TY - GEN
T1 - A more generalizable DNN based Automatic Segmentation of Brain Tumors from Multimodal low-resolution 2D MRI
AU - DIvya, B.
AU - Nair, Rajesh Parameshwaran
AU - Prakashini, K.
AU - Girish Menon, R.
AU - Litvak, Paul
AU - Mandava, Pitchaiah
AU - Vijayasenan, Deepu
AU - Sumam David, S.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - In the field of Neuro-oncology, there is a need for improved diagnosis and prognosis of brain tumors. Brain tumor segmentation is important for treatment planning and assessing the treatment outcomes. Manual segmentation of brain tumors is tedious, time-consuming, and subjective. In this work, an efficient encoder-decoder based architectures were implemented for automatic segmentation of brain tumors from low resolution 2D images. Ensemble of the multiple architectures (EMMA) improves the performance of the brain tumor segmentation. Furthermore, the computational requirements of the proposed models are lower than that of BraTS-challenge methods. The average Fl-scores on the BraTS-challenge validation dataset for Tumor Core, Whole Tumor, and Enhancing Tumor are 0.82, 0.87, and 0.78, respectively. The average Fl-scores on the KMC-Manipal dataset for TC, WT, and ET are 0.74, 0.82, and 0.68 respectively.
AB - In the field of Neuro-oncology, there is a need for improved diagnosis and prognosis of brain tumors. Brain tumor segmentation is important for treatment planning and assessing the treatment outcomes. Manual segmentation of brain tumors is tedious, time-consuming, and subjective. In this work, an efficient encoder-decoder based architectures were implemented for automatic segmentation of brain tumors from low resolution 2D images. Ensemble of the multiple architectures (EMMA) improves the performance of the brain tumor segmentation. Furthermore, the computational requirements of the proposed models are lower than that of BraTS-challenge methods. The average Fl-scores on the BraTS-challenge validation dataset for Tumor Core, Whole Tumor, and Enhancing Tumor are 0.82, 0.87, and 0.78, respectively. The average Fl-scores on the KMC-Manipal dataset for TC, WT, and ET are 0.74, 0.82, and 0.68 respectively.
UR - http://www.scopus.com/inward/record.url?scp=85126396939&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126396939&partnerID=8YFLogxK
U2 - 10.1109/INDICON52576.2021.9691588
DO - 10.1109/INDICON52576.2021.9691588
M3 - Conference contribution
AN - SCOPUS:85126396939
T3 - Proceedings of the 2021 IEEE 18th India Council International Conference, INDICON 2021
BT - Proceedings of the 2021 IEEE 18th India Council International Conference, INDICON 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE India Council International Conference, INDICON 2021
Y2 - 19 December 2021 through 21 December 2021
ER -