TN‐USMA Net: Triple normalization‐based gastrointestinal stromal tumors classification on multicenter EUS images with ultrasound‐specific pretraining and meta attention
Abstract
Purpose: Accurate quantification of gastrointestinal stromal tumors’ (GISTs) risk stratification on multicenter endoscopic ultrasound (EUS) images plays a pivotal role in aiding the surgical decision‐making process. This study focuses on automatically classifying higher‐risk and lower‐risk GISTs in the presence of a multicenter setting and limited data. Methods: In this study, we retrospectively enrolled 914 patients with GISTs (1824 EUS images in total) from 18 hospitals in China. We propose a triple normalization‐based deep learning framework with ultrasound‐specific pretraining and meta attention, namely, TN‐USMA model. The triple normalization module consists of the intensity normalization, size normalization, and spatial resolution normalization. First, the image intensity is standardized and same‐size regions of interest (ROIs) and same‐resolution tumor masks are generated in parallel. Then, the transfer learning strategy is utilized to mitigate the data scarcity problem. The same‐size ROIs are fed into a deep architecture with ultrasound‐specific pretrained weights, which are obtained from self‐supervised learning using a large volume of unlabeled ultrasound images. Meanwhile, tumors’ size features are calculated from the same‐resolution masks individually. Afterward, the size features together with two demographic features are integrated to the model before the final classification layer using a meta attention mechanism to further enhance feature representations. The diagnostic performance of the proposed method was compared with one radiomics‐based method and two state‐of‐the‐art deep learning methods. Four evaluation metrics, namely, the accuracy, the area under the receiver operator curve, the sensitivity, and the specificity were used to evaluate the model performance. Results: The proposed TN‐USMA model achieves an overall accuracy of 0.834 (95% confidence interval [CI]: 0.772, 0.885), an area under the receiver operator curve of 0.881 (95% CI: 0.825, 0.924), a sensitivity of 0.844 (95% CI: 0.672, 0.947), and a specificity of 0.832 (95% CI: 0.762, 0.888). The AUC significantly outperforms other two deep learning approaches (p < 0.05, DeLong et al). Moreover, the performance is stable under different variations of multicenter dataset partitions. Conclusions: The proposed TN‐USMA model can successfully differentiate higher‐risk GISTs from lower‐risk ones. It is accurate, robust, generalizable, and efficient for potential clinical applications.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Two of the five self-prediction studies compared their approach to models without self-supervised pre-training and reported slight relative improvements in performance of 1.12% and 0.690%.
“Two of the five studies compared their approach to models without self-supervised pre-training and reported slight relative improvements in performance of 1.12%67 and 0.690%63.”
From Self-supervised learning for medical image classification: a systematic review and implementation guidelines (2023) · cites this paper as [63]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · see citing works
(2008) · Journal of Machine Learning Research · Cited by 33,051 · see citing works
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602 · see citing works
DeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988) · Biometrics · doi:10.2307/2531595 · Cited by 22,649 · see citing works
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072 · see citing works
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157 · see citing works
Radiomics: Images Are More than Pictures, They Are Data
Gillies, R. J., Kinahan, P. E., & Hricak, H. (2016) · Radiology · doi:10.1148/radiol.2015151169 · Cited by 8,421 · see citing works
Dual Attention Network for Scene Segmentation
Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00326 · Cited by 7,351 · see citing works
Learning Transferable Architectures for Scalable Image Recognition
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00907 · Cited by 6,631 · see citing works
Shin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759 · see citing works
Radiomics: the bridge between medical imaging and personalized medicine
Lambin, P., Leijenaar, R. T. H., Deist, T. M., Peerlings, J., de Jong, E. E. C., van Timmeren, J., Sanduleanu, S., Larue, R. T. H. M., Even, A. J. G., Jochems, A., et al. (2017) · Nature Reviews Clinical Oncology · doi:10.1038/nrclinonc.2017.141 · Cited by 5,688 · see citing works
Diagnosis of gastrointestinal stromal tumors: A consensus approach
Fletcher, C. D. �., Berman, J. J., Corless, C. L., et al. (2002) · Human Pathology · doi:10.1053/hupa.2002.123545 · Cited by 3,461 · see citing works
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.222 · Cited by 3,150 · see citing works
Dataset of breast ultrasound images
Al-Dhabyani, W., Gomaa, M., Khaled, H., & Fahmy, A. (2020) · Data in Brief · doi:10.1016/j.dib.2019.104863 · Cited by 2,405 · see citing works
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial NetworksPreprint
Zhu, J.-Y., Park, T., Isola, P., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.10593 · Cited by 2,278 · see citing works
2012 IEEE Conference on Computer Vision and Pattern Recognition
Loy, C., Hospedales, T. M., Xiang, T., & Gong, S. (2012) · Cited by 1,883 · see citing works
Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks
Yu, L., Chen, H., Dou, Q., Qin, J., & Heng, P.-A. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2642839 · Cited by 1,140 · see citing works
Gastrointestinal stromal tumours: origin and molecular oncology
Corless, C. L., Barnett, C. M., & Heinrich, M. C. (2011) · Nature reviews. Cancer · doi:10.1038/nrc3143 · Cited by 903 · see citing works
Blay, J., Bonvalot, S., Casali, P. G., et al. (2005) · Annals of Oncology · doi:10.1093/annonc/mdi127 · Cited by 726 · see citing works
Gastrointestinal stromal tumour
Joensuu, H., Hohenberger, P., & Corless, C. L. (2013) · The Lancet · doi:10.1016/s0140-6736(13)60106-3 · Cited by 721 · see citing works
Contrast-limited adaptive histogram equalization: speed and effectiveness
Pizer, S. M., Johnston, R. E., Ericksen, J. P., et al. (2002) · doi:10.1109/vbc.1990.109340 · Cited by 711 · see citing works
Self-supervised learning for medical image analysis using image context restoration
Chen, L., Bentley, P., Mori, K., Misawa, K., Fujiwara, M., & Rueckert, D. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101539 · Cited by 575 · see citing works
Xie, Y., Xia, Y., Zhang, J., Song, Y., Feng, D. D., FULHAM, M. J., & Cai, W. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2876510 · Cited by 504 · see citing works
Zhou, Z., Sodha, V., Pang, J., Gotway, M. B., & Liang, J. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101840 · Cited by 353 · see citing works
Liu, M., Zhang, J., Adeli, E., & Shen, D. G. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2869989 · Cited by 308 · see citing works
The role of endoscopy in subepithelial lesions of the GI tract
Faulx, A. L., Kothari, S., Acosta, R. D., Agrawal, D., Bruining, D. H., Chandrasekhara, V., Eloubeidi, M. A., Fanelli, R. D., Gurudu, S., Khashab, M. A., et al. (2017) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2017.02.022 · Cited by 292 · see citing works
Truhn, D., Schrading, S., Haarburger, C., Schneider, H., Merhof, D., & Kuhl, C. (2019) · Radiology · doi:10.1148/radiol.2018181352 · Cited by 273 · see citing works
Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey
Huang, Q., Zhang, F., & Li, X. (2018) · BioMed Research International · doi:10.1155/2018/5137904 · Cited by 206 · see citing works
A gist of gastrointestinal stromal tumors: A review
Rammohan, A. (2012) · World Journal of Gastrointestinal Oncology · doi:10.4251/wjgo.v5.i6.102 · Cited by 194 · see citing works
Kohli, M. D., Summers, R. M., & Geis, J. R. (2017) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-017-9976-3 · Cited by 193 · see citing works
Ning, Z., Luo, J., Li, Y., Han, S., Feng, Q., Xu, Y., Chen, W., Chen, T., & Zhang, Y. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2841992 · Cited by 109 · see citing works
Lv, W., Ashrafinia, S., Ma, J., et al. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2956354 · Cited by 100 · see citing works
Wang, Y., Yue, W., Li, X., Liu, S., Guo, L., Xu, H., Zhang, H., & Yang, G. (2020) · IEEE Access · doi:10.1109/access.2020.2980290 · Cited by 96 · see citing works
Self-citationAge-based computer-aided diagnosis approach for pancreatic cancer on endoscopic ultrasound images
Kurt, M., Özkan, M., Çakıroğlu, M., Kocaman, O., Yılmaz, B., Can, G., Korkmaz, U., Dandıl, E., & Ekşi, Z. (2016) · Endoscopic Ultrasound · doi:10.4103/2303-9027.180473 · Cited by 93 · see citing works
Guidelines For Training in Electronic Ultrasound
Dam, J. V., Brady, P. G., Freeman, M., et al. (1999) · Gastrointestinal Endoscopy · doi:10.1016/s0016-5107(99)70312-3 · Cited by 66 · see citing works
Gao, Y., Liu, Y., Wang, Y., Shi, Z., & Yu, J. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2894692 · Cited by 57 · see citing works
Self-citationLim, T. W., Choi, C. W., Kang, D. H., et al. (2016) · Medicine · doi:10.1097/md.0000000000005246 · Cited by 49 · see citing works
Niessen, W. J., & Viergever, M. A. (2001) · Cited by 40 · see citing works
The Role of Artificial Intelligence in Endoscopic Ultrasound for Pancreatic Disorders
Tonozuka, R., Mukai, S., & Itoi, T. (2020) · Diagnostics · doi:10.3390/diagnostics11010018 · Cited by 29 · see citing works
Kang, J. H., Lim, J. S., Kim, J., et al. (2008) · European Radiology · doi:10.1007/s00330-008-1224-2 · Cited by 28 · see citing works
Li, X., Jiang, F., Guo, Y., Jin, Z., & Wang, Y. (2019) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-019-01993-3 · Cited by 27 · see citing works
Self-citationZhao, B., Zhang, J., Mei, D., et al. (2018) · Scandinavian Journal of Gastroenterology · doi:10.1080/00365521.2018.1515319 · Cited by 15 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Huang, S.-C., Pareek, A., Jensen, M., Lungren, M. P., Yeung, S., & Chaudhari, A. S. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00811-0 · Cited by 479 · see citing works
- Authors
- Liu, C., Qiao, M., Jiang, F., Guo, Y., Jin, Z., & Wang, Y.
- Affiliations
- Fudan University (CN)
- Changhai Hospital (CN)
- Corresponding author
- Guo, Yi
- Wang, Yuanyuan
- Venue
- Medical Physics
- Publisher
- Wiley
- Published
- 2021-08-30
- Volume
- 48
- Issue
- 11
- Pages
- 7199-7214
- ISSN
- 0094-2405 (ISSN-L)
- 2473-4209
- OpenAlex
- W3194875602
- Cited by
- 22
- References
- 45
- Citations by year
- 2026: 1 · 2025: 8 · 2024: 7 · 2023: 2 · 2022: 3 · 2021: 1
- FWCI
- 1.14
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Medical Physics (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (61771143, 61871135, 81830058)
- Science and Technology Commission of Shanghai Municipality (20DZ1100104)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Gastroenterology › Gastrointestinal Tumor Research and Treatment
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- gastrointestinal stromal tumor, endoscopic ultrasound, risk stratification, tumor classification, intensity normalization, size normalization, self-supervised learning, meta-attention, transfer learning, deep learning classification, surgical decision-making
- MeSH terms
- Humans, Retrospective Studies, Ultrasonography, Endosonography, Gastrointestinal Stromal Tumors
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
