• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.1
• /
• pp.249-268
• /
• 2014

Relevance feedback is an effective tool to bridge the gap between superficial image contents and medically-relevant sense in content-based medical image retrieval. In this paper, we propose an interactive medical image search framework based on pairwise constraint propagation. The basic idea is to obtain pairwise constraints from user feedback and propagate them to the entire image set to reconstruct the similarity matrix, and then rank medical images on this new manifold. In contrast to most of the algorithms that only concern manifold structure, the proposed method integrates pairwise constraint information in a feedback procedure and resolves the small sample size and the asymmetrical training typically in relevance feedback. We also introduce a long-term feedback strategy for our retrieval tasks. Experiments on two medical image datasets indicate the proposed approach can significantly improve the performance of medical image retrieval. The experiments also indicate that the proposed approach outperforms previous relevance feedback models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2359-2376
• /
• 2022

With the exponential growth of medical image big data represented by high-resolution CT images(CTI), the high-resolution CTI data is of great importance for clinical research and diagnosis. The paper takes lung CTI as an example to study. Retrieving answer CTIs similar to the input one from the large-scale lung CTI database can effectively assist physicians to diagnose. Compared with the conventional content-based image retrieval(CBIR) methods, the CBIR for lung CTIs demands higher retrieval accuracy in both the contour shape and the internal details of the organ. In traditional supervised deep learning networks, the learning of the network relies on the labeling of CTIs which is a very time-consuming task. To address this issue, the paper proposes a Weakly Supervised Similarity Evaluation Network (WSSENet) for efficiently support similarity analysis of lung CTIs. We conducted extensive experiments to verify the effectiveness of the WSSENet based on which the CBIR is performed.

• Journal of Biomedical Engineering Research
• /
• v.22 no.1
• /
• pp.1-7
• /
• 2001

본 논문에서는 초음파 의료영상 데이터베이스로부터 원하는 영상들을 찾아내기 위한 내용기반 영상 검색기법을 제안한다. 전체 영상 검색 시스템은 공간영역의 히스토그램과 웨이브릿 변환영역에서 부대역의 통계적 특성벡터를 이용한 2단계 검색 알고리즘을 사용하였다. 또한 히스토그램의 인덱싱 기법으로 Legendre 모멘트를 이용해서 데이터베이스에 저장되는 인덱스의 크기를 최소화시켜서 기존의 히스토그램을 이용한 검색방법 비해서 검색속도를 높이면서 검색결과를 개선시켰다.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.240-250
• /
• 2011

To enable a relevance feedback paradigm to evolve itself by users' feedback, a reinforcement learning method is proposed. The feature space of the medical images is partitioned into positive and negative hypercubes by the system. Each hypercube constitutes an individual in a genetic algorithm infrastructure. The rules take recombination and mutation operators to make new rules for better exploring the feature space. The effectiveness of the rules is checked by a scoring method by which the ineffective rules will be omitted gradually and the effective ones survive. Our experiments on a set of 10,004 images from the IRMA database show that the proposed approach can better describe the semantic content of images for image retrieval with respect to other existing approaches in the literature.

• Journal of the Semiconductor & Display Technology
• /
• v.6 no.1 s.18
• /
• pp.49-52
• /
• 2007

The recent advances in digital imaging and computing technology have resulted in a rapid accumulation of digital media in the personal computing and entertainment industry. In addition, large collections of such data already exist in many scientific application domains such as the geographic information systems (GIS), digital library, trademark imaging, satellite imaging and medical imaging. Thus, the need for content-based retrieval from visual media, such as image and video data, is ever increasing rapidly in many applications.

• Korean Journal of Radiology
• /
• v.22 no.2
• /
• pp.281-290
• /
• 2021

Objective: To assess the performance of content-based image retrieval (CBIR) of chest CT for diffuse interstitial lung disease (DILD). Materials and Methods: The database was comprised by 246 pairs of chest CTs (initial and follow-up CTs within two years) from 246 patients with usual interstitial pneumonia (UIP, n = 100), nonspecific interstitial pneumonia (NSIP, n = 101), and cryptogenic organic pneumonia (COP, n = 45). Sixty cases (30-UIP, 20-NSIP, and 10-COP) were selected as the queries. The CBIR retrieved five similar CTs as a query from the database by comparing six image patterns (honeycombing, reticular opacity, emphysema, ground-glass opacity, consolidation and normal lung) of DILD, which were automatically quantified and classified by a convolutional neural network. We assessed the rates of retrieving the same pairs of query CTs, and the number of CTs with the same disease class as query CTs in top 1-5 retrievals. Chest radiologists evaluated the similarity between retrieved CTs and queries using a 5-scale grading system (5-almost identical; 4-same disease; 3-likelihood of same disease is half; 2-likely different; and 1-different disease). Results: The rate of retrieving the same pairs of query CTs in top 1 retrieval was 61.7% (37/60) and in top 1-5 retrievals was 81.7% (49/60). The CBIR retrieved the same pairs of query CTs more in UIP compared to NSIP and COP (p = 0.008 and 0.002). On average, it retrieved 4.17 of five similar CTs from the same disease class. Radiologists rated 71.3% to 73.0% of the retrieved CTs with a similarity score of 4 or 5. Conclusion: The proposed CBIR system showed good performance for retrieving chest CTs showing similar patterns for DILD.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.25 no.4
• /
• pp.313-332
• /
• 2014

With the increased creation, distribution, and use of image in context of the development of digital technologies and internet, research endeavors have accumulated drastically. As two dominant aspects of image retrieval have been considered content-based and concept-based image retrieval, concept-based image retrieval has been focused in the field of Library and Information Science. This study aims to systematically review the accumulated research of image retrieval from the perspective of LIS field. In order to achieve the purpose of this study, two data sets were prepared: a total of 282 image retrieval research papers from Web of Science, and a total of 35 image retrieval research from DBpia in Kore for comparison. For data analysis, systematic review methodology was utilized with bibliographic analysis of individual research papers in the data sets. The findings of this study demonstrated that two sub-areas, image indexing and description and image needs and image behavior, were dominant. Among these sub-areas, the results indicated that there were emerging areas such as collective indexing, image retrieval in terms of multi-language and multi-culture environments, and affective indexing and use. For the user-centered image retrieval research, college and graduate students were found prominent user groups for research while specific user groups such as medical/health related users, artists, and museum users were found considerably. With the comparison with the distribution of sub-areas of image retrieval research in Korea, considerable similarities were found. The findings of this study expect to guide research directions and agenda for future.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.4
• /
• pp.273-280
• /
• 2013

This paper presents novel OCS-LBP (Oriented Center Symmetric Local Binary Patterns) based on orientation of pixel gradient and image retrieval system based on BoF (Bag-of-Feature) and random forest classifier. Feature vectors extracted from training data are clustered into code book and each feature is transformed new BoF feature using code book. BoF features are applied to random forest for training and random forest having N classes is constructed by combining several decision trees. For testing, the same OCS-LBP feature is extracted from a query image and BoF is applied to trained random forest classifier. In contrast to conventional retrieval system, query image selects similar K-nearest neighbor (K-NN) classes after random forest is performed. Then, Top K similar images are retrieved from database images that are only labeled K-NN classes. Compared with other retrieval algorithms, the proposed method shows both fast processing time and improved retrieval performance.

• Journal of Korea Multimedia Society
• /
• v.10 no.6
• /
• pp.707-715
• /
• 2007

The need for content-based retrieval from visual media, such as image and video data, is ever increasing rapidly in many applications, such as electronic art museums, internet shopping malls, internet search engines, and medical information systems. In our previous research, we proposed an architecture, called the HERMES, which is a Web Service-enabled visual media retrieval framework. In this paper, we propose the Web Service workflows that are employed in the HERMES. We describe how we designed the workflows for service registration and query processing in the framework. We especially explain how metadata and ontology can be utilized to realize more intelligent content-based retrieval on visual media data.

• Annual Conference of KIPS
• /
• 2004.11a
• /
• pp.43-46
• /
• 2004

현재 병리 의사에 의해 주관적으로 이루어지고 있는 병리 영상의 진단에 도움을 주기 위해 병리영상에서 객관적으로 추출 가능한 정보를 이용하여 유방종양 검색 시스템을 개발하였다. 다중 특징을 이용한 내용 기반 검색 방법을 사용하였으며, 영상에서 자동으로 추출 가능한 다양한 특징을 검색의 파라미터로 이용하였다. 진단에 도움을 주기 위해 전체 영상 뿐만 아니라 관심 있는 영역의 부분영상도 추출하여 검색이 가능하게 설계하였으며 시스템의 평가를 위해 단일 특징을 이용하여 영상을 검색 하였을 때와 다중 특징을 이용하여 영상을 검색 하였을 때의 검색율을 비교하였다. 향후 이 시스템은 병리영상의 진단에 있어 객관적이고 높은 재현성을 가지게 하는 보조도구로 사용될 수 있을 것이다.