• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÀÚ±âÁöµµÇнÀÀ¸·Î Ãß·ÐµÈ Æ¯Â¡À» ÀÌ¿ëÇÑ CT ¿µ»óÀÇ º¸°£ ¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) Interpolation Method for CT Image Reconstruction using Features Inferred by Self-Supervised Learning
ÀúÀÚ(Author) ÀÓÁÖ¿ø   ¹ÚÁø¾Æ   Joowon Lim   Jinah Park  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 09 PP. 1007 ~ 1013 (2021. 09)
Çѱ۳»¿ë
(Korean Abstract)
º¼·ý µ¥ÀÌÅÍ´Â 3Â÷¿ø ³»ºÎ Á¤º¸¸¦ °¡Áö°í À־ Á¤·®ÀûÀÎ ºÐ¼®ÀÌ °¡´ÉÇÏ´Ù. ƯÈ÷ ÀǷ῵»ó µ¥ÀÌÅÍ´Â ÀÎü ³»ºÎ ±¸Á¶¸¦ 3Â÷¿øÀ¸·Î ½Ã°¢È­ ÇÒ ¼ö ÀÖÀ¸³ª À̸¦ À§Çؼ­´Â ±ÕµîÇÑ º¹¼¿ÀÌ ÇÊ¿äÇÏ´Ù. ÇÏÁö¸¸ CT µ¥ÀÌÅÍÀÇ °æ¿ì ¹æ»ç¼±·®À» ÁÙÀ̱â À§ÇØ ½½¶óÀ̽º À̹ÌÁö »çÀÌÀÇ °£°ÝÀÌ ³ÐÀº º¼·ý µ¥ÀÌÅ͸¦ ¾ò´Â °æ¿ì°¡ ÀÖ´Ù. ÀÌ °æ¿ì, 3Â÷¿øÀ¸·Î À籸¼ºÇÒ ¶§ ºÒ¿¬¼ÓÀûÀ¸·Î ½Ã°¢È­µÇ°Å³ª Á¤·®ÀûÀÎ ¿ÀÂ÷¸¦ À¯¹ßÇÒ ¼ö ÀÖ¾î À̹ÌÁö º¸°£ÀÌ ÇÊ¿äÇÏ°Ô µÈ´Ù. º» ³í¹®¿¡¼­´Â °íÈ­ÁúÀÇ ½½¶óÀ̽º À̹ÌÁö·ÎºÎÅÍ CT À̹ÌÁö ½½¶óÀ̽º °£ÀÇ º¸°£¿¡ ÇÊ¿äÇÑ Á¤º¸¸¦ ÀÚ±âÁöµµÇнÀÀ¸·Î À¯ÃßÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÏ°íÀÚ ÇÑ´Ù. À̸¦ À§ÇÏ¿© Ãà¼ÒÇÑ ½½¶óÀ̽º À̹ÌÁö¸¦ ½Å°æ¸ÁÀÇ ÀԷ°ªÀ¸·Î ³Ö°í, ½Å°æ¸ÁÀº ÀÌ À̹ÌÁö¸¦ ¿øº» À̹ÌÁö·Î º¹¿øÇÏ´Â °úÁ¤À» ÇнÀÇÑ´Ù. º» ¿¬±¸¿¡¼­ Á¦¾ÈÇÏ´Â ¹æ¹ýÀº ÃÖ±ÙÁ¢ ÀÌ¿ô º¸°£¹ý°ú »ï¼±Çü º¸°£¹ýº¸´Ù ¼¼ºÎ Á¤º¸¸¦ À¯ÃßÇÏ´Â ÀåÁ¡À» º¸ÀÌ°í Âü°ªÀ» °¡Áö°í Áöµµ ÇнÀÀ¸·Î ÇнÀÇÑ ½Å°æ¸Á °á°úº¸´Ù ¼º´ÉÀÌ ÀúÇϵÇÁö ¾ÊÀ½À» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Since volumetric data includes internal information, it has an advantage of performing quantitative analysis. Especially medical image data render 3D structures of internal organs, and cubic voxel is necessary for accurate visualization. However, CT image volume is acquired in low z-resolution to reduce X-ray dose exposure. Between slices, image interpolation is a necessary step for visualization as well as for 3D data analysis. In this paper, we propose a self-supervised learning algorithm as an interpolation method that uses the information from the high-resolution images to infer missing information between slices. To achieve this, downscaled slice images are given as the input of the network, and the network recovers the original slice images from the downscaled images. The result of our method outperformed the commonly practiced interpolation methods - nearest-neighbor and trilinear interpolation – in the field, with respect to estimating details. Also, we verified that the proposed algorithm performs comparably with the supervised model with the same network.
Å°¿öµå(Keyword) ÀÇ·á ¿µ»ó   º¼·ý µ¥ÀÌÅÍ   º¸°£¹ý   ÃÊÇØ»óÈ­   ÀÚ±âÁöµµÇнÀ   medical image   volume data   interpolation   super resolution   self-supervised learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå