Ciencias Exactas y Ciencias de la Salud

Now showing 1 - 2 of 2

Lights, camera, and domain shift: using superpixels for domain generalization in image segmentation for multimodal endoscopies
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-05) Martínez García Peña, Rafael; Ochoa Ruiz, Gilberto; puemcuervo, emipsanchez; Falcón Morales, Luis Eduardo; Gónzales Mendoza, Miguel; School of Engineering and Sciences; Campus Monterrey; Ali, Sharib
Deep Learning models have made great advancements in image processing. Their ability to identify key parts of images and provide fast and accurate segmentation has been proven and used in many fields, such as city navigation and object recognition. However, there is one field that is both in need of the extra information that computers can provide and has proven elusive for the goals of robustness and accuracy: Medicine. In the medical field, limitations in the amount of data and in the variation introduced by factors such as differences in instrumentation introduce a grave threat to the accuracy of a model known as domain shift. Domain shift occurs when we train with data that has a set of characteristics that is not wholly representative of the entire set of data a task encompasses. When it is present, models that have no tools to deal with it can observe a degradation to their accuracy to such degree that they can be transformed from usable to useless. To better explore this topic, we discuss two techniques: Domain adaptation, where we find how to make a model better at predicting for specific domain of data inside a task, and Domain generalization, where we find how to make a model better at predicting data for any domain inside a task. In addition, we discuss several image segmentation models that have shown good results for medical tasks: U-Net, Attention U-Net, DeepLab, Efficient U-Net, and EndoUDA. Following this exploration, we propose a solution model based on a domain generalization technique: Patch-based consistency. We use a superpixel generator known as SLIC (Simple Linear Iterative Clustering) to provide low-level, domain-agnostic information to different models in order to encourage our networks to learn more global features. This framework, which we refer to as SUPRA (SUPeRpixel Augmented), is used in tandem with U-Net, Attention U-Net, and Efficient U-Net in an effort to improve results in endoscopies where light modalities are switched: Something commonly seen in lesion detection tasks (particularly in Barrett's Esophagus and Polyp detection). We find that the best of these models, SUPRA-UNet, shows significant qualities that make it a better choice than unaugmented networks for lesion detection: Not only does it provide less noisy and smoother predictions, but it outperforms other networks by over 20% IoU versus the best results (U-Net) in a target domain that presents significant lighting differences from the training set.
Characterization of jet fire flame temperature zones using a deep learning-based segmentation approach
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-12-02) Pérez Guerrero, Carmina; OCHOA RUIZ, GILBERTO; 352103; Ochoa Ruiz, Gilberto; puemcuervo; González Mendoza, Miguel; Mata Miquel, Christian; School of Engineering and Sciences; Campus Monterrey; Palacios Rosas, Adriana
Jet fires are relatively small and have the least severe effects among the diverse fire accidents that can occur in industrial plants; however, they are usually involved in a process known as domino effect, that leads to more severe events, such as explosions or the initiation of another fire, making the analysis of such fires an important part of risk analysis. One such analysis would be the segmentation of different radiation zones within the flame, therefore this thesis presents an exploratory research regarding several traditional computer vision and Deep Learning segmentation approaches to solve this specific problem. A data set of propane jet fires is used to train and evaluate the different approaches. Different metrics are correlated to a manual ranking performed by experts to make an evaluation that closely resembles the expert’s criteria. Additionally, given the difference in the distribution of the zones and background of the images, different loss functions, that seek to alleviate data imbalance, are explored. The Hausdorff Distance and Adjusted Rand Index were the metrics with the highest correlation and the best results were obtained from training with a Weighted Cross-Entropy Loss. The best performing models were found to be the UNet architecture, along with its recent variations, Attention UNet and UNet++. These models are then used to segment a group of vertical jet flames of varying pipe outlet diameters to extract their main geometrical characteristics. Attention UNet obtained the best general performance in the approximation of both height and area of the flames, while also showing a statistically significant difference between it and UNet++. UNet obtained the best overall performance for the approximation of the lift-off distances; however, there is not enough data to prove a statistically significant difference between UNet and its two variations. The only instance where UNet++ outperformed the other models, was while obtaining the lift-off distances of the jet flames with 0.01275 m pipe outlet diameter. In general, the explored models show good agreement between the experimental and predicted values for relatively large turbulent propane jet flames, released in sonic and subsonic regimes; thus, making these radiation zones segmentation models, a suitable approach for different jet flame risk management scenarios.

Ciencias Exactas y Ciencias de la Salud

Browse

Filters

Settings

Sort By

Results per page

Search Results