Search

Survival analysis plays a crucial role in estimating the likelihood of future events for patients by modeling time-to-event data, particularly in healthcare settings where predictions about outcomes such as death and disease recurrence are essential. However, this analysis poses challenges due to the presence of censored data, where time-to-event information is missing for certain data points. Yet, censored data can offer valuable insights, provided we appropriately incorporate the censoring time during modeling. In this paper, we propose SurvCORN, a novel method utilizing conditional ordinal ranking networks to predict survival curves directly. Additionally, we introduce SurvMAE, a metric designed to evaluate the accuracy of model predictions in estimating time-to-event outcomes. Through empirical evaluation on two real-world cancer datasets, we demonstrate SurvCORN's ability to maintain accurate ordering between patient outcomes while improving individual time-to-event predictions. Our contributions extend recent advancements in ordinal regression to survival analysis, offering valuable insights into accurate prognosis in healthcare settings.

Self-supervised learning (SSL) methods are popular since they can address situations with limited annotated data by directly utilising the underlying data distribution. However, the adoption of such methods is not explored enough in ultrasound (US) imaging, especially for fetal assessment. We investigate the potential of dual-encoder SSL in utilizing unlabelled US video data to improve the performance of challenging downstream Standard Fetal Cardiac Planes (SFCP) classification using limited labelled 2D US images. We study 7 SSL approaches based on reconstruction, contrastive loss, distillation, and information theory and evaluate them extensively on a large private US dataset. Our observations and findings are consolidated from more than 500 downstream training experiments under different settings. Our primary observation shows that for SSL training, the variance of the dataset is more crucial than its size because it allows the model to learn generalisable representations, which improve the performance of downstream tasks. Overall, the BarlowTwins method shows robust performance, irrespective of the training settings and data variations, when used as an initialisation for downstream tasks. Notably, full fine-tuning with 1% of labelled data outperforms ImageNet initialisation by 12% in F1-score and outperforms other SSL initialisations by at least 4% in F1-score, thus making it a promising candidate for transfer learning from US video to image data., Comment: Simplifying Medical Ultrasound: 4th International Workshop, ASMUS 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, Proceedings

Adapting foundation models for medical image analysis requires finetuning them on a considerable amount of data because of extreme distribution shifts between natural (source) data used for pretraining and medical (target) data. However, collecting task-specific medical data for such finetuning at a central location raises many privacy concerns. Although Federated learning (FL) provides an effective means for training on private decentralized data, communication costs in federating large foundation models can quickly become a significant bottleneck, impacting the solution's scalability. In this work, we address this problem of efficient communication while ensuring effective learning in FL by combining the strengths of Parameter-Efficient Fine-tuning (PEFT) with FL. Specifically, we study plug-and-play Low-Rank Adapters (LoRA) in a federated manner to adapt the Segment Anything Model (SAM) for 3D medical image segmentation. Unlike prior works that utilize LoRA and finetune the entire decoder, we critically analyze the contribution of each granular component of SAM on finetuning performance. Thus, we identify specific layers to be federated that are very efficient in terms of communication cost while producing on-par accuracy. Our experiments show that retaining the parameters of the SAM model (including most of the decoder) in their original state during adaptation is beneficial because fine-tuning on small datasets tends to distort the inherent capabilities of the underlying foundation model. On Fed-KiTS, our approach decreases communication cost (~48x) compared to full fine-tuning while increasing performance (~6% Dice score) in 3D segmentation tasks. Our approach performs similar to SAMed while achieving ~2.8x reduction in communication and parameters to be finetuned. We further validate our approach with experiments on Fed-IXI and Prostate MRI datasets.

Imaging modalities such as Computed Tomography (CT) and Positron Emission Tomography (PET) are key in cancer detection, inspiring Deep Neural Networks (DNN) models that merge these scans for tumor segmentation. When both CT and PET scans are available, it is common to combine them as two channels of the input to the segmentation model. However, this method requires both scan types during training and inference, posing a challenge due to the limited availability of PET scans, thereby sometimes limiting the process to CT scans only. Hence, there is a need to develop a flexible DNN architecture that can be trained/updated using only CT scans but can effectively utilize PET scans when they become available. In this work, we propose a parameter-efficient multi-modal adaptation (PEMMA) framework for lightweight upgrading of a transformer-based segmentation model trained only on CT scans to also incorporate PET scans. The benefits of the proposed approach are two-fold. Firstly, we leverage the inherent modularity of the transformer architecture and perform low-rank adaptation (LoRA) of the attention weights to achieve parameter-efficient adaptation. Secondly, since the PEMMA framework attempts to minimize cross modal entanglement, it is possible to subsequently update the combined model using only one modality, without causing catastrophic forgetting of the other modality. Our proposed method achieves comparable results with the performance of early fusion techniques with just 8% of the trainable parameters, especially with a remarkable +28% improvement on the average dice score on PET scans when trained on a single modality.

Deploying deep learning (DL) models in medical applications relies on predictive performance and other critical factors, such as conveying trustworthy predictive uncertainty. Uncertainty estimation (UE) methods provide potential solutions for evaluating prediction reliability and improving the model confidence calibration. Despite increasing interest in UE, challenges persist, such as the need for explicit methods to capture aleatoric uncertainty and align uncertainty estimates with real-life disagreements among domain experts. This paper proposes an Expert Disagreement-Guided Uncertainty Estimation (EDUE) for medical image segmentation. By leveraging variability in ground-truth annotations from multiple raters, we guide the model during training and incorporate random sampling-based strategies to enhance calibration confidence. Our method achieves 55% and 23% improvement in correlation on average with expert disagreements at the image and pixel levels, respectively, better calibration, and competitive segmentation performance compared to the state-of-the-art deep ensembles, requiring only a single forward pass.

Predicting the likelihood of survival is of paramount importance for individuals diagnosed with cancer as it provides invaluable information regarding prognosis at an early stage. This knowledge enables the formulation of effective treatment plans that lead to improved patient outcomes. In the past few years, deep learning models have provided a feasible solution for assessing medical images, electronic health records, and genomic data to estimate cancer risk scores. However, these models often fall short of their potential because they struggle to learn regression-aware feature representations. In this study, we propose Survival Rank-N Contrast (SurvRNC) method, which introduces a loss function as a regularizer to obtain an ordered representation based on the survival times. This function can handle censored data and can be incorporated into any survival model to ensure that the learned representation is ordinal. The model was extensively evaluated on a HEad \& NeCK TumOR (HECKTOR) segmentation and the outcome-prediction task dataset. We demonstrate that using the SurvRNC method for training can achieve higher performance on different deep survival models. Additionally, it outperforms state-of-the-art methods by 3.6% on the concordance index. The code is publicly available on https://github.com/numanai/SurvRNC

Deep learning (DL) models have been advancing automatic medical image analysis on various modalities, including echocardiography, by offering a comprehensive end-to-end training pipeline. This approach enables DL models to regress ejection fraction (EF) directly from 2D+time echocardiograms, resulting in superior performance. However, the end-to-end training pipeline makes the learned representations less explainable. The representations may also fail to capture the continuous relation among echocardiogram clips, indicating the existence of spurious correlations, which can negatively affect the generalization. To mitigate this issue, we propose CoReEcho, a novel training framework emphasizing continuous representations tailored for direct EF regression. Our extensive experiments demonstrate that CoReEcho: 1) outperforms the current state-of-the-art (SOTA) on the largest echocardiography dataset (EchoNet-Dynamic) with MAE of 3.90 & R2 of 82.44, and 2) provides robust and generalizable features that transfer more effectively in related downstream tasks. The code is publicly available at https://github.com/fadamsyah/CoReEcho.

The accurate recognition of symptoms in clinical reports is significantly important in the fields of healthcare and biomedical natural language processing. These entities serve as essential building blocks for clinical information extraction, enabling retrieval of critical medical insights from vast amounts of textual data. Furthermore, the ability to identify and categorize these entities is fundamental for developing advanced clinical decision support systems, aiding healthcare professionals in diagnosis and treatment planning. In this study, we participated in SympTEMIST, a shared task on the detection of symptoms, signs and findings in Spanish medical documents. We combine a set of large language models fine-tuned with the data released by the organizers.

Despite major advances in artificial intelligence (AI) for medicine and healthcare, the deployment and adoption of AI technologies remain limited in real-world clinical practice. In recent years, concerns have been raised about the technical, clinical, ethical and legal risks associated with medical AI. To increase real world adoption, it is essential that medical AI tools are trusted and accepted by patients, clinicians, health organisations and authorities. This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare. The FUTURE-AI consortium was founded in 2021 and currently comprises 118 inter-disciplinary experts from 51 countries representing all continents, including AI scientists, clinicians, ethicists, and social scientists. Over a two-year period, the consortium defined guiding principles and best practices for trustworthy AI through an iterative process comprising an in-depth literature review, a modified Delphi survey, and online consensus meetings. The FUTURE-AI framework was established based on 6 guiding principles for trustworthy AI in healthcare, i.e. Fairness, Universality, Traceability, Usability, Robustness and Explainability. Through consensus, a set of 28 best practices were defined, addressing technical, clinical, legal and socio-ethical dimensions. The recommendations cover the entire lifecycle of medical AI, from design, development and validation to regulation, deployment, and monitoring. FUTURE-AI is a risk-informed, assumption-free guideline which provides a structured approach for constructing medical AI tools that will be trusted, deployed and adopted in real-world practice. Researchers are encouraged to take the recommendations into account in proof-of-concept stages to facilitate future translation towards clinical practice of medical AI.

Federated learning (FL) is a distributed machine learning (ML) framework where multiple clients collaborate to train a model without exposing their private data. FL involves cycles of local computations and bi-directional communications between the clients and server. To bolster data security during this process, FL algorithms frequently employ a differential privacy (DP) mechanism that introduces noise into each client's model updates before sharing. However, while enhancing privacy, the DP mechanism often hampers convergence performance. In this paper, we posit that an optimal balance exists between the number of local steps and communication rounds, one that maximizes the convergence performance within a given privacy budget. Specifically, we present a proof for the optimal number of local steps and communication rounds that enhance the convergence bounds of the DP version of the ScaffNew algorithm. Our findings reveal a direct correlation between the optimal number of local steps, communication rounds, and a set of variables, e.g the DP privacy budget and other problem parameters, specifically in the context of strongly convex optimization. We furthermore provide empirical evidence to validate our theoretical findings.

The number of studies on deep learning for medical diagnosis is expanding, and these systems are often claimed to outperform clinicians. However, only a few systems have shown medical efficacy. From this perspective, we examine a wide range of deep learning algorithms for the assessment of glioblastoma - a common brain tumor in older adults that is lethal. Surgery, chemotherapy, and radiation are the standard treatments for glioblastoma patients. The methylation status of the MGMT promoter, a specific genetic sequence found in the tumor, affects chemotherapy's effectiveness. MGMT promoter methylation improves chemotherapy response and survival in several cancers. MGMT promoter methylation is determined by a tumor tissue biopsy, which is then genetically tested. This lengthy and invasive procedure increases the risk of infection and other complications. Thus, researchers have used deep learning models to examine the tumor from brain MRI scans to determine the MGMT promoter's methylation state. We employ deep learning models and one of the largest public MRI datasets of 585 participants to predict the methylation status of the MGMT promoter in glioblastoma tumors using MRI scans. We test these models using Grad-CAM, occlusion sensitivity, feature visualizations, and training loss landscapes. Our results show no correlation between these two, indicating that external cohort data should be used to verify these models' performance to assure the accuracy and reliability of deep learning systems in cancer diagnosis., Comment: 12 pages, 10 figures, MedIA

Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and survival analysis, where we demonstrated that the challenge's improvement over the previous state-of-the-art led to significant boosts in downstream performance. Our findings also suggest that eosinophils and neutrophils play an important role in the tumour microevironment. We release challenge models and WSI-level results to foster the development of further methods for biomarker discovery.

Deep learning models have been effective for various fetal ultrasound segmentation tasks. However, generalization to new unseen data has raised questions about their effectiveness for clinical adoption. Normally, a transition to new unseen data requires time-consuming and costly quality assurance processes to validate the segmentation performance post-transition. Segmentation quality assessment efforts have focused on natural images, where the problem has been typically formulated as a dice score regression task. In this paper, we propose a simplified Fetal Ultrasound Segmentation Quality Assessment (FUSQA) model to tackle the segmentation quality assessment when no masks exist to compare with. We formulate the segmentation quality assessment process as an automated classification task to distinguish between good and poor-quality segmentation masks for more accurate gestational age estimation. We validate the performance of our proposed approach on two datasets we collect from two hospitals using different ultrasound machines. We compare different architectures, with our best-performing architecture achieving over 90% classification accuracy on distinguishing between good and poor-quality segmentation masks from an unseen dataset. Additionally, there was only a 1.45-day difference between the gestational age reported by doctors and estimated based on CRL measurements using well-segmented masks. On the other hand, this difference increased and reached up to 7.73 days when we calculated CRL from the poorly segmented masks. As a result, AI-based approaches can potentially aid fetal ultrasound segmentation quality assessment and might detect poor segmentation in real-time screening in the future., Comment: 13 pages, 3 figures, 3 tables

The success of Deep Neural Network (DNN) models significantly depends on the quality of provided annotations. In medical image segmentation, for example, having multiple expert annotations for each data point is common to minimize subjective annotation bias. Then, the goal of estimation is to filter out the label noise and recover the ground-truth masks, which are not explicitly given. This paper proposes a probabilistic model for noisy observations that allows us to build a confident classification and segmentation models. To accomplish it, we explicitly model label noise and introduce a new information-based regularization that pushes the network to recover the ground-truth labels. In addition, for segmentation task we adjust the loss function by prioritizing learning in high-confidence regions where all the annotators agree on labeling. We evaluate the proposed method on a series of classification tasks such as noisy versions of MNIST, CIFAR-10, Fashion-MNIST datasets as well as CIFAR-10N, which is real-world dataset with noisy human annotations. Additionally, for segmentation task, we consider several medical imaging datasets, such as, LIDC and RIGA that reflect real-world inter-variability among multiple annotators. Our experiments show that our algorithm outperforms state-of-the-art solutions for the considered classification and segmentation problems.

Lung cancer is a leading cause of death worldwide. Early-stage detection of lung cancer is essential for a more favorable prognosis. Radiogenomics is an emerging discipline that combines medical imaging and genomics features for modeling patient outcomes non-invasively. This study presents a radiogenomics pipeline that has: 1) a novel mixed architecture (RA-Seg) to segment lung cancer through attention and recurrent blocks; and 2) deep feature classifiers to distinguish Epidermal Growth Factor Receptor (EGFR) mutation status. We evaluate the proposed algorithm on multiple public datasets to assess its generalizability and robustness. We demonstrate how the proposed segmentation and classification methods outperform existing baseline and SOTA approaches (73.54 Dice and 93 F1 scores)., Comment: 4 pages, 3 figures, 3 tables. Preprint to International Symposium on Biomedical Imaging (ISBI) 2023

We have gained access to vast amounts of multi-omics data thanks to Next Generation Sequencing. However, it is challenging to analyse this data due to its high dimensionality and much of it not being annotated. Lack of annotated data is a significant problem in machine learning, and Self-Supervised Learning (SSL) methods are typically used to deal with limited labelled data. However, there is a lack of studies that use SSL methods to exploit inter-omics relationships on unlabelled multi-omics data. In this work, we develop a novel and efficient pre-training paradigm that consists of various SSL components, including but not limited to contrastive alignment, data recovery from corrupted samples, and using one type of omics data to recover other omic types. Our pre-training paradigm improves performance on downstream tasks with limited labelled data. We show that our approach outperforms the state-of-the-art method in cancer type classification on the TCGA pan-cancer dataset in semi-supervised setting. Moreover, we show that the encoders that are pre-trained using our approach can be used as powerful feature extractors even without fine-tuning. Our ablation study shows that the method is not overly dependent on any pretext task component. The network architectures in our approach are designed to handle missing omic types and multiple datasets for pre-training and downstream training. Our pre-training paradigm can be extended to perform zero-shot classification of rare cancers., Comment: Preprint of an article published in Pacific Symposium on Biocomputing $\copyright$ 2022 World Scientific Publishing Co., Singapore, http://psb.stanford.edu/

When oncologists estimate cancer patient survival, they rely on multimodal data. Even though some multimodal deep learning methods have been proposed in the literature, the majority rely on having two or more independent networks that share knowledge at a later stage in the overall model. On the other hand, oncologists do not do this in their analysis but rather fuse the information in their brain from multiple sources such as medical images and patient history. This work proposes a deep learning method that mimics oncologists' analytical behavior when quantifying cancer and estimating patient survival. We propose TMSS, an end-to-end Transformer based Multimodal network for Segmentation and Survival prediction that leverages the superiority of transformers that lies in their abilities to handle different modalities. The model was trained and validated for segmentation and prognosis tasks on the training dataset from the HEad & NeCK TumOR segmentation and the outcome prediction in PET/CT images challenge (HECKTOR). We show that the proposed prognostic model significantly outperforms state-of-the-art methods with a concordance index of 0.763+/-0.14 while achieving a comparable dice score of 0.772+/-0.030 to a standalone segmentation model. The code is publicly available.

Glaucoma is one of the most severe eye diseases, characterized by rapid progression and leading to irreversible blindness. It is often the case that diagnostics is carried out when one's sight has already significantly degraded due to the lack of noticeable symptoms at early stage of the disease. Regular glaucoma screenings of the population shall improve early-stage detection, however the desirable frequency of etymological checkups is often not feasible due to the excessive load imposed by manual diagnostics on limited number of specialists. Considering the basic methodology to detect glaucoma is to analyze fundus images for the optic-disc-to-optic-cup ratio, Machine Learning algorithms can offer sophisticated methods for image processing and classification. In our work, we propose an advanced image pre-processing technique combined with a multi-view network of deep classification models to categorize glaucoma. Our Glaucoma Automated Retinal Detection Network (GARDNet) has been successfully tested on Rotterdam EyePACS AIROGS dataset with an AUC of 0.92, and then additionally fine-tuned and tested on RIM-ONE DL dataset with an AUC of 0.9308 outperforming the state-of-the-art of 0.9272. Our code is available on https://github.com/ahmed1996said/gardnet, Comment: Keywords: Glaucoma Classification, Color Fundus Images. Computer Aided Diagnosis. Deep Learning

Accurate prognosis of a tumor can help doctors provide a proper course of treatment and, therefore, save the lives of many. Traditional machine learning algorithms have been eminently useful in crafting prognostic models in the last few decades. Recently, deep learning algorithms have shown significant improvement when developing diagnosis and prognosis solutions to different healthcare problems. However, most of these solutions rely solely on either imaging or clinical data. Utilizing patient tabular data such as demographics and patient medical history alongside imaging data in a multimodal approach to solve a prognosis task has started to gain more interest recently and has the potential to create more accurate solutions. The main issue when using clinical and imaging data to train a deep learning model is to decide on how to combine the information from these sources. We propose a multimodal network that ensembles deep multi-task logistic regression (MTLR), Cox proportional hazard (CoxPH) and CNN models to predict prognostic outcomes for patients with head and neck tumors using patients' clinical and imaging (CT and PET) data. Features from CT and PET scans are fused and then combined with patients' electronic health records for the prediction. The proposed model is trained and tested on 224 and 101 patient records respectively. Experimental results show that our proposed ensemble solution achieves a C-index of 0.72 on The HECKTOR test set that saved us the first place in prognosis task of the HECKTOR challenge. The full implementation based on PyTorch is available on \url{https://github.com/numanai/BioMedIA-Hecktor2021}., Comment: 9 pages, 5 figures

For personalized medicines, very crucial intrinsic information is present in high dimensional omics data which is difficult to capture due to the large number of molecular features and small number of available samples. Different types of omics data show various aspects of samples. Integration and analysis of multi-omics data give us a broad view of tumours, which can improve clinical decision making. Omics data, mainly DNA methylation and gene expression profiles are usually high dimensional data with a lot of molecular features. In recent years, variational autoencoders (VAE) have been extensively used in embedding image and text data into lower dimensional latent spaces. In our project, we extend the idea of using a VAE model for low dimensional latent space extraction with the self-supervised learning technique of feature subsetting. With VAEs, the key idea is to make the model learn meaningful representations from different types of omics data, which could then be used for downstream tasks such as cancer type classification. The main goals are to overcome the curse of dimensionality and integrate methylation and expression data to combine information about different aspects of same tissue samples, and hopefully extract biologically relevant features. Our extension involves training encoder and decoder to reconstruct the data from just a subset of it. By doing this, we force the model to encode most important information in the latent representation. We also added an identity to the subsets so that the model knows which subset is being fed into it during training and testing. We experimented with our approach and found that SubOmiEmbed produces comparable results to the baseline OmiEmbed with a much smaller network and by using just a subset of the data. This work can be improved to integrate mutation-based genomic data as well.

Despite the introduction of vaccines, Coronavirus disease (COVID-19) remains a worldwide dilemma, continuously developing new variants such as Delta and the recent Omicron. The current standard for testing is through polymerase chain reaction (PCR). However, PCRs can be expensive, slow, and/or inaccessible to many people. X-rays on the other hand have been readily used since the early 20th century and are relatively cheaper, quicker to obtain, and typically covered by health insurance. With a careful selection of model, hyperparameters, and augmentations, we show that it is possible to develop models with 83% accuracy in binary classification and 64% in multi-class for detecting COVID-19 infections from chest x-rays., Comment: 15 pages, 13 figures

Cancer is one of the leading causes of death worldwide, and head and neck (H&N) cancer is amongst the most prevalent types. Positron emission tomography and computed tomography are used to detect, segment and quantify the tumor region. Clinically, tumor segmentation is extensively time-consuming and prone to error. Machine learning, and deep learning in particular, can assist to automate this process, yielding results as accurate as the results of a clinician. In this paper, we investigate a vision transformer-based method to automatically delineate H&N tumor, and compare its results to leading convolutional neural network (CNN)-based models. We use multi-modal data from CT and PET scans to perform the segmentation task. We show that a solution with a transformer-based model has the potential to achieve comparable results to CNN-based ones. With cross validation, the model achieves a mean dice similarity coefficient (DSC) of 0.736, mean precision of 0.766 and mean recall of 0.766. This is only 0.021 less than the 2020 competition winning model (cross validated in-house) in terms of the DSC score. On the testing set, the model performs similarly, with DSC of 0.736, precision of 0.773, and recall of 0.760, which is only 0.023 lower in DSC than the 2020 competition winning model. This work shows that cancer segmentation via transformer-based models is a promising research area to further explore., Comment: 8 pages, 2 figures (3 more figures in Appendix), 2 tables; accepted to MIDL conference

Contrastive learning has proven useful in many applications where access to labelled data is limited. The lack of annotated data is particularly problematic in medical image segmentation as it is difficult to have clinical experts manually annotate large volumes of data such as cardiac structures in ultrasound images of the heart. In this paper, We propose a self supervised contrastive learning method to segment the left ventricle from echocardiography when limited annotated images exist. Furthermore, we study the effect of contrastive pretraining on two well-known segmentation networks, UNet and DeepLabV3. Our results show that contrastive pretraining helps improve the performance on left ventricle segmentation, particularly when annotated data is scarce. We show how to achieve comparable results to state-of-the-art fully supervised algorithms when we train our models in a self-supervised fashion followed by fine-tuning on just 5\% of the data. We show that our solution outperforms what is currently published on a large public dataset (EchoNet-Dynamic) achieving a Dice score of 0.9252. We also compare the performance of our solution on another smaller dataset (CAMUS) to demonstrate the generalizability of our proposed solution. The code is available at (https://github.com/BioMedIA-MBZUAI/contrastive-echo).

Quick and accurate diagnosis is of paramount importance to mitigate the effects of COVID-19 infection, particularly for severe cases. Enormous effort has been put towards developing deep learning methods to classify and detect COVID-19 infections from chest radiography images. However, recently some questions have been raised surrounding the clinical viability and effectiveness of such methods. In this work, we investigate the impact of multi-task learning (classification and segmentation) on the ability of CNNs to differentiate between various appearances of COVID-19 infections in the lung. We also employ self-supervised pre-training approaches, namely MoCo and inpainting-CXR, to eliminate the dependence on expensive ground truth annotations for COVID-19 classification. Finally, we conduct a critical evaluation of the models to assess their deploy-readiness and provide insights into the difficulties of fine-grained COVID-19 multi-class classification from chest X-rays., Comment: Accepted to Conference on Medical Image Understanding and Analysis (MIUA) 2022