{"title":"Classification of Focal Liver Lesions Using Deep Learning with Fine-Tuning","authors":"Weibin Wang, Y. Iwamoto, Xianhua Han, Yenwei Chen, Qingqing Chen, Dong Liang, Lanfen Lin, Hongjie Hu, Qiaowei Zhang","doi":"10.1145/3299852.3299860","DOIUrl":"https://doi.org/10.1145/3299852.3299860","url":null,"abstract":"Liver cancer is one of the leading causes of death worldwide. Computer-aided diagnoses play an important role in liver lesion diagnoses (classification). Recently, several deep-learning-based computer-aided diagnosis systems have been proposed for the classification of liver lesions. The effectiveness of these systems has been demonstrated; however, the main challenge in deep-learning-based medical image classification is the lack of annotated training samples. In this paper, we demonstrate that transfer learning and fine-tuning can significantly improve the accuracy of liver lesion classification, especially for small training samples. We used the residual convolutional neural network (ResNet), which is a state-of-the-art network, as our baseline network for focal liver lesion classification using multi-phase CT images. Fine-tuning significantly improved the classification accuracy from 83.7% to 91.2%. This classification accuracy (91.2%) is higher than that of state-of-the-art methods.","PeriodicalId":210874,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Medicine and Image Processing","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114564766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Proceedings of the 2018 International Conference on Digital Medicine and Image Processing","authors":"","doi":"10.1145/3299852","DOIUrl":"https://doi.org/10.1145/3299852","url":null,"abstract":"","PeriodicalId":210874,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Medicine and Image Processing","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125514332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Momentous Innovations in the Prospective Method of Drug Development","authors":"S. J. Ibrahim, M. Thangamani","doi":"10.1145/3299852.3299854","DOIUrl":"https://doi.org/10.1145/3299852.3299854","url":null,"abstract":"The innovative work (Research and development) pipeline is a huge cost for pharmaceutical Organizations. In spite of the requirement for more advancement, Research and development profitability has vegetated or decayed over various years.1-3 More present, the industry has not exhaustively evaluated the effect of new developments in pharmaceutical improvement and market get to particularly as far as basic achievement measurements, for example, clinical preliminary productivity, the probability of medication dispatch and patient access. To invigorate activity on this diagnostic issue, we accumulated and translated hard confirmation on the effect of chosen developments estimated against particular achievement measurements. The general objective of the investigation is to invigorate expansive dialog on how the business can utilize inventive methodologies in medicate advancement and market access to enhance proficiency, revive profitability and revitalize supportability. It is unmistakable in openly evaluating the effect of the most encouraging advancements in sedate improvement on preliminary productivity and accomplishment in dispatch and getting model endorsement around the world. We recommend that it makes convincing, information-driven case for expediting the selection of new market get to forms for drugs. In particular, it demonstrates that the four developments assessed---adaptive trial designs, patient-centric trials, precision medicine trials and real-world data trials reliably convey in contrast to industry achievement touchstone.","PeriodicalId":210874,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Medicine and Image Processing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127064522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Study of Conversion of Graphical Symbols for Psychological Cognition","authors":"Yu-Che Huang, Ko-Jou Hsiao, Yan-Jie Chen","doi":"10.1145/3299852.3299855","DOIUrl":"https://doi.org/10.1145/3299852.3299855","url":null,"abstract":"The transformation of graphics comes from the recognition of symbolic semantics, related cognition will affect human cognition, different countries, cultures, years, age, gender, etc. For the people will have different cognitive differences. How to provide better images to satisfy users, making it easier to learn and cognize, and reduce factors such as misjudgment or misunderstanding, will come to be an important issue. Whether in normal healthy users or in dementia due to advanced age, the relationship between image and cognition must be taken seriously. This study will make a change design for image and symbol semantics to study the responses and cognition of different subjects and provide a reference for future rehabilitation learning or cognitive learning.","PeriodicalId":210874,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Medicine and Image Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122415670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Handheld Food Localization and Food Recognition Using Convolutional Neural Network","authors":"Duan-Yu Chen, Hao-Syuan Wang","doi":"10.1145/3299852.3299862","DOIUrl":"https://doi.org/10.1145/3299852.3299862","url":null,"abstract":"In modern society, calories and carbohydrate intake leads to the obesities and diabetes sharply increases. For this reason, food recognition and its application attracted more and more attention. However, a variety of problem such as deformation and color difference cause the difficulty in this task. Especially, localization problem of food item is the most difficult, because the background always colorful and messy. In view of this, optical flow algorithm, which commonly used for foreground separation, is employed in this paper. Based on the speed information, hand-held objects can be isolated from background according to the estimated optical flows. Then, gradient and RGB color value of each pixel in an image are used for recognition. With the advantage of convolutional neural network, high stability and high tolerance, we finally get the remarkable precision in the experiment results, which show the feasibility of our proposed approach for real-world environments.","PeriodicalId":210874,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Medicine and Image Processing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123564768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}