The DOI matches its Crossref record; 11 of the 13 references it cites were found in a registry or an index.
Off-the-shelf convolutional neural network features for pulmonary nodule detection in computed tomography scans
Abstract
Convolutional neural networks (CNNs) have emerged as the most powerful technique for a range of different tasks in computer vision. Recent work suggested that CNN features are generic and can be used for classification tasks outside the exact domain for which the networks were trained. In this work we use the features from one such network, OverFeat, trained for object detection in natural images, for nodule detection in computed tomography scans. We use 865 scans from the publicly available LIDC data set, read by four thoracic radiologists. Nodule candidates are generated by a state-of-the-art nodule detection system. We extract 2D sagittal, coronal and axial patches for each nodule candidate and extract 4096 features from the penultimate layer of OverFeat and classify these with linear support vector machines. We show for various configurations that the off-the-shelf CNN features perform surprisingly well, but not as good as the dedicated detection system. When both approaches are combined, significantly better results are obtained than either approach alone. We conclude that CNN features have great potential to be used for detection tasks in volumetric medical data.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“It is likely that artificial intelligence (AI) technologies will be incorporated into clinical practise, with applications such as image-based diagnostics in radiology demonstrating accuracy and efficacy rivalling speciality trained physicians [1–2].”
From Exploration of exposure to artificial intelligence in undergraduate medical education: a Canadian cross-sectional mixed-methods study (2022) · cites this paper as [2]
In the citing paper
“It is likely that artificial intelligence (AI) technologies will be incorporated into clinical practise, with applications such as image-based diagnostics in radiology demonstrating accuracy and efficacy rivalling speciality trained physicians [1–2].”
From Exploration of exposure to artificial intelligence in undergraduate medical education: a Canadian cross-sectional mixed-methods study (2022) · cites this paper as [2]
In the citing paper
“To complement “off-the-shelf” CNN features, [10], [9], [12] all add and integrate various other hand-crafted image features as hybrid inputs for the final CADe classification.”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [9]
Citations
Cites
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
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
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
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2014.131 · Cited by 4,451
An analysis of single-layer networks in unsupervised feature learning
Coates, A., Ng, A. Y., & Lee, H. (2011) · Cited by 2,760
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680
CNN Features off-the-shelf: an Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · arXiv · doi:10.48550/arxiv.1403.6382 · Cited by 607
Roth, H. R., Lu, L., Seff, A., Cherry, K. M., Hoffman, J., Wang, S., Liu, J., Turkbey, E., & Summers, R. M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10404-1_65 · Cited by 355
Computer-aided Diagnosis: How to Move from the Laboratory to the Clinic
van Ginneken, B., Schaefer-Prokop, C. M., & Prokop, M. (2011) · Radiology · doi:10.1148/radiol.11091710 · Cited by 306
van Ginneken, B., Armato, S. G., de Hoop, B., de Vorst, S. V. A.-V., Duindam, T., Niemeijer, M., Murphy, K., Schilham, A. M. R., Retico, A., Fantacci, M. E., et al. (2010) · Medical Image Analysis · doi:10.1016/j.media.2010.05.005 · Cited by 298
Research works printed but not linked: 2
- jacobs, 2013, Benchmarking computer-aided detection of pulmonary nodules on the recently completed publicly available LIDC/IDRI database, Radiological Society of North America Annual Meeting
- krizhevsky, 2012, Ima-genet classification with deep convolutional neural net-works, NIPS, 1097
Cited by
Sorted by citations
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
Self-citationShin, 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
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B., & Liang, J. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2535302 · Cited by 3,277
“This analysis is in contrast to [28], [29], who provided only”
ResultArtificial intelligence in healthcare
Yu, K.-H., Beam, A. L., & Kohane, I. S. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0305-z · Cited by 2,817
Greenspan, H. K., van Ginneken, B., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2553401 · Cited by 1,725
“[27] integration of CNN-based features with handcrafted features enabled improved performance in a nodule detection system.”
MethodSetio, A. A. A., Traverso, A., de Bel, T., Berens, M. S. N., van den Bogaard, C., Cerello, P., Chen, H., Dou, Q., Fantacci, M. E., Geurts, B. H. J., et al. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.06.015 · Cited by 1,456
Self-citationSetio, 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
Self-citationDeep learning for brain MRI segmentation: state of the art and future directions
Akkus, Z., Galimzianova, A., Hoogi, A., Rubin, D. L., & Erickson, B. J. (2017) · Journal of Digital Imaging · doi:10.1007/s10278-017-9983-4 · Cited by 1,129
Brain tumor classification for MR images using transfer learning and fine-tuning
Swati, Z. N. K., Zhao, Q., Kabir, M., Ali, F., Ali, Z., Ahmad, S., & Lu, J. (2019) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2019.05.001 · Cited by 895
Deep learning in medical imaging and radiation therapy
Sahiner, B., Pezeshk, A. X., Hadjiiski, L. M., Wang, X., Drukker, K., Cha, K. H., Summers, R. M., & Giger, M. L. (2018) · Medical Physics · doi:10.1002/mp.13264 · Cited by 763
“A number of studies used pretrained CNNs for extracting features, which are sometimes referred to as the off-the-shelf CNN features.(305) A relatively small labeled dataset can then be used to train a classifier such as an SVM for the problem at hand.”
BackgroundImproving Computer-Aided Detection UsingConvolutional Neural Networks and Random View Aggregation
Roth, H. R., Lu, L., Liu, J., Yao, J., Seff, A., Cherry, K., Kim, L., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2015.2482920 · Cited by 608
“This strategy has been adapted to computer-aided pulmonary embolism detection ([52]), lung nodule classification ([11], [53]) in CT images and polyp detection in colonoscopy videos ([54], [55]).”
MethodDeep learning for automated skeletal bone age assessment in X-ray images
Spampinato, C., Palazzo, S., Giordano, D., Aldinucci, M., & Leonardi, R. M. (2016) · Medical Image Analysis · doi:10.1016/j.media.2016.10.010 · Cited by 436
“After The usage of off-the-shelf CNN features has been also recently investigated (Wolterink et al., 2015; van Ginneken et al., 2015).”
Deep learning for lung Cancer detection and classification
Asuntha, A., & Srinivasan, A. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08394-3 · Cited by 383
Zhang, R., Zheng, Y., Mak, T. W. C., Yu, R., Wong, S. H., Lau, J., & Poon, C. C. Y. (2016) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2635662 · Cited by 383
Towards automatic pulmonary nodule management in lung cancer screening with deep learning
Ciompi, F., Chung, K., van Riel, S. J., Setio, A. A. A., Gerke, P. K., Jacobs, C., Scholten, E. T., Schaefer‐Prokop, C. M., Wille, M. M. W., Marchianò, A. V., et al. (2017) · Scientific Reports · doi:10.1038/srep46479 · Cited by 412
Self-citationMedical image analysis based on deep learning approach
Puttagunta, M. K., & Ravi, S. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10707-4 · Cited by 349
“Pulmonary nodule detection using deep learning has been successfully applied in [82, 108, 136, 157].”
MethodGlioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning
Yang, Y., Yan, L., Zhang, X., Han, Y., Nan, H., Hu, Y., Hu, B., Yan, S., Zhang, J., Cheng, D.-L., et al. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00804 · Cited by 317
Pre-trained convolutional neural networks as feature extractors for tuberculosis detection
Lopes, U. K., & Valiati, J. F. (2017) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2017.08.001 · Cited by 294
Ciompi, F., de Hoop, B., van Riel, S. J., Chung, K., Scholten, E. T., Oudkerk, M., de Jong, P. A., Prokop, M., & Ginneken, B. V. (2015) · Medical Image Analysis · doi:10.1016/j.media.2015.08.001 · Cited by 289
“, 2010; Jacobs et al., 2014). On the other and, a model for the assessment of malignancy of a detected leion, known as the PanCan model, has been recently presented by cWilliams et al. (2013). Several factors are used as input variables of he model, including nodule size, nodule type and presence of spicuation, amongs…”
MethodSelf-citationMasood, A., Sheng, B., Li, P., Hou, X., Wei, X., Qin, J., & Feng, D. (2018) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2018.01.005 · Cited by 292
“There are two main methods of using CNN, either the researcher can model their own CNN architecture or they can use off-the-shelf CNN for acquiring the features [24].”
MethodA deep learning method for classifying mammographic breast density categories
Mohamed, A. A., Berg, W. A., Peng, H., Luo, Y., Jankowitz, R. C., & Wu, S. (2017) · Medical Physics · doi:10.1002/mp.12683 · Cited by 269
“For example, Bram van Ginneken et al. 39 used features extracted from the first fully connected layer of the CNN and then fed these features into a linear support vector machine for classification.”
BackgroundMethodContent-based brain tumor retrieval for MR images using transfer learning
Swati, Z. N. K., Zhao, Q., Kabir, M., Ali, F., Ali, Z., Ahmed, S., & Lu, J. (2019) · IEEE Access · doi:10.1109/access.2019.2892455 · Cited by 246
“This transfer learning and fine-tuning suggested an alternative to [5], [7], [8], [22], [51], and [52], Once the model was successfully optimized and trained, we extracted features of the training and testing datasets from the trained model.”
MethodQuantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats
Napel, S. A., Mu, W., Jardim‐Perassi, B. V., Aerts, H. J. W. L., & Gillies, R. J. (2018) · Cancer · doi:10.1002/cncr.31630 · Cited by 235
“127 Using a similar approach, a multiview CNN model based on a publicly available pretrained CNN-F model 128 was used for estimating a patient’s risk of developing breast cancer.”
MethodGu, Y., Lu, X., Yang, L., Zhang, B., Yu, D., Zhao, Y., Gao, L., Wu, L., & Zhou, T. (2018) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2018.10.011 · Cited by 222
Artificial Intelligence in Healthcare: Review, Ethics, Trust Challenges & Future Research Directions
Kumar, P., Chauhan, S., & Awasthi, L. K. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.105894 · Cited by 259
Radiological images and machine learning: Trends, perspectives, and prospects
Zhang, Z., & Sejdić, E. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.02.017 · Cited by 249
“However, several studies use CNNs to extract features for medical images and achieve good performance in classification [83, 84].”
BackgroundLi, X., Pang, T., Xiong, B., Liu, W., Liang, P., & Wang, T. (2017) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei.2017.8301998 · Cited by 210
“Besides, results from [19] show that integration of CNN-based features with handcrafted features can improve a nodule detection system performance.”
BackgroundDeep Learning for Lung Cancer Nodules Detection and Classification in CT Scans
Riquelme, D., & Akhloufi, M. A. (2020) · AI · doi:10.3390/ai1010003 · Cited by 214
“[27] propose the use of transfer learning from OverFeat [28], a previously trained network for object detection in natural images.”
BackgroundZhen, X., Chen, J., Zhong, Z., Hrycushko, B. A., Zhou, L., Jiang, S. B., Albuquerque, K., & Gu, X. (2017) · Physics in Medicine and Biology · doi:10.1088/1361-6560/aa8d09 · Cited by 191
Farag, A. A., Lü, L., Roth, H. R., Liu, J., Turkbey, E. B., & Summers, R. M. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2624198 · Cited by 185
Lung nodule detection in CT using 3D convolutional neural networks
Huang, X., Shan, J., & Vaidya, V. (2017) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2017.7950542 · Cited by 180
Zheng, S., Guo, J., Cui, X., Veldhuis, R. N. J., Oudkerk, M., & van Ooijen, P. M. A. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2935553 · Cited by 172
Exploring Deep Learning and Transfer Learning for Colonic Polyp Classification
Ribeiro, E. F., Uhl, A., Wimmer, G., & Häfner, M. (2016) · Computational and Mathematical Methods in Medicine · doi:10.1155/2016/6584725 · Cited by 169
“…the medical imaging domain using off-the-shelf CNNs. Examples include the identification and pathology of X-ray and computer tomography modalities [25], automatic classification of pulmonary perifissural nodules [41], pulmonary nodule detection [26], and mammography mass lesion classification [42].”
BackgroundMethodBreast Mass Classification from Mammograms using Deep Convolutional Neural NetworksPreprint
Lévy, D., & Jain, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.00542 · Cited by 229
“An important metric for diagnostic applications is maximizing recall, since the cost of a false negative (patient remaining undiagnosed) is much higer than a false positive (an additional biopsy).”
BackgroundMethodConvolutional neural network transfer for automated glaucoma identification
Orlando, J. I., Prokofyeva, E., del Fresno, M., & Blaschko, M. B. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2255740 · Cited by 151
Pucchio, A., Rathagirishnan, R., Caton, N., Gariscsak, P. J., Del Papa, J., Nabhen, J. J., Vo, V., Lee, W., & Moraes, F. Y. (2022) · BMC Medical Education · doi:10.1186/s12909-022-03896-5 · Cited by 138
“It is likely that artificial intelligence (AI) technologies will be incorporated into clinical practise, with applications such as image-based diagnostics in radiology demonstrating accuracy and efficacy rivalling speciality trained physicians [1–2].”
BackgroundMulti-resolution convolutional networks for chest X-ray radiograph based lung nodule detection
Li, X., Shen, L., Xie, X., Huang, S., Xie, Z., Hong, X., & Yu, J. (2019) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2019.101744 · Cited by 142
Masood, A., Yang, P., Sheng, B., Li, H., Li, P., Qin, J., Lanfranchi, V., Kim, J., & Feng, D. D. (2019) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2019.2955458 · Cited by 142
“Nodules were accurately classified by using the fully connected layers (Fc) of CNN integrated with SVM classifier in [13].”
MethodPolat, H., & Mehr, H. D. (2019) · Applied Sciences · doi:10.3390/app9050940 · Cited by 142
“Results showed that each method could detect nodules by over 70% sensitivity [9].”
MethodComparison of Deep Transfer Learning Strategies for Digital Pathology
Mormont, R., Geurts, P., & Marée, R. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00303 · Cited by 134
“Some of the first applications of deep transfer learning in biomedical imaging were reported in [2, 6, 39] for pulmonary nodule detection in chest x-rays and CT-scans using Decaf and OverFeat.”
BackgroundSegRoot: A high throughput segmentation method for root image analysis
Wang, T., Rostamza, M., Song, Z., Wang, L., McNickle, G. G., Iyer‐Pascuzzi, A. S., Qiu, Z., & Jin, J. (2019) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2019.05.017 · Cited by 125
Ramachandran, S., George, J., Skaria, S., & Varun, V. V. (2018) · SPIE Medical Imaging: Computer-Aided Diagnosis · doi:10.1117/12.2293699 · Cited by 120
“van Ginneken et al [23] uses the popular convolutional neural network architecture, OverFeat, which is a network trained for object detection in natural images, to extract features for nodule detection in computed tomography (CT) scans.”
MethodEnsemble of convolutional neural networks for bioimage classification
Nanni, L., Ghidoni, S., & Brahnam, S. (2018) · Applied Computing and Informatics · doi:10.1016/j.aci.2018.06.002 · Cited by 122
Lung nodule detection and classification from Thorax CT-scan using RetinaNet with transfer learning
Harsono, I. W., Liawatimena, S., & Cenggoro, T. W. (2020) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2020.03.013 · Cited by 126
Improved U-NET network for pulmonary nodules segmentation
Tong, G., Li, Y., Chen, H., Zhang, Q., & Jiang, H. (2018) · Optik · doi:10.1016/j.ijleo.2018.08.086 · Cited by 118
Pre-training on Grayscale ImageNet Improves Medical Image Classification
Xie, Y., & Richmond, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11024-6_37 · Cited by 112
“ConvNet-based algorithms are rapidly replacing traditional machine learning algorithms, based on human-engineered features, for tasks such as image classification [2], object detection [3], and semantic segmentation [4].”
MethodMask R-CNN-Based Detection and Segmentation for Pulmonary Nodule 3D Visualization Diagnosis
Cai, L., Long, T., Dai, Y., & Huang, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2976432 · Cited by 113
Masood, A., Sheng, B., Yang, P., Li, P., Li, H., Kim, J., & Feng, D. D. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2972918 · Cited by 110
“The effectiveness of mRFCN is verified by comparing with existing methods CNN [12], MTANNs [6], FCN [13], and MC-CNN [14]; the results are depicted in Table II.”
BackgroundMethodDeep Learning Trends for Focal Brain Pathology Segmentation in MRI
Havaei, M., Guizard, N., Larochelle, H., & Jodoin, P. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-50478-0_6 · Cited by 103
“The first one is to generate features from the base model and then train a classifier such as SVM or logistic regression with those generated features [7],[28], [5].”
MethodLung nodule detection using 3D convolutional neural networks trained on weakly labeled data
Anirudh, R., Thiagarajan, J. J., Bremer, P., & Kim, H. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2214876 · Cited by 110
“Next, Ginneken et al.(5) have shown promising results using an off-the-shelf convolutional neural network (CNN), one that is pre-trained for an image recognition task.”
BackgroundMultiple Feature Integration for Classification of Thoracic Disease in Chest Radiography
Ho, T. K., & Gwak, J. (2019) · Applied Sciences · doi:10.3390/app9194130 · Cited by 96
“These studies motivate the extended applications of CNNs or ensemble models on bioimage datasets [33,34] as feature extractors.”
BackgroundEnsemble Learners of Multiple Deep CNNs for Pulmonary Nodules Classification Using CT Images
Zhang, B., Qi, S., Monkam, P., Li, C., Yang, F., Yao, Y., & Qian, W. (2019) · IEEE Access · doi:10.1109/access.2019.2933670 · Cited by 99
“Using deep CNNs as tools of feature extraction, the traditional machine learning (ML) algorithms are applied to fuse the hand-crafted features and CNN learned features and give the final prediction [11], [12].”
MethodAntropova, N. O., Abé, H., & Giger, M. L. (2018) · Journal of medical imaging · doi:10.1117/1.jmi.5.1.014503 · Cited by 97
Khosravan, N., Çelik, H., Türkbey, B., Jones, E. C., Wood, B. J., & Bağcı, U. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.10.010 · Cited by 94
“In very recent frameworks, Convolutional Neural Networks (CNN) have been used for feature extraction and off-the-shelf clas-sification methods in most CAD systems (van Ginneken et al. (2015); Ciompi et al. (2015); Tsehay et al. (2017a); Le et al. (2017)).”
Method3D deep learning for detecting pulmonary nodules in CT scans
Gruetzemacher, R., Gupta, A., & Paradice, D. (2018) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocy098 · Cited by 95
VisNet: Deep Convolutional Neural Networks for Forecasting Atmospheric Visibility
Palvanov, A., & Cho, Y. I. (2019) · Sensors · doi:10.3390/s19061343 · Cited by 93
“As shown in Table 1, the task of classification in this study involves distinguishing 41, 21, and 7 classes of images using a single model described in Figure 1.”
BackgroundMethodBreast Cancer Detection Using Transfer Learning in Convolutional Neural Networks
Guan, S., & Loew, M. H. (2017) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2017.8457948 · Cited by 91
“Currently, CNN has been applied to medical image classification in three major ways: 1) training CNN from scratch [16]–[18]; 2) using pre-trained CNN model to extract features from medical images [19]–[21] and 3) fine-tuning pretrained CNN model on medical images [22]–[24].”
MethodBanerjee, I., Crawley, A., Bhethanabotla, M., Daldrup-Link, H. E., & Rubin, D. L. (2017) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2017.05.002 · Cited by 90
Li, H., Giger, M. L., Huynh, B. Q., & Antropova, N. O. (2017) · Journal of medical imaging · doi:10.1117/1.jmi.4.4.041304 · Cited by 87
Pulmonary nodule detection in medical images: A survey
Zhang, J., Xia, Y., Cui, H., & Zhang, Y. (2018) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2018.01.011 · Cited by 83
Zhou, Z., Gou, F., Tan, Y., & Wu, J. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3198509 · Cited by 82
“Ginneken [12] et al. introduced transfer learning into nodule detection.”
BackgroundPulmonary Nodule Detection Based on CT Images Using Convolution Neural Network
Jin, X., Zhang, Y., & Jin, Q.-L. (2016) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2016.1053 · Cited by 81
Effects of Hypertension, Diabetes, and Smoking on Age and Sex Prediction from Retinal Fundus Images
Kim, Y. D., Noh, K. J., Byun, S. J., Lee, S., Kim, T., Sunwoo, L., Lee, K. J., Kang, S., Park, K. H., & Park, S. J. (2020) · Scientific Reports · doi:10.1038/s41598-020-61519-9 · Cited by 86
Lung Nodule Classification on Computed Tomography Images Using Deep Learning
Naik, A., & Edla, D. R. (2020) · Wireless Personal Communications · doi:10.1007/s11277-020-07732-1 · Cited by 81
“Combination of high level features such as lobulation, margin, calcification, spiculation, sphericity and CNN features improves the classification accuracy [72, 136, 160].”
BackgroundMethodInfluentialLearning to Read Chest X-Ray Images from 16000+ Examples Using CNN
Dong, Y. C., Pan, Y., Zhang, J., & Xu, W. (2017) · IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies · doi:10.1109/chase.2017.59 · Cited by 77
“However, most recent CAD systems depends on the high resolution magnetic resonance imaging (MRI) or computed tomograph (CT) images, while ignoring the plain old X-rays that are much more widely utilized.”
BackgroundMethodInfluentialAutomated Pneumonia Diagnosis using a Customized Sequential Convolutional Neural Network
Siddiqi, R. (2019) · International Conference on Deep Learning Technologies (ICDLT) · doi:10.1145/3342999.3343001 · Cited by 78
Abidin, A. Z., Deng, B., DSouza, A. M., Nagarajan, M., Coan, P., & Wismüller, A. (2018) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2018.01.008 · Cited by 79
Lung Cancer Detection and Classification Based on Alexnet CNN
Agarwal, A., Patni, K., & Rajeswari, D. (2021) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces51350.2021.9489033 · Cited by 76
Towards radiologist-level cancer risk assessment in CT lung screening using deep learning
Trajanovski, S., Mavroeidis, D., Swisher, C. L., Gebre, B. G., Veeling, B. S., Wiemker, R., Klinder, T., Tahmasebi, A., Regis, S. M., Wald, C., et al. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.101883 · Cited by 79
Building medical image classifiers with very limited data using segmentation networks
Wong, K. C. L., Syeda-Mahmood, T. F., & Moradi, M. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.07.010 · Cited by 72
Bansal, G., Chamola, V., Narang, P., Kumar, S., & Raman, S. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2019.1164 · Cited by 67
“Studies [26, 39, 40] show XGBoost dominates classification of structured datasets.”
BackgroundMethodManzanera, O. M., Meles, S. K., Leenders, K. L., Renken, R. J., Pagani, M., Arnaldi, D., Nobili, F. M., Obeso, J. A., Rodríguez‐Oroz, M., Morbelli, S. D., et al. (2019) · International Journal of Neural Systems · doi:10.1142/s0129065719500102 · Cited by 63
Liu, S., Xie, Y., Jirapatnakul, A. C., & Reeves, A. P. (2017) · Journal of medical imaging · doi:10.1117/1.jmi.4.4.041308 · Cited by 63
Understanding Clinical Mammographic Breast Density Assessment: a Deep Learning Perspective
Mohamed, A. A., Luo, Y., Peng, H., Jankowitz, R. C., & Wu, S. (2017) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-017-0022-2 · Cited by 63
“In biomedical imaging analyses, deep learning demonstrated impressive capabilities in thoraco-abdominal lymph node detection and interstitial lung disease classification [7], chest pathology identification [8, 9], real-time 2D/3D image registration [10], mammographic lesion detection and diagnosis [11], image segmenta…”
BackgroundA Hybrid CNN and RBF-Based SVM Approach for Breast Cancer Classification in Mammograms
Alkhaleefah, M., & Wu, C.-C. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00159 · Cited by 59
“Another work [6] used the features from a pre-trained OverFeat CNN that was trained for object detection in nat-ural images, for nodule detection in computed tomography scans.”
MethodMorphoCluster: Efficient Annotation of Plankton Images by Clustering
Schröder, S., Kiko, R., & Koch, R. (2020) · Sensors · doi:10.3390/s20113060 · Cited by 70
Ravishankar, H., Prabhu, S. M., Vaidya, V., & Singhal, N. (2016) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2016.7493382 · Cited by 58
“CNNs have also been recently explored for medical imaging tasks, such as detection of nodules in CTs [7] and landmark points in 3-D MRIs [8].”
MethodLiu, X., Fu, T., Pan, Z., Liu, D., Hu, W., Liu, J., & Zhang, K. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2856276 · Cited by 58
“Recent work [36], [37] suggested that hand-designed features and deep features are complementary and combining them can generate more powerful representation.”
BackgroundConvolutional neural networks for lung cancer screening in computed tomography (CT) scans
Rao, P., Pereira, N. A., & Srinivasan, R. (2016) · International Conference on Contemporary Computing and Informatics (IC3I) · doi:10.1109/ic3i.2016.7918014 · Cited by 58
“hand crafted features which are tailored to the particular task at hand [1, 2].”
BackgroundDeepLN: A framework for automatic lung nodule detection using multi-resolution CT screening images
Xu, X., Wang, C., Guo, J., Yang, L., Bai, H., Li, W., & Zhang, Y. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.105128 · Cited by 56
Sharma, S., & Mehra, R. (2019) · The Visual Computer · doi:10.1007/s00371-019-01768-6 · Cited by 57
Nahmias, D., Cohen, A., Nissim, N., & Elovici, Y. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.01.003 · Cited by 50
Lung Nodule Detection in CT Images Using a Raw Patch-Based Convolutional Neural Network
Wang, Q., Shen, F., Shen, L., Huang, J., & Sheng, W. (2019) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-019-00221-3 · Cited by 50
“According to the Ginneken’s work [31], it is an arduous task to classify adhesion pulmonary nodules attached lung wall because lung wall J Digit Imaging (2019) 32:971–979 972”
BackgroundAutomated lung cancer diagnosis using three-dimensional convolutional neural networks
Pérez, G., & Arbeláez, P. (2020) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-020-02197-7 · Cited by 48
“In the case of deep learning strategies, few methods added convolutional neural networks (CNN) in addition to handcrafted features or use CNN to extract features and classify using a different methodology [5, 49].”
MethodQuality and content analysis of fundus images using deep learning
Chalakkal, R. J., Abdulla, W. H., & Thulaseedharan, S. S. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.03.019 · Cited by 52
Decision and feature level fusion of deep features extracted from public COVID-19 data-sets
İlhan, H. O., Serbes, G., & Aydın, N. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02945-8 · Cited by 51
“otential for having benefit from knowledge transfer in medical data sets. For instance, in [58], a pre-trained CNN was employed as a feature extractor with the aim of chest pathology identification. In [59], pre-trained CNN based features have shown improved performance as they were fused with traditional handcrafted fe…”
MethodGuo, Z., Zhao, L., Yuan, J., & Yu, H. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3131671 · Cited by 47
Gupta, A., Saar, T., Märtens, O., & Moullec, Y. L. (2018) · Medical Physics · doi:10.1002/mp.12746 · Cited by 45
Sun, L., Wang, Z., Pu, H., Yuan, G., Guo, L., Pu, T., & Peng, Z. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104357 · Cited by 45
Wang, W., & Chakraborty, G. (2020) · Applied Intelligence · doi:10.1007/s10489-020-01990-z · Cited by 45
“For nodule detection, during 2015-16, there are works based on 2D images [8, 9], and more recently 3D images are used with higher sensitivity [10–14].”
BackgroundCao, P., Liu, X., Yang, J., Zhao, D., Li, W., Huang, M., & Zai͏̈ane, O. R. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.11.007 · Cited by 39
A novel biomedical image indexing and retrieval system via deep preference learning
Pang, S., Orgun, M. A., & Yu, Z. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.02.003 · Cited by 40
Image Restoration for Low-Dose CT via Transfer Learning and Residual Network
Zhong, A., Li, B., Luo, N., Xu, Y. X., Zhou, L., & Zhen, X. (2020) · IEEE Access · doi:10.1109/access.2020.3002534 · Cited by 37
“More-over, ImageNet-pretrained CNNs have been widely used for object detection and segmentation, such as chest pathology identification [39]–[42].”
MethodCui, X., Zheng, S., Heuvelmans, M. A., Du, Y., Sidorenkov, G. A., Fan, S., Li, Y., Xie, Y., Zhu, Z., Dorrius, M. D., et al. (2021) · European Journal of Radiology · doi:10.1016/j.ejrad.2021.110068 · Cited by 43
Ahn, E., Kumar, A., Kim, J., Li, C., Feng, D. D., & FULHAM, M. J. (2016) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2016.7493400 · Cited by 36
“The domain transferred CNNs (DT-CNNs), achieved good performance in image classification [9-11] because they learned generic image features from nonmedical images and then quantified those generic features within medical data.”
BackgroundFeature Representation Using Deep Autoencoder for Lung Nodule Image Classification
Mao, K., Tang, R., Wang, X., Zhang, W., & Wu, H. (2018) · Complexity · doi:10.1155/2018/3078374 · Cited by 36
Yin, X.-X., Hadjiloucas, S., Zhang, Y., & Tian, Z. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106510 · Cited by 36
Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network
Diniz, P. H. B., Valente, T. L. A., Diniz, J. O. B., Silva, A. C., Gattass, M., Ventura, N., Muniz, B. C., & Gasparetto, E. L. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.04.011 · Cited by 34
Image-based surrogate biomarkers for molecular subtypes of colorectal cancer
Popovici, V. C., Budínská, E., Dušek, L., Kozubek, M., & Bosman, F. T. (2017) · Bioinformatics · doi:10.1093/bioinformatics/btx027 · Cited by 30
Fu, L., Ma, J., Ren, Y., Han, Y. S., & Zhao, J. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2253995 · Cited by 33
Metadata
- Authors
- van Ginneken, B., Setio, A. A. A., Jacobs, C., & Ciompi, F.
- Affiliations
- Radboud University Medical Center (NL)
- Venue
- 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)
- Publisher
- IEEE
- Published
- 2015-04
- Pages
- 286-289
- OpenAlex
- W1516595210
- Cited by
- 278
- References
- 13
- Citations by year
- 2026: 3 · 2025: 5 · 2024: 11 · 2023: 9 · 2022: 17 · 2021: 29 · 2020: 48 · 2019: 51 · 2018: 39 · 2017: 43 · 2016: 20 · 2015: 3
- FWCI
- 19.72
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Symposium on Biomedical Imaging (ISBI) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Lung Cancer Diagnosis and Treatment
- Keywords
- lung nodule detection, convolutional neural network features, transfer learning, computed tomography, LIDC, volumetric medical data, feature extraction, support vector machine, object detection
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
