A promptable CT foundation model for solid tumor evaluation
Abstract Carcinogenesis is inherently complex, resulting in heterogeneous tumors with variable outcomes and frequent metastatic potential. Conventional longitudinal evaluation methods like RECIST 1.1 remain labor-intensive and prone to measurement errors, while existing AI solutions face critical li...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | npj Precision Oncology |
| Online Access: | https://doi.org/10.1038/s41698-025-00903-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849744520880586752 |
|---|---|
| author | Léo Machado Léo Alberge Hélène Philippe Elodie Ferreres Julien Khlaut Julie Dupuis Korentin Le Floch Denis Habip Gatenyo Pascal Roux Jules Grégory Maxime Ronot Corentin Dancette Tom Boeken Daniel Tordjman Pierre Manceron Paul Hérent |
| author_facet | Léo Machado Léo Alberge Hélène Philippe Elodie Ferreres Julien Khlaut Julie Dupuis Korentin Le Floch Denis Habip Gatenyo Pascal Roux Jules Grégory Maxime Ronot Corentin Dancette Tom Boeken Daniel Tordjman Pierre Manceron Paul Hérent |
| author_sort | Léo Machado |
| collection | DOAJ |
| description | Abstract Carcinogenesis is inherently complex, resulting in heterogeneous tumors with variable outcomes and frequent metastatic potential. Conventional longitudinal evaluation methods like RECIST 1.1 remain labor-intensive and prone to measurement errors, while existing AI solutions face critical limitations due to tumor heterogeneity, insufficient annotations, and lack of user interaction. We developed ONCOPILOT, an interactive CT-based foundation model dedicated to 3D tumor segmentation, significantly refining RECIST 1.1 evaluations with active radiologist engagement. Trained on more than 8000 CT scans, ONCOPILOT employs intuitive visual prompts, including point-click, bounding boxes, and edit-points. It attains segmentation accuracy that matches or exceeds state-of-the-art methods, provides radiologist-level precision for RECIST 1.1 measurements, reduces inter-observer variability, and enhances workflow efficiency. Integrating clinical expertise with interactive AI capabilities, ONCOPILOT facilitates widespread access to advanced biomarkers, notably volumetric tumor analyses, thereby supporting improved clinical decision-making, patient stratification, and accelerating advancements in oncology research. |
| format | Article |
| id | doaj-art-5cddc59c3cbb467dbdb3527496999548 |
| institution | DOAJ |
| issn | 2397-768X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Precision Oncology |
| spelling | doaj-art-5cddc59c3cbb467dbdb35274969995482025-08-20T03:14:07ZengNature Portfolionpj Precision Oncology2397-768X2025-04-01911810.1038/s41698-025-00903-yA promptable CT foundation model for solid tumor evaluationLéo Machado0Léo Alberge1Hélène Philippe2Elodie Ferreres3Julien Khlaut4Julie Dupuis5Korentin Le Floch6Denis Habip Gatenyo7Pascal Roux8Jules Grégory9Maxime Ronot10Corentin Dancette11Tom Boeken12Daniel Tordjman13Pierre Manceron14Paul Hérent15Raidium, Paris Biotech SantéRaidium, Paris Biotech SantéRaidium, Paris Biotech SantéRaidium, Paris Biotech SantéRaidium, Paris Biotech SantéRaidium, Paris Biotech SantéRaidium, Paris Biotech SantéDepartment of Radiology, Hôpital Cochin, AP-HPCentre d’Imagerie du NordAP-HP. Nord, Department of Radiology, FHU MOSAIC, Beaujon HospitalAP-HP. Nord, Department of Radiology, FHU MOSAIC, Beaujon HospitalRaidium, Paris Biotech SantéDepartment of Vascular and Oncological Interventional Radiology, Université Paris Cité, AP-HP, Hôpital Européen Georges Pompidou, HEKA INRIARaidium, Paris Biotech SantéRaidium, Paris Biotech SantéRaidium, Paris Biotech SantéAbstract Carcinogenesis is inherently complex, resulting in heterogeneous tumors with variable outcomes and frequent metastatic potential. Conventional longitudinal evaluation methods like RECIST 1.1 remain labor-intensive and prone to measurement errors, while existing AI solutions face critical limitations due to tumor heterogeneity, insufficient annotations, and lack of user interaction. We developed ONCOPILOT, an interactive CT-based foundation model dedicated to 3D tumor segmentation, significantly refining RECIST 1.1 evaluations with active radiologist engagement. Trained on more than 8000 CT scans, ONCOPILOT employs intuitive visual prompts, including point-click, bounding boxes, and edit-points. It attains segmentation accuracy that matches or exceeds state-of-the-art methods, provides radiologist-level precision for RECIST 1.1 measurements, reduces inter-observer variability, and enhances workflow efficiency. Integrating clinical expertise with interactive AI capabilities, ONCOPILOT facilitates widespread access to advanced biomarkers, notably volumetric tumor analyses, thereby supporting improved clinical decision-making, patient stratification, and accelerating advancements in oncology research.https://doi.org/10.1038/s41698-025-00903-y |
| spellingShingle | Léo Machado Léo Alberge Hélène Philippe Elodie Ferreres Julien Khlaut Julie Dupuis Korentin Le Floch Denis Habip Gatenyo Pascal Roux Jules Grégory Maxime Ronot Corentin Dancette Tom Boeken Daniel Tordjman Pierre Manceron Paul Hérent A promptable CT foundation model for solid tumor evaluation npj Precision Oncology |
| title | A promptable CT foundation model for solid tumor evaluation |
| title_full | A promptable CT foundation model for solid tumor evaluation |
| title_fullStr | A promptable CT foundation model for solid tumor evaluation |
| title_full_unstemmed | A promptable CT foundation model for solid tumor evaluation |
| title_short | A promptable CT foundation model for solid tumor evaluation |
| title_sort | promptable ct foundation model for solid tumor evaluation |
| url | https://doi.org/10.1038/s41698-025-00903-y |
| work_keys_str_mv | AT leomachado apromptablectfoundationmodelforsolidtumorevaluation AT leoalberge apromptablectfoundationmodelforsolidtumorevaluation AT helenephilippe apromptablectfoundationmodelforsolidtumorevaluation AT elodieferreres apromptablectfoundationmodelforsolidtumorevaluation AT julienkhlaut apromptablectfoundationmodelforsolidtumorevaluation AT juliedupuis apromptablectfoundationmodelforsolidtumorevaluation AT korentinlefloch apromptablectfoundationmodelforsolidtumorevaluation AT denishabipgatenyo apromptablectfoundationmodelforsolidtumorevaluation AT pascalroux apromptablectfoundationmodelforsolidtumorevaluation AT julesgregory apromptablectfoundationmodelforsolidtumorevaluation AT maximeronot apromptablectfoundationmodelforsolidtumorevaluation AT corentindancette apromptablectfoundationmodelforsolidtumorevaluation AT tomboeken apromptablectfoundationmodelforsolidtumorevaluation AT danieltordjman apromptablectfoundationmodelforsolidtumorevaluation AT pierremanceron apromptablectfoundationmodelforsolidtumorevaluation AT paulherent apromptablectfoundationmodelforsolidtumorevaluation AT leomachado promptablectfoundationmodelforsolidtumorevaluation AT leoalberge promptablectfoundationmodelforsolidtumorevaluation AT helenephilippe promptablectfoundationmodelforsolidtumorevaluation AT elodieferreres promptablectfoundationmodelforsolidtumorevaluation AT julienkhlaut promptablectfoundationmodelforsolidtumorevaluation AT juliedupuis promptablectfoundationmodelforsolidtumorevaluation AT korentinlefloch promptablectfoundationmodelforsolidtumorevaluation AT denishabipgatenyo promptablectfoundationmodelforsolidtumorevaluation AT pascalroux promptablectfoundationmodelforsolidtumorevaluation AT julesgregory promptablectfoundationmodelforsolidtumorevaluation AT maximeronot promptablectfoundationmodelforsolidtumorevaluation AT corentindancette promptablectfoundationmodelforsolidtumorevaluation AT tomboeken promptablectfoundationmodelforsolidtumorevaluation AT danieltordjman promptablectfoundationmodelforsolidtumorevaluation AT pierremanceron promptablectfoundationmodelforsolidtumorevaluation AT paulherent promptablectfoundationmodelforsolidtumorevaluation |