Transfer Learning for Mortality Prediction in Non-Small Cell Lung Cancer with Low-Resolution Histopathology Slide Snapshots
High-resolution whole slide image scans of histopathology slides have been widely used in recent years for prediction in cancer. However, in some cases, clinical informatics practitioners may only have access to low-resolution snapshots of histopathology slides, not high-resolution scans. We evaluated strategies for training neural network prognostic models in non-small cell lung cancer (NSCLC) based on low-resolution snapshots, using data from the Veterans Affairs Precision Oncology Data Repository. We compared strategies without transfer learning, with transfer learning from general domain images, and with transfer learning from publicly available high-resolution histopathology scans. We found transfer learning from high-resolution scans achieved significantly better performance than other strategies. Our contribution provides a foundation for future development of prognostic models in NSCLC that incorporate data from low-resolution pathology slide snapshots alongside known clinical predictors.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:310 |
---|---|
Enthalten in: |
Studies in health technology and informatics - 310(2024) vom: 25. Jan., Seite 735-739 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Clark, Matthew [VerfasserIn] |
---|
Links: |
---|
Themen: |
Deep learning |
---|
Anmerkungen: |
Date Completed 26.01.2024 Date Revised 26.01.2024 published: Print Citation Status MEDLINE |
---|
doi: |
10.3233/SHTI231062 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM367603306 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM367603306 | ||
003 | DE-627 | ||
005 | 20240126232231.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240125s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3233/SHTI231062 |2 doi | |
028 | 5 | 2 | |a pubmed24n1271.xml |
035 | |a (DE-627)NLM367603306 | ||
035 | |a (NLM)38269906 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Clark, Matthew |e verfasserin |4 aut | |
245 | 1 | 0 | |a Transfer Learning for Mortality Prediction in Non-Small Cell Lung Cancer with Low-Resolution Histopathology Slide Snapshots |
264 | 1 | |c 2024 | |
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 26.01.2024 | ||
500 | |a Date Revised 26.01.2024 | ||
500 | |a published: Print | ||
500 | |a Citation Status MEDLINE | ||
520 | |a High-resolution whole slide image scans of histopathology slides have been widely used in recent years for prediction in cancer. However, in some cases, clinical informatics practitioners may only have access to low-resolution snapshots of histopathology slides, not high-resolution scans. We evaluated strategies for training neural network prognostic models in non-small cell lung cancer (NSCLC) based on low-resolution snapshots, using data from the Veterans Affairs Precision Oncology Data Repository. We compared strategies without transfer learning, with transfer learning from general domain images, and with transfer learning from publicly available high-resolution histopathology scans. We found transfer learning from high-resolution scans achieved significantly better performance than other strategies. Our contribution provides a foundation for future development of prognostic models in NSCLC that incorporate data from low-resolution pathology slide snapshots alongside known clinical predictors | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a deep learning | |
650 | 4 | |a medical images | |
650 | 4 | |a pathology | |
650 | 4 | |a prognosis | |
650 | 4 | |a transfer learning | |
700 | 1 | |a Meyer, Christopher |e verfasserin |4 aut | |
700 | 1 | |a Ramos-Cejudo, Jaime |e verfasserin |4 aut | |
700 | 1 | |a Elbers, Danne C |e verfasserin |4 aut | |
700 | 1 | |a Pierce-Murray, Karen |e verfasserin |4 aut | |
700 | 1 | |a Fricks, Rafael |e verfasserin |4 aut | |
700 | 1 | |a Alterovitz, Gil |e verfasserin |4 aut | |
700 | 1 | |a Rao, Luigi |e verfasserin |4 aut | |
700 | 1 | |a Brophy, Mary T |e verfasserin |4 aut | |
700 | 1 | |a Do, Nhan V |e verfasserin |4 aut | |
700 | 1 | |a Grossman, Robert L |e verfasserin |4 aut | |
700 | 1 | |a Fillmore, Nathanael R |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Studies in health technology and informatics |d 1991 |g 310(2024) vom: 25. Jan., Seite 735-739 |w (DE-627)NLM091691567 |x 1879-8365 |7 nnns |
773 | 1 | 8 | |g volume:310 |g year:2024 |g day:25 |g month:01 |g pages:735-739 |
856 | 4 | 0 | |u http://dx.doi.org/10.3233/SHTI231062 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 310 |j 2024 |b 25 |c 01 |h 735-739 |