TY - GEN
T1 - A Liver Segmentation Algorithm with Interactive Error Correction for Abdominal CT Images
T2 - 4th IFIP TC 12 International Conference on Computational Intelligence in Data Science, ICCIDS 2021
AU - Nayantara, P. Vaidehi
AU - Kamath, Surekha
AU - Manjunath, K. N.
AU - Rajagopal, K. V.
N1 - Funding Information:
The work is supported by KStePS, DST, Government of Karnataka, India. The authors are grateful to Manipal Institute of Technology, MAHE, Manipal for providing the facilities to carry out the research and Kasturba Medical College, Manipal, for providing the patient data.
Publisher Copyright:
© 2021, IFIP International Federation for Information Processing.
PY - 2021
Y1 - 2021
N2 - An automatic method for segmenting the liver from the portal venous phase of abdominal CT images using the K-Means clustering method is described in this paper. We have incorporated an interactive technique for correcting the errors in the liver segmentation results using power law transformation. The proposed method was validated on abdominal CT volumes of fifteen patients obtained from Kasturba Medical College, Manipal. The average values of the various standard evaluation metrics obtained are as follows: Dice coefficient = 0.9361, Jaccard index = 0.8805, volumetric overlap error = 0.1195, absolute volume difference = 4.048%, average symmetric surface distance = 1.7282 mm and maximum symmetric surface distance = 38.039 mm. The quantitative and qualitative results obtained in our preliminary work show that the K-Means clustering technique along with power law transformation is effective in producing good liver segmentation outputs. As future work, we will attempt to automate the power law transformation technique.
AB - An automatic method for segmenting the liver from the portal venous phase of abdominal CT images using the K-Means clustering method is described in this paper. We have incorporated an interactive technique for correcting the errors in the liver segmentation results using power law transformation. The proposed method was validated on abdominal CT volumes of fifteen patients obtained from Kasturba Medical College, Manipal. The average values of the various standard evaluation metrics obtained are as follows: Dice coefficient = 0.9361, Jaccard index = 0.8805, volumetric overlap error = 0.1195, absolute volume difference = 4.048%, average symmetric surface distance = 1.7282 mm and maximum symmetric surface distance = 38.039 mm. The quantitative and qualitative results obtained in our preliminary work show that the K-Means clustering technique along with power law transformation is effective in producing good liver segmentation outputs. As future work, we will attempt to automate the power law transformation technique.
UR - http://www.scopus.com/inward/record.url?scp=85121868142&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85121868142&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-92600-7_13
DO - 10.1007/978-3-030-92600-7_13
M3 - Conference contribution
AN - SCOPUS:85121868142
SN - 9783030925994
T3 - IFIP Advances in Information and Communication Technology
SP - 132
EP - 140
BT - Computational Intelligence in Data Science - 4th IFIP TC 12 International Conference, ICCIDS 2021, Revised Selected Papers
A2 - Krishnamurthy, Vallidevi
A2 - Jaganathan, Suresh
A2 - Rajaram, Kanchana
A2 - Shunmuganathan, Saraswathi
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 18 March 2021 through 20 March 2021
ER -