Search

Foundation models in computational pathology promise to unlock the development of new clinical decision support systems and models for precision medicine. However, there is a mismatch between most clinical analysis, which is defined at the level of one or more whole slide images, and foundation models to date, which process the thousands of image tiles contained in a whole slide image separately. The requirement to train a network to aggregate information across a large number of tiles in multiple whole slide images limits these models' impact. In this work, we present a slide-level foundation model for H&E-stained histopathology, PRISM, that builds on Virchow tile embeddings and leverages clinical report text for pre-training. Using the tile embeddings, PRISM produces slide-level embeddings with the ability to generate clinical reports, resulting in several modes of use. Using text prompts, PRISM achieves zero-shot cancer detection and sub-typing performance approaching and surpassing that of a supervised aggregator model. Using the slide embeddings with linear classifiers, PRISM surpasses supervised aggregator models. Furthermore, we demonstrate that fine-tuning of the PRISM slide encoder yields label-efficient training for biomarker prediction, a task that typically suffers from low availability of training data; an aggregator initialized with PRISM and trained on as little as 10% of the training data can outperform a supervised baseline that uses all of the data.

Self-supervised learning (SSL) has emerged as a key technique for training networks that can generalize well to diverse tasks without task-specific supervision. This property makes SSL desirable for computational pathology, the study of digitized images of tissues, as there are many target applications and often limited labeled training samples. However, SSL algorithms and models have been primarily developed in the field of natural images and whether their performance can be improved by adaptation to particular domains remains an open question. In this work, we present an investigation of modifications to SSL for pathology data, specifically focusing on the DINOv2 algorithm. We propose alternative augmentations, regularization functions, and position encodings motivated by the characteristics of pathology images. We evaluate the impact of these changes on several benchmarks to demonstrate the value of tailored approaches., Comment: Presented at DCA in MI Workshop, CVPR 2024

Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language. However, their capabilities wane in highly specialized domains underrepresented in the pretraining corpus, such as physical and biomedical sciences. This work explores how to repurpose general LLMs into effective task solvers for specialized domains. We introduce a novel, model-agnostic framework for learning custom input tags, which are parameterized as continuous vectors appended to the LLM's embedding layer, to condition the LLM. We design two types of input tags: domain tags are used to delimit specialized representations (e.g., chemical formulas) and provide domain-relevant context; function tags are used to represent specific functions (e.g., predicting molecular properties) and compress function-solving instructions. We develop a three-stage protocol to learn these tags using auxiliary data and domain knowledge. By explicitly disentangling task domains from task functions, our method enables zero-shot generalization to unseen problems through diverse combinations of the input tags. It also boosts LLM's performance in various specialized domains, such as predicting protein or chemical properties and modeling drug-target interactions, outperforming expert models tailored to these tasks.

In certain types of cancerous tissue, mitotic count has been shown to be associated with tumor proliferation, poor prognosis, and therapeutic resistance. Due to the high inter-rater variability of mitotic counting by pathologists, convolutional neural networks (CNNs) have been employed to reduce the subjectivity of mitosis detection in hematoxylin and eosin (H&E)-stained whole slide images. However, most existing models have performance that lags behind expert panel review and only incorporate visual information. In this work, we demonstrate that pre-trained large-scale vision-language models that leverage both visual features and natural language improve mitosis detection accuracy. We formulate the mitosis detection task as an image captioning task and a visual question answering (VQA) task by including metadata such as tumor and scanner types as context. The effectiveness of our pipeline is demonstrated via comparison with various baseline models using 9,501 mitotic figures and 11,051 hard negatives (non-mitotic figures that are difficult to characterize) from the publicly available Mitosis Domain Generalization Challenge (MIDOG22) dataset., Comment: Submitted to IEEE ISBI 2024. Under review

Randomized experiments often need to be stopped prematurely due to the treatment having an unintended harmful effect. Existing methods that determine when to stop an experiment early are typically applied to the data in aggregate and do not account for treatment effect heterogeneity. In this paper, we study the early stopping of experiments for harm on heterogeneous populations. We first establish that current methods often fail to stop experiments when the treatment harms a minority group of participants. We then use causal machine learning to develop CLASH, the first broadly-applicable method for heterogeneous early stopping. We demonstrate CLASH's performance on simulated and real data and show that it yields effective early stopping for both clinical trials and A/B tests., Comment: NeurIPS 2023 (spotlight)

With the recent advances in A.I. methodologies and their application to medical imaging, there has been an explosion of related research programs utilizing these techniques to produce state-of-the-art classification performance. Ultimately, these research programs culminate in submission of their work for consideration in peer reviewed journals. To date, the criteria for acceptance vs. rejection is often subjective; however, reproducible science requires reproducible review. The Machine Learning Education Sub-Committee of SIIM has identified a knowledge gap and a serious need to establish guidelines for reviewing these studies. Although there have been several recent papers with this goal, this present work is written from the machine learning practitioners standpoint. In this series, the committee will address the best practices to be followed in an A.I.-based study and present the required sections in terms of examples and discussion of what should be included to make the studies cohesive, reproducible, accurate, and self-contained. This first entry in the series focuses on the task of image classification. Elements such as dataset curation, data pre-processing steps, defining an appropriate reference standard, data partitioning, model architecture and training are discussed. The sections are presented as they would be detailed in a typical manuscript, with content describing the necessary information that should be included to make sure the study is of sufficient quality to be considered for publication. The goal of this series is to provide resources to not only help improve the review process for A.I.-based medical imaging papers, but to facilitate a standard for the information that is presented within all components of the research study. We hope to provide quantitative metrics in what otherwise may be a qualitative review process.

Factorized layers--operations parameterized by products of two or more matrices--occur in a variety of deep learning contexts, including compressed model training, certain types of knowledge distillation, and multi-head self-attention architectures. We study how to initialize and regularize deep nets containing such layers, examining two simple, understudied schemes, spectral initialization and Frobenius decay, for improving their performance. The guiding insight is to design optimization routines for these networks that are as close as possible to that of their well-tuned, non-decomposed counterparts; we back this intuition with an analysis of how the initialization and regularization schemes impact training with gradient descent, drawing on modern attempts to understand the interplay of weight-decay and batch-normalization. Empirically, we highlight the benefits of spectral initialization and Frobenius decay across a variety of settings. In model compression, we show that they enable low-rank methods to significantly outperform both unstructured sparsity and tensor methods on the task of training low-memory residual networks; analogs of the schemes also improve the performance of tensor decomposition techniques. For knowledge distillation, Frobenius decay enables a simple, overcomplete baseline that yields a compact model from over-parameterized training without requiring retraining with or pruning a teacher network. Finally, we show how both schemes applied to multi-head attention lead to improved performance on both translation and unsupervised pre-training., Comment: ICLR 2021 camera-ready, amended due to error pointed out in arXiv:2209.13569v1 (amendment shown in blue)

We propose a deep learning-based technique for detection and quantification of abdominal aortic aneurysms (AAAs). The condition, which leads to more than 10,000 deaths per year in the United States, is asymptomatic, often detected incidentally, and often missed by radiologists. Our model architecture is a modified 3D U-Net combined with ellipse fitting that performs aorta segmentation and AAA detection. The study uses 321 abdominal-pelvic CT examinations performed by Massachusetts General Hospital Department of Radiology for training and validation. The model is then further tested for generalizability on a separate set of 57 examinations with differing patient demographics and acquisition characteristics than the original dataset. DeepAAA achieves high performance on both sets of data (sensitivity/specificity 0.91/0.95 and 0.85 / 1.0 respectively), on contrast and non-contrast CT scans and works with image volumes with varying numbers of images. We find that DeepAAA exceeds literature-reported performance of radiologists on incidental AAA detection. It is expected that the model can serve as an effective background detector in routine CT examinations to prevent incidental AAAs from being missed., Comment: Accepted for publication at MICCAI 2019

We propose a 4D convolutional neural network (CNN) for the segmentation of retrospective ECG-gated cardiac CT, a series of single-channel volumetric data over time. While only a small subset of volumes in the temporal sequence is annotated, we define a sparse loss function on available labels to allow the network to leverage unlabeled images during training and generate a fully segmented sequence. We investigate the accuracy of the proposed 4D network to predict temporally consistent segmentations and compare with traditional 3D segmentation approaches. We demonstrate the feasibility of the 4D CNN and establish its performance on cardiac 4D CCTA., Comment: MICCAI, STACOM, 2019

The amounts of muscle and fat in a person's body, known as body composition, are correlated with cancer risks, cancer survival, and cardiovascular risk. The current gold standard for measuring body composition requires time-consuming manual segmentation of CT images by an expert reader. In this work, we describe a two-step process to fully automate the analysis of CT body composition using a DenseNet to select the CT slice and U-Net to perform segmentation. We train and test our methods on independent cohorts. Our results show Dice scores (0.95-0.98) and correlation coefficients (R=0.99) that are favorable compared to human readers. These results suggest that fully automated body composition analysis is feasible, which could enable both clinical use and large-scale population studies.

Data diversity is critical to success when training deep learning models. Medical imaging data sets are often imbalanced as pathologic findings are generally rare, which introduces significant challenges when training deep learning models. In this work, we propose a method to generate synthetic abnormal MRI images with brain tumors by training a generative adversarial network using two publicly available data sets of brain MRI. We demonstrate two unique benefits that the synthetic images provide. First, we illustrate improved performance on tumor segmentation by leveraging the synthetic images as a form of data augmentation. Second, we demonstrate the value of generative models as an anonymization tool, achieving comparable tumor segmentation results when trained on the synthetic data versus when trained on real subject data. Together, these results offer a potential solution to two of the largest challenges facing machine learning in medical imaging, namely the small incidence of pathological findings, and the restrictions around sharing of patient data., Comment: Accepted for 2018 Workshop on Simulation and Synthesis in Medical Imaging - SASHIMI2018