Deep learning image analysis quantifies tumor heterogeneity and identifies microsatellite instability in colon cancer
© 2022 Wiley Periodicals LLC..
BACKGROUND AND OBJECTIVES: Deep learning utilizing convolutional neural networks (CNNs) applied to hematoxylin & eosin (H&E)-stained slides numerically encodes histomorphological tumor features. Tumor heterogeneity is an emerging biomarker in colon cancer that is, captured by these features, whereas microsatellite instability (MSI) is an established biomarker traditionally assessed by immunohistochemistry or polymerase chain reaction.
METHODS: H&E-stained slides from The Cancer Genome Atlas (TCGA) colon cohort are passed through the CNN. Resulting imaging features are used to cluster morphologically similar slide regions. Tile-level pairwise similarities are calculated and used to generate a tumor heterogeneity score (THS). Patient-level THS is then correlated with TCGA-reported biomarkers, including MSI-status.
RESULTS: H&E-stained images from 313 patients generated 534 771 tiles. Deep learning automatically identified and annotated cells by type and clustered morphologically similar slide regions. MSI-high tumors demonstrated significantly higher THS than MSS/MSI-low (p < 0.001). THS was higher in MLH1-silent versus non-silent tumors (p < 0.001). The sequencing derived MSIsensor score also correlated with THS (r = 0.51, p < 0.0001).
CONCLUSIONS: Deep learning provides spatially resolved visualization of imaging-derived biomarkers and automated quantification of tumor heterogeneity. Our novel THS correlates with MSI-status, indicating that with expanded training sets, translational tools could be developed that predict MSI-status using H&E-stained images alone.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:127 |
|---|---|
| Enthalten in: |
Journal of surgical oncology - 127(2023), 3 vom: 17. März, Seite 426-433 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Rubinstein, Jill C [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Colon cancer |
|---|
| Anmerkungen: |
Date Completed 31.01.2023 Date Revised 02.02.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1002/jso.27118 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM347663044 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM347663044 | ||
| 003 | DE-627 | ||
| 005 | 20231226034352.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1002/jso.27118 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1158.xml |
| 035 | |a (DE-627)NLM347663044 | ||
| 035 | |a (NLM)36251352 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Rubinstein, Jill C |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Deep learning image analysis quantifies tumor heterogeneity and identifies microsatellite instability in colon cancer |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 31.01.2023 | ||
| 500 | |a Date Revised 02.02.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2022 Wiley Periodicals LLC. | ||
| 520 | |a BACKGROUND AND OBJECTIVES: Deep learning utilizing convolutional neural networks (CNNs) applied to hematoxylin & eosin (H&E)-stained slides numerically encodes histomorphological tumor features. Tumor heterogeneity is an emerging biomarker in colon cancer that is, captured by these features, whereas microsatellite instability (MSI) is an established biomarker traditionally assessed by immunohistochemistry or polymerase chain reaction | ||
| 520 | |a METHODS: H&E-stained slides from The Cancer Genome Atlas (TCGA) colon cohort are passed through the CNN. Resulting imaging features are used to cluster morphologically similar slide regions. Tile-level pairwise similarities are calculated and used to generate a tumor heterogeneity score (THS). Patient-level THS is then correlated with TCGA-reported biomarkers, including MSI-status | ||
| 520 | |a RESULTS: H&E-stained images from 313 patients generated 534 771 tiles. Deep learning automatically identified and annotated cells by type and clustered morphologically similar slide regions. MSI-high tumors demonstrated significantly higher THS than MSS/MSI-low (p < 0.001). THS was higher in MLH1-silent versus non-silent tumors (p < 0.001). The sequencing derived MSIsensor score also correlated with THS (r = 0.51, p < 0.0001) | ||
| 520 | |a CONCLUSIONS: Deep learning provides spatially resolved visualization of imaging-derived biomarkers and automated quantification of tumor heterogeneity. Our novel THS correlates with MSI-status, indicating that with expanded training sets, translational tools could be developed that predict MSI-status using H&E-stained images alone | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a colon cancer | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a microsatellite instability | |
| 650 | 4 | |a tumor heterogeneity | |
| 700 | 1 | |a Foroughi Pour, Ali |e verfasserin |4 aut | |
| 700 | 1 | |a Zhou, Jie |e verfasserin |4 aut | |
| 700 | 1 | |a Sheridan, Todd B |e verfasserin |4 aut | |
| 700 | 1 | |a White, Brian S |e verfasserin |4 aut | |
| 700 | 1 | |a Chuang, Jeffrey H |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of surgical oncology |d 1969 |g 127(2023), 3 vom: 17. März, Seite 426-433 |w (DE-627)NLM000052930 |x 1096-9098 |7 nnns |
| 773 | 1 | 8 | |g volume:127 |g year:2023 |g number:3 |g day:17 |g month:03 |g pages:426-433 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1002/jso.27118 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 127 |j 2023 |e 3 |b 17 |c 03 |h 426-433 | ||