INTRACRANIAL HEMORRHAGE DETECTION IN CT SCAN BASED ON ARTIFICIAL INTELLIGENCE METHOD

Tharek, Dr. Anas (2021) INTRACRANIAL HEMORRHAGE DETECTION IN CT SCAN BASED ON ARTIFICIAL INTELLIGENCE METHOD. Masters thesis, Universiti Putra Malaysia.

Text Anas Thesis 210411.pdf Restricted to Registered users only Download (4MB)

Abstract

Missed detection of intracranial hemorrhage in Head CT scan has significantly impacted patient morbidity and mortality. Early detection of intracranial hemorrhage enable patients to receive appropriate treatment which resulted in a better outcome. In the normal situation, not all head CT scan will be reviewed by the radiologist at the same time the scan was done. The primary iv team is the one who will see through the images first. Some of the primary team has limited experience in interpreting the CT scan hence increase the probability to miss the hemorrhage. The advancement of computer science in artificial intelligence will help to aid the doctor in the detection of hemorrhage in head CT scan. The main objective of this study is to develop an algorithm model capable of detecting intracranial hemorrhage in a head CT scan. We are using deep learning from a convolutional neural network (CNN) to produce this algorithm module. This was a cross-sectional study using secondary data, in which 200 data was collected from public datasets. This dataset is owned by Abdul Kader Helwan, an academic staff at Al-Manar University of Tripoli, Lebanon. Permission to use the dataset for this research was officially obtained from the owner. All of samples have been anonymized into secondary data. The data is divided into train, validation, and test samples. The algorithm model is trained using deep learning via a Jupyter Notebook platform. To analyze the algorithm model performance we are using a confusion matrix to measure the accuracy, sensitivity, specificity, precision, and F1 score. This study showed that from 200 training data, 95 samples were true positive, 95 samples were true negative, 7 samples were false positive, and 3 samples were false negative. This algorithm model shows high sensitivity (0.9694), high specificity (0.9314), high precision (0.9314), and high accuracy (0.9500) with F1 score of 0.9500. Hence, this study has proved that deep learning by using CNN enables us to create an accurate classifier that can differentiate between head CT scan with hemorrhage and without hemorrhage.

Item Type:	Thesis (Masters)
Subjects:	Medicine > Medicine (General)
Depositing User:	ENCIK SAIFUL FADZLY JAMALUDIN
Date Deposited:	24 Jun 2026 07:37
Last Modified:	24 Jun 2026 07:37
URI:	https://repositori.mohe.gov.my/id/eprint/292

Actions (login required)

View Item