Index
Spatiotemporal Denoising in Time Resolved Computed Tomography
X-ray image synthesis via an open source framework
Use a new open source framework generating X-ray images for deep learning model training.
Requirement: Python, CT reconstruction
Please attach your CV and transcripts to fuxin.fan@fau.de
Data-Driven Discovery of Killer Whale Vocalization Sub-Units using Deep Learning
Cross-validation of Network Architectures and Training Data for Learning-based X-ray Scatter Estimation
Pretraining Transformers For Predictive Maintenance In Manufacturing
In the domain of predictive maintenance within manufacturing industries, the introduction of transformer-based machine learning models marks a significant leap towards more sophisticated anomaly detection mechanisms. These models can discern complex patterns in time series data, predicting potential equipment malfunctions before they lead to costly downtimes. The methodology of this thesis builds on two promising approaches: the first leverages a masked autoencoder framework designed for transformers to predict obscured parts of the input data, thereby learning the normal operational patterns of the machinery [1]. The second approach utilizes the reconstruction loss of a Variational Autoencoder (VAE) to signal deviations from the norm, which may indicate anomalies [2]. Both approaches are integral to this research’s objective of enhancing predictive maintenance strategies.
Furthering the innovation in this field, the thesis will incorporate cutting-edge transformer models such as TranAD and AnomalyBERT, which have shown exceptional results in quickly and accurately identifying anomalies in multivariate time series data [3][4]. TranAD’s focus score-based self-conditioning and adversarial training, along with AnomalyBERT’s data degradation scheme for self-supervised learning, position these models at the forefront of the predictive maintenance revolution.
The anticipated outcomes of this research encompass the development and validation of a robust framework for industrial anomaly detection. This will be achieved by adapting and optimizing transformer networks that are proficient in handling the high volatility and label scarcity characteristic of industrial datasets.
The implications of this study are profound, offering not only a technological edge to predictive maintenance but also a significant academic contribution to the application of AI in manufacturing. The models and methodologies derived from this thesis could serve as benchmarks for future research and applications in the AI and industrial maintenance landscape.
References
[1] Tang, Peiwang & Zhang, Xianchao. (2022). MTSMAE: Masked Autoencoders for Multivariate Time-Series Forecasting.
[2] Niu, Zijian, Ke Yu, and Xiaofei Wu. (2020). “LSTM-Based VAE-GAN for Time-Series Anomaly Detection.” Sensors 20, no. 13: 3738. https://doi.org/10.3390/s20133738.
[3] Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings. “TranAD: deep transformer networks for anomaly detection in multivariate time series data.” Proceedings of the VLDB Endowment 15.6 (2022): 1201-1214. https://doi.org/10.14778/3514061.3514067.
[4] Yungi Jeong, Eunseok Yang, Jung Hyun Ryu, Imseong Park, Myungjoo Kang. “ANOMALYBERT: SELF-SUPERVISED TRANSFORMER FOR TIME SERIES ANOMALY DETECTION USING DATA DEGRADATION SCHEME.” Presented at the ICLR 2023 workshop on Machine Learning for IoT.
Reinforcement learning to learn mean average precision learning
Killer Whale Localization using Deep Learning
Detection and Tracking of Killer Whale Scarring Patterns using Deep Learning
Deep Learning based Vascular Contouring in Photon-Counting Computed Tomography
Thesis Description
Heart diseases, particularly ischemic strokes, are a leading global cause of mortality and morbidity. Atherosclerotic
plaque formation thickens blood vessels walls, serving as a risk indicator for future ischemic stroke
occurrences [1] [2]. Automatic estimation of the vessel wall thickness would offer new potential for screening
patients with respect to high-risk artherosclerotic plaques. The vessel wall thickness can be obtained by segmenting
the vessel wall in cross-section images along the vessels’ centerlines from medical imaging modalities
such as Magnetic Resonance Imaging (MRI) and Computer Tomography (CT). Classical vessel segmentation
methods such as Region Growing [3] and Adaptive Frangi Filtering [4] pose significant challenges as they need to
be manually tuned and do not scale with an increase in data. These issues are adressed by deep learning based
approaches as they do not need manual configuration during inference and can benefit from large amounts of
data. However, popular deep learning based segmentation algorithms such as the U-net pose challenges when
predicting contour points of vessels as these algorithms predict discrete segmentation maps which require further
conversion into the continous domain [5]. Thus, they are dependant on the input resolution and not suitabe to
predict contours on a submillimeter scale. A more suitable way to predict vessel contour points is to perform
deep learning based radius regression on polar unfolded cross-section images as proposed by Ablas et al. [6] or
Chen et al. [7] on black-blood MRI images. The aim of this thesis is to translate the approach to Computer
Tomography data from Photon-Counting CT scanners (PCCT). Furthermore, the thesis aims to exploit the
potential of PCCT scanners and investigate the impact on the prediction of Photon-Counting-based spectral
image information to be able to implicitly suppress non-vessel-like structures. For this purpose, different architectures
(e.g. attention mechanisms [8]) to perform the radius regression are tested and compared against a state
of the art segmentation baseline algorithm on standard inputs. The models are trained and tested on manually
annotated real world CT data. To capture the details of both inner and outer vessel contours, conventional loss
functions and metrics for segmentation, like Intersection-over-Union (IoU), fall short in accommodating subtle
variations in border regions, such as small plaques in the vessel wall. To evaluate the models with respect to
the final application, a suitable distance-based metric should be found that not only accounts for these small
variations but also addresses the multiscale characteristics of the different vessels in the dataset. To ensure
and improve data quality, part of the work will be the iterative training of the model to find errorneous annotations
for manual corrections. Finally, the individual cross-section predictions are converted back to 3D meshes.
Summary:
1. State of the art research
2. Development of a deep learning based algorithm for inner and outer vessel wall contouring on Photon-
Counting CT data
(a) Investigation of the impact of Photon-Counting-based spectral image information
(b) Investigation and optimization of different architectures for vessel contour regression
(c) Investigation of different loss functions and metrics that address the multiscale characteristics and
infrequent occurences of anomalities in the training set
3. Comparison against various baseline algorithms
4. Reconstruction of 3D mesh from contour predictions on 2D cross-sections
5. Evaluation of the developed pipeline and its impact with respect to the final application
References
[1] L. E. Chambless, A. R. Folsom, L. X. Clegg, et al. Carotid wall thickness is predictive of incident clinical
stroke: The atherosclerosis risk in communities (aric) study. American Journal of Epidemiology, 151:478–
487, 3 2000.
[2] Gregory L. Burke, Gregory W. Evans, Ward A. Riley, et al. Arterial wall thickness is associated with
prevalent cardiovascular disease in middle-aged adults. Stroke, 26:386–391, 3 1995.
[3] S.A. Hojjatoleslami and J. Kittler. Region growing: a new approach. IEEE Transactions on Image Processing,
7:1079–1084, 7 1998.
[4] Alejandro Frangi, W J Niessen, Koen Vincken, and Max Viergever. Multiscale vessel enhancement filtering.
Med. Image Comput. Comput. Assist. Interv., 1496, 10 2000.
[5] Florian Thamm, Felix Denzinger, Leonhard Rist, Celia Martin Vicario, Florian Kordon, and Andreas Maier.
Segmentation of the carotid lumen and vessel wall using deep learning and location priors. 1 2022.
[6] Dieuwertje Alblas, Christoph Brune, and Jelmer M. Wolterink. Deep learning-based carotid artery vessel
wall segmentation in black-blood mri using anatomical priors. 12 2021.
[7] Li Chen, Jie Sun, Gador Canton, et al. Automated artery localization and vessel wall segmentation using
tracklet refinement and polar conversion. IEEE Access, 8:217603–217614, 2020.
[8] Wentao Liu, Huihua Yang, Tong Tian, Xipeng Pan, andWeijin Xu. Multiscale attention aggregation network
for 2d vessel segmentation. pages 1436–1440. IEEE, 5 2022.
Development of an Oriented Bone Detection Algorithm on X-Ray Images
Mobile C-arms are a tool commonly used in trauma and orthopedic surgery. They have many different applications, including spine, knee, and wrist surgery. With the possibility of intra-operative imaging, mobile C-arms are a great enrichment for checking the progress of the surgery or for providing guidance during minimally invasive procedures. However, there is one drawback to using them, and that is the relatively increased radiation exposure of the patient and the surgical staff [1]. Collimation is an option for reducing the radiation exposure. By focusing the x-ray beams only on the region of interest, it becomes possible to reduce the irradiated area and consequently lower radiation doses. Another effect of choosing the field-of-view is enhanced contrast and improved image quality. Enhanced image quality is consistently sought after in surgical procedures, as it can significantly benefit the surgeon and contribute to
better and more efficient surgical outcomes [2]. Therefore, the accurate adjustment of the collimators has a great impact on the outcome of the surgery, the patient and the medical staff involved. Nevertheless, this crucial adjustment is frequently overlooked due to lack of time and insufficient training of the staff. Software that automatically finds the region of interest can
help to properly adjust the collimation without additional effort for the medical staff. Various hardware- and software-based approaches have previously been employed to address this issue. Yap et al.[3] proposed a deep-learning based method to detect the region of interest. They have used a Faster R-CNN to predict axis-aligned boxes covering the region of interest. The experiments focus on the detection of breast lesion and only consider breast ultrasound data. The aim of this master thesis is to use Transformer networks for finding bounding boxes of bones from various anatomical regions to automate the collimation which leads to a reduction of radiation exposure and increase in image quality.
References
[1] Yang-Sub Lee, Hae-Kag Lee, Jae-Hwan Cho, and Ham-Gyum Kim. Analysis of radiation risk to patients
from intra-operative use of the mobile x-ray system (c-arm). J. Res. Med. Sci., 20(1):7–12, January 2015.
[2] Thomas Werncke, Christian von Falck, Matthias Luepke, Georg Stamm, Frank K Wacker, and Bernhard
Christian Meyer. Collimation and image quality of c-arm computed tomography. Invest. Radiol.,
50(8):514–521, August 2015.
[3] Moi Hoon Yap, Manu Goyal, Fatima Osman, Robert Mart´ı, Erika Denton, Arne Juette, and Reyer Zwiggelaar.
Breast ultrasound region of interest detection and lesion localisation. Artificial Intelligence in Medicine,
107:101880, 2020.