Filters








753 Hits in 6.0 sec

A Comprehensive Review of Computer-Aided Diagnosis of Pulmonary Nodules based on Computed Tomography Scans

Wenming Cao, Rui Wu, Guitao Cao, Zhihai He
2020 IEEE Access  
The experimental benchmarks for nodule analysis are first described and summarized, covering public datasets of lung CT scans, commonly used evaluation metrics, and various medical competitions.  ...  Therefore, with the explosive growth of CT data, it is of great clinical significance to exploit an effective Computer-Aided Diagnosis (CAD) system for radiologists on automatic nodule analysis.  ...  [61] proposed a multi-task 2D CNN with Margin Ranking loss (MTMR-Net) to construct the CADx system for nodule analysis.  ... 
doi:10.1109/access.2020.3018666 fatcat:efatgjz7srg5vjfqrx75ttyzbu

Risk Stratification of Lung Nodules Using 3D CNN-Based Multi-task Learning [chapter]

Sarfaraz Hussein, Kunlin Cao, Qi Song, Ulas Bagci
2017 Lecture Notes in Computer Science  
Risk stratification of lung nodules is a task of primary importance in lung cancer diagnosis.  ...  Moreover, we also acquire the task dependent feature representation for six high-level nodule attributes and fuse this complementary information via a Multi-task learning (MTL) framework.  ...  [7] first segmented the lung nodules using appearance-based models and used spherical harmonic analysis to perform shape analysis. The final step was the classification using k-nearest neighbor.  ... 
doi:10.1007/978-3-319-59050-9_20 fatcat:oq23wasdgrggpevudeg5c5a3ei

Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches

Sarfaraz Hussein, Pujan Kandel, Candice W. Bolan, Michael B. Wallace, Ulas Bagci
2019 IEEE Transactions on Medical Imaging  
Motivated by the radiologists' interpretations of the scans, we then show how to incorporate task-dependent feature representations into a CAD system via a graph-regularized sparse multi-task learning  ...  Our first approach is based on supervised learning for which we demonstrate significant gains with deep learning algorithms, particularly by utilizing a 3D convolutional neural network and transfer learning  ...  Following up on the application of deep learning for almost all tasks in the visual domain, we studied the influence of different pre-trained deep networks for lung nodule classification.  ... 
doi:10.1109/tmi.2019.2894349 pmid:30676950 fatcat:woorhrucqjbcxhulknvh2irjta

Attention-Enhanced Cross-Task Network for Analysing Multiple Attributes of Lung Nodules in CT [article]

Xiaohang Fu, Lei Bi, Ashnil Kumar, Michael Fulham, Jinman Kim
2021 arXiv   pre-print
Current state-of-the-art methods that score multiple attributes rely on deep learning-based multi-task learning (MTL) schemes.  ...  Our model also performs competitively when repurposed for benign-malignant classification.  ...  [12] reported Multi-Task deep model with Margin Ranking loss (MTMR-Net), which leveraged the Siamese network architecture with a 152-layer ResNet [15] backbone to simultaneously score attributes and  ... 
arXiv:2103.03931v2 fatcat:qxpewluygfbc5d4ueti5fun27i

A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis [article]

Xiaozheng Xie, Jianwei Niu, Xuefeng Liu, Zhengsu Chen, Shaojie Tang, Shui Yu
2020 arXiv   pre-print
Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area.  ...  In this survey, we summarize the current progress on integrating medical domain knowledge into deep learning models for various tasks, such as disease diagnosis, lesion, organ and abnormality detection  ...  The multi-task learning (MTL) framework is proposed to incorporate the above information into the main task of lung nodule classification.  ... 
arXiv:2004.12150v3 fatcat:2cqumcjkizgivmo67reznxacie

A survey of pulmonary nodule detection, segmentation and classification in computed tomography with deep learning techniques

Jianrong Wu, Tianyi Qian
2019 Journal of Medical Artificial Intelligence  
Acknowledgements It is so appreciated for support and help from workmates in the project of Miying in Tencent. Footnote Conflicts of Interest: J Wu and T Qian are Tencent employees.  ...  LUNA16 The LUNA16 dataset was created for the challenge of LUng Nodule Analysis 2016 including 888 CT scans, which were gathered from LIDC-IDRI with slice thickness less than 3mm.  ...  (37) propose a method for pulmonary nodule detection utilizing multi-group patches cut out from the lung images.  ... 
doi:10.21037/jmai.2019.04.01 fatcat:s44bw5iwpjf6bpaxqpwi44ysmu

Multi-Level Cross Residual Network for Lung Nodule Classification

Juan Lyu, Xiaojun Bi, Sai Ho Ling
2020 Sensors  
nodules) of lung nodules, respectively.  ...  To illustrate the performance of ML-xResNet, we apply the model to process ternary classification (benign, indeterminate, and malignant lung nodules) and binary classification (benign and malignant lung  ...  Then, they applied a Siamese network with a margin loss to learning to rank the most malignancy-related features to improve the distinguishing ability of the network.  ... 
doi:10.3390/s20102837 pmid:32429401 fatcat:wfgbc4r3bzcwlgz7hasv4yz4na

Knowledge-based Collaborative Deep Learning for Benign-Malignant Lung Nodule Classification on Chest CT

Yutong Xie, Yong Xia, Jianpeng Zhang, Yang Song, Dagan Feng, Michael Fulham, Weidong Cai
2018 IEEE Transactions on Medical Imaging  
The penalty loss function is used for better reduction of the false negative rate with a minimal effect on the overall performance of the MV-KBC model.  ...  In this paper, we propose a multi-view knowledge-based collaborative (MV-KBC) deep model to separate malignant from benign nodules using limited chest CT data.  ...  [31] proposed 3D CNN multi-task learning for lung nodule characterization.  ... 
doi:10.1109/tmi.2018.2876510 pmid:30334786 fatcat:vstymhfyijgshfsk24b6ckrbna

Diagnose Like a Radiologist: Hybrid Neuro-Probabilistic Reasoning for Attribute-Based Medical Image Diagnosis

Gangming Zhao, Quanlong Feng, Chaoqi Chen, Zhen Zhou, Yizhou Yu
2021 IEEE Transactions on Pattern Analysis and Machine Intelligence  
On the LIDC-IDRI benchmark dataset for benign-malignant classification of pulmonary nodules in CT images, our method achieves a new state-of-the-art accuracy of 95.36% and an AUC of 96.54%.  ...  We have successfully applied our hybrid reasoning algorithm to two challenging medical image diagnosis tasks.  ...  'B' And 'M' are the Number of Benign and Malignant Lung Nodules Used for Model Training.  ... 
doi:10.1109/tpami.2021.3130759 pmid:34822325 fatcat:obh3bcyf65a6dcnc47svv23zpu

The Pitfalls of Sample Selection: A Case Study on Lung Nodule Classification [article]

Vasileios Baltatzis, Kyriaki-Margarita Bintsi, Loic Le Folgoc, Octavio E. Martinez Manzanera, Sam Ellis, Arjun Nair, Sujal Desai, Ben Glocker, Julia A. Schnabel
2021 arXiv   pre-print
In lung nodule classification, for example, many works report results on the publicly available LIDC dataset.  ...  with respect to very simple baseline methods, highlighting that the selected data distribution may play an even more important role than the model architecture.  ...  1040 84.20 NoduleX [3] 394 270 93.20 Multi-crop CNN [17] 880 495 87.14 Multi-task w/ margin ranking loss [8] 972 450 93.50  ... 
arXiv:2108.05386v1 fatcat:l7ahpm25jzg4zjoub2rhppwrxu

Combating Ambiguity for Hash-code Learning in Medical Instance Retrieval [article]

Jiansheng Fang, Huazhu Fu, Dan Zeng, Xiao Yan, Yuguang Yan, Jiang Liu
2021 arXiv   pre-print
The segmentation loss allows exploring subtle spatial differences for good spatial-discriminability while the classification loss utilizes class-aware semantic information for good semantic-separability  ...  Y-Net can learn highly discriminative convolutional features by unifying the pixel-wise segmentation loss and classification loss.  ...  All deep models are trained from scratch with 500 epochs. It spends approximately 3 hours for training our Y-Net. The pixel-wise cross-entropy loss is used in the segmentation task.  ... 
arXiv:2105.08872v1 fatcat:5ga4eudoorchja5xwswm453jje

Attention-Guided Feature Extraction and Multiscale Feature Fusion 3D ResNet for Automated Pulmonary Nodule Detection

Guanglu Zhang, Hongjun Zhang, Yuhua Yao, Qiuhui Shen
2022 IEEE Access  
Automatic detection of pulmonary nodules is critical for the early diagnosis and prevention of lung cancer. Computed tomography (CT) is an effective and economical lung cancer detection method.  ...  Therefore, the automatic localization of pulmonary nodules in CT images is a challenging task.  ...  LOSS FUNCTION Candidate nodule detection and nodule classification prediction share a 3D residual network, and the lung nodule detection model is a multi-task learning model.Our loss function is composed  ... 
doi:10.1109/access.2022.3182104 fatcat:l33qo4oal5f4vfo6i5gmbm536i

Ensemble Learning of Multiple-View 3D-CNNs Model for Micro-Nodules Identification in CT Images

Patrice Monkam, Shouliang Qi, Mingjie Xu, Haoming Li, Fangfang Han, Yueyang Teng, Wei Qian
2019 IEEE Access  
The results demonstrate that developing an automatic system for discriminating between micro-nodules and non-nodules in CT images is feasible, which extends lung cancer studies to micro-nodules.  ...  Then, five distinct 3D-CNN models are built and implemented on one size of the nodule candidates.  ...  ACKNOWLEDGMENT The authors would like to express their sincere gratitude to the National Cancer Institute and the Foundation for the National Institutes of Health for their critical role in the creation  ... 
doi:10.1109/access.2018.2889350 fatcat:gzqktx4h7nhbfdkidy7h3uxztm

Cascaded-Recalibrated Multiple Instance Deep Model for Pathologic-Level Lung Cancer Prediction in CT Images

Qingfeng Wang, Ying Zhou, Jun Huang, Zhiqin Liu, Weidong Zhang, Qiyu Liu, Jie-Zhi Cheng, Carmen De Maio
2022 Computational Intelligence and Neuroscience  
MIL model provides substantial improvements for the pathologic-level lung cancer prediction by using the CT images.  ...  This cascaded-recalibrated MIL deep model incorporates a cascaded recalibration mechanism at the nodule level and attribute level, which fuses the informative attribute features into nodule embeddings  ...  University of Science and Technology under Grants 19zx7143 and 20zx7137, in part by the Bethune Charitable Foundation, under Grant J202002E001. e Grants 19zx7143 and 20zx7137 provided financial support for  ... 
doi:10.1155/2022/9469234 pmid:35733559 pmcid:PMC9208922 fatcat:e6owqfad25hypfwyl45ro7ntly

A survey on deep learning in medical image analysis

Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen A.W.M. van der Laak, Bram van Ginneken, Clara I. Sánchez
2017 Medical Image Analysis  
We survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks and provide concise overviews of studies per application area.  ...  This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year.  ...  Acknowledgments The authors would like to thank members of the Diagnostic Image Analysis Group for discussions and suggestions.  ... 
doi:10.1016/j.media.2017.07.005 pmid:28778026 fatcat:esbj72ftwvbgzh6jgw367k73j4
« Previous Showing results 1 — 15 out of 753 results