A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma : a multi-cohort study
© The Author(s), 2020..
BACKGROUND: To explore the prognostic value of radiomics-based and digital pathology-based imaging biomarkers from macroscopic magnetic resonance imaging (MRI) and microscopic whole-slide images for patients with nasopharyngeal carcinoma (NPC).
METHODS: We recruited 220 NPC patients and divided them into training (n = 132), internal test (n = 44), and external test (n = 44) cohorts. The primary endpoint was failure-free survival (FFS). Radiomic features were extracted from pretreatment MRI and selected and integrated into a radiomic signature. The histopathological signature was extracted from whole-slide images of biopsy specimens using an end-to-end deep-learning method. Incorporating two signatures and independent clinical factors, a multi-scale nomogram was constructed. We also tested the correlation between the key imaging features and genetic alternations in an independent cohort of 16 patients (biological test cohort).
RESULTS: Both radiomic and histopathologic signatures presented significant associations with treatment failure in the three cohorts (C-index: 0.689-0.779, all p < 0.050). The multi-scale nomogram showed a consistent significant improvement for predicting treatment failure compared with the clinical model in the training (C-index: 0.817 versus 0.730, p < 0.050), internal test (C-index: 0.828 versus 0.602, p < 0.050) and external test (C-index: 0.834 versus 0.679, p < 0.050) cohorts. Furthermore, patients were stratified successfully into two groups with distinguishable prognosis (log-rank p < 0.0010) using our nomogram. We also found that two texture features were related to the genetic alternations of chromatin remodeling pathways in another independent cohort.
CONCLUSION: The multi-scale imaging features showed a complementary value in prognostic prediction and may improve individualized treatment in NPC.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2020 |
|---|---|
| Erschienen: |
2020 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:12 |
|---|---|
| Enthalten in: |
Therapeutic advances in medical oncology - 12(2020) vom: 21., Seite 1758835920971416 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Zhang, Fan [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Digital pathology |
|---|
| Anmerkungen: |
Date Revised 10.11.2023 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1177/1758835920971416 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM319668223 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM319668223 | ||
| 003 | DE-627 | ||
| 005 | 20231225171935.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1177/1758835920971416 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1065.xml |
| 035 | |a (DE-627)NLM319668223 | ||
| 035 | |a (NLM)33403013 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Zhang, Fan |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma |b a multi-cohort study |
| 264 | 1 | |c 2020 | |
| 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 Revised 10.11.2023 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © The Author(s), 2020. | ||
| 520 | |a BACKGROUND: To explore the prognostic value of radiomics-based and digital pathology-based imaging biomarkers from macroscopic magnetic resonance imaging (MRI) and microscopic whole-slide images for patients with nasopharyngeal carcinoma (NPC) | ||
| 520 | |a METHODS: We recruited 220 NPC patients and divided them into training (n = 132), internal test (n = 44), and external test (n = 44) cohorts. The primary endpoint was failure-free survival (FFS). Radiomic features were extracted from pretreatment MRI and selected and integrated into a radiomic signature. The histopathological signature was extracted from whole-slide images of biopsy specimens using an end-to-end deep-learning method. Incorporating two signatures and independent clinical factors, a multi-scale nomogram was constructed. We also tested the correlation between the key imaging features and genetic alternations in an independent cohort of 16 patients (biological test cohort) | ||
| 520 | |a RESULTS: Both radiomic and histopathologic signatures presented significant associations with treatment failure in the three cohorts (C-index: 0.689-0.779, all p < 0.050). The multi-scale nomogram showed a consistent significant improvement for predicting treatment failure compared with the clinical model in the training (C-index: 0.817 versus 0.730, p < 0.050), internal test (C-index: 0.828 versus 0.602, p < 0.050) and external test (C-index: 0.834 versus 0.679, p < 0.050) cohorts. Furthermore, patients were stratified successfully into two groups with distinguishable prognosis (log-rank p < 0.0010) using our nomogram. We also found that two texture features were related to the genetic alternations of chromatin remodeling pathways in another independent cohort | ||
| 520 | |a CONCLUSION: The multi-scale imaging features showed a complementary value in prognostic prediction and may improve individualized treatment in NPC | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a digital pathology | |
| 650 | 4 | |a multi-scale features | |
| 650 | 4 | |a nasopharyngeal carcinoma | |
| 650 | 4 | |a radiomics | |
| 650 | 4 | |a survival analysis | |
| 700 | 1 | |a Zhong, Lian-Zhen |e verfasserin |4 aut | |
| 700 | 1 | |a Zhao, Xun |e verfasserin |4 aut | |
| 700 | 1 | |a Dong, Di |e verfasserin |4 aut | |
| 700 | 1 | |a Yao, Ji-Jin |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Si-Yang |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Ye |e verfasserin |4 aut | |
| 700 | 1 | |a Zhu, Ding |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Yin |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Guo-Jie |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Yi-Ming |e verfasserin |4 aut | |
| 700 | 1 | |a Li, Dan |e verfasserin |4 aut | |
| 700 | 1 | |a Wei, Jiang |e verfasserin |4 aut | |
| 700 | 1 | |a Tian, Jie |e verfasserin |4 aut | |
| 700 | 1 | |a Shan, Hong |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Therapeutic advances in medical oncology |d 2009 |g 12(2020) vom: 21., Seite 1758835920971416 |w (DE-627)NLM19877978X |x 1758-8340 |7 nnns |
| 773 | 1 | 8 | |g volume:12 |g year:2020 |g day:21 |g pages:1758835920971416 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1177/1758835920971416 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 12 |j 2020 |b 21 |h 1758835920971416 | ||