Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learning
Studies have shown that colorectal cancer prognosis can be predicted by deep learning-based analysis of histological tissue sections of the primary tumor. So far, this has been achieved using a binary prediction. Survival curves might contain more detailed information and thus enable a more fine-gra...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
26 September 2023
|
| In: |
npj precision oncology
Year: 2023, Volume: 7, Pages: 1-12 |
| ISSN: | 2397-768X |
| DOI: | 10.1038/s41698-023-00451-3 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1038/s41698-023-00451-3 Verlag, kostenfrei, Volltext: https://www.nature.com/articles/s41698-023-00451-3 
|
| Author Notes: | Julia Höhn, Eva Krieghoff-Henning, Christoph Wies, Lennard Kiehl, Martin J. Hetz, Tabea-Clara Bucher, Jitendra Jonnagaddala, Kurt Zatloukal, Heimo Müller, Markus Plass, Emilian Jungwirth, Timo Gaiser, Matthias Steeg, Tim Holland-Letz, Hermann Brenner, Michael Hoffmeister and Titus J. Brinker |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1871925398 | ||
| 003 | DE-627 | ||
| 005 | 20240808160356.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231205s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1038/s41698-023-00451-3 |2 doi | |
| 035 | |a (DE-627)1871925398 | ||
| 035 | |a (DE-599)KXP1871925398 | ||
| 035 | |a (OCoLC)1425209037 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Höhn, Julia |e VerfasserIn |0 (DE-588)1236930169 |0 (DE-627)1762751291 |4 aut | |
| 245 | 1 | 0 | |a Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learning |c Julia Höhn, Eva Krieghoff-Henning, Christoph Wies, Lennard Kiehl, Martin J. Hetz, Tabea-Clara Bucher, Jitendra Jonnagaddala, Kurt Zatloukal, Heimo Müller, Markus Plass, Emilian Jungwirth, Timo Gaiser, Matthias Steeg, Tim Holland-Letz, Hermann Brenner, Michael Hoffmeister and Titus J. Brinker |
| 264 | 1 | |c 26 September 2023 | |
| 300 | |b Illustrationen | ||
| 300 | |a 12 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Online veröffentlicht: 26. September 2023 | ||
| 500 | |a Gesehen am 05.12.2023 | ||
| 520 | |a Studies have shown that colorectal cancer prognosis can be predicted by deep learning-based analysis of histological tissue sections of the primary tumor. So far, this has been achieved using a binary prediction. Survival curves might contain more detailed information and thus enable a more fine-grained risk prediction. Therefore, we established survival curve-based CRC survival predictors and benchmarked them against standard binary survival predictors, comparing their performance extensively on the clinical high and low risk subsets of one internal and three external cohorts. Survival curve-based risk prediction achieved a very similar risk stratification to binary risk prediction for this task. Exchanging other components of the pipeline, namely input tissue and feature extractor, had largely identical effects on model performance independently of the type of risk prediction. An ensemble of all survival curve-based models exhibited a more robust performance, as did a similar ensemble based on binary risk prediction. Patients could be further stratified within clinical risk groups. However, performance still varied across cohorts, indicating limited generalization of all investigated image analysis pipelines, whereas models using clinical data performed robustly on all cohorts. | ||
| 650 | 4 | |a Colorectal cancer | |
| 650 | 4 | |a Mathematics and computing | |
| 650 | 4 | |a Prognostic markers | |
| 700 | 1 | |a Krieghoff-Henning, Eva |d 1976- |e VerfasserIn |0 (DE-588)132407914 |0 (DE-627)52267786X |0 (DE-576)299126706 |4 aut | |
| 700 | 1 | |a Wies, Christoph |e VerfasserIn |0 (DE-588)1307730442 |0 (DE-627)1868667650 |4 aut | |
| 700 | 1 | |a Kiehl, Lennard |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hetz, Martin J. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Bucher, Tabea-Clara |e VerfasserIn |4 aut | |
| 700 | 1 | |a Jonnagaddala, Jitendra |e VerfasserIn |4 aut | |
| 700 | 1 | |a Zatloukal, Kurt |e VerfasserIn |4 aut | |
| 700 | 1 | |a Müller, Heimo |e VerfasserIn |4 aut | |
| 700 | 1 | |a Plass, Markus |e VerfasserIn |4 aut | |
| 700 | 1 | |a Jungwirth, Emilian |e VerfasserIn |4 aut | |
| 700 | 1 | |a Gaiser, Timo |d 1975- |e VerfasserIn |0 (DE-588)1030402280 |0 (DE-627)735221685 |0 (DE-576)378226533 |4 aut | |
| 700 | 1 | |a Steeg, Matthias |e VerfasserIn |0 (DE-588)1271490005 |0 (DE-627)1820321053 |4 aut | |
| 700 | 1 | |a Holland-Letz, Tim |e VerfasserIn |0 (DE-588)142336491 |0 (DE-627)658880470 |0 (DE-576)343311291 |4 aut | |
| 700 | 1 | |a Brenner, Hermann |e VerfasserIn |0 (DE-588)1020516445 |0 (DE-627)691247005 |0 (DE-576)360642136 |4 aut | |
| 700 | 1 | |a Hoffmeister, Michael |d 1973- |e VerfasserIn |0 (DE-588)134103726 |0 (DE-627)560880820 |0 (DE-576)277089565 |4 aut | |
| 700 | 1 | |a Brinker, Titus Josef |d 1990- |e VerfasserIn |0 (DE-588)1156309395 |0 (DE-627)1018860487 |0 (DE-576)502097434 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t npj precision oncology |d [London] : Springer Nature, 2017 |g 7(2023), Artikel-ID 98, Seite 1-12 |h Online-Ressource |w (DE-627)884384454 |w (DE-600)2891458-2 |w (DE-576)486547728 |x 2397-768X |7 nnas |a Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learning |
| 773 | 1 | 8 | |g volume:7 |g year:2023 |g elocationid:98 |g pages:1-12 |g extent:12 |a Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learning |
| 856 | 4 | 0 | |u https://doi.org/10.1038/s41698-023-00451-3 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://www.nature.com/articles/s41698-023-00451-3 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20231205 | ||
| 993 | |a Article | ||
| 994 | |a 2023 | ||
| 998 | |g 1156309395 |a Brinker, Titus Josef |m 1156309395:Brinker, Titus Josef |d 50000 |e 50000PB1156309395 |k 0/50000/ |p 17 |y j | ||
| 998 | |g 134103726 |a Hoffmeister, Michael |m 134103726:Hoffmeister, Michael |d 50000 |e 50000PH134103726 |k 0/50000/ |p 16 | ||
| 998 | |g 1020516445 |a Brenner, Hermann |m 1020516445:Brenner, Hermann |d 850000 |d 851600 |d 50000 |e 850000PB1020516445 |e 851600PB1020516445 |e 50000PB1020516445 |k 0/850000/ |k 1/850000/851600/ |k 0/50000/ |p 15 | ||
| 998 | |g 142336491 |a Holland-Letz, Tim |m 142336491:Holland-Letz, Tim |d 50000 |e 50000PH142336491 |k 0/50000/ |p 14 | ||
| 998 | |g 1271490005 |a Steeg, Matthias |m 1271490005:Steeg, Matthias |d 60000 |d 63400 |e 60000PS1271490005 |e 63400PS1271490005 |k 0/60000/ |k 1/60000/63400/ |p 13 | ||
| 998 | |g 1030402280 |a Gaiser, Timo |m 1030402280:Gaiser, Timo |d 60000 |e 60000PG1030402280 |k 0/60000/ |p 12 | ||
| 998 | |g 1307730442 |a Wies, Christoph |m 1307730442:Wies, Christoph |d 50000 |e 50000PW1307730442 |k 0/50000/ |p 3 | ||
| 999 | |a KXP-PPN1871925398 |e 4425374436 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"id":{"eki":["1871925398"],"doi":["10.1038/s41698-023-00451-3"]},"recId":"1871925398","type":{"media":"Online-Ressource","bibl":"article-journal"},"name":{"displayForm":["Julia Höhn, Eva Krieghoff-Henning, Christoph Wies, Lennard Kiehl, Martin J. Hetz, Tabea-Clara Bucher, Jitendra Jonnagaddala, Kurt Zatloukal, Heimo Müller, Markus Plass, Emilian Jungwirth, Timo Gaiser, Matthias Steeg, Tim Holland-Letz, Hermann Brenner, Michael Hoffmeister and Titus J. Brinker"]},"language":["eng"],"physDesc":[{"noteIll":"Illustrationen","extent":"12 S."}],"relHost":[{"physDesc":[{"extent":"Online-Ressource"}],"note":["Gesehen am 20. April 2017"],"origin":[{"publisher":"Springer Nature","dateIssuedDisp":"[2017]-","publisherPlace":"[London]"}],"pubHistory":["20 March 2017-"],"id":{"issn":["2397-768X"],"eki":["884384454"],"zdb":["2891458-2"]},"recId":"884384454","name":{"displayForm":["published by Springer Nature in partnership with The Hormel Institute, University of Minnesota"]},"title":[{"title":"npj precision oncology","title_sort":"npj precision oncology","subtitle":"a natureresearch journal"}],"part":{"pages":"1-12","text":"7(2023), Artikel-ID 98, Seite 1-12","volume":"7","year":"2023","extent":"12"},"language":["eng"],"disp":"Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learningnpj precision oncology","type":{"bibl":"periodical","media":"Online-Ressource"},"titleAlt":[{"title":"a nature research journal"},{"title":"Precision oncology"}]}],"person":[{"display":"Höhn, Julia","role":"aut","family":"Höhn","given":"Julia"},{"role":"aut","display":"Krieghoff-Henning, Eva","family":"Krieghoff-Henning","given":"Eva"},{"family":"Wies","given":"Christoph","role":"aut","display":"Wies, Christoph"},{"given":"Lennard","family":"Kiehl","role":"aut","display":"Kiehl, Lennard"},{"given":"Martin J.","family":"Hetz","role":"aut","display":"Hetz, Martin J."},{"given":"Tabea-Clara","family":"Bucher","display":"Bucher, Tabea-Clara","role":"aut"},{"role":"aut","display":"Jonnagaddala, Jitendra","given":"Jitendra","family":"Jonnagaddala"},{"family":"Zatloukal","given":"Kurt","display":"Zatloukal, Kurt","role":"aut"},{"family":"Müller","given":"Heimo","display":"Müller, Heimo","role":"aut"},{"family":"Plass","given":"Markus","display":"Plass, Markus","role":"aut"},{"given":"Emilian","family":"Jungwirth","role":"aut","display":"Jungwirth, Emilian"},{"given":"Timo","family":"Gaiser","display":"Gaiser, Timo","role":"aut"},{"family":"Steeg","given":"Matthias","display":"Steeg, Matthias","role":"aut"},{"family":"Holland-Letz","given":"Tim","role":"aut","display":"Holland-Letz, Tim"},{"role":"aut","display":"Brenner, Hermann","family":"Brenner","given":"Hermann"},{"role":"aut","display":"Hoffmeister, Michael","given":"Michael","family":"Hoffmeister"},{"family":"Brinker","given":"Titus Josef","role":"aut","display":"Brinker, Titus Josef"}],"title":[{"title_sort":"Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learning","title":"Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learning"}],"origin":[{"dateIssuedDisp":"26 September 2023","dateIssuedKey":"2023"}],"note":["Online veröffentlicht: 26. September 2023","Gesehen am 05.12.2023"]} | ||
| SRT | |a HOEHNJULIACOLORECTAL2620 | ||