UMobileNetV2 model for semantic segmentation of gastrointestinal tract in MRI scans

• Main Authors: Sharma, Neha, Gupta, Sheifali, Gupta, Deepali, Gupta, Punit, Juneja, Sapna, Shah, Asadullah, Shaikh, Asadullah
• Format: Article
• Language: English; English
• Published: Public Library of Science 2024
• Subjects: T10.5 Communication of technical information
• Online Access: http://irep.iium.edu.my/112411/2/112411_UMobileNetV2%20model%20for%20semantic%20segmentation_SCOPUS.pdf; http://irep.iium.edu.my/112411/3/112411_UMobileNetV2%20model%20for%20semantic%20segmentation.pdf; http://irep.iium.edu.my/112411/; https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0302880&type=printable; https://doi.org/10.1371/journal.pone.0302880
• Institution: Universiti Islam Antarabangsa Malaysia

Gastrointestinal (GI) cancer is leading general tumour in the Gastrointestinal tract, which is fourth significant reason of tumour death in men and women. The common cure for GI cancer is radiation treatment, which contains directing a high-energy X-ray beam onto the tumor while avoiding healthy organs. To provide high dosages of X-rays, a system needs for accurately segmenting the GI tract organs. The study presents a UMobileNetV2 model for semantic segmentation of small and large intestine and stomach in MRI images of the GI tract. The model uses MobileNetV2 as an encoder in the contraction path and UNet layers as a decoder in the expansion path. The UW-Madison database, which contains MRI scans from 85 patients and 38,496 images, is used for evaluation. This automated technology has the capability to enhance the pace of cancer therapy by aiding the radio oncologist in the process of segmenting the organs of the GI tract. The UMobileNetV2 model is compared to three transfer learning models: Xception, ResNet 101, and NASNet mobile, which are used as encoders in UNet architecture. The model is analyzed using three distinct optimizers, i.e., Adam, RMS, and SGD. The UMobileNetV2 model with the combination of Adam optimizer outperforms all other transfer learning models. It obtains a dice coefficient of 0.8984, an IoU of 0.8697, and a validation loss of 0.1310, proving its ability to reliably segment the stomach and intestines in MRI images of gastrointestinal cancer patients