This paper aims to present a review of neural networks used in medical image processing. We classify neural networks by its processing goals and the nature of medical images. Main contributions, advantages, and drawbacks of the methods are mentioned in the paper. Problematic issues of neural network application for medical image processing and an outlook for the future research are also discussed. By this survey, we try to answer the following two important questions: (1) What are the major applications of neural networks in medical image processing now and in the nearby future? (2) What are the major strengths and weakness of applying neural networks for solving medical image processing tasks? We believe that this would be very helpful researchers who are involved in medical image processing with neural network techniques.
{"title":"Survey on Neural Networks Used for Medical Image Processing.","authors":"Zhenghao Shi, Lifeng He, Kenji Suzuki, Tsuyoshi Nakamura, Hidenori Itoh","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>This paper aims to present a review of neural networks used in medical image processing. We classify neural networks by its processing goals and the nature of medical images. Main contributions, advantages, and drawbacks of the methods are mentioned in the paper. Problematic issues of neural network application for medical image processing and an outlook for the future research are also discussed. By this survey, we try to answer the following two important questions: (1) What are the major applications of neural networks in medical image processing now and in the nearby future? (2) What are the major strengths and weakness of applying neural networks for solving medical image processing tasks? We believe that this would be very helpful researchers who are involved in medical image processing with neural network techniques.</p>","PeriodicalId":88523,"journal":{"name":"International journal of computational science","volume":"3 1","pages":"86-100"},"PeriodicalIF":0.0,"publicationDate":"2009-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4699299/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144183133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
For genomic applications, signature-finding algorithms identify over-represented signatures (words) in collections of DNA sequences. The results can be presented as a specific sequence of bases, a consensus sequence showing possible combination of bases, or a matrix of weighted possibilities at each position. These results are often compared to a biological set of binding sites (i.e., known functional elements), which are usually represented as weighted matrices. The comparison is made by scoring the signatures against each weight matrix to identify the best option for a positive hit. However, this approach can misclassify results when applied to short sequences, which are a frequent result of signature finders. We describe a novel method using a window around the original sequences (those which the signature is based upon) to improve the comparison and identify a more significant measure of similarity. In doing so, our method transforms a list of DNA signatures into a resource of characterized binding sites with known functional roles and identifies novel elements in need of further elucidation.
{"title":"Finding Occurrences of Relevant Functional Elements in Genomic Signatures.","authors":"Edwin Jacox, Laura Elnitski","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>For genomic applications, signature-finding algorithms identify over-represented signatures (words) in collections of DNA sequences. The results can be presented as a specific sequence of bases, a consensus sequence showing possible combination of bases, or a matrix of weighted possibilities at each position. These results are often compared to a biological set of binding sites (i.e., known functional elements), which are usually represented as weighted matrices. The comparison is made by scoring the signatures against each weight matrix to identify the best option for a positive hit. However, this approach can misclassify results when applied to short sequences, which are a frequent result of signature finders. We describe a novel method using a window around the original sequences (those which the signature is based upon) to improve the comparison and identify a more significant measure of similarity. In doing so, our method transforms a list of DNA signatures into a resource of characterized binding sites with known functional roles and identifies novel elements in need of further elucidation.</p>","PeriodicalId":88523,"journal":{"name":"International journal of computational science","volume":"2 5","pages":"599-606"},"PeriodicalIF":0.0,"publicationDate":"2008-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2800375/pdf/nihms70363.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"28625952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号