arXiv subjects

Tripti Bameta

Publications and source records attributed to Tripti Bameta.

9 recordsLinked to original sources

arXiv2024

Semantic Segmentation Based Quality Control of Histopathology Whole Slide Images

We developed a software pipeline for quality control (QC) of histopathology whole slide images (WSIs) that segments various regions, such as blurs of different levels, tissue regions, tissue folds, and pen marks. Given the necessity and increasing availability of GPUs for processing WSIs, the proposed pipeline comprises multiple lightweight deep learning models to strike a balance between accuracy and speed. The pipeline was evaluated in all TCGAs, which is the largest publicly available WSI dataset containing more than 11,000 histopathological images from 28 organs. It was compared to a previous work, which was not based on deep learning, and it showed consistent improvement in segmentation results across organs. To minimize annotation effort for tissue and blur segmentation, annotated images were automatically prepared by mosaicking patches (sub-images) from various WSIs whose labels were identified using a patch classification tool HistoROI. Due to the generality of our trained QC pipeline and its extensive testing the potential impact of this work is broad. It can be used for automated pre-processing any WSI cohort to enhance the accuracy and reliability of large-scale histopathology image analysis for both research and clinical use. We have made the trained models, training scripts, training data, and inference results publicly available at https://github.com/abhijeetptl5/wsisegqc, which should enable the research community to use the pipeline right out of the box or further customize it to new datasets and applications in the future.

eess.IV↗

arXiv2024

Efficient Quality Control of Whole Slide Pathology Images with Human-in-the-loop Training

Histopathology whole slide images (WSIs) are being widely used to develop deep learning-based diagnostic solutions, especially for precision oncology. Most of these diagnostic softwares are vulnerable to biases and impurities in the training and test data which can lead to inaccurate diagnoses. For instance, WSIs contain multiple types of tissue regions, at least some of which might not be relevant to the diagnosis. We introduce HistoROI, a robust yet lightweight deep learning-based classifier to segregate WSI into six broad tissue regions -- epithelium, stroma, lymphocytes, adipose, artifacts, and miscellaneous. HistoROI is trained using a novel human-in-the-loop and active learning paradigm that ensures variations in training data for labeling-efficient generalization. HistoROI consistently performs well across multiple organs, despite being trained on only a single dataset, demonstrating strong generalization. Further, we have examined the utility of HistoROI in improving the performance of downstream deep learning-based tasks using the CAMELYON breast cancer lymph node and TCGA lung cancer datasets. For the former dataset, the area under the receiver operating characteristic curve (AUC) for metastasis versus normal tissue of a neural network trained using weakly supervised learning increased from 0.88 to 0.92 by filtering the data using HistoROI. Similarly, the AUC increased from 0.88 to 0.93 for the classification between adenocarcinoma and squamous cell carcinoma on the lung cancer dataset. We also found that the performance of the HistoROI improves upon HistoQC for artifact detection on a test dataset of 93 annotated WSIs. The limitations of the proposed model are analyzed, and potential extensions are also discussed.

eess.IV↗

arXiv2024

HER2 and FISH Status Prediction in Breast Biopsy H&E-Stained Images Using Deep Learning

The current standard for detecting human epidermal growth factor receptor 2 (HER2) status in breast cancer patients relies on HER2 amplification, identified through fluorescence in situ hybridization (FISH) or immunohistochemistry (IHC). However, hematoxylin and eosin (H\&E) tumor stains are more widely available, and accurately predicting HER2 status using H\&E could reduce costs and expedite treatment selection. Deep Learning algorithms for H&E have shown effectiveness in predicting various cancer features and clinical outcomes, including moderate success in HER2 status prediction. In this work, we employed a customized weak supervision classification technique combined with MoCo-v2 contrastive learning to predict HER2 status. We trained our pipeline on 182 publicly available H&E Whole Slide Images (WSIs) from The Cancer Genome Atlas (TCGA), for which annotations by the pathology team at Yale School of Medicine are publicly available. Our pipeline achieved an Area Under the Curve (AUC) of 0.85 across four different test folds. Additionally, we tested our model on 44 H&E slides from the TCGA-BRCA dataset, which had an HER2 score of 2+ and included corresponding HER2 status and FISH test results. These cases are considered equivocal for IHC, requiring an expensive FISH test on their IHC slides for disambiguation. Our pipeline demonstrated an AUC of 0.81 on these challenging H&E slides. Reducing the need for FISH test can have significant implications in cancer treatment equity for underserved populations.

eess.IV↗

arXiv2023

Combining Datasets with Different Label Sets for Improved Nucleus Segmentation and Classification

Segmentation and classification of cell nuclei in histopathology images using deep neural networks (DNNs) can save pathologists' time for diagnosing various diseases, including cancers, by automating cell counting and morphometric assessments. It is now well-known that the accuracy of DNNs increases with the sizes of annotated datasets available for training. Although multiple datasets of histopathology images with nuclear annotations and class labels have been made publicly available, the set of class labels differ across these datasets. We propose a method to train DNNs for instance segmentation and classification on multiple datasets where the set of classes across the datasets are related but not the same. Specifically, our method is designed to utilize a coarse-to-fine class hierarchy, where the set of classes labeled and annotated in a dataset can be at any level of the hierarchy, as long as the classes are mutually exclusive. Within a dataset, the set of classes need not even be at the same level of the class hierarchy tree. Our results demonstrate that segmentation and classification metrics for the class set used by the test split of a dataset can improve by pre-training on another dataset that may even have a different set of classes due to the expansion of the training set enabled by our method. Furthermore, generalization to previously unseen datasets also improves by combining multiple other datasets with different sets of classes for training. The improvement is both qualitative and quantitative. The proposed method can be adapted for various loss functions, DNN architectures, and application domains.

cs.CV↗

arXiv2021

Nucleosome sliding can influence the spreading of histone modifications

Nucleosomes are the fundamental building blocks of chromatin that not only help in the folding of chromatin but also in carrying epigenetic information. It is known that nucleosome sliding is responsible for dynamically organizing chromatin structure and the resulting gene regulation. Since sliding can move two neighboring nucleosomes physically close or away, can it play a role in the spreading of histone modifications? We investigate this by simulating a stochastic model that couples nucleosome dynamics with the kinetics of histone modifications. We show that the sliding of nucleosomes can affect the modification pattern as well as the time it takes to modify a given region of chromatin. Exploring different nucleosome densities and modification kinetic parameters, we show that nucleosome sliding can be important for creating histone modification domains. Our model predicts that nucleosome density coupled with sliding dynamics can create an asymmetric histone modification profile around regulatory regions. We also compute the probability distribution of modified nucleosomes and relaxation kinetics of modifications. Our predictions are comparable with known experimental results.

physics.bio-ph↗

arXiv2015

A Multispecies Exclusion Model Inspired By Transcriptional Interference

We introduce exclusion models of two distinguishable species of hard rods with their distinct sites of entry and exit under open boundary conditions. In the first model both species of rods move in the same direction whereas in the other two models they move in the opposite direction. These models are motivated by the biological phenomenon known as Transcriptional Interference. Therefore, the rules for the kinetics of the models, particularly the rules for the outcome of the encounter of the rods, are also formulated to mimic those observed in Transcriptional Interference. By a combination of mean-field theory and computer simulation of these models we demonstrate how the flux of one species of rods is completely switched off by the other. Exploring the parameter space of the model we also establish the conditions under which switch-like regulation of two fluxes is possible; from the extensive analysis we discover more than one possible mechanism of this phenomenon.

physics.bio-ph↗

arXiv2015

Sufficient conditions for the additivity of stall forces generated by multiple filaments or motors

Molecular motors and cytoskeletal filaments work collectively most of the time under opposing forces. This opposing force may be due to cargo carried by motors or resistance coming from the cell membrane pressing against the cytoskeletal filaments. Some recent studies have shown that the collective maximum force (stall force) generated by multiple cytoskeletal filaments or molecular motors may not always be just a simple sum of the stall forces of the individual filaments or motors. To understand this excess or deficit in the collective force, we study a broad class of models of both cytoskeletal filaments and molecular motors. We argue that the stall force generated by a group of filaments or motors is additive, that is, the stall force of $N$ number of filaments (motors) is $N$ times the stall force of one filament (motor), when the system is in equilibrium at stall. Conversely, we show that this additive property typically does not hold true when the system is not at equilibrium at stall. We thus present a novel and unified understanding of the existing models exhibiting such non-addivity, and generalise our arguments by developing new models that demonstrate this phenomena. We also propose a quantity similar to thermodynamic efficiency to easily predict this deviation from stall-force additivity for filament and motor collectives.

cond-mat.soft↗

arXiv2015

Mixed molecular motor traffic on nucleic acid tracks: models of transcriptional interference and regulation of gene expression

RNA polymerase (RNAP) is molecular machine that polymerizes a RNA molecule, a linear heteropolymer, using a single stranded DNA (ssDNA) as the corresponding template; the sequence of monomers of the RNA is dictated by that of monomers on the ssDNA template. While polymerizing a RNA, the RNAP walks step-by-step on the ssDNA template in a specific direction. Thus, a RNAP can be regarded also as a molecular motor and the sites of start and stop of its walk on the DNA mark the two ends of the genetic message that it transcribes into RNA. Interference of transcription of two overlapping genes is believed to regulate the levels of their expression, i.e., the overall rate of the corresponding RNA synthesis, through suppressive effect of one on the other. Here we model this process as a mixed traffic of two groups of RNAP motors that are characterized by two distinct pairs of start and stop sites. Each group polymerizes identical copies of a RNA while the RNAs polymerized by the two groups are different. These models, which may also be viewed as two interfering totally asymmetric simple exclusion processes, account for all modes of transcriptional interference in spite of their extreme simplicity. A combination of mean-field theory and computer simulation of these models demonstrate the physical origin of the switch-like regulation of the two interfering genes in both co-directional and contra-directional traffic of the two groups of RNAP motors.

physics.bio-ph↗

arXiv2012

Broad-tailed force distributions and velocity ordering in a heterogeneous membrane model for collective cell migration

Correlated velocity patterns and associated large length-scale transmission of traction forces have been observed in collective live cell migration as a response to a "wound". We argue that a simple physical model of a force-driven heterogeneous elastic membrane sliding over a viscous substrate can qualitatively explain a few experimentally observed facts: (i) the growth of velocity ordering which spreads from the wound boundary to the interior, (ii) the exponential tails of the traction force distributions, and (iii) the swirling pattern of velocities in the interior of the tissue.

physics.bio-ph↗