arXiv subjects

Samira Masoudi

Publications and source records attributed to Samira Masoudi.

4 recordsLinked to original sources

arXiv2020

Adipose Tissue Segmentation in Unlabeled Abdomen MRI using Cross Modality Domain Adaptation

Abdominal fat quantification is critical since multiple vital organs are located within this region. Although computed tomography (CT) is a highly sensitive modality to segment body fat, it involves ionizing radiations which makes magnetic resonance imaging (MRI) a preferable alternative for this purpose. Additionally, the superior soft tissue contrast in MRI could lead to more accurate results. Yet, it is highly labor intensive to segment fat in MRI scans. In this study, we propose an algorithm based on deep learning technique(s) to automatically quantify fat tissue from MR images through a cross modality adaptation. Our method does not require supervised labeling of MR scans, instead, we utilize a cycle generative adversarial network (C-GAN) to construct a pipeline that transforms the existing MR scans into their equivalent synthetic CT (s-CT) images where fat segmentation is relatively easier due to the descriptive nature of HU (hounsfield unit) in CT images. The fat segmentation results for MRI scans were evaluated by expert radiologist. Qualitative evaluation of our segmentation results shows average success score of 3.80/5 and 4.54/5 for visceral and subcutaneous fat segmentation in MR images.

eess.IV↗

arXiv2019

Instance-Level Microtubule Tracking

We propose a new method of instance-level microtubule (MT) tracking in time-lapse image series using recurrent attention. Our novel deep learning algorithm segments individual MTs at each frame. Segmentation results from successive frames are used to assign correspondences among MTs. This ultimately generates a distinct path trajectory for each MT through the frames. Based on these trajectories, we estimate MT velocities. To validate our proposed technique, we conduct experiments using real and simulated data. We use statistics derived from real time-lapse series of MT gliding assays to simulate realistic MT time-lapse image series in our simulated data. This dataset is employed as pre-training and hyperparameter optimization for our network before training on the real data. Our experimental results show that the proposed supervised learning algorithm improves the precision for MT instance velocity estimation drastically to 71.3% from the baseline result (29.3%). We also demonstrate how the inclusion of temporal information into our deep network can reduce the false negative rates from 67.8% (baseline) down to 28.7% (proposed). Our findings in this work are expected to help biologists characterize the spatial arrangement of MTs, specifically the effects of MT-MT interactions.

cs.CV↗

arXiv2019

Microtubule Motility Analysis based on Time-Lapse Fluorescence Microscopy

This paper describes an investigation into part of the mechanical mechanisms underlying the formation of mitotic spindle, the cellular machinery responsible for chromosomal separation during cell division. In normal eukaryotic cells, spindles are composed of microtubule filaments that radiate outward from two centrosomes. In many transformed cells, however, centrosome number is misregulated resulting in cells with more than two centrosomes. Addressing the question of how these cells accommodate these additional structures by coalescing supernumerary centrosomes to form normal spindles will provide a powerful insight toward understanding the proliferation of cancer cells and developing new therapeutics. The process of centrosome coalescence is thought to involve motor proteins that function to slide microtubules relative to one another. Here we use in vitro motility assays combined with fluorescence microscopy to visualize, characterize and quantify microtubule-microtubule interactions. After segmenting the microtubules, their speed and direction of movement are the extracted features to cluster their interaction type. In order to evaluate the potential of our processing algorithm, we created a simulated dataset similar to the time-lapse series. Once our procedure has been optimized using the simulated data, we will apply it to the real data. Results of our analyses will provide a quantitative description of interaction among microtubules. This is a potentially important step toward more thorough understanding of cancer.

q-bio.SC↗

arXiv2019

Multiple Microtubule Tracking in Microscopy Time-Lapse Images Using Piecewise-stationary Multiple Motion Model Kalman Smoother

Microtubules are inherently dynamic sub-cellular filamentuous polymers that are spatially organized within the cell by motor proteins which cross-link and move microtubules. In-vitro microtubule motility assays, in which motors attached to a surface move microtubules along it, have been used traditionally to study motor function. However, the way in which microtubule-microtubule interactions affect microtubule movement remains largely unexplored. To address this question, time-lapse image series of in-vitro microtubule motility assays were obtained using total internal reflection fluorescence (TIRF) microscopy. Categorized as a general problem of multiple object tracking (MOT), particular challenges arising in this project include low feature diversity, dynamic instability, sudden changes in microtubules motility patterns, as well as their instantaneous appearance/disappearance. This work describes a new application of piecewise-stationary multiple motion model Kalman smoother (PMMS) for modeling individual microtubules motility trends. To both evaluate the capability of this procedure and optimize its hyper-parameters, a large dataset simulating the series of time-lapse images was used first. Next, we applied it to the sequence of frames from the real data. Results of our analyses provide a quantitative description of microtubule velocity which, in turn, enumerates the occurrence of microtubule-microtubule interactions per frame.

q-bio.QM↗