Deep sparse feature selection for computer aided endoscopy diagnosis

Cong, Yang; Wang, Shuai; Ji, Liu; Cao, Jiang; Yang, Yunsheng; Luo, Jiebo

doi:10.1016/j.patcog.2014.09.010

Cited by 54 publications

(25 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There have been some works in the last two years on endoscopy image analysis with deep learning [71][72][73]. Other approaches include using deep sparse feature selection (see, e.g., [74]). …”

Section: Discussion and Outlookmentioning

confidence: 99%

Polyp Detection and Segmentation from Video Capsule Endoscopy: A Review

Prasath

2016

J. Imaging

View full text Add to dashboard Cite

Video capsule endoscopy (VCE) is used widely nowadays for visualizing the gastrointestinal (GI) tract. Capsule endoscopy exams are prescribed usually as an additional monitoring mechanism and can help in identifying polyps, bleeding, etc. To analyze the large scale video data produced by VCE exams, automatic image processing, computer vision, and learning algorithms are required. Recently, automatic polyp detection algorithms have been proposed with various degrees of success. Though polyp detection in colonoscopy and other traditional endoscopy procedure based images is becoming a mature field, due to its unique imaging characteristics, detecting polyps automatically in VCE is a hard problem. We review different polyp detection approaches for VCE imagery and provide systematic analysis with challenges faced by standard image processing and computer vision methods.

show abstract

Section: Discussion and Outlookmentioning

confidence: 99%

Polyp Detection and Segmentation from Video Capsule Endoscopy: A Review

Prasath

2016

J. Imaging

View full text Add to dashboard Cite

show abstract

“…The first one is that we use the I800 dataset proposed in Cong et al [2015] to compare our method with the traditional supervised framework. The I800 dataset [Cong et al 2015] is annotated with pixel-level ground truth. It includes 389 lesion images and 400 normal images.…”

Section: Evaluation Of Latent Concept Codebookmentioning

confidence: 99%

“…Over the past few years, many computer-aided endoscopy diagnosis systems have been proposed, such as feature extraction [Coimbra and Cunha 2006;Wu et al 2007;Riaz et al 2012], feature selection [Cong et al 2015;Huang et al 2008;Li and Meng 2012], lesion classification [Buchner et al 2010;Li and Meng 2009;Kumar et al 2012;Yuan et al 2015;Mamonov et al 2014], video summarization [Chu et al 2010;Mehmood et al 2014;Iakovidis et al 2010], image enhancement [Muto et al 2011;Shahidi et al 2003;Gono et al 2004], and video segmentation [Mackiewicz et al 2008;Shen et al 2012]. Even though most of the existing systems obtain attractive performance, they stand on top of large detailed annotated images.…”

Section: Introductionmentioning

confidence: 99%

Multi-Class Latent Concept Pooling for Computer-Aided Endoscopy Diagnosis

Wang

Cong

Fan

et al. 2017

ACM Trans. Multimedia Comput. Commun. Appl.

Self Cite

View full text Add to dashboard Cite

Successful computer-aided diagnosis systems typically rely on training datasets containing sufficient and richly annotated images. However, detailed image annotation is often time consuming and subjective, especially for medical images, which becomes the bottleneck for the collection of large datasets and then building computer-aided diagnosis systems. In this article, we design a novel computer-aided endoscopy diagnosis system to deal with the multi-classification problem of electronic endoscopy medical records (EEMRs) containing sets of frames, while labels of EEMRs can be mined from the corresponding text records using an automatic text-matching strategy without human special labeling. With unambiguous EEMR labels and ambiguous frame labels, we propose a simple but effective pooling scheme called Multi-class Latent Concept Pooling, which learns a codebook from EEMRs with different classes step by step and encodes EEMRs based on a soft weighting strategy. In our method, a computer-aided diagnosis system can be extended to new unseen classes with ease and applied to the standard single-instance classification problem even though detailed annotated images are unavailable. In order to validate our system, we collect 1,889 EEMRs with more than 59K frames and successfully mine labels for 348 of them. The experimental results show that our proposed system significantly outperforms the state-of-the-art methods. Moreover, we apply the learned latent concept codebook to detect the abnormalities in endoscopy images and compare it with a supervised learning classifier, and the evaluation shows that our codebook learning method can effectively extract the true prototypes related to different classes from the ambiguous data.

show abstract

“…Depending on the lesions, the decision support systems can be classified to handle bleeding [10], [11], Helicobacter pylori [12], [13], Crohn's disease [7], tumors [14], polyps [15], ulcers [2], and cancers [16], [17]. The commonly used classification models are support vector machine (SVM) [17], [18], neural network [19], fuzzy logic principles [20], clustering-based methods [21], and filter-based methods [22]. For supportive systems, they usually provide some support to guide and make a diagnosis easier for clinicians, such as enhancing image quality [23], detecting informative frames [24], pose detection for endoscopy [25], WCE color video segmentation [26], and feature detection [27].…”

Section: A Computer-aided Endoscopic Diagnosis Systemsmentioning

confidence: 99%

Computer-Aided Endoscopic Diagnosis Without Human-Specific Labeling

Wang

Cong

Fan

et al. 2016

IEEE Trans. Biomed. Eng.

Self Cite

View full text Add to dashboard Cite

Abstract-Goal: Most state-of-the-art computer-aided endoscopic diagnosis methods require pixelwise labeled data to train various supervised machine learning models. However, it is a tedious and time-consuming work to collect sufficient precisely labeled image data. Fortunately, we can easily obtain huge endoscopic medical reports including the diagnostic text and images, which can be considered as weakly labeled data. Methods: In this paper, our motivation is to design a new computer-aided endoscopic diagnosis system without human specific labeling; in comparison with most state of the arts, ours only depends on the endoscopic images with weak labels mined from the diagnostic text. To achieve this, we first cast the endoscopic image folder and included images as bag and instances and represent each instance based on the global bag-of-words model. We then adopt a feature mapping scheme to represent each bag by mining the most suspicious lesion instance from each positive bag automatically. In order to achieve self-online updating from sequential new coming data, an online metric learning method is used to optimize the bag-level classification. Results: Our computer-aided endoscopic diagnosis system achieves an AUC of 0.93 on a new endoscopic image dataset captured from 424 volunteers with more than 12k images. Conclusion: The system performance outperforms other state of the arts when we mine the most positive instances from positive bags and adopt the online phase to mine more information from the unseen bags. Significance: We present the first weakly labeled endoscopic image dataset for computer-aided endoscopic diagnosis and a novel system that is suitable for use in clinical settings.Index Terms-Computer-aided endoscopic diagnosis, multiple instance learning (MIL), online metric learning, weakly labeled data.

show abstract

Deep sparse feature selection for computer aided endoscopy diagnosis

Cited by 54 publications

References 47 publications

Polyp Detection and Segmentation from Video Capsule Endoscopy: A Review

Polyp Detection and Segmentation from Video Capsule Endoscopy: A Review

Multi-Class Latent Concept Pooling for Computer-Aided Endoscopy Diagnosis

Computer-Aided Endoscopic Diagnosis Without Human-Specific Labeling

Contact Info

Product

Resources

About