Comparable Performance of Deep Learning–Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer
Radiomic features extracted from segmented tumor regions have shown great power in gene mutation prediction, while deep learning–based (DL-based) segmentation helps to address the inherent limitations of manual segmentation. We therefore investigated whether deep learning–based segmentation is feasi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-07-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2021.696706/full |
| _version_ | 1818907310604419072 |
|---|---|
| author | Guangwen Zhang Lei Chen Aie Liu Xianpan Pan Jun Shu Ye Han Yi Huan Jinsong Zhang |
| author_facet | Guangwen Zhang Lei Chen Aie Liu Xianpan Pan Jun Shu Ye Han Yi Huan Jinsong Zhang |
| author_sort | Guangwen Zhang |
| collection | DOAJ |
| description | Radiomic features extracted from segmented tumor regions have shown great power in gene mutation prediction, while deep learning–based (DL-based) segmentation helps to address the inherent limitations of manual segmentation. We therefore investigated whether deep learning–based segmentation is feasible in predicting KRAS/NRAS/BRAF mutations of rectal cancer using MR-based radiomics. In this study, we proposed DL-based segmentation models with 3D V-net architecture. One hundred and eight patients’ images (T2WI and DWI) were collected for training, and another 94 patients’ images were collected for validation. We evaluated the DL-based segmentation manner and compared it with the manual-based segmentation manner through comparing the gene prediction performance of six radiomics-based models on the test set. The performance of the DL-based segmentation was evaluated by Dice coefficients, which are 0.878 ± 0.214 and 0.955 ± 0.055 for T2WI and DWI, respectively. The performance of the radiomics-based model in gene prediction based on DL-segmented VOI was evaluated by AUCs (0.714 for T2WI, 0.816 for DWI, and 0.887 for T2WI+DWI), which were comparable to that of corresponding manual-based VOI (0.637 for T2WI, P=0.188; 0.872 for DWI, P=0.181; and 0.906 for T2WI+DWI, P=0.676). The results showed that 3D V-Net architecture could conduct reliable rectal cancer segmentation on T2WI and DWI images. All-relevant radiomics-based models presented similar performances in KRAS/NRAS/BRAF prediction between the two segmentation manners. |
| first_indexed | 2024-12-19T21:53:06Z |
| format | Article |
| id | doaj.art-46c82563c3de4494b4bb45af09a57b2f |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-19T21:53:06Z |
| publishDate | 2021-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-46c82563c3de4494b4bb45af09a57b2f2022-12-21T20:04:21ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-07-011110.3389/fonc.2021.696706696706Comparable Performance of Deep Learning–Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal CancerGuangwen Zhang0Lei Chen1Aie Liu2Xianpan Pan3Jun Shu4Ye Han5Yi Huan6Jinsong Zhang7Department of Radiology, Xijing Hospital, Fourth Military Medical University, Xi’an, ChinaDepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaDepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaDepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaDepartment of Radiology, Xijing Hospital, Fourth Military Medical University, Xi’an, ChinaDepartment of Radiology, Xijing Hospital, Fourth Military Medical University, Xi’an, ChinaDepartment of Radiology, Xijing Hospital, Fourth Military Medical University, Xi’an, ChinaDepartment of Radiology, Xijing Hospital, Fourth Military Medical University, Xi’an, ChinaRadiomic features extracted from segmented tumor regions have shown great power in gene mutation prediction, while deep learning–based (DL-based) segmentation helps to address the inherent limitations of manual segmentation. We therefore investigated whether deep learning–based segmentation is feasible in predicting KRAS/NRAS/BRAF mutations of rectal cancer using MR-based radiomics. In this study, we proposed DL-based segmentation models with 3D V-net architecture. One hundred and eight patients’ images (T2WI and DWI) were collected for training, and another 94 patients’ images were collected for validation. We evaluated the DL-based segmentation manner and compared it with the manual-based segmentation manner through comparing the gene prediction performance of six radiomics-based models on the test set. The performance of the DL-based segmentation was evaluated by Dice coefficients, which are 0.878 ± 0.214 and 0.955 ± 0.055 for T2WI and DWI, respectively. The performance of the radiomics-based model in gene prediction based on DL-segmented VOI was evaluated by AUCs (0.714 for T2WI, 0.816 for DWI, and 0.887 for T2WI+DWI), which were comparable to that of corresponding manual-based VOI (0.637 for T2WI, P=0.188; 0.872 for DWI, P=0.181; and 0.906 for T2WI+DWI, P=0.676). The results showed that 3D V-Net architecture could conduct reliable rectal cancer segmentation on T2WI and DWI images. All-relevant radiomics-based models presented similar performances in KRAS/NRAS/BRAF prediction between the two segmentation manners.https://www.frontiersin.org/articles/10.3389/fonc.2021.696706/fullrectal cancerdeep learningradiomicsmagnetic resonance imaginggene mutation |
| spellingShingle | Guangwen Zhang Lei Chen Aie Liu Xianpan Pan Jun Shu Ye Han Yi Huan Jinsong Zhang Comparable Performance of Deep Learning–Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer Frontiers in Oncology rectal cancer deep learning radiomics magnetic resonance imaging gene mutation |
| title | Comparable Performance of Deep Learning–Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer |
| title_full | Comparable Performance of Deep Learning–Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer |
| title_fullStr | Comparable Performance of Deep Learning–Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer |
| title_full_unstemmed | Comparable Performance of Deep Learning–Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer |
| title_short | Comparable Performance of Deep Learning–Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer |
| title_sort | comparable performance of deep learning based to manual based tumor segmentation in kras nras braf mutation prediction with mr based radiomics in rectal cancer |
| topic | rectal cancer deep learning radiomics magnetic resonance imaging gene mutation |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2021.696706/full |
| work_keys_str_mv | AT guangwenzhang comparableperformanceofdeeplearningbasedtomanualbasedtumorsegmentationinkrasnrasbrafmutationpredictionwithmrbasedradiomicsinrectalcancer AT leichen comparableperformanceofdeeplearningbasedtomanualbasedtumorsegmentationinkrasnrasbrafmutationpredictionwithmrbasedradiomicsinrectalcancer AT aieliu comparableperformanceofdeeplearningbasedtomanualbasedtumorsegmentationinkrasnrasbrafmutationpredictionwithmrbasedradiomicsinrectalcancer AT xianpanpan comparableperformanceofdeeplearningbasedtomanualbasedtumorsegmentationinkrasnrasbrafmutationpredictionwithmrbasedradiomicsinrectalcancer AT junshu comparableperformanceofdeeplearningbasedtomanualbasedtumorsegmentationinkrasnrasbrafmutationpredictionwithmrbasedradiomicsinrectalcancer AT yehan comparableperformanceofdeeplearningbasedtomanualbasedtumorsegmentationinkrasnrasbrafmutationpredictionwithmrbasedradiomicsinrectalcancer AT yihuan comparableperformanceofdeeplearningbasedtomanualbasedtumorsegmentationinkrasnrasbrafmutationpredictionwithmrbasedradiomicsinrectalcancer AT jinsongzhang comparableperformanceofdeeplearningbasedtomanualbasedtumorsegmentationinkrasnrasbrafmutationpredictionwithmrbasedradiomicsinrectalcancer |