DB
D. Böhm
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
With a 5-year survival rate of only 9%, pancreatic cancer is one of the deadliest types of cancer. Among other things, this is caused by the extreme difficulty of diagnosing recurrent pancreatic cancer in an early stage. One of the important next steps in discovering pancreatic cancer automatically on a CT scan is finding healthy pancreatic tissue. This research explores the feasibility of segmenting the pancreas on a CT scan using a deep learning approach, focusing on postoperative cases after pancre- atic resection, by combining state-of-the-art segmentation models for the preoperative pancreas with novel techniques, such as 3D Multi-Scale Convolutional Blocks (MCBs) and KNet architectures. Us- ing pretraining on preoperative data, a complete segmentation pipeline was designed to segment the pancreas in the postoperative state. The experimental results demonstrate that deep learning models can effectively segment the pancreas, despite the increased complexity and difficulty of the postoper- ative state. Notably, employing advanced techniques such as the KNet architecture and MCBs yields significant performance improvements. The newly designed architectures presented in this research, MKNet, MSKNet, and MAKNet, achieve state-of-the-art results for both preoperative and postoperative pancreas segmentation, greatly improving the Hausdorff Distance (HD) and 95th Percentile Hausdorff Distance (HD95) in particular. In the preoperative state, substantial performance improvements were observed compared to the previous state-of-the-art, with a 12.17% increase for HD and a 14.64% in- crease for HD95. Similarly, in the postoperative state, improvements of 11.99% for HD and 13.25% for HD95 were measured. Additionally, qualitative evaluations were conducted with seven experienced radiologists and radiotherapists to validate the algorithm’s performance in a clinical context. Remark- ably, in 83% of the cases, the algorithm was evaluated to accurately segment the pancreas, requiring minimal or no modifications according to the medical experts. This study not only contributes to the state-of-the-art in pancreas segmentation but also introduces comprehensive quantitative and qualitative evaluation methodologies. Furthermore, it addresses the segmentation of the postoperative pancreas, which has not yet been touched upon in previous re- search. Limitations are acknowledged, such as the availability of a limited dataset, and future research directions are proposed, including generalizability and enhancements to the proposed models. Despite the limited availability of data, which impacts the performance and generalization capabilities to some degree, the research in this thesis showcases the capability of the MKNet family architectures to ac- curately segment the postoperative pancreas, offering potential benefits for medical applications, data annotation acceleration, and future research in this domain.
...
With a 5-year survival rate of only 9%, pancreatic cancer is one of the deadliest types of cancer. Among other things, this is caused by the extreme difficulty of diagnosing recurrent pancreatic cancer in an early stage. One of the important next steps in discovering pancreatic cancer automatically on a CT scan is finding healthy pancreatic tissue. This research explores the feasibility of segmenting the pancreas on a CT scan using a deep learning approach, focusing on postoperative cases after pancre- atic resection, by combining state-of-the-art segmentation models for the preoperative pancreas with novel techniques, such as 3D Multi-Scale Convolutional Blocks (MCBs) and KNet architectures. Us- ing pretraining on preoperative data, a complete segmentation pipeline was designed to segment the pancreas in the postoperative state. The experimental results demonstrate that deep learning models can effectively segment the pancreas, despite the increased complexity and difficulty of the postoper- ative state. Notably, employing advanced techniques such as the KNet architecture and MCBs yields significant performance improvements. The newly designed architectures presented in this research, MKNet, MSKNet, and MAKNet, achieve state-of-the-art results for both preoperative and postoperative pancreas segmentation, greatly improving the Hausdorff Distance (HD) and 95th Percentile Hausdorff Distance (HD95) in particular. In the preoperative state, substantial performance improvements were observed compared to the previous state-of-the-art, with a 12.17% increase for HD and a 14.64% in- crease for HD95. Similarly, in the postoperative state, improvements of 11.99% for HD and 13.25% for HD95 were measured. Additionally, qualitative evaluations were conducted with seven experienced radiologists and radiotherapists to validate the algorithm’s performance in a clinical context. Remark- ably, in 83% of the cases, the algorithm was evaluated to accurately segment the pancreas, requiring minimal or no modifications according to the medical experts. This study not only contributes to the state-of-the-art in pancreas segmentation but also introduces comprehensive quantitative and qualitative evaluation methodologies. Furthermore, it addresses the segmentation of the postoperative pancreas, which has not yet been touched upon in previous re- search. Limitations are acknowledged, such as the availability of a limited dataset, and future research directions are proposed, including generalizability and enhancements to the proposed models. Despite the limited availability of data, which impacts the performance and generalization capabilities to some degree, the research in this thesis showcases the capability of the MKNet family architectures to ac- curately segment the postoperative pancreas, offering potential benefits for medical applications, data annotation acceleration, and future research in this domain.
Bachelor thesis
(2020)
-
Dennis Böhm, Bram van Kooten, Dylan Franken, Govert de Gans, Bas Musters, Lydia Chen, Stefan Hugtenburg
Most courses in the Computer Science Bachelor at the Delft University of Technology make use of lab sessions. During these lab sessions students can ask questions about course material and get feedback on their assignment. Moreover, their knowledge about assignments can be orally tested. In order to properly help the students, teaching assistants, or TAs, are selected to assist the lecturer during the lab sessions. With the number of students in the Bachelor quickly growing, the process of manually recruiting students to become a TA and assigning the TAs to lab sessions is becoming very time consuming and almost impossible. During a Bachelor End Project in 2018 four students (van Deursen et al., 2018) created the Teach- ing Assistant Management (TAM) platform. This project aimed to ease the process of recruiting and scheduling TAs. All parties involved in the process of appointing TAs can use TAM to provide their input. Lecturers can register their courses on TAM and students are able to indicate their interest and availability to help with different courses. However, the first version of TAM missed a number of important features. For example, student avail- ability data had to be extracted manually and teachers still had to email their TA selection to the coordinator. This project aims to continue and improve TAM with these missing features. In order to achieve this goal TAM 2.0 has been developed. TAM 2.0 consists of three components: a MySQL database, a back end written using Spring and Java containing the business logic, and a front end website created using Vue to provide an interface to its users. TAM 2.0 also integrated LabraCORE. LabraCORE provides user and course information to several platforms and stores it conveniently in one central place.
...
Most courses in the Computer Science Bachelor at the Delft University of Technology make use of lab sessions. During these lab sessions students can ask questions about course material and get feedback on their assignment. Moreover, their knowledge about assignments can be orally tested. In order to properly help the students, teaching assistants, or TAs, are selected to assist the lecturer during the lab sessions. With the number of students in the Bachelor quickly growing, the process of manually recruiting students to become a TA and assigning the TAs to lab sessions is becoming very time consuming and almost impossible. During a Bachelor End Project in 2018 four students (van Deursen et al., 2018) created the Teach- ing Assistant Management (TAM) platform. This project aimed to ease the process of recruiting and scheduling TAs. All parties involved in the process of appointing TAs can use TAM to provide their input. Lecturers can register their courses on TAM and students are able to indicate their interest and availability to help with different courses. However, the first version of TAM missed a number of important features. For example, student avail- ability data had to be extracted manually and teachers still had to email their TA selection to the coordinator. This project aims to continue and improve TAM with these missing features. In order to achieve this goal TAM 2.0 has been developed. TAM 2.0 consists of three components: a MySQL database, a back end written using Spring and Java containing the business logic, and a front end website created using Vue to provide an interface to its users. TAM 2.0 also integrated LabraCORE. LabraCORE provides user and course information to several platforms and stores it conveniently in one central place.