Artificial intelligence for advance requesting of immunohistochemistry in diagnostically uncertain prostate biopsies
© 2021. The Author(s)..
The use of immunohistochemistry in the reporting of prostate biopsies is an important adjunct when the diagnosis is not definite on haematoxylin and eosin (H&E) morphology alone. The process is however inherently inefficient with delays while waiting for pathologist review to make the request and duplicated effort reviewing a case more than once. In this study, we aimed to capture the workflow implications of immunohistochemistry requests and demonstrate a novel artificial intelligence tool to identify cases in which immunohistochemistry (IHC) is required and generate an automated request. We conducted audits of the workflow for prostate biopsies in order to understand the potential implications of automated immunohistochemistry requesting and collected prospective cases to train a deep neural network algorithm to detect tissue regions that presented ambiguous morphology on whole slide images. These ambiguous foci were selected on the basis of the pathologist requesting immunohistochemistry to aid diagnosis. A gradient boosted trees classifier was then used to make a slide-level prediction based on the outputs of the neural network prediction. The algorithm was trained on annotations of 219 immunohistochemistry-requested and 80 control images, and tested by threefold cross-validation. Validation was conducted on a separate validation dataset of 222 images. Non IHC-requested cases were diagnosed in 17.9 min on average, while IHC-requested cases took 33.4 min over multiple reporting sessions. We estimated 11 min could be saved on average per case by automated IHC requesting, by removing duplication of effort. The tool attained 99% accuracy and 0.99 Area Under the Curve (AUC) on the test data. In the validation, the average agreement with pathologists was 0.81, with a mean AUC of 0.80. We demonstrate the proof-of-principle that an AI tool making automated immunohistochemistry requests could create a significantly leaner workflow and result in pathologist time savings.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:34 |
---|---|
Enthalten in: |
Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc - 34(2021), 9 vom: 20. Sept., Seite 1780-1794 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Chatrian, Andrea [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 24.01.2022 Date Revised 03.04.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1038/s41379-021-00826-6 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM325664528 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM325664528 | ||
003 | DE-627 | ||
005 | 20240403232337.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1038/s41379-021-00826-6 |2 doi | |
028 | 5 | 2 | |a pubmed24n1362.xml |
035 | |a (DE-627)NLM325664528 | ||
035 | |a (NLM)34017063 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Chatrian, Andrea |e verfasserin |4 aut | |
245 | 1 | 0 | |a Artificial intelligence for advance requesting of immunohistochemistry in diagnostically uncertain prostate biopsies |
264 | 1 | |c 2021 | |
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 24.01.2022 | ||
500 | |a Date Revised 03.04.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2021. The Author(s). | ||
520 | |a The use of immunohistochemistry in the reporting of prostate biopsies is an important adjunct when the diagnosis is not definite on haematoxylin and eosin (H&E) morphology alone. The process is however inherently inefficient with delays while waiting for pathologist review to make the request and duplicated effort reviewing a case more than once. In this study, we aimed to capture the workflow implications of immunohistochemistry requests and demonstrate a novel artificial intelligence tool to identify cases in which immunohistochemistry (IHC) is required and generate an automated request. We conducted audits of the workflow for prostate biopsies in order to understand the potential implications of automated immunohistochemistry requesting and collected prospective cases to train a deep neural network algorithm to detect tissue regions that presented ambiguous morphology on whole slide images. These ambiguous foci were selected on the basis of the pathologist requesting immunohistochemistry to aid diagnosis. A gradient boosted trees classifier was then used to make a slide-level prediction based on the outputs of the neural network prediction. The algorithm was trained on annotations of 219 immunohistochemistry-requested and 80 control images, and tested by threefold cross-validation. Validation was conducted on a separate validation dataset of 222 images. Non IHC-requested cases were diagnosed in 17.9 min on average, while IHC-requested cases took 33.4 min over multiple reporting sessions. We estimated 11 min could be saved on average per case by automated IHC requesting, by removing duplication of effort. The tool attained 99% accuracy and 0.99 Area Under the Curve (AUC) on the test data. In the validation, the average agreement with pathologists was 0.81, with a mean AUC of 0.80. We demonstrate the proof-of-principle that an AI tool making automated immunohistochemistry requests could create a significantly leaner workflow and result in pathologist time savings | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
700 | 1 | |a Colling, Richard T |e verfasserin |4 aut | |
700 | 1 | |a Browning, Lisa |e verfasserin |4 aut | |
700 | 1 | |a Alham, Nasullah Khalid |e verfasserin |4 aut | |
700 | 1 | |a Sirinukunwattana, Korsuk |e verfasserin |4 aut | |
700 | 1 | |a Malacrino, Stefano |e verfasserin |4 aut | |
700 | 1 | |a Haghighat, Maryam |e verfasserin |4 aut | |
700 | 1 | |a Aberdeen, Alan |e verfasserin |4 aut | |
700 | 1 | |a Monks, Amelia |e verfasserin |4 aut | |
700 | 1 | |a Moxley-Wyles, Benjamin |e verfasserin |4 aut | |
700 | 1 | |a Rakha, Emad |e verfasserin |4 aut | |
700 | 1 | |a Snead, David R J |e verfasserin |4 aut | |
700 | 1 | |a Rittscher, Jens |e verfasserin |4 aut | |
700 | 1 | |a Verrill, Clare |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc |d 1992 |g 34(2021), 9 vom: 20. Sept., Seite 1780-1794 |w (DE-627)NLM012660051 |x 1530-0285 |7 nnns |
773 | 1 | 8 | |g volume:34 |g year:2021 |g number:9 |g day:20 |g month:09 |g pages:1780-1794 |
856 | 4 | 0 | |u http://dx.doi.org/10.1038/s41379-021-00826-6 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 34 |j 2021 |e 9 |b 20 |c 09 |h 1780-1794 |