Filters








858 Hits in 5.7 sec

A Dataset of Pulmonary Lesions With Multiple-Level Attributes and Fine Contours

Ping Li, Xiangwen Kong, Johann Li, Guangming Zhu, Xiaoyuan Lu, Peiyi Shen, Syed Afaq Ali Shah, Mohammed Bennamoun, Tao Hua
2021 Frontiers in Digital Health  
In this paper, we introduce a dataset of pulmonary lesions for designing the computer-aided diagnosis (CAD) systems. The dataset has fine contour annotations and nine attribute annotations.  ...  We define the structure of the dataset in detail, and then discuss the relationship of the attributes and pathology, and the correlation between the nine attributes with the chi-square test.  ...  CONCLUSION This paper presents a dataset of lung lesions with fine contour annotation and attribute and explores the correlation between the attributes of the dataset.  ... 
doi:10.3389/fdgth.2020.609349 pmid:34713070 pmcid:PMC8521952 fatcat:fer5h5jlr5hejetfmhyafpljpi

A Systematic Collection of Medical Image Datasets for Deep Learning [article]

Johann Li, Guangming Zhu, Cong Hua, Mingtao Feng, BasheerBennamoun, Ping Li, Xiaoyuan Lu, Juan Song, Peiyi Shen, Xu Xu, Lin Mei, Liang Zhang (+2 others)
2021 arXiv   pre-print
Thus, as comprehensive as possible, this paper provides a collection of medical image datasets with their associated challenges for deep learning research.  ...  The lack of data in the medical imaging field creates a bottleneck for the application of deep learning to medical image analysis.  ...  Acknowledgments We thanks for the projects of National Natural Science Foundation of China (62072358), Zhejiang University special scientific research fund for COVID-19 preverntion and control, National  ... 
arXiv:2106.12864v1 fatcat:bjzkgce2xvaexmb6cdznws7fye

Classification and Segmentation of Pulmonary Lesions in CT Images Using a Combined VGG-XGBoost Method, and an Integrated Fuzzy Clustering-Level Set Technique [article]

Niloofar Akhavan Javan, Ali Jebreili, Babak Mozafari, Morteza Hosseinioun, S. AmirAli Gh. Ghahramani
2022 arXiv   pre-print
Finally, if a lesion is detected in the CT-scan image, it is segmented using a hybrid approach based on Fuzzy Clustering and Level Set.  ...  However, lung illness diagnosis is time-intensive and requires the expertise of a pulmonary disease specialist, subject to a significant rate of inaccuracy.  ...  Mahjoub and Behsazteb Medical Imaging Center for providing local CT-scan images of patients with human lung problems and providing diverse comments and reports on these images, which enabled us not only  ... 
arXiv:2101.00948v2 fatcat:lb7ss37idfa4joferliv5lddi4

CT Morphological Features Integrated With Whole-Lesion Histogram Parameters to Predict Lung Metastasis for Colorectal Cancer Patients With Pulmonary Nodules

TingDan Hu, ShengPing Wang, Xiangyu E, Ye Yuan, Lv Huang, JiaZhou Wang, DeBing Shi, Yuan Li, WeiJun Peng, Tong Tong
2019 Frontiers in Oncology  
Methods: Our study enrolled 196 CRC patients with pulmonary nodules (136 in the training dataset and 60 in the validation dataset).  ...  efficacy of single-slice and whole-lesion histogram analysis.  ...  This study has received funding by the National Natural Science Foundation of China (Grant No. 81971687) and the Shanghai Committee of Science and Technology of China (Grant No. 19YF1409900).  ... 
doi:10.3389/fonc.2019.01241 pmid:31803619 pmcid:PMC6877751 fatcat:otdi2ilqbjawpilzmdr5uves74

Interleaved text/image Deep Mining on a large-scale radiology database

Hoo-Chang Shin, Le Lu, Lauren Kim, Ari Seff, Jianhua Yao, Ronald M. Summers
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
-Using the most relevant weights (document-level-h2) task model helps the curve to converge more quickly and reach a higher accuracy, but the final performance difference is less than what previously observed  ...  The sentence-level image-topic classification accuracy plots using variations of AlexNet 8-layers show that -It is beneficial to start from ImageNet CNN weights.  ...  Benefits of using ImageNet dataset as pre-training for this task with medical images and improvements of fine-tuning from CNN neural networks of similar tasks (e.g., from document-level-h1 CNN model to  ... 
doi:10.1109/cvpr.2015.7298712 dblp:conf/cvpr/ShinLKSYS15 fatcat:pjq3duo4rbeplcjmuhzyg6nmcy

Comparative evaluation of conventional and deep learning methods for semi-automated segmentation of pulmonary nodules on CT

Francesco Bianconi, Mario Luca Fravolini, Sofia Pizzoli, Isabella Palumbo, Matteo Minestrini, Maria Rondini, Susanna Nuvoli, Angela Spanu, Barbara Palumbo
2021 Quantitative Imaging in Medicine and Surgery  
Of the 2,309 nodules, 1,418 (61.4%) were benign and 891 (38.6%) were malignant, with 884 (99.21%) papillary carcinomas.  ...  This study included 2,309 thyroid nodules in 1,697 patients with histopathological and cytopathological diagnoses of benign and malignant nodules from January 2018 to August 2020.  ...  The big promise of radiomics is to offer a non-invasive, full-field procedure for the characterisation of pulmonary lesions.  ... 
doi:10.21037/qims-20-1365 pmid:34341735 pmcid:PMC8245934 fatcat:5ooe3zjdd5h4tkyrpobebmqwli

The application of conventional us and transthoracic ultrasound elastography in evaluating peripheral pulmonary lesions

Hong Wei, Yuchan Lu, Qiao Ji, Hang Zhou, Xianli Zhou
2018 Experimental and Therapeutic Medicine  
For conventional US, a lesion diameter ≥5 cm, irregular contour, presence of air bronchogram and non-abundant vascularity were predictive factors of malignancy (P<0.05).  ...  For ARFIimaging scores, an elasticity score of 3 or greater was predictive of malignancy, with a sensitivity of 83.6% (46/55) and a specificity of 52.8% (19/36).  ...  Funding The present study was funded by the Scientific Research of Heilongjiang Province Health and Family Planning Commission (grant no. 2014-334).  ... 
doi:10.3892/etm.2018.6335 pmid:30116370 pmcid:PMC6090271 fatcat:qvc7tqzckbcifjezf67isze5py

Multicriteria 3D PET image segmentation

Francisco Javier Alvarez Padilla, Eloise Grossiord, Barbara Romaniuk, Benoit Naegel, Camille Kurtz, Hugues Talbot, Laurent Najman, Romain Guillemot, Dimitri Papathanassiou, Nicolas Passat
2015 2015 International Conference on Image Processing Theory, Tools and Applications (IPTA)  
The analysis of images acquired with Positron Emission Tomography (PET) is challenging.  ...  Preliminary results on synthetic and real images confirm the relevance of this methodology, both as a segmentation approach and as an experimental framework for criteria evaluation.  ...  Left: CT image, with a tissue-based color rendering. Right: PET image (FDG), with a pulmonary tumor. Fig. 3 . 3 Left: initial phantom (2D slice). Right: segmentation result.  ... 
doi:10.1109/ipta.2015.7367162 dblp:conf/ipta/PadillaGRNKTNGP15 fatcat:ezvp7jvy6ncsth4uhhwxuts3qq

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.  ...  Besides prediction of malignancy, the areas of detected nodules and the semantic high-level attributes could be provided.  ...  (36) integrated a set of 3D CNNs with different sizes of receptive field to involve multi-level contextual information around pulmonary nodules.  ... 
doi:10.21037/jmai.2019.04.01 fatcat:s44bw5iwpjf6bpaxqpwi44ysmu

Attributed Abnormality Graph Embedding for Clinically Accurate X-Ray Report Generation [article]

Sixing Yan, William K. Cheung, Keith Chiu, Terence M. Tong, Charles K. Cheung, Simon See
2022 arXiv   pre-print
A gating mechanism is adopted and integrated with various decoders for the generation.  ...  In this paper, we introduce a novel fined-grained knowledge graph structure called an attributed abnormality graph (ATAG).  ...  model [43] with an adaptive attention module and a one-level LSTM decoder, SentSAT [12] with a two-level LSTM decoder, CoAtt [11] with additional label features in addition to SentSAT, and SentSAT  ... 
arXiv:2207.01208v2 fatcat:qqheb2oe6zffjgilqwb2hjqoia

An RDAU-NET model for lesion segmentation in breast ultrasound images

Zhemin Zhuang, Nan Li, Alex Noel Joseph Raj, Vijayalakshmi G. V. Mahesh, Shunmin Qiu, Varenyam Achal
2019 PLoS ONE  
The localization and segmentation of the lesions in breast ultrasound (BUS) images are helpful for clinical diagnosis of the disease.  ...  The experimental results illustrate that the proposed RDAU-NET model can accurately segment breast lesions when compared to other deep learning models and thus has a good prospect for clinical diagnosis  ...  Acknowledgments We would like to acknowledge the following for providing the Ultrasound Datasets. Author Contributions Conceptualization: Zhemin Zhuang, Nan Li. Mahesh.  ... 
doi:10.1371/journal.pone.0221535 pmid:31442268 pmcid:PMC6707567 fatcat:wgjvukzutvealm7zzpmkfzhzgy

State-of-the-art review on deep learning in medical imaging

Jasjit S Suri
2019 Frontiers in Bioscience  
We would like to thank the publishers for approving usage of images in our paper. We would like to thank MediaLab Asia, DEITY for their encouragement and support.  ...  Multiple layers of convolution, ReLu and pooling are applied to extract high level features.  ...  There are several complications in computational estimation of brain lesion i.e., they can occur at multiple sites, shape and size of lesions vary and their intensity profiles overlap with healthy parts  ... 
doi:10.2741/4725 fatcat:lh5b3okh4jcq5aogjfowjfdaqy

Analysis of Tracheobronchial Diverticula Based on Semantic Segmentation of CT Images via the Dual-Channel Attention Network

Maoyi Zhang, Changqing Ding, Shuli Guo
2022 Frontiers in Public Health  
Since the area of TD lesion is small and similar to surrounding organs, we designed the atrous spatial pyramid pooling (ASPP) and attention mechanisms, which can efficiently complete the segmentation of  ...  Tracheobronchial diverticula (TD) is a common cystic lesion that can be easily neglected; hence accurate and rapid identification is critical for later diagnosis.  ...  In addition, considering the smallness of the lesion and its complex background, a two-channel network was designed to achieve the segmentation task with both rough and fine-grained results, which consisted  ... 
doi:10.3389/fpubh.2021.813717 pmid:35071176 pmcid:PMC8766980 fatcat:nl5qq75xnrhfzjixgfwcbxcgvy

A CT-Based Radiomic Signature for the Differentiation of Pulmonary Hamartomas from Carcinoid Tumors

Ayten Kayi Cangir, Kaan Orhan, Yusuf Kahya, Ayse Uğurum Uğurum Yücemen, İslam Aktürk, Hilal Ozakinci, Aysegul Gursoy Gursoy Coruh, Serpil Dizbay Dizbay Sak
2022 Diagnostics  
Radiomics features may be used to differentiate PHs from PCTs with high levels of accuracy, even without the presence of fat on the CT.  ...  In this study, CT radiomic features are evaluated to differentiate pulmonary hamartomas (PHs) from pulmonary carcinoid tumors (PCTs). A total of 138 patients (78 PCTs and 60 PHs) were evaluated.  ...  The clinical information of the patients remained blinded from them and was manually delineated for all lesions. The senior clinicians reviewed all contours (KO, AGÇ) (Figure 1 ).  ... 
doi:10.3390/diagnostics12020416 pmid:35204507 pmcid:PMC8871366 fatcat:elgk6hz26fhdnfjh4oai3lnwqa

Editorial: Machine Learning for Non/Less-Invasive Methods in Health Informatics

Kun Qian, Liang Zhang, Kezhi Li, Juan Liu
2021 Frontiers in Digital Health  
Li et al. built a dataset of pulmonary lesions with multiple-level attributes and fine contours.  ...  A family of multi-task and multi-label learning classifiers was employed to represent different levels of eye diseases.  ...  Copyright © 2021 Qian, Zhang, Li and Liu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY).  ... 
doi:10.3389/fdgth.2021.763109 pmid:34713208 pmcid:PMC8526547 fatcat:4zmip7e6lnfytnkcepvoc7xhim
« Previous Showing results 1 — 15 out of 858 results