Deep Shape Analysis on Abdominal Organs for Diabetes Prediction

Gutiérrez-Becker, Benjamín; Gatidis, Sergios; Gutmann, Daniel A.P.; Peters, Annette; Schlett, Christopher L.; Bamberg, Fabian; Wachinger, Christian

doi:10.1007/978-3-030-04747-4_21

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The network is trained completely, allowing it to learn an optimal representation without relying on manually created shape descriptors. To evaluate the proposed method, we extend the Brain Print form descriptor to Abdomen Print and compare the results (Gutiérrez-Becker et al 2018).…”

Section: Literature Reviewmentioning

confidence: 99%

Integrating Machine Learning for Accurate Prediction of Early Diabetes

Bandhu,

Litoriya,

Rathore

et al. 2023

International Journal of Cyber Behavior, Psychology and Learning

View full text Add to dashboard Cite

In the current world, where diabetes is day by day becoming a very common and fatal disease, it's important that proper measures be taken in order to deal with it. As per the studies, early prediction of diabetes can lead to improved treatment to avoid further complications of the disease, and in order to do so efficiently, machine learning techniques are a great deal. In this study, various factors are taken into consideration, like blood pressure, pregnancy, glucose level, age, insulin, skin thickness, and diabetes pedigree function, which together can be useful to predict whether a person has a risk of developing diabetes or not and help society with the early diagnosis of diabetes. This model is trained using three main classification algorithms, namely support vector, random forest, and decision tree classifiers. The prediction results of each of the classifiers are summarized in this study, and the decision tree gives 78.89% accuracy.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Integrating Machine Learning for Accurate Prediction of Early Diabetes

Bandhu,

Litoriya,

Rathore

et al. 2023

International Journal of Cyber Behavior, Psychology and Learning

View full text Add to dashboard Cite

show abstract

“…This shape descriptor is typically a low-dimensional representation learned from the population shape data; PCA scores is an example of such shape descriptor. Subsequent analyses are application-dependent and may vary from binary prediction of a pathology [25], a localized detection of a morphological defect [26], or understanding subtleties of the morphology and testing the associated scientific hypotheses [47].…”

Section: Introductionmentioning

confidence: 99%

DeepSSM: A Blueprint for Image-to-Shape Deep Learning Models

Bhalodia¹,

Elhabian²,

Adams³

et al. 2021

Preprint

View full text Add to dashboard Cite

Statistical shape modeling (SSM) characterizes anatomical variations in a population of shapes generated from medical images. Statistical analysis of shapes requires consistent shape representation across samples in shape cohort. Establishing this representation entails a processing pipeline that includes anatomy segmentation, image re-sampling, shape-based registration, and nonlinear, iterative optimization. These shape representations are then used to extract low-dimensional shape descriptors that are anatomically relevant to facilitate subsequent statistical analyses in different applications. However, the current process of obtaining these shape descriptors from imaging data relies on human and computational resources, requiring domain expertise for segmenting anatomies of interest. Moreover, this same taxing pipeline needs to be repeated to infer shape descriptors for new image data using a pre-trained/existing shape model. Here, we propose DeepSSM, a deep learning-based framework for learning the functional mapping from images to low-dimensional shape descriptors and their associated shape representations, thereby inferring statistical representation of anatomy directly from 3D images. Once trained using an existing shape model, DeepSSM circumvents the heavy and manual pre-processing and segmentation required by classical models and significantly improves the computational time, making it a viable solution for fully end-to-end shape modeling applications. In addition, we introduce a model-based data-augmentation strategy to address data scarcity, a typical scenario in shape modeling applications. Finally, this paper presents and analyzes two different architectural variants of DeepSSM with different loss functions using three medical datasets and their downstream clinical application. Experiments showcase that DeepSSM performs comparably or better to the state-of-the-art SSM both quantitatively and on application-driven downstream tasks. Therefore, DeepSSM aims to provide a comprehensive blueprint for deep learning-based image-to-shape models.

show abstract

Deep Shape Analysis on Abdominal Organs for Diabetes Prediction

Cited by 2 publications

References 20 publications

Integrating Machine Learning for Accurate Prediction of Early Diabetes

Integrating Machine Learning for Accurate Prediction of Early Diabetes

DeepSSM: A Blueprint for Image-to-Shape Deep Learning Models

Contact Info

Product

Resources

About