A Deep Learning Model to Predict the Response to Neoadjuvant Chemoradiotherapy by the Pretreatment Apparent Diffusion Coefficient Images of Locally Advanced Rectal Cancer
Copyright © 2020 Zhu, Zhang, Shi, Li and Sun..
BACKGROUND AND PURPOSE: Pretreatment prediction of the response to neoadjuvant chemoradiotherapy (NCRT) helps to determine the subsequent plans for the patients with locally advanced rectal cancer (LARC). If the good responders (GR) and non-good responders (non-GR) can be accurately predicted, they can choose to intensify the neoadjuvant chemoradiotherapy to decrease the risk of tumor progression during NCRT and increase the chance of organ preservation. Compared with radiomics methods, deep learning (DL) may adaptively extract features from the images without the need of feature definition. However, DL suffers from limited training samples and signal discrepancy among different scanners. This study aims to construct a DL model to predict GRs by training apparent diffusion coefficient (ADC) images from different scanners.
METHODS: The study retrospectively recruited 700 participants, chronologically divided into a training group (n = 500) and a test group (n = 200). Deep convolutional neural networks were constructed to classify GRs and non-GRs. The networks were designed with a max-pooling layer parallelized by a center-cropping layer to extract features from both the macro and micro scale. ADC images and T2-weighted images were collected at 1.5 Tesla and 3.0 Tesla. The networks were trained by the image patches delineated by radiologists in ADC images and T2-weighted images, respectively. Pathological results were used as the ground truth. The deep learning models were evaluated on the test group and compared with the prediction by mean ADC value.
RESULTS: Area under curve (AUC) of receiver operating characteristic (ROC) is 0.851 (95% CI: 0.789-0.914) for DL model with ADC images (DL_ADC), significantly larger (P = 0.018, Z = 2.367) than that of mean ADC with AUC = 0.723 (95% CI: 0.637-0.809). The sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of DL_ADC model are 94.3%, 68.3%, 87.4% and 83.7%, respectively. The DL model with T2-weighted images (DL_T2) produces an AUC of 0.721 (95% CI: 0.640-0.802), significantly (P = 0.000, Z = 3.554) lower than that of DL_ADC model.
CONCLUSION: Deep learning model reveals the potential of pretreatment apparent diffusion coefficient images for the prediction of good responders to neoadjuvant chemoradiotherapy.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2020 |
|---|---|
| Erschienen: |
2020 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:10 |
|---|---|
| Enthalten in: |
Frontiers in oncology - 10(2020) vom: 28., Seite 574337 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Zhu, Hai-Tao [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Apparent diffusion coefficient |
|---|
| Anmerkungen: |
Date Revised 18.04.2022 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.3389/fonc.2020.574337 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM317620789 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM317620789 | ||
| 003 | DE-627 | ||
| 005 | 20231226202213.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.3389/fonc.2020.574337 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1058.xml |
| 035 | |a (DE-627)NLM317620789 | ||
| 035 | |a (NLM)33194680 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Zhu, Hai-Tao |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A Deep Learning Model to Predict the Response to Neoadjuvant Chemoradiotherapy by the Pretreatment Apparent Diffusion Coefficient Images of Locally Advanced Rectal Cancer |
| 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 18.04.2022 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Copyright © 2020 Zhu, Zhang, Shi, Li and Sun. | ||
| 520 | |a BACKGROUND AND PURPOSE: Pretreatment prediction of the response to neoadjuvant chemoradiotherapy (NCRT) helps to determine the subsequent plans for the patients with locally advanced rectal cancer (LARC). If the good responders (GR) and non-good responders (non-GR) can be accurately predicted, they can choose to intensify the neoadjuvant chemoradiotherapy to decrease the risk of tumor progression during NCRT and increase the chance of organ preservation. Compared with radiomics methods, deep learning (DL) may adaptively extract features from the images without the need of feature definition. However, DL suffers from limited training samples and signal discrepancy among different scanners. This study aims to construct a DL model to predict GRs by training apparent diffusion coefficient (ADC) images from different scanners | ||
| 520 | |a METHODS: The study retrospectively recruited 700 participants, chronologically divided into a training group (n = 500) and a test group (n = 200). Deep convolutional neural networks were constructed to classify GRs and non-GRs. The networks were designed with a max-pooling layer parallelized by a center-cropping layer to extract features from both the macro and micro scale. ADC images and T2-weighted images were collected at 1.5 Tesla and 3.0 Tesla. The networks were trained by the image patches delineated by radiologists in ADC images and T2-weighted images, respectively. Pathological results were used as the ground truth. The deep learning models were evaluated on the test group and compared with the prediction by mean ADC value | ||
| 520 | |a RESULTS: Area under curve (AUC) of receiver operating characteristic (ROC) is 0.851 (95% CI: 0.789-0.914) for DL model with ADC images (DL_ADC), significantly larger (P = 0.018, Z = 2.367) than that of mean ADC with AUC = 0.723 (95% CI: 0.637-0.809). The sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of DL_ADC model are 94.3%, 68.3%, 87.4% and 83.7%, respectively. The DL model with T2-weighted images (DL_T2) produces an AUC of 0.721 (95% CI: 0.640-0.802), significantly (P = 0.000, Z = 3.554) lower than that of DL_ADC model | ||
| 520 | |a CONCLUSION: Deep learning model reveals the potential of pretreatment apparent diffusion coefficient images for the prediction of good responders to neoadjuvant chemoradiotherapy | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a apparent diffusion coefficient | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a good responder | |
| 650 | 4 | |a magnetic resonance imaging | |
| 650 | 4 | |a rectal cancer | |
| 700 | 1 | |a Zhang, Xiao-Yan |e verfasserin |4 aut | |
| 700 | 1 | |a Shi, Yan-Jie |e verfasserin |4 aut | |
| 700 | 1 | |a Li, Xiao-Ting |e verfasserin |4 aut | |
| 700 | 1 | |a Sun, Ying-Shi |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Frontiers in oncology |d 2011 |g 10(2020) vom: 28., Seite 574337 |w (DE-627)NLM218189583 |x 2234-943X |7 nnns |
| 773 | 1 | 8 | |g volume:10 |g year:2020 |g day:28 |g pages:574337 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.3389/fonc.2020.574337 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 10 |j 2020 |b 28 |h 574337 | ||