Vishwa S. Parekh

Adway U. Kanhere, Pranav Kulkarni, Paul H. Yi et al.

Segmentation is one of the most primary tasks in deep learning for medical imaging, owing to its multiple downstream clinical applications. However, generating manual annotations for medical images is time-consuming, requires high skill, and is an expensive effort, especially for 3D images. One potential solution is to aggregate knowledge from partially annotated datasets from multiple groups to collaboratively train global models using Federated Learning. To this end, we propose SegViz, a federated learning-based framework to train a segmentation model from distributed non-i.i.d datasets with partial annotations. The performance of SegViz was compared against training individual models separately on each dataset as well as centrally aggregating all the datasets in one place and training a single model. The SegViz framework using FedBN as the aggregation strategy demonstrated excellent performance on the external BTCV set with dice scores of 0.93, 0.83, 0.55, and 0.75 for segmentation of liver, spleen, pancreas, and kidneys, respectively, significantly ($p<0.05$) better (except spleen) than the dice scores of 0.87, 0.83, 0.42, and 0.48 for the baseline models. In contrast, the central aggregation model significantly ($p<0.05$) performed poorly on the test dataset with dice scores of 0.65, 0, 0.55, and 0.68. Our results demonstrate the potential of the SegViz framework to train multi-task models from distributed datasets with partial labels. All our implementations are open-source and available at https://anonymous.4open.science/r/SegViz-B746

Guangyao Zheng, Samson Zhou, Vladimir Braverman et al.

Selective experience replay is a popular strategy for integrating lifelong learning with deep reinforcement learning. Selective experience replay aims to recount selected experiences from previous tasks to avoid catastrophic forgetting. Furthermore, selective experience replay based techniques are model agnostic and allow experiences to be shared across different models. However, storing experiences from all previous tasks make lifelong learning using selective experience replay computationally very expensive and impractical as the number of tasks increase. To that end, we propose a reward distribution-preserving coreset compression technique for compressing experience replay buffers stored for selective experience replay. We evaluated the coreset compression technique on the brain tumor segmentation (BRATS) dataset for the task of ventricle localization and on the whole-body MRI for localization of left knee cap, left kidney, right trochanter, left lung, and spleen. The coreset lifelong learning models trained on a sequence of 10 different brain MR imaging environments demonstrated excellent performance localizing the ventricle with a mean pixel error distance of 12.93 for the compression ratio of 10x. In comparison, the conventional lifelong learning model localized the ventricle with a mean pixel distance of 10.87. Similarly, the coreset lifelong learning models trained on whole-body MRI demonstrated no significant difference (p=0.28) between the 10x compressed coreset lifelong learning models and conventional lifelong learning models for all the landmarks. The mean pixel distance for the 10x compressed models across all the landmarks was 25.30, compared to 19.24 for the conventional lifelong learning models. Our results demonstrate that the potential of the coreset-based ERB compression method for compressing experiences without a significant drop in performance.

Guangyao Zheng, Michael A. Jacobs, Vladimir Braverman et al.

Federated learning is a recent development in the machine learning area that allows a system of devices to train on one or more tasks without sharing their data to a single location or device. However, this framework still requires a centralized global model to consolidate individual models into one, and the devices train synchronously, which both can be potential bottlenecks for using federated learning. In this paper, we propose a novel method of asynchronous decentralized federated lifelong learning (ADFLL) method that inherits the merits of federated learning and can train on multiple tasks simultaneously without the need for a central node or synchronous training. Thus, overcoming the potential drawbacks of conventional federated learning. We demonstrate excellent performance on the brain tumor segmentation (BRATS) dataset for localizing the left ventricle on multiple image sequences and image orientation. Our framework allows agents to achieve the best performance with a mean distance error of 7.81, better than the conventional all-knowing agent's mean distance error of 11.78, and significantly (p=0.01) better than a conventional lifelong learning agent with a distance error of 15.17 after eight rounds of training. In addition, all ADFLL agents have comparable or better performance than a conventional LL agent. In conclusion, we developed an ADFLL framework with excellent performance and speed-up compared to conventional RL agents.

Guangyao Zheng, Shuhao Lai, Vladimir Braverman et al.

While Deep Reinforcement Learning has been widely researched in medical imaging, the training and deployment of these models usually require powerful GPUs. Since imaging environments evolve rapidly and can be generated by edge devices, the algorithm is required to continually learn and adapt to changing environments, and adjust to low-compute devices. To this end, we developed three image coreset algorithms to compress and denoise medical images for selective experience replayed-based lifelong reinforcement learning. We implemented neighborhood averaging coreset, neighborhood sensitivity-based sampling coreset, and maximum entropy coreset on full-body DIXON water and DIXON fat MRI images. All three coresets produced 27x compression with excellent performance in localizing five anatomical landmarks: left knee, right trochanter, left kidney, spleen, and lung across both imaging environments. Maximum entropy coreset obtained the best performance of $11.97\pm 12.02$ average distance error, compared to the conventional lifelong learning framework's $19.24\pm 50.77$.

Pranav Kulkarni, Adway Kanhere, Paul H. Yi et al.

Numerous large-scale chest x-ray datasets have spearheaded expert-level detection of abnormalities using deep learning. However, these datasets focus on detecting a subset of disease labels that could be present, thus making them distributed and non-iid with partial labels. Recent literature has indicated the impact of batch normalization layers on the convergence of federated learning due to domain shift associated with non-iid data with partial labels. To that end, we propose FedFBN, a federated learning framework that draws inspiration from transfer learning by using pretrained networks as the model backend and freezing the batch normalization layers throughout the training process. We evaluate FedFBN with current FL strategies using synthetic iid toy datasets and large-scale non-iid datasets across scenarios with partial and complete labels. Our results demonstrate that FedFBN outperforms current aggregation strategies for training global models using distributed and non-iid data with partial labels.

Pranav Kulkarni, Adway Kanhere, Paul H. Yi et al.

Chest X-ray (CXR) datasets hosted on Kaggle, though useful from a data science competition standpoint, have limited utility in clinical use because of their narrow focus on diagnosing one specific disease. In real-world clinical use, multiple diseases need to be considered since they can co-exist in the same patient. In this work, we demonstrate how federated learning (FL) can be used to make these toy CXR datasets from Kaggle clinically useful. Specifically, we train a single FL classification model (`global`) using two separate CXR datasets -- one annotated for presence of pneumonia and the other for presence of pneumothorax (two common and life-threatening conditions) -- capable of diagnosing both. We compare the performance of the global FL model with models trained separately on both datasets (`baseline`) for two different model architectures. On a standard, naive 3-layer CNN architecture, the global FL model achieved AUROC of 0.84 and 0.81 for pneumonia and pneumothorax, respectively, compared to 0.85 and 0.82, respectively, for both baseline models (p>0.05). Similarly, on a pretrained DenseNet121 architecture, the global FL model achieved AUROC of 0.88 and 0.91 for pneumonia and pneumothorax, respectively, compared to 0.89 and 0.91, respectively, for both baseline models (p>0.05). Our results suggest that FL can be used to create global `meta` models to make toy datasets from Kaggle clinically useful, a step forward towards bridging the gap from bench to bedside.

Pranav Kulkarni, Adway Kanhere, Paul H. Yi et al.

Federated learning (FL) is a promising paradigm to collaboratively train a global chest x-ray (CXR) classification model using distributed datasets while preserving patient privacy. A significant, yet relatively underexplored, challenge in FL is class-heterogeneity, where clients have different sets of classes. We propose surgical aggregation, a FL method that uses selective aggregation to collaboratively train a global model using distributed, class-heterogeneous datasets. Unlike other methods, our method does not rely on the assumption that clients share the same classes as other clients, know the classes of other clients, or have access to a fully annotated dataset. We evaluate surgical aggregation using class-heterogeneous CXR datasets across IID and non-IID settings. Our results show that our method outperforms current methods and has better generalizability.

Pranav Kulkarni, Adway Kanhere, Eliot Siegel et al.

Large-scale medical imaging datasets have accelerated deep learning (DL) for medical image analysis. However, the large scale of these datasets poses a challenge for researchers, resulting in increased storage and bandwidth requirements for hosting and accessing them. Since different researchers have different use cases and require different resolutions or formats for DL, it is neither feasible to anticipate every researcher's needs nor practical to store data in multiple resolutions and formats. To that end, we propose the Medical Image Streaming Toolkit (MIST), a format-agnostic database that enables streaming of medical images at different resolutions and formats from a single high-resolution copy. We evaluated MIST across eight popular, large-scale medical imaging datasets spanning different body parts, modalities, and formats. Our results showed that our framework reduced the storage and bandwidth requirements for hosting and downloading datasets without impacting image quality. We demonstrate that MIST addresses the challenges posed by large-scale medical imaging datasets by building a data-efficient and format-agnostic database to meet the diverse needs of researchers and reduce barriers to DL research in medical imaging.

Pranav Kulkarni, Adway Kanhere, Dharmam Savani et al.

Curating annotations for medical image segmentation is a labor-intensive and time-consuming task that requires domain expertise, resulting in "narrowly" focused deep learning (DL) models with limited translational utility. Recently, foundation models like the Segment Anything Model (SAM) have revolutionized semantic segmentation with exceptional zero-shot generalizability across various domains, including medical imaging, and hold a lot of promise for streamlining the annotation process. However, SAM has yet to be evaluated in a crowd-sourced setting to curate annotations for training 3D DL segmentation models. In this work, we explore the potential of SAM for crowd-sourcing "sparse" annotations from non-experts to generate "dense" segmentation masks for training 3D nnU-Net models, a state-of-the-art DL segmentation model. Our results indicate that while SAM-generated annotations exhibit high mean Dice scores compared to ground-truth annotations, nnU-Net models trained on SAM-generated annotations perform significantly worse than nnU-Net models trained on ground-truth annotations ($p<0.001$, all).

Guangyao Zheng, Michael A. Jacobs, Vladimir Braverman et al.

Self-supervised learning has revolutionized medical imaging by enabling efficient and generalizable feature extraction from large-scale unlabeled datasets. Recently, self-supervised foundation models have been extended to three-dimensional (3D) computed tomography (CT) data, generating compact, information-rich embeddings with 1408 features that achieve state-of-the-art performance on downstream tasks such as intracranial hemorrhage detection and lung cancer risk forecasting. However, these embeddings have been shown to encode demographic information, such as age, sex, and race, which poses a significant risk to the fairness of clinical applications. In this work, we propose a Variation Autoencoder (VAE) based adversarial debiasing framework to transform these embeddings into a new latent space where demographic information is no longer encoded, while maintaining the performance of critical downstream tasks. We validated our approach on the NLST lung cancer screening dataset, demonstrating that the debiased embeddings effectively eliminate multiple encoded demographic information and improve fairness without compromising predictive accuracy for lung cancer risk at 1-year and 2-year intervals. Additionally, our approach ensures the embeddings are robust against adversarial bias attacks. These results highlight the potential of adversarial debiasing techniques to ensure fairness and equity in clinical applications of self-supervised 3D CT embeddings, paving the way for their broader adoption in unbiased medical decision-making.

Guangyao Zheng, Michael A. Jacobs, Vishwa S. Parekh

Self-supervised foundation models have recently been successfully extended to encode three-dimensional (3D) computed tomography (CT) images, with excellent performance across several downstream tasks, such as intracranial hemorrhage detection and lung cancer risk forecasting. However, as self-supervised models learn from complex data distributions, questions arise concerning whether these embeddings capture demographic information, such as age, sex, or race. Using the National Lung Screening Trial (NLST) dataset, which contains 3D CT images and demographic data, we evaluated a range of classifiers: softmax regression, linear regression, linear support vector machine, random forest, and decision tree, to predict sex, race, and age of the patients in the images. Our results indicate that the embeddings effectively encoded age and sex information, with a linear regression model achieving a root mean square error (RMSE) of 3.8 years for age prediction and a softmax regression model attaining an AUC of 0.998 for sex classification. Race prediction was less effective, with an AUC of 0.878. These findings suggest a detailed exploration into the information encoded in self-supervised learning frameworks is needed to help ensure fair, responsible, and patient privacy-protected healthcare AI.

Skylar Chan, Pranav Kulkarni, Paul H. Yi et al.

Quantum machine learning (QML) has the potential for improving the multi-label classification of rare, albeit critical, diseases in large-scale chest x-ray (CXR) datasets due to theoretical quantum advantages over classical machine learning (CML) in sample efficiency and generalizability. While prior literature has explored QML with CXRs, it has focused on binary classification tasks with small datasets due to limited access to quantum hardware and computationally expensive simulations. To that end, we implemented a Jax-based framework that enables the simulation of medium-sized qubit architectures with significant improvements in wall-clock time over current software offerings. We evaluated the performance of our Jax-based framework in terms of efficiency and performance for hybrid quantum transfer learning for long-tailed classification across 8, 14, and 19 disease labels using large-scale CXR datasets. The Jax-based framework resulted in up to a 58% and 95% speed-up compared to PyTorch and TensorFlow implementations, respectively. However, compared to CML, QML demonstrated slower convergence and an average AUROC of 0.70, 0.73, and 0.74 for the classification of 8, 14, and 19 CXR disease labels. In comparison, the CML models had an average AUROC of 0.77, 0.78, and 0.80 respectively. In conclusion, our work presents an accessible implementation of hybrid quantum transfer learning for long-tailed CXR classification with a computationally efficient Jax-based framework.

Pranav Kulkarni, Adway Kanhere, Harshita Kukreja et al.

Generative Adversarial Network (GAN)-based synthesis of fat suppressed (FS) MRIs from non-FS proton density sequences has the potential to accelerate acquisition of knee MRIs. However, GANs trained on single-site data have poor generalizability to external data. We show that federated learning can improve multi-center generalizability of GANs for synthesizing FS MRIs, while facilitating privacy-preserving multi-institutional collaborations.

Pranav Kulkarni, Andrew Chan, Nithya Navarathna et al.

The proliferation of artificial intelligence (AI) in radiology has shed light on the risk of deep learning (DL) models exacerbating clinical biases towards vulnerable patient populations. While prior literature has focused on quantifying biases exhibited by trained DL models, demographically targeted adversarial bias attacks on DL models and its implication in the clinical environment remains an underexplored field of research in medical imaging. In this work, we demonstrate that demographically targeted label poisoning attacks can introduce undetectable underdiagnosis bias in DL models. Our results across multiple performance metrics and demographic groups like sex, age, and their intersectional subgroups show that adversarial bias attacks demonstrate high-selectivity for bias in the targeted group by degrading group model performance without impacting overall model performance. Furthermore, our results indicate that adversarial bias attacks result in biased DL models that propagate prediction bias even when evaluated with external datasets.

Guangyao Zheng, Shuhao Lai, Vladimir Braverman et al.

Deep reinforcement learning(DRL) is increasingly being explored in medical imaging. However, the environments for medical imaging tasks are constantly evolving in terms of imaging orientations, imaging sequences, and pathologies. To that end, we developed a Lifelong DRL framework, SERIL to continually learn new tasks in changing imaging environments without catastrophic forgetting. SERIL was developed using selective experience replay based lifelong learning technique for the localization of five anatomical landmarks in brain MRI on a sequence of twenty-four different imaging environments. The performance of SERIL, when compared to two baseline setups: MERT(multi-environment-best-case) and SERT(single-environment-worst-case) demonstrated excellent performance with an average distance of $9.90\pm7.35$ pixels from the desired landmark across all 120 tasks, compared to $10.29\pm9.07$ for MERT and $36.37\pm22.41$ for SERT($p<0.05$), demonstrating the excellent potential for continuously learning multiple tasks across dynamically changing imaging environments.

Pranav Kulkarni, Sean Garin, Adway Kanhere et al.

As the adoption of Artificial Intelligence (AI) systems within the clinical environment grows, limitations in bandwidth and compute can create communication bottlenecks when streaming imaging data, leading to delays in patient care and increased cost. As such, healthcare providers and AI vendors will require greater computational infrastructure, therefore dramatically increasing costs. To that end, we developed ISLE, an intelligent streaming framework for high-throughput, compute- and bandwidth- optimized, and cost effective AI inference for clinical decision making at scale. In our experiments, ISLE on average reduced data transmission by 98.02% and decoding time by 98.09%, while increasing throughput by 2,730%. We show that ISLE results in faster turnaround times, and reduced overall cost of data, transmission, and compute, without negatively impacting clinical decision making using AI systems.

Pranav Kulkarni, Adway Kanhere, Paul H. Yi et al.

The Imaging Data Commons (IDC) is a cloud-based database that provides researchers with open access to cancer imaging data, with the goal of facilitating collaboration. However, cohort discovery within the IDC database has a significant technical learning curve. Recently, large language models (LLM) have demonstrated exceptional utility for natural language processing tasks. We developed Text2Cohort, a LLM-powered toolkit to facilitate user-friendly natural language cohort discovery in the IDC. Our method translates user input into IDC queries using grounding techniques and returns the query's response. We evaluate Text2Cohort on 50 natural language inputs, from information extraction to cohort discovery. Our toolkit successfully generated responses with an 88% accuracy and 0.94 F1 score. We demonstrate that Text2Cohort can enable researchers to discover and curate cohorts on IDC with high levels of accuracy using natural language in a more intuitive and user-friendly way.

Alex E. Bocchieri, Vishwa S. Parekh, Kathryn R. Wagner. Shivani Ahlawat et al.

A current clinical challenge is identifying limb girdle muscular dystrophy 2I(LGMD2I)tissue changes in the thighs, in particular, separating fat, fat-infiltrated muscle, and muscle tissue. Deep learning algorithms have the ability to learn different features by using the inherent tissue contrasts from multiparametric magnetic resonance imaging (mpMRI). To that end, we developed a novel multiparametric deep learning network (MPDL) tissue signature model based on mpMRI and applied it to LGMD2I. We demonstrate a new tissue signature model of muscular dystrophy with the MPDL algorithm segments different tissue types with excellent results.

Vishwa S. Parekh, John Laterra, Chetan Bettegowda et al.

Radiomics is an exciting new area of texture research for extracting quantitative and morphological characteristics of pathological tissue. However, to date, only single images have been used for texture analysis. We have extended radiomic texture methods to use multiparametric (mp) data to get more complete information from all the images. These mpRadiomic methods could potentially provide a platform for stratification of tumor grade as well as assessment of treatment response in brain tumors. In brain, multiparametric MRI (mpMRI) are based on contrast enhanced T1-weighted imaging (T1WI), T2WI, Fluid Attenuated Inversion Recovery (FLAIR), Diffusion Weighted Imaging (DWI) and Perfusion Weighted Imaging (PWI). Therefore, we applied our multiparametric radiomic framework (mpRadiomic) on 24 patients with brain tumors (8 grade II and 16 grade IV). The mpRadiomic framework classified grade IV tumors from grade II tumors with a sensitivity and specificity of 93% and 100%, respectively, with an AUC of 0.95. For treatment response, the mpRadiomic framework classified pseudo-progression from true-progression with an AUC of 0.93. In conclusion, the mpRadiomic analysis was able to effectively capture the multiparametric brain MRI texture and could be used as potential biomarkers for distinguishing grade IV from grade II tumors as well as determining true-progression from pseudo-progression.

Vishwa S. Parekh, Michael A. Jacobs

Radiomics is a rapidly growing field that deals with modeling the textural information present in the different tissues of interest for clinical decision support. However, the process of generating radiomic images is computationally very expensive and could take substantial time per radiological image for certain higher order features, such as, gray-level co-occurrence matrix(GLCM), even with high-end GPUs. To that end, we developed RadSynth, a deep convolutional neural network(CNN) model, to efficiently generate radiomic images. RadSynth was tested on a breast cancer patient cohort of twenty-four patients(ten benign, ten malignant and four normal) for computation of GLCM entropy images from post-contrast DCE-MRI. RadSynth produced excellent synthetic entropy images compared to traditional GLCM entropy images. The average percentage difference and correlation between the two techniques were 0.07 $\pm$ 0.06 and 0.97, respectively. In conclusion, RadSynth presents a new powerful tool for fast computation and visualization of the textural information present in the radiological images.

Vishwa S. Parekh, Michael A. Jacobs

Multiparametric radiological imaging is vital for detection, characterization and diagnosis of many different diseases. The use of radiomics for quantitative extraction of textural features from radiological imaging is increasing moving towards clinical decision support. However, current methods in radiomics are limited to using single images for the extraction of these textural features and may limit the applicable scope of radiomics in different clinical settings. Thus, in the current form, they are not capable of capturing the true underlying tissue characteristics in high dimensional multiparametric imaging space. To overcome this challenge, we have developed a multiparametric imaging radiomic framework termed MPRAD for extraction of radiomic features from high dimensional datasets. MPRAD was tested on two different organs and diseases; breast cancer and cerebrovascular accidents in brain, commonly referred to as stroke. The MPRAD framework classified malignant from benign breast lesions with excellent sensitivity and specificity of 87% and 80.5% respectively with an AUC of 0.88 providing a 9%-28% increase in AUC over single radiomic parameters. More importantly, in breast, the glandular tissue MPRAD were similar between each group with no significance differences. Similarly, the MPRAD features in brain stroke demonstrated increased performance in distinguishing the perfusion-diffusion mismatch compared to single parameter radiomics and there were no differences within the white and gray matter tissue. In conclusion, we have introduced the use of multiparametric radiomics into a clinical setting

Vishwa S. Parekh, Katarzyna J. Macura, Susan Harvey et al.

A new paradigm is beginning to emerge in Radiology with the advent of increased computational capabilities and algorithms. This has led to the ability of real time learning by computer systems of different lesion types to help the radiologist in defining disease. For example, using a deep learning network, we developed and tested a multiparametric deep learning (MPDL) network for segmentation and classification using multiparametric magnetic resonance imaging (mpMRI) radiological images. The MPDL network was constructed from stacked sparse autoencoders with inputs from mpMRI. Evaluation of MPDL consisted of cross-validation, sensitivity, and specificity. Dice similarity between MPDL and post-DCE lesions were evaluated. We demonstrate high sensitivity and specificity for differentiation of malignant from benign lesions of 90% and 85% respectively with an AUC of 0.93. The Integrated MPDL method accurately segmented and classified different breast tissue from multiparametric breast MRI using deep leaning tissue signatures.

Vishwa S. Parekh, Jeremy R. Jacobs, Michael A. Jacobs

The evaluation and treatment of acute cerebral ischemia requires a technique that can determine the total area of tissue at risk for infarction using diagnostic magnetic resonance imaging (MRI) sequences. Typical MRI data sets consist of T1- and T2-weighted imaging (T1WI, T2WI) along with advanced MRI parameters of diffusion-weighted imaging (DWI) and perfusion weighted imaging (PWI) methods. Each of these parameters has distinct radiological-pathological meaning. For example, DWI interrogates the movement of water in the tissue and PWI gives an estimate of the blood flow, both are critical measures during the evolution of stroke. In order to integrate these data and give an estimate of the tissue at risk or damaged, we have developed advanced machine learning methods based on unsupervised non-linear dimensionality reduction (NLDR) techniques. NLDR methods are a class of algorithms that uses mathematically defined manifolds for statistical sampling of multidimensional classes to generate a discrimination rule of guaranteed statistical accuracy and they can generate a two- or three-dimensional map, which represents the prominent structures of the data and provides an embedded image of meaningful low-dimensional structures hidden in their high-dimensional observations. In this manuscript, we develop NLDR methods on high dimensional MRI data sets of preclinical animals and clinical patients with stroke. On analyzing the performance of these methods, we observed that there was a high of similarity between multiparametric embedded images from NLDR methods and the ADC map and perfusion map. It was also observed that embedded scattergram of abnormal (infarcted or at risk) tissue can be visualized and provides a mechanism for automatic methods to delineate potential stroke volumes and early tissue at risk.