Charles Lu

Charles Lu, Anastasios N. Angelopoulos, Stuart Pomerantz · berkeley

The regulatory approval and broad clinical deployment of medical AI have been hampered by the perception that deep learning models fail in unpredictable and possibly catastrophic ways. A lack of statistically rigorous uncertainty quantification is a significant factor undermining trust in AI results. Recent developments in distribution-free uncertainty quantification present practical solutions for these issues by providing reliability guarantees for black-box models on arbitrary data distributions as formally valid finite-sample prediction intervals. Our work applies these new uncertainty quantification methods -- specifically conformal prediction -- to a deep-learning model for grading the severity of spinal stenosis in lumbar spine MRI. We demonstrate a technique for forming ordinal prediction sets that are guaranteed to contain the correct stenosis severity within a user-defined probability (confidence interval). On a dataset of 409 MRI exams processed by the deep-learning model, the conformal method provides tight coverage with small prediction set sizes. Furthermore, we explore the potential clinical applicability of flagging cases with high uncertainty predictions (large prediction sets) by quantifying an increase in the prevalence of significant imaging abnormalities (e.g. motion artifacts, metallic artifacts, and tumors) that could degrade confidence in predictive performance when compared to a random sample of cases.

Charles Lu, Ken Chang, Praveer Singh et al.

Breast cancer is the most common cancers and early detection from mammography screening is crucial in improving patient outcomes. Assessing mammographic breast density is clinically important as the denser breasts have higher risk and are more likely to occlude tumors. Manual assessment by experts is both time-consuming and subject to inter-rater variability. As such, there has been increased interest in the development of deep learning methods for mammographic breast density assessment. Despite deep learning having demonstrated impressive performance in several prediction tasks for applications in mammography, clinical deployment of deep learning systems in still relatively rare; historically, mammography Computer-Aided Diagnoses (CAD) have over-promised and failed to deliver. This is in part due to the inability to intuitively quantify uncertainty of the algorithm for the clinician, which would greatly enhance usability. Conformal prediction is well suited to increase reliably and trust in deep learning tools but they lack realistic evaluations on medical datasets. In this paper, we present a detailed analysis of three possible applications of conformal prediction applied to medical imaging tasks: distribution shift characterization, prediction quality improvement, and subgroup fairness analysis. Our results show the potential of distribution-free uncertainty quantification techniques to enhance trust on AI algorithms and expedite their translation to usage.

Charles Lu, Syed Rakin Ahmed, Praveer Singh et al.

Estimating the test performance of software AI-based medical devices under distribution shifts is crucial for evaluating the safety, efficiency, and usability prior to clinical deployment. Due to the nature of regulated medical device software and the difficulty in acquiring large amounts of labeled medical datasets, we consider the task of predicting the test accuracy of an arbitrary black-box model on an unlabeled target domain without modification to the original training process or any distributional assumptions of the original source data (i.e. we treat the model as a "black-box" and only use the predicted output responses). We propose a "black-box" test estimation technique based on conformal prediction and evaluate it against other methods on three medical imaging datasets (mammography, dermatology, and histopathology) under several clinically relevant types of distribution shift (institution, hardware scanner, atlas, hospital). We hope that by promoting practical and effective estimation techniques for black-box models, manufacturers of medical devices will develop more standardized and realistic evaluation procedures to improve the robustness and trustworthiness of clinical AI tools.

Charles Lu, Yaodong Yu, Sai Praneeth Karimireddy et al.

Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning since it can be easily applied as a post-processing step to already trained models. In this paper, we extend conformal prediction to the federated learning setting. The main challenge we face is data heterogeneity across the clients - this violates the fundamental tenet of exchangeability required for conformal prediction. We propose a weaker notion of partial exchangeability, better suited to the FL setting, and use it to develop the Federated Conformal Prediction (FCP) framework. We show FCP enjoys rigorous theoretical guarantees and excellent empirical performance on several computer vision and medical imaging datasets. Our results demonstrate a practical approach to incorporating meaningful uncertainty quantification in distributed and heterogeneous environments. We provide code used in our experiments https://github.com/clu5/federated-conformal.

Charles Lu, Baihe Huang, Sai Praneeth Karimireddy et al.

The acquisition of training data is crucial for machine learning applications. Data markets can increase the supply of data, particularly in data-scarce domains such as healthcare, by incentivizing potential data providers to join the market. A major challenge for a data buyer in such a market is choosing the most valuable data points from a data seller. Unlike prior work in data valuation, which assumes centralized data access, we propose a federated approach to the data acquisition problem that is inspired by linear experimental design. Our proposed data acquisition method achieves lower prediction error without requiring labeled validation data and can be optimized in a fast and federated procedure. The key insight of our work is that a method that directly estimates the benefit of acquiring data for test set prediction is particularly compatible with a decentralized market setting.

Charles Lu, Mohammad Mohammadi Amiri, Ramesh Raskar

Decentralized data markets can provide more equitable forms of data acquisition for machine learning. However, to realize practical marketplaces, efficient techniques for seller selection need to be developed. We propose and benchmark federated data measurements to allow a data buyer to find sellers with relevant and diverse datasets. Diversity and relevance measures enable a buyer to make relative comparisons between sellers without requiring intermediate brokers and training task-dependent models.

Charles Lu, Jayasheree Kalpathy-Cramer

Federated learning has attracted considerable interest for collaborative machine learning in healthcare to leverage separate institutional datasets while maintaining patient privacy. However, additional challenges such as poor calibration and lack of interpretability may also hamper widespread deployment of federated models into clinical practice, leading to user distrust or misuse of ML tools in high-stakes clinical decision-making. In this paper, we propose to address these challenges by incorporating an adaptive conformal framework into federated learning to ensure distribution-free prediction sets that provide coverage guarantees. Importantly, these uncertainty estimates can be obtained without requiring any additional modifications to the model. Empirical results on the MedMNIST medical imaging benchmark demonstrate our federated method provides tighter coverage over local conformal predictions on 6 different medical imaging datasets for 2D and 3D multi-class classification tasks. Furthermore, we correlate class entropy with prediction set size to assess task uncertainty.

Charles Lu, Ken Chang, Praveer Singh et al.

Despite the intense attention and considerable investment into clinical machine learning research, relatively few applications have been deployed at a large-scale in a real-world clinical environment. While research is important in advancing the state-of-the-art, translation is equally important in bringing these techniques and technologies into a position to ultimately impact healthcare. We believe a lack of appreciation for several considerations are a major cause for this discrepancy between expectation and reality. To better characterize a holistic perspective among researchers and practitioners, we survey several practitioners with commercial experience in developing CML for clinical deployment. Using these insights, we identify several main categories of challenges in order to better design and develop clinical machine learning applications.

Charles Lu, Andreanne Lemay, Ken Chang et al.

Deep learning has the potential to automate many clinically useful tasks in medical imaging. However translation of deep learning into clinical practice has been hindered by issues such as lack of the transparency and interpretability in these "black box" algorithms compared to traditional statistical methods. Specifically, many clinical deep learning models lack rigorous and robust techniques for conveying certainty (or lack thereof) in their predictions -- ultimately limiting their appeal for extensive use in medical decision-making. Furthermore, numerous demonstrations of algorithmic bias have increased hesitancy towards deployment of deep learning for clinical applications. To this end, we explore how conformal predictions can complement existing deep learning approaches by providing an intuitive way of expressing uncertainty while facilitating greater transparency to clinical users. In this paper, we conduct field interviews with radiologists to assess possible use-cases for conformal predictors. Using insights gathered from these interviews, we devise two clinical use-cases and empirically evaluate several methods of conformal predictions on a dermatology photography dataset for skin lesion classification. We show how to modify conformal predictions to be more adaptive to subgroup differences in patient skin tones through equalized coverage. Finally, we compare conformal prediction against measures of epistemic uncertainty.

Charles Lu, Andreanne Lemay, Katharina Hoebel et al.

As machine learning (ML) continue to be integrated into healthcare systems that affect clinical decision making, new strategies will need to be incorporated in order to effectively detect and evaluate subgroup disparities to ensure accountability and generalizability in clinical workflows. In this paper, we explore how epistemic uncertainty can be used to evaluate disparity in patient demographics (race) and data acquisition (scanner) subgroups for breast density assessment on a dataset of 108,190 mammograms collected from 33 clinical sites. Our results show that even if aggregate performance is comparable, the choice of uncertainty quantification metric can significantly the subgroup level. We hope this analysis can promote further work on how uncertainty can be leveraged to increase transparency of machine learning applications for clinical deployment.

Sharut Gupta, Praveer Singh, Ken Chang et al.

Model brittleness is a key concern when deploying deep learning models in real-world medical settings. A model that has high performance at one institution may suffer a significant decline in performance when tested at other institutions. While pooling datasets from multiple institutions and retraining may provide a straightforward solution, it is often infeasible and may compromise patient privacy. An alternative approach is to fine-tune the model on subsequent institutions after training on the original institution. Notably, this approach degrades model performance at the original institution, a phenomenon known as catastrophic forgetting. In this paper, we develop an approach to address catastrophic forget-ting based on elastic weight consolidation combined with modulation of batch normalization statistics under two scenarios: first, for expanding the domain from one imaging system's data to another imaging system's, and second, for expanding the domain from a large multi-institutional dataset to another single institution dataset. We show that our approach outperforms several other state-of-the-art approaches and provide theoretical justification for the efficacy of batch normalization modulation. The results of this study are generally applicable to the deployment of any clinical deep learning model which requires domain expansion.

Giorgio Pietro Biondetti, Romane Gauriau, Christopher P. Bridge et al.

As interest in applying machine learning techniques for medical images continues to grow at a rapid pace, models are starting to be developed and deployed for clinical applications. In the clinical AI model development lifecycle (described by Lu et al. [1]), a crucial phase for machine learning scientists and clinicians is the proper design and collection of the data cohort. The ability to recognize various forms of biases and distribution shifts in the dataset is critical at this step. While it remains difficult to account for all potential sources of bias, techniques can be developed to identify specific types of bias in order to mitigate their impact. In this work we analyze how the distribution of scanner manufacturers in a dataset can contribute to the overall bias of deep learning models. We evaluate convolutional neural networks (CNN) for both classification and segmentation tasks, specifically two state-of-the-art models: ResNet [2] for classification and U-Net [3] for segmentation. We demonstrate that CNNs can learn to distinguish the imaging scanner manufacturer and that this bias can substantially impact model performance for both classification and segmentation tasks. By creating an original synthesis dataset of brain data mimicking the presence of more or less subtle lesions we also show that this bias is related to the difficulty of the task. Recognition of such bias is critical to develop robust, generalizable models that will be crucial for clinical applications in real-world data distributions.

Charles Lu, Julia Strout, Romane Gauriau et al.

Healthcare is one of the most promising areas for machine learning models to make a positive impact. However, successful adoption of AI-based systems in healthcare depends on engaging and educating stakeholders from diverse backgrounds about the development process of AI models. We present a broadly accessible overview of the development life cycle of clinical AI models that is general enough to be adapted to most machine learning projects, and then give an in-depth case study of the development process of a deep learning based system to detect aortic aneurysms in Computed Tomography (CT) exams. We hope other healthcare institutions and clinical practitioners find the insights we share about the development process useful in informing their own model development efforts and to increase the likelihood of successful deployment and integration of AI in healthcare.

Charles Lu, M. Marx, M. Zahid et al.

Cilia are hairlike structures protruding from nearly every cell in the body. Diseases known as ciliopathies, where cilia function is disrupted, can result in a wide spectrum of disorders. However, most techniques for assessing ciliary motion rely on manual identification and tracking of cilia; this process is laborious and error-prone, and does not scale well. Even where automated ciliary motion analysis tools exist, their applicability is limited. Here, we propose an end-to-end computational machine learning pipeline that automatically identifies regions of cilia from videos, extracts patches of cilia, and classifies patients as exhibiting normal or abnormal ciliary motion. In particular, we demonstrate how convolutional LSTM are able to encode complex features while remaining sensitive enough to differentiate between a variety of motion patterns. Our framework achieves 90% with only a few hundred training epochs. We find that the combination of segmentation and classification networks in a single pipeline yields performance comparable to existing computational pipelines, while providing the additional benefit of an end-to-end, fully-automated analysis toolbox for ciliary motion.