Dual Adversarial Deconfounding Autoencoder for joint batch-effects removal from multi-center and multi-scanner radiomics data
Abstract Medical imaging represents the primary tool for investigating and monitoring several diseases, including cancer. The advances in quantitative image analysis have developed towards the extraction of biomarkers able to support clinical decisions. To produce robust results, multi-center studies are often set up. However, the imaging information must be denoised from confounding factors – known as batch-effect – like scanner-specific and center-specific influences. Moreover, in non-solid cancers, like lymphomas, effective biomarkers require an imaging-based representation of the disease that accounts for its multi-site spreading over the patient’s body. In this work, we address the dual-factor deconfusion problem and we propose a deconfusion algorithm to harmonize the imaging information of patients affected by Hodgkin Lymphoma in a multi-center setting. We show that the proposed model successfully denoises data from domain-specific variability while it coherently preserves the spatial relationship between imaging descriptions of peer lesions, which is a strong prognostic biomarker for tumor heterogeneity assessment. This harmonization step allows to significantly improve the performance in prognostic models, enabling building exhaustive patient representations and delivering more accurate analyses. This work lays the groundwork for performing large-scale and reproducible analyses on multi-center data that are urgently needed to convey the translation of imaging-based biomarkers into the clinical practice as effective prognostic tools. The code is available on GitHub at this<jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/LaraCavinato/Dual-ADAE">link</jats:ext-link>.
| Medienart: |
|
|---|
Preprint| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
bioRxiv.org - (2024) vom: 23. Apr. Zur Gesamtaufnahme - year:2024 |
|---|
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Cavinato, Lara [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| doi: |
10.1101/2023.01.16.524181 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
XBI038449471 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | XBI038449471 | ||
| 003 | DE-627 | ||
| 005 | 20240425104738.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230119s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1101/2023.01.16.524181 |2 doi | |
| 035 | |a (DE-627)XBI038449471 | ||
| 035 | |a (biorXiv)10.1101/2023.01.16.524181 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Cavinato, Lara |e verfasserin |0 (orcid)0000-0001-7007-0205 |4 aut | |
| 245 | 1 | 0 | |a Dual Adversarial Deconfounding Autoencoder for joint batch-effects removal from multi-center and multi-scanner radiomics data |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Abstract Medical imaging represents the primary tool for investigating and monitoring several diseases, including cancer. The advances in quantitative image analysis have developed towards the extraction of biomarkers able to support clinical decisions. To produce robust results, multi-center studies are often set up. However, the imaging information must be denoised from confounding factors – known as batch-effect – like scanner-specific and center-specific influences. Moreover, in non-solid cancers, like lymphomas, effective biomarkers require an imaging-based representation of the disease that accounts for its multi-site spreading over the patient’s body. In this work, we address the dual-factor deconfusion problem and we propose a deconfusion algorithm to harmonize the imaging information of patients affected by Hodgkin Lymphoma in a multi-center setting. We show that the proposed model successfully denoises data from domain-specific variability while it coherently preserves the spatial relationship between imaging descriptions of peer lesions, which is a strong prognostic biomarker for tumor heterogeneity assessment. This harmonization step allows to significantly improve the performance in prognostic models, enabling building exhaustive patient representations and delivering more accurate analyses. This work lays the groundwork for performing large-scale and reproducible analyses on multi-center data that are urgently needed to convey the translation of imaging-based biomarkers into the clinical practice as effective prognostic tools. The code is available on GitHub at this<jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/LaraCavinato/Dual-ADAE">link</jats:ext-link> | ||
| 650 | 4 | |a Biology |7 (dpeaa)DE-84 | |
| 650 | 4 | |a 570 |7 (dpeaa)DE-84 | |
| 700 | 1 | |a Massi, Michela Carlotta |e verfasserin |0 (orcid)0000-0001-5393-8180 |4 aut | |
| 700 | 1 | |a Sollini, Martina |e verfasserin |0 (orcid)0000-0003-2214-6492 |4 aut | |
| 700 | 1 | |a Kirienko, Margarita |e verfasserin |0 (orcid)0000-0002-3923-1151 |4 aut | |
| 700 | 1 | |a Ieva, Francesca |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t bioRxiv.org |g (2024) vom: 23. Apr. |
| 773 | 1 | 8 | |g year:2024 |g day:23 |g month:04 |
| 856 | 4 | 0 | |u https://doi.org/10.1038/s41598-023-45983-7 |x 0 |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1101/2023.01.16.524181 |x 0 |z kostenfrei |3 Volltext |
| 912 | |a GBV_XBI | ||
| 951 | |a AR | ||
| 952 | |j 2024 |b 23 |c 04 | ||