A Novel and Efficient Digital Pathology Classifier for Predicting Cancer Biomarkers Using Sequencer Architecture
Copyright © 2023 American Society for Investigative Pathology. Published by Elsevier Inc. All rights reserved..
In digital pathology tasks, transformers have achieved state-of-the-art results, surpassing convolutional neural networks (CNNs). However, transformers are usually complex and resource intensive. This study developed a novel and efficient digital pathology classifier called DPSeq to predict cancer biomarkers through fine-tuning a sequencer architecture integrating horizontal and vertical bidirectional long short-term memory networks. Using hematoxylin and eosin-stained histopathologic images of colorectal cancer from two international data sets (The Cancer Genome Atlas and Molecular and Cellular Oncology), the predictive performance of DPSeq was evaluated in a series of experiments. DPSeq demonstrated exceptional performance for predicting key biomarkers in colorectal cancer (microsatellite instability status, hypermutation, CpG island methylator phenotype status, BRAF mutation, TP53 mutation, and chromosomal instability), outperforming most published state-of-the-art classifiers in a within-cohort internal validation and a cross-cohort external validation. In addition, under the same experimental conditions using the same set of training and testing data sets, DPSeq surpassed four CNNs (ResNet18, ResNet50, MobileNetV2, and EfficientNet) and two transformer (Vision Transformer and Swin Transformer) models, achieving the highest area under the receiver operating characteristic curve and area under the precision-recall curve values in predicting microsatellite instability status, BRAF mutation, and CpG island methylator phenotype status. Furthermore, DPSeq required less time for both training and prediction because of its simple architecture. Therefore, DPSeq appears to be the preferred choice over transformer and CNN models for predicting cancer biomarkers.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:193 |
|---|---|
| Enthalten in: |
The American journal of pathology - 193(2023), 12 vom: 27. Dez., Seite 2122-2132 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Cen, Min [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Biomarkers, Tumor |
|---|
| Anmerkungen: |
Date Completed 20.11.2023 Date Revised 29.11.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.ajpath.2023.09.006 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM362711445 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM362711445 | ||
| 003 | DE-627 | ||
| 005 | 20231226091812.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.ajpath.2023.09.006 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1208.xml |
| 035 | |a (DE-627)NLM362711445 | ||
| 035 | |a (NLM)37775043 | ||
| 035 | |a (PII)S0002-9440(23)00359-0 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Cen, Min |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A Novel and Efficient Digital Pathology Classifier for Predicting Cancer Biomarkers Using Sequencer Architecture |
| 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 20.11.2023 | ||
| 500 | |a Date Revised 29.11.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2023 American Society for Investigative Pathology. Published by Elsevier Inc. All rights reserved. | ||
| 520 | |a In digital pathology tasks, transformers have achieved state-of-the-art results, surpassing convolutional neural networks (CNNs). However, transformers are usually complex and resource intensive. This study developed a novel and efficient digital pathology classifier called DPSeq to predict cancer biomarkers through fine-tuning a sequencer architecture integrating horizontal and vertical bidirectional long short-term memory networks. Using hematoxylin and eosin-stained histopathologic images of colorectal cancer from two international data sets (The Cancer Genome Atlas and Molecular and Cellular Oncology), the predictive performance of DPSeq was evaluated in a series of experiments. DPSeq demonstrated exceptional performance for predicting key biomarkers in colorectal cancer (microsatellite instability status, hypermutation, CpG island methylator phenotype status, BRAF mutation, TP53 mutation, and chromosomal instability), outperforming most published state-of-the-art classifiers in a within-cohort internal validation and a cross-cohort external validation. In addition, under the same experimental conditions using the same set of training and testing data sets, DPSeq surpassed four CNNs (ResNet18, ResNet50, MobileNetV2, and EfficientNet) and two transformer (Vision Transformer and Swin Transformer) models, achieving the highest area under the receiver operating characteristic curve and area under the precision-recall curve values in predicting microsatellite instability status, BRAF mutation, and CpG island methylator phenotype status. Furthermore, DPSeq required less time for both training and prediction because of its simple architecture. Therefore, DPSeq appears to be the preferred choice over transformer and CNN models for predicting cancer biomarkers | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 650 | 7 | |a Biomarkers, Tumor |2 NLM | |
| 650 | 7 | |a Proto-Oncogene Proteins B-raf |2 NLM | |
| 650 | 7 | |a EC 2.7.11.1 |2 NLM | |
| 700 | 1 | |a Li, Xingyu |e verfasserin |4 aut | |
| 700 | 1 | |a Guo, Bangwei |e verfasserin |4 aut | |
| 700 | 1 | |a Jonnagaddala, Jitendra |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Hong |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Xu Steven |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The American journal of pathology |d 1925 |g 193(2023), 12 vom: 27. Dez., Seite 2122-2132 |w (DE-627)NLM000077895 |x 1525-2191 |7 nnns |
| 773 | 1 | 8 | |g volume:193 |g year:2023 |g number:12 |g day:27 |g month:12 |g pages:2122-2132 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.ajpath.2023.09.006 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 193 |j 2023 |e 12 |b 27 |c 12 |h 2122-2132 | ||