Tobias Schlosser

Tobias Schlosser

Faculty of Medicine Carl Gustav Carus, Dresden University of Technology, Dresden, Saxony, Germany
+1
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 January 2022 in Journal of Intelligent Manufacturing
Verified
Journal Article
Open access
PDF file
Tobias SchlosserTobias Schlosser
Tobias Schlosser
MFMichael Friedrich
Michael Friedrich
FBFrederik Beuth
Frederik Beuth
Danny KowerkoDanny Kowerko
Danny Kowerko
In the semiconductor industry, automated visual inspection aims to improve the detection and recognition of manufacturing defects by leveraging the power of artificial intelligence and computer vision systems, enabling manufacturers to profit from an increased yield and reduced manufacturing costs. Previous domain-specific contributions often utilized classical computer vision approaches, whereas more novel systems deploy deep learning based ones. However, a persistent problem in the domain stems from the recognition of very small defect patterns which are often in the size of only a few $$\mu $$ μ m and pixels within vast amounts of high-resolution imagery. While these defect patterns occur on the significantly larger wafer surface, classical machine and deep learning solutions have problems in dealing with the complexity of this challenge. This contribution introduces a novel hybrid multistage system of stacked deep neural networks (SH-DNN) which allows the localization of the finest structures within pixel size via a classical computer vision pipeline, while the classification process is realized by deep neural networks. The proposed system draws the focus over the level of detail from its structures to more task-relevant areas of interest. As the created test environment shows, our SH-DNN-based multistage system surpasses current approaches of learning-based automated visual inspection. The system reaches a performance (F1-score) of up to 99.5%, corresponding to a relative improvement of the system’s fault detection capabilities by 8.6-fold. Moreover, by specifically selecting models for the given manufacturing chain, runtime constraints are satisfied while improving the detection capabilities of currently deployed approaches.

10 October 2023 in Bioengineering
Verified
Journal Article
Open access
PDF file
ASArunodhayan Sampath Sampathkumar
Arunodhayan Sampath Sampathkumar
Tobias SchlosserTobias Schlosser
Tobias Schlosser
HLHolger Langner
Holger Langner
MRMarc Ritter
Marc Ritter
Danny KowerkoDanny Kowerko
Danny Kowerko
Optical coherence tomography (OCT)-based retinal imagery is often utilized to determine influential factors in patient progression and treatment, for which the retinal layers of the human eye are investigated to assess a patient’s health status and eyesight. In this contribution, we propose a machine learning (ML)-based multistage system of stacked multiscale encoders and decoders for the image segmentation of OCT imagery of the retinal layers to enable the following evaluation regarding the physiological and pathological states. Our proposed system’s results highlight its benefits compared to currently investigated approaches by combining commonly deployed methods from deep learning (DL) while utilizing deep neural networks (DNN). We conclude that by stacking multiple multiscale encoders and decoders, improved scores for the image segmentation task can be achieved. Our retinal-layer-based segmentation results in a final segmentation performance of up to 82.25±0.74% for the Sørensen–Dice coefficient, outperforming the current best single-stage model by 1.55% with a score of 80.70±0.20%, given the evaluated peripapillary OCT data set. Additionally, we provide results on the data sets Duke SD-OCT, Heidelberg, and UMN to illustrate our model’s performance on especially noisy data sets.

13 January 2025 in Journal of Intelligent Manufacturing
Verified
Journal Article
Open access
PDF file
MFMichael Friedrich
Michael Friedrich
Tobias SchlosserTobias Schlosser
Tobias Schlosser
Danny KowerkoDanny Kowerko
Danny Kowerko
In semiconductor wafer dicing, one particular area of interest is the process of visual inspection to detect manufacturing defects that occur throughout the manufacturing process. Emerging defect patterns are typically in the micrometer range, translating to barely visible defects in pixel size on high-resolution imagery. The availability of rarely occurring defects is generally limited due to the labor-intensive nature of the related, highly specialized annotation task. Therefore, this contribution proposes a hybrid system for wafer and chip image data synthesis utilizing wafer and dicing path templates for the synthetic generation of large quantities of labeled flawless and, rarely, faulty chip and dicing street imagery. These are utilized for subsequent deep learning based defect detection and classification by employing a residual neural network as the core classifier for our visual inspection system. Our results show promising prospects when the original image data are supplemented with synthesized images by creating so-called composite data sets. Compared to the system’s baseline on the original data set, an F1-score-based relative improvement of up to 3.98 times was achieved. Furthermore, a novel synthetic-composite leave-one-out cross-validation (SC-LOOCV) method is proposed as a means to analyze the quality of our synthesized data for each specific wafer type. Based on these experiments, we scored a relative improvement of up to 5.99. For all our wafer types, overall relative improvement factors of 1.99 (composite) and 2.83 (SC-LOOCV) highlight the benefits of our realized system.

6 March 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
Tobias SchlosserTobias Schlosser
Tobias Schlosser
FBFrederik Beuth
Frederik Beuth
TMTrixy Meyer
Trixy Meyer
ASArunodhayan Sampath Sampathkumar
Arunodhayan Sampath Sampathkumar
GSGabriel Stolze
Gabriel Stolze
Danny KowerkoDanny Kowerko
Danny Kowerko
In ophthalmology, intravitreal operative medication therapy (IVOM) is a widespread treatment for diseases related to the age-related macular degeneration (AMD), the diabetic macular edema, as well as the retinal vein occlusion. However, in real-world settings, patients often suffer from loss of vision on time scales of years despite therapy, whereas the prediction of the visual acuity (VA) and the earliest possible detection of deterioration under real-life conditions is challenging due to heterogeneous and incomplete data. In this contribution, we present a workflow for the development of a research-compatible data corpus fusing different IT systems of the department of ophthalmology of a German maximum care hospital. The extensive data corpus allows predictive statements of the expected progression of a patient and his or her VA in each of the three diseases. For the disease AMD, we found out a significant deterioration of the visual acuity over time. Within our proposed multistage system, we subsequently classify the VA progression into the three groups of therapy “winners”, “stabilizers”, and “losers” (WSL classification scheme). Our OCT biomarker classification using an ensemble of deep neural networks results in a classification accuracy (F1-score) of over 98%, enabling us to complete incomplete OCT documentations while allowing us to exploit them for a more precise VA modelling process. Our VA prediction requires at least four VA examinations and optionally OCT biomarkers from the same time period to predict the VA progression within a forecasted time frame, whereas our prediction is currently restricted to IVOM/no therapy. We achieve a final prediction accuracy of 69% in macro average F1-score, while being in the same range as the ophthalmologists with 57.8 and $$50 \pm 10.7$$ 50 ± 10.7 % F1-score.

21 August 2024 in Computers
Verified
Journal Article
Open access
PDF file
SMSara Moniri
Sara Moniri
Tobias SchlosserTobias Schlosser
Tobias Schlosser
Danny KowerkoDanny Kowerko
Danny Kowerko
The Persian language, also known as Farsi, is distinguished by its intricate morphological richness, yet it contends with a paucity of linguistic resources. With an estimated 110 million speakers, it finds prevalence across Iran, Tajikistan, Uzbekistan, Iraq, Russia, Azerbaijan, and Afghanistan. However, despite its widespread usage, scholarly investigations into Persian document retrieval remain notably scarce. This circumstance is primarily attributed to the absence of standardized test collections, which impedes the advancement of comprehensive research endeavors within this realm. As data corpora are the foundation of natural language processing applications, this work aims at Persian language datasets to address their availability and structure. Subsequently, we motivate a learning-based framework for the processing of Persian texts and their recognition, for which current state-of-the-art approaches from deep learning, such as deep neural networks, are further discussed. Our investigations highlight the challenges of realizing such a system while emphasizing its possible benefits for an otherwise rarely covered language.

Verified
Journal Article
Open access
PDF file
RVRichard Vogel
Richard Vogel
Tobias SchlosserTobias Schlosser
Tobias Schlosser
RMRobert Manthey
Robert Manthey
MRMarc Ritter
Marc Ritter
MVMatthias Vodel
Matthias Vodel
KSKristan Alexander Schneider
Kristan Alexander Schneider
Background. The importance of explainable artificial intelligence and machine learning (XAI/XML) is increasingly being recognized, aiming to understand how information contributes to decisions, the method’s bias, or sensitivity to data pathologies. Efforts are often directed to post hoc explanations of black box models. These approaches add additional sources for errors without resolving their shortcomings. Less effort is directed into the design of intrinsically interpretable approaches. Methods. We introduce an intrinsically interpretable methodology motivated by ensemble learning: the League of Experts (LoE) model. We establish the theoretical framework first and then deduce a modular meta algorithm. In our description, we focus primarily on classification problems. However, LoE applies equally to regression problems. Specific to classification problems, we employ classical decision trees as classifier ensembles as a particular instance. This choice facilitates the derivation of human-understandable decision rules for the underlying classification problem, which results in a derived rule learning system denoted as RuleLoE. Results. In addition to 12 KEEL classification datasets, we employ two standard datasets from particularly relevant domains—medicine and finance—to illustrate the LoE algorithm. The performance of LoE with respect to its accuracy and rule coverage is comparable to common state-of-the-art classification methods. Moreover, LoE delivers a clearly understandable set of decision rules with adjustable complexity, describing the classification problem. Conclusions. LoE is a reliable method for classification and regression problems with an accuracy that seems to be appropriate for situations in which underlying causalities are in the center of interest rather than just accurate predictions or classifications.