Biology subjects

Riesterer, J. L.

Publications and source records attributed to Riesterer, J. L..

7 recordsLinked to original sources

bioRxiv2023

Towards Generalizability and Robustness in Biological Object Detection in Electron Microscopy Images

Machine learning approaches have the potential for meaningful impact in the biomedical field. However, there are often challenges unique to biomedical data that prohibits the adoption of these innovations. For example, limited data, data volatility, and data shifts all compromise model robustness and generalizability. Without proper tuning and data management, deploying machine learning models in the presence of unaccounted for corruptions leads to reduced or misleading performance. This study explores techniques to enhance model generalizability through iterative adjustments. Specifically, we investigate a detection tasks using electron microscopy images and compare models trained with different normalization and augmentation techniques. We found that models trained with Group Normalization or texture data augmentation outperform other normalization techniques and classical data augmentation, enabling them to learn more generalized features. These improvements persist even when models are trained and tested on disjoint datasets acquired through diverse data acquisition protocols. Results hold true for transformerand convolution-based detection architectures. The experiments show an impressive 29% boost in average precision, indicating significant enhancements in the models generalizibality. This underscores the models capacity to effectively adapt to diverse datasets and demonstrates their increased resilience in real-world applications.

bioengineering↗

bioRxiv2023

Efficient semi-supervised semantic segmentation of electron microscopy cancer images with sparse annotations

Electron microscopy (EM) enables imaging at nanometer resolution and can shed light on how cancer evolves to develop resistance to therapy. Acquiring these images has become a routine task; however, analyzing them is now the bottleneck, as manual structure identification is very time-consuming and can take up to several months for a single sample. Deep learning approaches offer a suitable solution to speed up the analysis. In this work, we present a study of several state-of-the-art deep learning models for the task of segmenting nuclei and nucleoli in volumes from tumor biopsies. We compared previous results obtained with the ResUNet architecture to the more recent UNet++, FracTALResNet, SenFormer, and CEECNet models. In addition, we explored the utilization of unlabeled images through semi-supervised learning with Cross Pseudo Supervision. We have trained and evaluated all of the models on sparse manual labels from three fully annotated in-house datasets that we have made available on demand, demonstrating improvements in terms of 3D Dice score. From the analysis of these results, we drew conclusions on the relative gains of using more complex models, semi-supervised learning as well as next steps for the mitigation of the manual segmentation bottleneck.

bioengineering↗

bioRxiv2021

Robust Segmentation of Cellular Ultrastructure on Sparsely Labeled 3D Electron Microscopy Images using Deep Learning

A deeper understanding of the cellular and subcellular organization of tumor cells and their interactions with the tumor microenvironment will shed light on how cancer evolves and guide effective therapy choices. Electron microscopy (EM) images can provide detailed view of the cellular ultrastructure and are being generated at an ever-increasing rate. However, the bottleneck in their analysis is the delineation of the cellular structures to enable interpretable rendering. We have mitigated this limitation by using deep learning, specifically, the ResUNet architecture, to segment cells and subcellular ultrastructure. Our initial prototype focuses on segmenting nuclei and nucleoli in 3D FIB-SEM images of tumor biopsies obtained from patients with metastatic breast and pancreatic cancers. Trained with sparse manual labels, our method results in accurate segmentation of nuclei and nucleoli with best Dice score of 0.99 and 0.98 respectively. This method can be extended to other cellular structures, enabling deeper analysis of inter- and intracellular state and interactions.

cancer biology↗

bioRxiv2021

Noise Reconstruction & Removal Network: A New Architecture to Denoise FIB-SEM Images

Recent advances in Focused Ion Beam-Scanning Electron Microscopy (FIB-SEM) allows the imaging and analysis of cellular ultrastructure at nanoscale resolution, but the collection of labels and/or noise-free data sets has several challenges, often immutable. Reasons range from time consuming manual annotations, requiring highly trained specialists, to introducing imaging artifacts from the prolonged scanning during acquisition. We propose a fully unsupervised Noise Reconstruction and Removal Network for denoising scanning electron microscopy images. The architecture, inspired by gated recurrent units, reconstructs and removes the noise by synthesizing the sequential data. At the same time the fully unsupervised training guides the network in distinguishing true signal from noise and gives comparable results to supervised architectures. We demonstrate that this new network specialized on 3D electron microscopy data sets, achieves comparable and even better results than supervised networks.

bioengineering↗

bioRxiv2020

An Integrated Clinical, Omic, and Image Atlas of an Evolving Metastatic Breast Cancer

Mechanisms of therapeutic resistance manifest in metastatic cancers as tumor cell intrinsic alterations and extrinsic microenvironmental influences that can change during treatment. To support the development of methods for the identification of these mechanisms in individual patients, we present here an Omic and Multidimensional Spatial (OMS) Atlas generated from four serial biopsies of a metastatic breast cancer patient during 3.5 years of therapy. This resource links detailed, longitudinal clinical metadata including treatment times and doses, anatomic imaging, and blood-based response measurements to exploratory analytics including comprehensive DNA, RNA, and protein profiles, images of multiplexed immunostaining, and 2- and 3-dimensional scanning electron micrographs. These data reveal aspects of therapy-associated heterogeneity and evolution of the cancers genome, signaling pathways, immune microenvironment, cellular composition and organization, and ultrastructure. We present illustrative examples showing how integrative analyses of these data provide insights into potential mechanisms of response and resistance, and suggest novel therapeutic vulnerabilities.

cancer biology↗

bioRxiv2020

Multiscale cardiac imaging to capture the whole heart and its internal cellular architecture, with applications to congenital heart disease

Efficient cardiac pumping depends on the morphological structure of the heart, but also on its sub-cellular (ultrastructural) architecture, which enables cardiac contraction. In cases of congenital heart defects, localized sub-cellular disruptions in architecture that increase the risk of heart failure are only starting to be discovered. This is in part due to a lack of technologies that can image the three dimensional (3D) heart structure, assessing malformations; and its ultrastructure, assessing disruptions. We present here a multiscale, correlative imaging procedure that achieves high-resolution images of the whole heart, using 3D micro-computed tomography (micro-CT); and its ultrastructure, using 3D scanning electron microscopy (SEM). This combination of technologies has not been possible before in imaging the same cardiac sample due to the heart large size, even when studying small fetal and neonatal animal models (~5x5x5mm3). Here, we achieved uniform fixation and staining of the whole heart, without losing ultrastructural preservation (at the nm resolution range). Our approach enables multiscale studies of cardiac architecture in models of congenital heart disease and beyond.

developmental biology↗

bioRxiv2019

A workflow for visualizing human cancer biopsies using large-format electron microscopy

Recent developments in large format electron microscopy have enabled generation of images that provide detailed ultrastructural information on normal and diseased cells and tissues. Analyses of these images increase our understanding of cellular organization and interactions and disease-related changes therein. In this manuscript, we describe a workflow for two-dimensional (2D) and three-dimensional (3D) imaging, including both optical and scanning electron microscopy (SEM) methods, that allow pathologists and cancer biology researchers to identify areas of interest from human cancer biopsies. The protocols and mounting strategies described in this workflow are compatible with 2D large format EM mapping, 3D focused ion beam-SEM and serial block face-SEM. The flexibility to use diverse imaging technologies available at most academic institutions makes this workflow useful and applicable for most life science samples. Volumetric analysis of the biopsies studied here revealed morphological, organizational and ultrastructural aspects of the tumor cells and surrounding environment that cannot be revealed by conventional 2D EM imaging. Our results indicate that although 2D EM is still an important tool in many areas of diagnostic pathology, 3D images of ultrastructural relationships between both normal and cancerous cells, in combination with their extracellular matrix, enables cancer researchers and pathologists to better understand the progression of the disease and identify potential therapeutic targets.

cancer biology↗