Deep Morphology Learning Enhances Ex Vivo Drug Profiling-Based Precision Medicine ...
Drug testing in patient biopsy-derived cells can identify potent treatments for patients suffering from relapsed or refractory hematologic cancers. Here we investigate the use of weakly supervised deep learning on cell morphologies (DML) to comple-ment diagnostic marker-based identifi cation of mali...
Main Authors: | , , , , , , , , , , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
ETH Zurich
2022
|
Subjects: | |
Online Access: | https://dx.doi.org/10.3929/ethz-b-000584166 http://hdl.handle.net/20.500.11850/584166 |
id |
ftdatacite:10.3929/ethz-b-000584166 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.3929/ethz-b-000584166 2024-04-28T08:17:04+00:00 Deep Morphology Learning Enhances Ex Vivo Drug Profiling-Based Precision Medicine ... Heinemann, Tim Kornauth, Christoph Severin, Yannik Vladimer, Gregory I. Pemovska, Tea Hadzijusufovic, Emir Agis, Hermine Krauth, Maria-Theresa Sperr, Wolfgang R. Valent, Peter Jäger, Ulrich Simonitsch-Klupp, Ingrid Superti-Furga, Giulio Staber, Philipp B. Snijder, Berend 2022 application/pdf https://dx.doi.org/10.3929/ethz-b-000584166 http://hdl.handle.net/20.500.11850/584166 en eng ETH Zurich article-journal Text ScholarlyArticle Journal Article 2022 ftdatacite https://doi.org/10.3929/ethz-b-000584166 2024-04-02T12:32:08Z Drug testing in patient biopsy-derived cells can identify potent treatments for patients suffering from relapsed or refractory hematologic cancers. Here we investigate the use of weakly supervised deep learning on cell morphologies (DML) to comple-ment diagnostic marker-based identifi cation of malignant and nonmalignant cells in drug testing. Across 390 biopsies from 289 patients with diverse blood cancers, DML-based drug responses show improved reproducibility and clustering of drugs with the same mode of action. DML does so by adapting to batch effects and by autonomously recognizing disease-associated cell morphologies. In a post hoc analysis of 66 patients, DML-recommended treatments led to improved progression-free survival compared with marker-based recommendations and physician's choice-based treatments. Treatments recommended by both immunofl uorescence and DML doubled the fraction of patients achieving exceptional clinical responses. Thus, DML-enhanced ex vivo drug screening is a promising tool in ... : Blood Cancer Discovery, 3 (6) ... Article in Journal/Newspaper DML DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
English |
description |
Drug testing in patient biopsy-derived cells can identify potent treatments for patients suffering from relapsed or refractory hematologic cancers. Here we investigate the use of weakly supervised deep learning on cell morphologies (DML) to comple-ment diagnostic marker-based identifi cation of malignant and nonmalignant cells in drug testing. Across 390 biopsies from 289 patients with diverse blood cancers, DML-based drug responses show improved reproducibility and clustering of drugs with the same mode of action. DML does so by adapting to batch effects and by autonomously recognizing disease-associated cell morphologies. In a post hoc analysis of 66 patients, DML-recommended treatments led to improved progression-free survival compared with marker-based recommendations and physician's choice-based treatments. Treatments recommended by both immunofl uorescence and DML doubled the fraction of patients achieving exceptional clinical responses. Thus, DML-enhanced ex vivo drug screening is a promising tool in ... : Blood Cancer Discovery, 3 (6) ... |
format |
Article in Journal/Newspaper |
author |
Heinemann, Tim Kornauth, Christoph Severin, Yannik Vladimer, Gregory I. Pemovska, Tea Hadzijusufovic, Emir Agis, Hermine Krauth, Maria-Theresa Sperr, Wolfgang R. Valent, Peter Jäger, Ulrich Simonitsch-Klupp, Ingrid Superti-Furga, Giulio Staber, Philipp B. Snijder, Berend |
spellingShingle |
Heinemann, Tim Kornauth, Christoph Severin, Yannik Vladimer, Gregory I. Pemovska, Tea Hadzijusufovic, Emir Agis, Hermine Krauth, Maria-Theresa Sperr, Wolfgang R. Valent, Peter Jäger, Ulrich Simonitsch-Klupp, Ingrid Superti-Furga, Giulio Staber, Philipp B. Snijder, Berend Deep Morphology Learning Enhances Ex Vivo Drug Profiling-Based Precision Medicine ... |
author_facet |
Heinemann, Tim Kornauth, Christoph Severin, Yannik Vladimer, Gregory I. Pemovska, Tea Hadzijusufovic, Emir Agis, Hermine Krauth, Maria-Theresa Sperr, Wolfgang R. Valent, Peter Jäger, Ulrich Simonitsch-Klupp, Ingrid Superti-Furga, Giulio Staber, Philipp B. Snijder, Berend |
author_sort |
Heinemann, Tim |
title |
Deep Morphology Learning Enhances Ex Vivo Drug Profiling-Based Precision Medicine ... |
title_short |
Deep Morphology Learning Enhances Ex Vivo Drug Profiling-Based Precision Medicine ... |
title_full |
Deep Morphology Learning Enhances Ex Vivo Drug Profiling-Based Precision Medicine ... |
title_fullStr |
Deep Morphology Learning Enhances Ex Vivo Drug Profiling-Based Precision Medicine ... |
title_full_unstemmed |
Deep Morphology Learning Enhances Ex Vivo Drug Profiling-Based Precision Medicine ... |
title_sort |
deep morphology learning enhances ex vivo drug profiling-based precision medicine ... |
publisher |
ETH Zurich |
publishDate |
2022 |
url |
https://dx.doi.org/10.3929/ethz-b-000584166 http://hdl.handle.net/20.500.11850/584166 |
genre |
DML |
genre_facet |
DML |
op_doi |
https://doi.org/10.3929/ethz-b-000584166 |
_version_ |
1797581875026329600 |