Onah, DFO;
Warsame, HR;
(2025)
Paediatric Pneumonia chest X-ray image classification with association to Lung cancer disease using ResNet50 Deep Learning Model.
In:
Proceedings of the 2024 IEEE International Conference on Big Data, BigData 2024.
(pp. pp. 8859-8861).
IEEE: Washington, DC, USA.
Preview |
Text
BigData2024Paper.pdf - Accepted Version Download (1MB) | Preview |
Abstract
In recent disease advancement and with increasing rate of cases of Pneumonia for the past decades, this has led to the overwhelming challenges within several health systems worldwide. This problem has necessitated the need for efficient and effective measures to mediate and alleviate these challenging issues. Pneumonia is largely caused by inflammation of the lungs because of cold temperature or associated with cold weather. Any delay in treating this disease could be dangerous and could develop to lung cancer. Medical diagnoses are carried out mostly at the beginning with a chest X-ray image to ascertain the presence of pneumonia within a patient. However, this process can be laborious and time sensitive, which might produce inaccurate outcomes or results. In this study, we proposed a ResNet50 architecture to extract the characteristic features from the chest X-ray images. This architecture helps to classify the features to allow us to predict or detect the presence of pneumonia in a patient X-ray image or not. In this study, we utilized dataset extracted from Kaggle which was made up of two distinctive files (1) for training (2) for testing. The dataset was preprocessed to balance the data, and the training data was divided into two sections or parts, one for the training set and the other for the validation set. To enhance our model performance, we performed data augmentation to increase the image variations and data generator was created to reduce the memory usage during the training phase of the model. The ResNet50 architecture was customized for the task with several hyperparameter tuning and the validation data was used to experiment on the model performance validation set. The model was evaluated and measured using classification reports and confusion matrix. We performed the experiment with the following optimization algorithms, SGD, Adam, Adamax and Adagrad, each achieving the following accuracy 93%, 90%, 92% and 89% respectively. We implement the following activation functions , ReLU and ULU within the research. Different validation split ratios were implemented to ascertain the best result. The best performance was observed when 90% or 80% of the training set data was used and 10% or 20% of the validation set data was used within the training set image files.
Type: | Proceedings paper |
---|---|
Title: | Paediatric Pneumonia chest X-ray image classification with association to Lung cancer disease using ResNet50 Deep Learning Model |
Event: | 2024 IEEE International Conference on Big Data (BigData) |
Dates: | 15 Dec 2024 - 18 Dec 2024 |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1109/BigData62323.2024.10825759 |
Publisher version: | https://doi.org/10.1109/bigdata62323.2024.10825759 |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
Keywords: | ResNet50, deep learning, CNN, LSTM, optimization, activation function |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL SLASH UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of Arts and Humanities UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of Arts and Humanities > Dept of Information Studies |
URI: | https://discovery.ucl.ac.uk/id/eprint/10205801 |




Archive Staff Only
![]() |
View Item |