Deep learning the high variability and randomness inside multimode fibers

ABSTRACTMorphometrics has been applied in several fields of science including botany. Plant leaves are been one of the most important organs in the identification of plants due to its high variability across different plant groups. The differences between and within plant species reflect variations in genotypes, development, evolution, and environment. While traditional morphometrics has contributed tremendously to reducing the problems that come with the identification of plants and delimitation of species based on morphology, technological advancements have led to the creation of deep learning digital solutions that made it easy to study leaves and detect more characters to complement already existing leaf datasets. In this study, we demonstrate the use of MorphoLeaf in generating morphometric dataset from 140 leaf specimens from seven Cucurbitaceae species via scanning of leaves, extracting landmarks, data extraction, landmarks data quantification, and reparametrization and normalization of leaf contours. PCA analysis revealed that blade area, blade perimeter, tooth area, tooth perimeter, height of (each position of the) tooth from tip, and the height of each (position of the) tooth from base are important and informative landmarks that contribute to the variation within the species studied. Our results demonstrate that MorphoLeaf can quantitatively track diversity in leaf specimens, and it can be applied to functionally integrate morphometrics and shape visualization in the digital identification of plants. The success of digital morphometrics in leaf outline analysis presents researchers with opportunities to apply and carry out more accurate image-based researches in diverse areas including, but not limited to, plant development, evolution, and phenotyping.

Download Full-text

Improving generalization of deep learning models for diagnostic pathology by increasing variability in training data: experiments on osteosarcoma subtypes

10.1101/2020.09.10.20192294 ◽

2020 ◽

Author(s):

Haiming Tang ◽

Nanfei Sun ◽

Steven Shen

Keyword(s):

Deep Learning ◽

Model Performance ◽

High Variability ◽

Training Data ◽

Classification Model ◽

Training Dataset ◽

Learning Models ◽

Diagnostic Pathology ◽

Model Generalization ◽

Histopathological Images

Artificial intelligence (AI) has an emerging progress in diagnostic pathology. A large number of studies of applying deep learning models to histopathological images have been published in recent years. While many studies claim high accuracies, they may fall into the pitfalls of overfitting and lack of generalization due to the high variability of the histopathological images. We use the example of Osteosarcoma to illustrate the pitfalls and how the addition of model input variability can help improve model performance. We use the publicly available osteosarcoma dataset to retrain a previously published classification model for osteosarcoma. We partition the same set of images into the training and testing datasets differently than the original study: the test dataset consists of images from one patient while the training dataset consists images of all other patients. The performance of the model on the test set using the new partition schema declines dramatically, indicating a lack of model generalization and overfitting.We also show the influence of training data variability on model performance by collecting a minimal dataset of 10 osteosarcoma subtypes as well as benign tissues and benign bone tumors of differentiation. We show the additions of more and more subtypes into the training data step by step under the same model schema yield a series of coherent models with increasing performances. In conclusion, we bring forward data preprocessing and collection tactics for histopathological images of high variability to avoid the pitfalls of overfitting and build deep learning models of higher generalization abilities.

Download Full-text

Deep learning assisted image transmission in multimode fibers

Adaptive Optics and Wavefront Control for Biological Systems V ◽

10.1117/12.2508383 ◽

2019 ◽

Author(s):

Babak Rahmani ◽

Damien Loterie ◽

Georgia Konstantinou ◽

Demetri Psaltis ◽

Christophe Moser

Keyword(s):

Deep Learning ◽

Image Transmission ◽

Multimode Fibers

Download Full-text

Deep learning characterizes optical pulses using speckle patterns at the end of multimode fibers

Scilight ◽

10.1063/10.0002039 ◽

2020 ◽

Vol 2020 (38) ◽

pp. 381102

Author(s):

Aili McConnon

Keyword(s):

Deep Learning ◽

Optical Pulses ◽

Multimode Fibers ◽

Speckle Patterns

Download Full-text

Challenges in Building of Deep Learning Models for Glioblastoma Segmentation: Evidence from Clinical Data

Studies in Health Technology and Informatics - Public Health and Informatics ◽

10.3233/shti210168 ◽

2021 ◽

Author(s):

Anvar Kurmukov ◽

Aleksandra Dalechina ◽

Talgat Saparov ◽

Mikhail Belyaev ◽

Svetlana Zolotova ◽

...

Keyword(s):

Deep Learning ◽

Clinical Data ◽

High Performance ◽

Heterogeneous Data ◽

High Variability ◽

Clinical Settings ◽

Training Procedure ◽

Imaging Data ◽

Magnetic Resonance Imaging Mri ◽

Segmentation Models

In this article, we compare the performance of a state-of-the-art segmentation network (UNet) on two different glioblastoma (GB) segmentation datasets. Our experiments show that the same training procedure yields almost twice as bad results on the retrospective clinical data compared to the BraTS challenge data (in terms of Dice score). We discuss possible reasons for such an outcome, including inter-rater variability and high variability in magnetic resonance imaging (MRI) scanners and scanner settings. The high performance of segmentation models, demonstrated on preselected imaging data, does not bring the community closer to using these algorithms in clinical settings. We believe that a clinically applicable deep learning architecture requires a shift from unified datasets to heterogeneous data.

Download Full-text