{"id":{"repo_id":"westminster","oai_identifier":"oai:westminsterresearch.westminster.ac.uk:x1v40"},"canonical_url":"https://search.dev.ndltd.org/etd/westminster/oai:westminsterresearch.westminster.ac.uk:x1v40","repository":{"repo_id":"westminster","name":"University of Westminster","base_url":"https://westminsterresearch.westminster.ac.uk/oai2"},"display":{"title":"An AI-Based Machine Vision Model for the Diagnosis of Neglected Tropical Diseases","abstract":"Neglected Tropical Diseases (NTDs) affect more than 1 billion of the world’s population[1], and yet, the area of rapid diagnostics is still in its infancy. Much work has been done on machine learning and integration of AI into the medical workflow with cancer and other diseases but the area of NTDs remains, as named, neglected. Little to no research has been done on image analysis of NTD images or on diagnostic neural network systems developed with NTDs in mind. As such, the primary objective of the research is to develop a clinical parasitology detection and diagnostic tool for NTD diagnosis with a primary focus on Schistosoma mansoni. NTD infections caused by parasitic worms are collectively known as helminthiases, the most important of which are soil-transmitted helminthiasis and schistosomiasis, both potentially fatal parasitic infections. Schistosomiasis, which includes intestinal schistosomiasis caused by Schistosoma mansoni, is the second highest infectious disease next to Malaria. According to the latest WHO report, helminthic infections, both soil-transmitted and schistosomiasis, are categorised under ‘neglected’ tropical diseases, as the people who are most affected are the poorest populations living in rural/conflict zoned tropical regions. The infections affect a significant amount of the world population; around 24%, in tropical and subtropical areas. This is interdisciplinary work amalgamating engineering/computer science disciplines and medical parasitology. The primary objective of the research is to design and develop an automated parasite diagnostic tool, using machine learning based image processing operations. This work covers exploratory research into image pre-processing techniques, common segmentation algorithms, feature extraction methodologies and neural networks, contributing a body of work regarding those techniques on Kato-Katz images. The findings from this work are also applicable to other ‘textured’ or difficult to segment, noisy images. This work culminates in a novel neural network model deployed as a computer application that provides the user with an infection intensity rate in real-time. This work addresses the limitations of clinical parasitology through the development of a neural network that utilises curated features for the detection of NTD parasites using Kato-Katz images. The dataset has kindly been provided by the University College London Hospital’s (UCLH’s) Parasitology Division.","abstract_html":"Neglected Tropical Diseases (NTDs) affect more than 1 billion of the world’s population[1], and yet, the area of rapid diagnostics is still in its infancy. Much work has been done on machine learning and integration of AI into the medical workflow with cancer and other diseases but the area of NTDs remains, as named, neglected. Little to no research has been done on image analysis of NTD images or on diagnostic neural network systems developed with NTDs in mind. As such, the primary objective of the research is to develop a clinical parasitology detection and diagnostic tool for NTD diagnosis with a primary focus on Schistosoma mansoni. NTD infections caused by parasitic worms are collectively known as helminthiases, the most important of which are soil-transmitted helminthiasis and schistosomiasis, both potentially fatal parasitic infections. Schistosomiasis, which includes intestinal schistosomiasis caused by Schistosoma mansoni, is the second highest infectious disease next to Malaria. According to the latest WHO report, helminthic infections, both soil-transmitted and schistosomiasis, are categorised under ‘neglected’ tropical diseases, as the people who are most affected are the poorest populations living in rural/conflict zoned tropical regions. The infections affect a significant amount of the world population; around 24%, in tropical and subtropical areas. This is interdisciplinary work amalgamating engineering/computer science disciplines and medical parasitology. The primary objective of the research is to design and develop an automated parasite diagnostic tool, using machine learning based image processing operations. This work covers exploratory research into image pre-processing techniques, common segmentation algorithms, feature extraction methodologies and neural networks, contributing a body of work regarding those techniques on Kato-Katz images. The findings from this work are also applicable to other ‘textured’ or difficult to segment, noisy images. This work culminates in a novel neural network model deployed as a computer application that provides the user with an infection intensity rate in real-time. This work addresses the limitations of clinical parasitology through the development of a neural network that utilises curated features for the detection of NTD parasites using Kato-Katz images. The dataset has kindly been provided by the University College London Hospital’s (UCLH’s) Parasitology Division.","abstract_has_math":false,"creators":["Sinada, Farah"],"institution":"University of Westminster","degree_name":"Ph.D.","degree_level":"PhD thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Reni, S.","Hayes, P.M.","Kale, I."],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-07-24T06:01:04Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:westminsterresearch.westminster.ac.uk:x1v40"],"render_values":[{"text":"oai:westminsterresearch.westminster.ac.uk:x1v40","href":null,"code":true}]}]},"links":{"outbound_url":"https://doi.org/10.34737/x1v40","outbound_label":"DOI","outbound_source":"dc:identifier.doi"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Reni, S.","Hayes, P.M.","Kale, I."]},{"key":"dc:creator","label":"Author","values":["Sinada, Farah"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:publisher","label":"Institution","values":["University of Westminster"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Computer Science and Engineering"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Westminster"]},{"key":"dc:relation","label":"Dc Relation","values":["https://westminsterresearch.westminster.ac.uk/item/x1v40/an-ai-based-machine-vision-model-for-the-diagnosis-of-neglected-tropical-diseases"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://westminsterresearch.westminster.ac.uk/item/x1v40/an-ai-based-machine-vision-model-for-the-diagnosis-of-neglected-tropical-diseases"]},{"key":"dc:type","label":"Dc Type","values":["Thesis or dissertation"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["PhD thesis"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["Ph.D."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:westminsterresearch.westminster.ac.uk:x1v40"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.34737/x1v40"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://westminsterresearch.westminster.ac.uk/download/ab562eb26995170c967c6e3a094513e089847861fbbf425b327a9dc6c40f1d68/10456535/PhD%20Thesis%20Farah%20Sinada_Final%20Corrected%20v2.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Neglected Tropical Diseases (NTDs) affect more than 1 billion of the world’s population[1], and yet, the area of rapid diagnostics is still in its infancy. Much work has been done on machine learning and integration of AI into the medical workflow with cancer and other diseases but the area of NTDs remains, as named, neglected. Little to no research has been done on image analysis of NTD images or on diagnostic neural network systems developed with NTDs in mind. As such, the primary objective of the research is to develop a clinical parasitology detection and diagnostic tool for NTD diagnosis with a primary focus on Schistosoma mansoni. NTD infections caused by parasitic worms are collectively known as helminthiases, the most important of which are soil-transmitted helminthiasis and schistosomiasis, both potentially fatal parasitic infections. Schistosomiasis, which includes intestinal schistosomiasis caused by Schistosoma mansoni, is the second highest infectious disease next to Malaria. According to the latest WHO report, helminthic infections, both soil-transmitted and schistosomiasis, are categorised under ‘neglected’ tropical diseases, as the people who are most affected are the poorest populations living in rural/conflict zoned tropical regions. The infections affect a significant amount of the world population; around 24%, in tropical and subtropical areas. This is interdisciplinary work amalgamating engineering/computer science disciplines and medical parasitology. The primary objective of the research is to design and develop an automated parasite diagnostic tool, using machine learning based image processing operations. This work covers exploratory research into image pre-processing techniques, common segmentation algorithms, feature extraction methodologies and neural networks, contributing a body of work regarding those techniques on Kato-Katz images. The findings from this work are also applicable to other ‘textured’ or difficult to segment, noisy images. This work culminates in a novel neural network model deployed as a computer application that provides the user with an infection intensity rate in real-time. This work addresses the limitations of clinical parasitology through the development of a neural network that utilises curated features for the detection of NTD parasites using Kato-Katz images. The dataset has kindly been provided by the University College London Hospital’s (UCLH’s) Parasitology Division."]},{"key":"dc:description.abstract","label":"Abstract","values":["Neglected Tropical Diseases (NTDs) affect more than 1 billion of the world’s population[1], and yet, the area of rapid diagnostics is still in its infancy. Much work has been done on machine learning and integration of AI into the medical workflow with cancer and other diseases but the area of NTDs remains, as named, neglected. Little to no research has been done on image analysis of NTD images or on diagnostic neural network systems developed with NTDs in mind. As such, the primary objective of the research is to develop a clinical parasitology detection and diagnostic tool for NTD diagnosis with a primary focus on Schistosoma mansoni. NTD infections caused by parasitic worms are collectively known as helminthiases, the most important of which are soil-transmitted helminthiasis and schistosomiasis, both potentially fatal parasitic infections. Schistosomiasis, which includes intestinal schistosomiasis caused by Schistosoma mansoni, is the second highest infectious disease next to Malaria. According to the latest WHO report, helminthic infections, both soil-transmitted and schistosomiasis, are categorised under ‘neglected’ tropical diseases, as the people who are most affected are the poorest populations living in rural/conflict zoned tropical regions. The infections affect a significant amount of the world population; around 24%, in tropical and subtropical areas. This is interdisciplinary work amalgamating engineering/computer science disciplines and medical parasitology. The primary objective of the research is to design and develop an automated parasite diagnostic tool, using machine learning based image processing operations. This work covers exploratory research into image pre-processing techniques, common segmentation algorithms, feature extraction methodologies and neural networks, contributing a body of work regarding those techniques on Kato-Katz images. The findings from this work are also applicable to other ‘textured’ or difficult to segment, noisy images. This work culminates in a novel neural network model deployed as a computer application that provides the user with an infection intensity rate in real-time. This work addresses the limitations of clinical parasitology through the development of a neural network that utilises curated features for the detection of NTD parasites using Kato-Katz images. The dataset has kindly been provided by the University College London Hospital’s (UCLH’s) Parasitology Division."]},{"key":"dc:title","label":"Title","values":["An AI-Based Machine Vision Model for the Diagnosis of Neglected Tropical Diseases"]}]}],"canonical_facts":{"dc:contributor.advisor":["Reni, S.","Hayes, P.M.","Kale, I."],"dc:creator":["Sinada, Farah"],"dc:date":["2025"],"dc:date.issued":["2025"],"dc:description":["Neglected Tropical Diseases (NTDs) affect more than 1 billion of the world’s population[1], and yet, the area of rapid diagnostics is still in its infancy. Much work has been done on machine learning and integration of AI into the medical workflow with cancer and other diseases but the area of NTDs remains, as named, neglected. Little to no research has been done on image analysis of NTD images or on diagnostic neural network systems developed with NTDs in mind. As such, the primary objective of the research is to develop a clinical parasitology detection and diagnostic tool for NTD diagnosis with a primary focus on Schistosoma mansoni. NTD infections caused by parasitic worms are collectively known as helminthiases, the most important of which are soil-transmitted helminthiasis and schistosomiasis, both potentially fatal parasitic infections. Schistosomiasis, which includes intestinal schistosomiasis caused by Schistosoma mansoni, is the second highest infectious disease next to Malaria. According to the latest WHO report, helminthic infections, both soil-transmitted and schistosomiasis, are categorised under ‘neglected’ tropical diseases, as the people who are most affected are the poorest populations living in rural/conflict zoned tropical regions. The infections affect a significant amount of the world population; around 24%, in tropical and subtropical areas. This is interdisciplinary work amalgamating engineering/computer science disciplines and medical parasitology. The primary objective of the research is to design and develop an automated parasite diagnostic tool, using machine learning based image processing operations. This work covers exploratory research into image pre-processing techniques, common segmentation algorithms, feature extraction methodologies and neural networks, contributing a body of work regarding those techniques on Kato-Katz images. The findings from this work are also applicable to other ‘textured’ or difficult to segment, noisy images. This work culminates in a novel neural network model deployed as a computer application that provides the user with an infection intensity rate in real-time. This work addresses the limitations of clinical parasitology through the development of a neural network that utilises curated features for the detection of NTD parasites using Kato-Katz images. The dataset has kindly been provided by the University College London Hospital’s (UCLH’s) Parasitology Division."],"dc:description.abstract":["Neglected Tropical Diseases (NTDs) affect more than 1 billion of the world’s population[1], and yet, the area of rapid diagnostics is still in its infancy. Much work has been done on machine learning and integration of AI into the medical workflow with cancer and other diseases but the area of NTDs remains, as named, neglected. Little to no research has been done on image analysis of NTD images or on diagnostic neural network systems developed with NTDs in mind. As such, the primary objective of the research is to develop a clinical parasitology detection and diagnostic tool for NTD diagnosis with a primary focus on Schistosoma mansoni. NTD infections caused by parasitic worms are collectively known as helminthiases, the most important of which are soil-transmitted helminthiasis and schistosomiasis, both potentially fatal parasitic infections. Schistosomiasis, which includes intestinal schistosomiasis caused by Schistosoma mansoni, is the second highest infectious disease next to Malaria. According to the latest WHO report, helminthic infections, both soil-transmitted and schistosomiasis, are categorised under ‘neglected’ tropical diseases, as the people who are most affected are the poorest populations living in rural/conflict zoned tropical regions. The infections affect a significant amount of the world population; around 24%, in tropical and subtropical areas. This is interdisciplinary work amalgamating engineering/computer science disciplines and medical parasitology. The primary objective of the research is to design and develop an automated parasite diagnostic tool, using machine learning based image processing operations. This work covers exploratory research into image pre-processing techniques, common segmentation algorithms, feature extraction methodologies and neural networks, contributing a body of work regarding those techniques on Kato-Katz images. The findings from this work are also applicable to other ‘textured’ or difficult to segment, noisy images. This work culminates in a novel neural network model deployed as a computer application that provides the user with an infection intensity rate in real-time. This work addresses the limitations of clinical parasitology through the development of a neural network that utilises curated features for the detection of NTD parasites using Kato-Katz images. The dataset has kindly been provided by the University College London Hospital’s (UCLH’s) Parasitology Division."],"dc:identifier":["oai:westminsterresearch.westminster.ac.uk:x1v40"],"dc:identifier.doi":["https://doi.org/10.34737/x1v40"],"dc:identifier.uri":["https://westminsterresearch.westminster.ac.uk/download/ab562eb26995170c967c6e3a094513e089847861fbbf425b327a9dc6c40f1d68/10456535/PhD%20Thesis%20Farah%20Sinada_Final%20Corrected%20v2.pdf"],"dc:publisher":["University of Westminster"],"dc:publisher.department":["Computer Science and Engineering"],"dc:publisher.institution":["University of Westminster"],"dc:relation":["https://westminsterresearch.westminster.ac.uk/item/x1v40/an-ai-based-machine-vision-model-for-the-diagnosis-of-neglected-tropical-diseases"],"dc:relation.isreferencedby":["https://westminsterresearch.westminster.ac.uk/item/x1v40/an-ai-based-machine-vision-model-for-the-diagnosis-of-neglected-tropical-diseases"],"dc:title":["An AI-Based Machine Vision Model for the Diagnosis of Neglected Tropical Diseases"],"dc:type":["Thesis or dissertation"],"dc:type.qualificationlevel":["PhD thesis"],"dc:type.qualificationname":["Ph.D."]},"updated_at":"2026-07-24T06:01:04Z"}