Shape and margin-aware lung nodule classification in low-dose CT images via soft activation mapping
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
A number of studies on lung nodule classification lack clinical/biological interpretations of the features extracted by convolutional neural network (CNN). The methods like class activation mapping (CAM) and gradient-based CAM (Grad-CAM) are tailored for interpreting localization and classification tasks while they ignored fine-grained features. Therefore, CAM and Grad-CAM cannot provide optimal interpretation for lung nodule categorization task in low-dose CT images, in that fine-grained pathological clues like discrete and irregular shape and margins of nodules are capable of enhancing sensitivity and specificity of nodule classification with regards to CNN. In this paper, we first develop a soft activation mapping (SAM) to enable fine-grained lung nodule shape & margin (LNSM) feature analysis with a CNN so that it can access rich discrete features. Secondly, by combining high-level convolutional features with SAM, we further propose a high-level feature enhancement scheme (HESAM) to localize LNSM features. Experiments on the LIDC-IDRI dataset indicate that 1) SAM captures more fine-grained and discrete attention regions than existing methods, 2) HESAM localizes more accurately on LNSM features and obtains the state-of-the-art predictive performance, reducing the false positive rate, and 3) we design and conduct a visually matching experiment which incorporates radiologists study to increase the confidence level of applying our method to clinical diagnosis.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
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
Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening
The National Lung Screening Trial Research Team (2011) · New England Journal of Medicine · doi:10.1056/nejmoa1102873 · Cited by 11,064
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46723-8_49 · Cited by 7,945 · cited 1×
“Furthermore, 3D-UNet (Çiçek et al., 2016; Wu et al., 2018) was proposed to segment volumetric medical data and conduct multi-task learning, by performing classification after the output layer of 3D-UNet.”
MethodRadiomics: extracting more information from medical images using advanced feature analysis
Lambin, P., Rios-Velazquez, E., Leijenaar, R., Carvalho, S., van Stiphout, R. G. P. M., Granton, P., Zegers, C. M. L., Gillies, R., Boellard, R., Dekker, A., et al. (2012) · European Journal of Cancer · doi:10.1016/j.ejca.2011.11.036 · Cited by 6,084
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“For the lack of annotated data in medical cases, transfer learning (Pan et al., 2010; Shin et al., 2016; Yosinski et al., 2014) have been introduced to solve this problem significantly.”
BackgroundLarge-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2010) · Proceedings of COMPSTAT'2010 · doi:10.1007/978-3-7908-2604-3_16 · Cited by 5,795 · cited 1×
“And optimizer is stochastic gradient decent (SGD) (Bottou, 2010).”
BackgroundShin, 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
Artificial intelligence in radiology
Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H., & Aerts, H. J. W. L. (2018) · Nature Reviews Cancer · doi:10.1038/s41568-018-0016-5 · Cited by 3,803
Brain tumor segmentation with Deep Neural Networks
Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., & Larochelle, H. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.05.004 · Cited by 3,278
Brain Tumor Segmentation with Deep Neural Networks
Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., & Larochelle, H. (2015) · arXiv · doi:10.48550/arxiv.1505.03540 · Cited by 3,278
Armato, S. G., McLennan, G., Bidaut, L., McNitt‐Gray, M. F., Meyer, C. R., Reeves, A. P., Zhao, B., Aberle, D. R., Henschke, C. I., Hoffman, E. A., et al. (2011) · Medical Physics · doi:10.1118/1.3528204 · Cited by 2,887
Understanding deep learning requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016) · arXiv · doi:10.48550/arxiv.1611.03530 · Cited by 2,838 · cited 1×
“So, if the number of training samples ( N ) is fixed and small, the standard FC counterpart with a huge amount of parameters is prone to overfitting the training data because of the high model complexity ( P/N , P denotes the number of model parameters) (Yu et al., 2006; Zhang et al., 2016).”
BackgroundAttention gated networks: learning to leverage salient regions in medical images
Schlemper, J., Oktay, O., Schaap, M., Heinrich, M., Kainz, B., Glocker, B., & Rueckert, D. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.01.012 · Cited by 2,014 · cited 1×
“…section, we will give a brief survey on following three aspects: 1) CNNs applied to medical image classification (Chen et al., 2017a; Litjens et al., 2017; Schlemper et al., 2019; Zhang et al., 2019), 2) UNet and its variants, 3) two activation mapping methods for attention regions localization.”
MethodSetio, A. A. A., Ciompi, F., Litjens, G., Gerke, P., Jacobs, C., van Riel, S. J., Wille, M. M. W., Naqibullah, M., Sanchez, C. I., & van Ginneken, B. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2536809 · Cited by 1,258
The importance of shape in early lexical learning
Landau, B., Smith, L. B., & Jones, S. S. (1988) · Cognitive Development · doi:10.1016/0885-2014(88)90014-7 · Cited by 1,174 · cited 1×
“And it is well-known that object shape is the single most important cue for human object recognition (Landau et al., 1988) as well as for deep neural networks (Kubilius et al., 2016).”
Background
Research works printed but not linked: 19
- Ahonen, 2007, Face description with local binary patterns: application to face recognition, IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 28, 2037, 10.1109/TPAMI.2006.244 · DOI · Paper page
- Brenner, 2007, Computed tomography an increasing source of radiation exposure, N. England J. Med., 357, 2277, 10.1056/NEJMra072149 · DOI · Paper page
- Chen, 2017, Low-dose CT via convolutional neural network, Biomed. Opt. Express, 8, 679, 10.1364/BOE.8.000679 · DOI · Paper page
- Choi, 2018, Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer, Med. Phys., 45, 1537, 10.1002/mp.12820 · DOI · Paper page
- Dou, 2017, Multilevel contextual 3D CNNs for false positive reduction in pulmonary nodule detection, IEEE Trans. Biomed. Eng. (TBME), 64, 1558, 10.1109/TBME.2016.2613502 · DOI · Paper page
- de González, 2009, Projected cancer risks from computed tomographic scans performed in the united states in 2007, Arch. Internal Med., 169, 2071, 10.1001/archinternmed.2009.440 · DOI · Paper page
- Kubilius, 2016, Deep neural networks as a computational model for human shape sensitivity, PLoS Comput. Biol., 12, 10.1371/journal.pcbi.1004896 · DOI · Paper page
- Lei, 2017, A novel approach for cirrhosis recognition via improved LBP algorithm and dictionary learning, Biomed. Signal Process. Control, 38, 281, 10.1016/j.bspc.2017.06.014 · DOI
- Li, 2004, Malignant versus benign nodules at CT screening for lung cancer: comparison of thin-section CT findings, Radiology, 233, 793, 10.1148/radiol.2333031018 · DOI · Paper page
- Litjens, 2017, A survey on deep learning in medical image analysis, Med. Image Anal., 42, 60, 10.1016/j.media.2017.07.005 · DOI · Paper page
- Pan, 2010, A survey on transfer learning, IEEE Trans. Knowl. Data Eng. (TKDE), 22, 1345, 10.1109/TKDE.2009.191 · DOI · Paper page
- Pesce, 2019, Learning to detect chest radiographs containing pulmonary lesions using visual attention networks, Med. Image Anal., 53, 26, 10.1016/j.media.2018.12.007 · DOI · Paper page
- Russakovsky, 2015, Imagenet large scale visual recognition challenge, Int. J. Comput. Vis. (IJCV), 115, 211, 10.1007/s11263-015-0816-y · DOI · Paper page
- Shan, 2019, Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose ct image reconstruction, Nature Mach. Intell., 1, 269, 10.1038/s42256-019-0057-9 · DOI · Paper page
- Shan, 2018, 3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-d trained network., IEEE Trans. Med. Imag. (TMI), 37, 1522, 10.1109/TMI.2018.2832217 · DOI · Paper page
- WHO, 2011, Description of the global burden of NCDs, their risk factors and determinants, Global Status Rep. Noncommun. Dis. 2010, 1
- Winkels, 2019, Pulmonary nodule detection in CT scans with equivariant CNNs, Med. Image Anal., 10.1016/j.media.2019.03.010 · DOI
- Zhang, 2019, Medical image classification using synergic deep learning, Med. Image Anal., 54, 10, 10.1016/j.media.2019.02.010 · DOI · Paper page
- Zhu, W., Liu, C., Fan, W., Xie, X., 2017. Deeplung: 3D deep convolutional nets for automated pulmonary nodule detection and classification. arXiv preprint arXiv1709.05538. · DOI
Cited by
Explainable artificial intelligence (XAI) in deep learning-based medical image analysis
van der Velden, B. H. M., Kuijf, H. J., Gilhuijs, K. G. A., & Viergever, M. A. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102470 · Cited by 1,328
On Interpretability of Artificial Neural Networks: A Survey
Fan, F.-L., Xiong, J., Li, M., & Wang, G. (2021) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2021.3066428 · Cited by 561
Self-citationNazir, S., Dickson, D. M., & Akram, M. U. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106668 · Cited by 283
“Lung nodule localization and classification on low-dose CT images (LIDC-IDRI public dataset) was implemented using soft activation mapping for fine-grained features analysis with a CNN [180].”
BackgroundMethodRobustness Analysis of Deep Learning-Based Lung Cancer Classification Using Explainable Methods
Malafaia, M., Silva, F., Neves, I., Pereira, T., & Oliveira, H. P. (2022) · IEEE Access · doi:10.1109/access.2022.3214824 · Cited by 25
“These models have been studied and implemented in several other studies to lung classification tasks, namely in Lei et al. [20].”
Method
Metadata
- Authors
- Lei, Y., Tian, Y., Shan, H., Zhang, J., Wang, G., & Kalra, M. K.
- Venue
- Medical Image Analysis
- Publisher
- Elsevier BV
- Published
- 2020-02
- Volume
- 60
- Pages
- 101628
- ISSN
- 1361-8415 (ISSN-L)
- OpenAlex
- W2995323791
- Cited by
- 90
- References
- 17
- FWCI
- 4.26
- Type
- journal article
- Language
- en
- Open access
- green
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- Funders
- Shanghai Municipal Science and Technology (2018SHZDZX01)
- National Natural Science Foundation of China (61673118)
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.