so contours, percentages, and measurements can support diagnosis, reporting, and patient discussions. The source does not name a separate storage tier or third-party integrations.

Data flow

CT images from chest, cardiac, and other radiology exams are processed in Philips Advanced Visualization Workspace. AI models classify the region of interest, segment lungs and aneurysm anatomy, and calculate percentages or other measurements for emphysema, COVID-19 lesions, and pulmonary fibrosis progression. Those outputs are then shown back to radiologists inside the Philips workflow for reporting and patient follow-up.

Solution architecture

4 components · 2 layers
  1. Compute
    • CT Pulmo Auto Results One of the co-developed CT applications productized in Advanced Visualization Workspace to automate pulmonary imaging results workflows.
    • CT Liver Analysis One of the co-developed applications included in Advanced Visualization Workspace for liver image analysis.
  2. Serving
    • Advanced Visualization Workspace Radiologist-facing image post-processing platform where the co-developed AI applications are delivered and their results are reviewed.
    • CT Scanner Console One of the co-developed applications included in Advanced Visualization Workspace for CT workflow support.

Architecture clues

  • Partnership agreement signed in 2016 around stroke, cardiovascular, and AI co-creation research pillars.
  • Some described features are investigational research and may not be commercially available or cleared for clinical use.
  • Two PhD students, two Philips researchers and an innovation account manager worked on-site in Lyon.

Evidence from the source

“HCL and Philips collaborated on the development of several algorithms and applications that are now part of Advanced Visualization Workspace, including CT Pulmo Auto Results, CT Scanner Console, and CT Liver Analysis.”
“Reducing the margin could reduce the X-ray dose on average by 20 per cent.”
“Using AI, we can now quantify the decay of the lung in a matter of seconds. By hand, it takes several hours per patient.”
“We needed to free up time to spend with patients. Every minute of drawing circles on images is a minute that cannot be spent talking to a patient, explaining their medical condition, or answering questions.”
“With AI, those five minutes are reduced to a few seconds. This means we can spend over twice as much time with our patients, discussing the outcome, answering questions, and offering explanations.”
Transparency Evidence & methodology 80/100 reference value · 93% confidence · 2 sources

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value80/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence93%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability23/25
    11 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency10/10
    2 source references document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Philips

    Co-creating AI solutions that free up time to spend with patients - Case study | Philips

    First-party
    https://www.philips.com/a-w/about/news/archive/case-studies/co-creating-ai-solutions-that-free-up-time-to-spend-with-patients.html
    Source type
    Vendor-published customer story
    Published
    Jul 11, 2025
    Supports
    • Customer
    • Region
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Business outcome
    • Metrics
    • Architecture
    • Publication date
  2. Fédération Hospitalière de France

    Hospices Civils de Lyon - HCL

    Healthcare federation
    https://etablissements.fhf.fr/annuaire/structure/structure1851

    The listing describes HCL as 13 public hospitals and a public-service healthcare institution; it reports a community of 24,000 people.

    Source type
    Healthcare institution directory
    Supports
    • Company size

Date evidence

  • Published on source page Jul 11, 2025 · Hospices Civils de Lyon (HCL) · First-party
    Open date source
Not separately sourced Industry. Treat these normalized attributes as lower-confidence until a dedicated source is added.