Abu Noman Md Sakib

2023

1. STI

   Segmentation of Hemorrhagic Areas in Human Brain from CT Scan Images

   Abu Noman Md Sakib, Nipa Anjum, and Sk. Md. Masudul Ahsan

   In 2022 4th International Conference on Sustainable Technologies for Industry 4.0 (STI), 2023

   Abs Bib Website

   Brain hemorrhage is potentially a fatal condition that results from internal bleeding in the human brain. In this study, Computed Tomography (CT) scan images have been used for segmentation tasks to pinpoint the area of hemorrhage. Unique data augmentation techniques using non-linear transformations like, Twirl and Spherical have been used along with traditional data augmentation techniques to increase variation in the dataset. The hemorrhagic portion of the brain in images that are easy to distinguish have been annotated to perform the segmentation task. The segmentation task was applied using U-Net and U-Net++ architecture. U-Net architecture has shown 84.33% Intersection over Union (IoU) and 91.34% dice coefficient score whereas U-Net++ has achieved 17.06% IoU and 28.27% dice coefficient score after applying some non-linear transformations on the dataset.

   @inproceedings{10103333,
     author = {Md Sakib, Abu Noman and Anjum, Nipa and Ahsan, Sk. Md. Masudul},
     booktitle = {2022 4th International Conference on Sustainable Technologies for Industry 4.0 (STI)},
     title = {Segmentation of Hemorrhagic Areas in Human Brain from CT Scan Images},
     year = {2023},
     publisher = {IEEE},
     address = {Dhaka, Bangladesh},
     pages = {1-5},
     doi = {10.1109/STI56238.2022.10103333},
     isbn = {978-1-6654-9045-0},
     dimensions = {true},
   }

2. ICICTD

   Classification of Brain Hemorrhage Using Deep Learning from CT Scan Images

   Nipa Anjum, Abu Noman Md. Sakib, and Sk. Md. Masudul Ahsan

   In Proceedings of International Conference on Information and Communication Technology for Development, 2023

   Abs Bib Website

   Brain hemorrhage is a life-threatening problem that happens by bleeding inside human head. In this study, computed tomography (CT) scan images have been used to classify whether the case is hemorrhage or non-hemorrhage. Different convolutional neural network (CNN) models have been observed along with some pre-trained deep learning models such as VGG16, VGG19, ResNet150, ResNet152 and InceptionV3. Pre-trained models have performed well on the dataset but all of them are heavyweight architectures in terms of number of total parameters. But the proposed model is a lightweight architecture as well as a well performing one. After evaluating the model performance, it has been observed that the proposed model gave 96.67% accuracy, 97.08% sensitivity and 96.25% specificity which is the best among other custom CNN models.

   @inproceedings{10.1007/978-981-19-7528-8_15,
     author = {Anjum, Nipa and Sakib, Abu Noman Md. and Masudul Ahsan, Sk. Md.},
     editor = {Ahmad, Mohiuddin and Uddin, Mohammad Shorif and Jang, Yeong Min},
     booktitle = {Proceedings of International Conference on Information and Communication Technology for Development},
     title = {Classification of Brain Hemorrhage Using Deep Learning from CT Scan Images},
     year = {2023},
     publisher = {Springer Nature Singapore},
     address = {Singapore},
     doi = {10.1007/978-981-19-7528-8_15},
     pages = {181-193},
     isbn = {978-981-19-7528-8},
     dimensions = {true},
   }