Academic submissions (CoCIS)

Permanent URI for this collection

http://10.29.1.53:4000/handle/10570/4083

Browse

Browsing Academic submissions (CoCIS) by Subject "Convolutional Neural Networks"
  • Item
    Automated intestinal parasite detection in stool samples using custom convolutional neural networks
    (Makerere University, 2022-03-10) Rwakazooba, Ezra Aliija
    Intestinal parasitic infections can cause serious health problems with relatively high infections in the developing world. Microscopy of stool remains the gold standard method for the diagnosis of intestinal parasites. However, this method can be time-consuming, and it is also challenging to maintain consistency in diagnosis across different technicians. This is also hindered by the few competent and skilled technicians in the developing countries where the prevalence of intestinal parasites is high. Deep learning has increasingly gained application ground in different challenging computer vision tasks. There is also growing literature of the use of the same technologies in health diagnostic fields such as microscopy. What is used in the state-of-art computer vision challenges, oftentimes gets applied to real-world challenges. However, this has met different limitations in sensitivity and specificity given the broader range of diversity in data sets; for example, in this study of intestinal parasite detection. In general, deep learning continues to provide good performance to computer vision problems across multiple disciplines. In this work, the use of AlexNet and GoogleNet models’ performance on the diagnosis of intestinal parasite eggs in stool samples is evaluated. This work goes ahead to compare these out-of-the-box fine-tuned models with a custom-trained Convolutional Neural Network on the same task. In all cases, accuracy from the out-of-the-box models is very high with GoogleNet ROC AUC of 0.99 and AlexNet ROC AUC of 1.00, and runs on a very low computing resource system, which speaks to the fact that out-of-box models can re-purposed for real-world health diagnostic challenges.
  • Item
    Predicting infectitious disease density in urban settings using Convolutional Neural Networks
    (Makerere University, 2021) Sanya, Rahman
    Rapid and unplanned urbanization is said to pose serious public health challenges to developing countries due to inequality in socio-economic wellbeing, decent housing, etc. Consequently, differential disease risk is experienced across even the same city. For example, overcrowded housing in high density neighborhoods do not only provide fertile ground for airborne infectious diseases to thrive, they also facilitate their rapid spread as a result of increased human contact. The close association observed between urban settings and infectious diseases raises important questions which have not received adequate research attention. For example, what is the nature of this association? What methods are available or are suitable for investigating this kind of association? Would existing methods for characterizing settlements as urban or rural be suitable for studying this kind of association? Furthermore, what can neighborhood characteristics tell us about disease occurrence in a population? With advances in deep learning and big data projected to shape the future of epidemiology and public health, this thesis attempts to answer some of the questions above by leveraging Convolutional Neural Networks (CNN) and using Tuberculosis disease (TB), an airborne infectious disease, as case study. The specific objectives include to, 1) determine potential of socio-economic data as predictor for infectious disease density, 2) determine potential of urban density data as predictor for infectious disease density, 3) build and evaluate a CNN model for identifying patterns in urban housing from satellite imagery, 4) build and evaluate a multimodal CNN model for predicting disease density from socio-economic and housing data, and 5) build and evaluate a siamese CNN model for predicting infectious disease density from housing image data. We developed a linear regression model to achieve each of objectives 1 and 2. CNN methods were developed in a variety of input modalities and architecture designs in both a regression and classification task formulation to fulfill objectives 3, 4, and 5. The TB data used was obtained from Uganda’s Health Management Information System, satellite imagery from Google Static Maps API, and socio-economic data from WorldPop. Socio-economic data was found to posses predictive power for estimating disease density. However, inherent limitations associated with data derived using current methods for quantifying urban density produced misleading results when used for the same purpose. On the other hand, CNN were found to be reasonable for detecting patterns in urban housing density. For example, we achieved 80% accuracy on a housing density detection task. Results from using CNN for inferring TB density from neighborhood characteristics were promising. For example, we attained reasonable accuracy (81.6%) on a task of predicting TB density with a single-input CNN model trained on housing data. The architecture of this overall best model was extended in a novel way inspired by the idea of siamese twins, what we call learning deep features over neighbor scenes. We achieved moderate improvement in prediction performance as a result of the proposed architecture. Despite these promising results however, the potential of CNN for inferring occurrence of a disease in a population requires further investigation. An interesting research direction would be exploring performance of deeper and larger multimodal network architectures using larger training sets. We expect DNN to play an important role in epidemiology of human infectious diseases in the future.