Demographic bias in misdiagnosis by computational pathology models.

Despite increasing numbers of regulatory approvals, deep learning-based computational pathology systems often overlook the impact of demographic factors on performance, potentially leading to biases. This concern is all the more important as computational pathology has leveraged large public datasets that underrepresent certain demographic groups. Using publicly available data from The Cancer Genome Atlas and the EBRAINS brain tumor atlas, as well as internal patient data, we show that whole-slide image classification models display marked performance disparities across different demographic groups when used to subtype breast and lung carcinomas and to predict IDH1 mutations in gliomas. For example, when using common modeling approaches, we observed performance gaps (in area under the receiver operating characteristic curve) between white and Black patients of 3.0% for breast cancer subtyping, 10.9% for lung cancer subtyping and 16.0% for IDH1 mutation prediction in gliomas. We found that richer feature representations obtained from self-supervised vision foundation models reduce performance variations between groups. These representations provide improvements upon weaker models even when those weaker models are combined with state-of-the-art bias mitigation strategies and modeling choices. Nevertheless, self-supervised vision foundation models do not fully eliminate these discrepancies, highlighting the continuing need for bias mitigation efforts in computational pathology. Finally, we demonstrate that our results extend to other demographic factors beyond patient race. Given these findings, we encourage regulatory and policy agencies to integrate demographic-stratified evaluation into their assessment guidelines.

Towards a general-purpose foundation model for computational pathology.

Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks, requiring the objective characterization of histopathological entities from whole-slide images (WSIs). The high resolution of WSIs and the variability of morphological features present significant challenges, complicating the large-scale annotation of data for high-performance applications. To address this challenge, current efforts have proposed the use of pretrained image encoders through transfer learning from natural image datasets or self-supervised learning on publicly available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using more than 100 million images from over 100,000 diagnostic H&E-stained WSIs (>77 TB of data) across 20 major tissue types. The model was evaluated on 34 representative CPath tasks of varying diagnostic difficulty. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient artificial intelligence models that can generalize and transfer to a wide range of diagnostically challenging tasks and clinical workflows in anatomic pathology.

A General-Purpose Self-Supervised Model for Computational Pathology.

Tissue phenotyping is a fundamental computational pathology (CPath) task in learning objective characterizations of histopathologic biomarkers in anatomic pathology. However, whole-slide imaging (WSI) poses a complex computer vision problem in which the large-scale image resolutions of WSIs and the enormous diversity of morphological phenotypes preclude large-scale data annotation. Current efforts have proposed using pretrained image encoders with either transfer learning from natural image datasets or self-supervised pretraining on publicly-available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using over 100 million tissue patches from over 100,000 diagnostic haematoxylin and eosin-stained WSIs across 20 major tissue types, and evaluated on 33 representative CPath clinical tasks in CPath of varying diagnostic difficulties. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree code classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient AI models that can generalize and transfer to a gamut of diagnostically-challenging tasks and clinical workflows in anatomic pathology.

Artificial intelligence for multimodal data integration in oncology.

In oncology, the patient state is characterized by a whole spectrum of modalities, ranging from radiology, histology, and genomics to electronic health records. Current artificial intelligence (AI) models operate mainly in the realm of a single modality, neglecting the broader clinical context, which inevitably diminishes their potential. Integration of different data modalities provides opportunities to increase robustness and accuracy of diagnostic and prognostic models, bringing AI closer to clinical practice. AI models are also capable of discovering novel patterns within and across modalities suitable for explaining differences in patient outcomes or treatment resistance. The insights gleaned from such models can guide exploration studies and contribute to the discovery of novel biomarkers and therapeutic targets. To support these advances, here we present a synopsis of AI methods and strategies for multimodal data fusion and association discovery. We outline approaches for AI interpretability and directions for AI-driven exploration through multimodal data interconnections. We examine challenges in clinical adoption and discuss emerging solutions.

Anisotropic and viscoelastic tensile mechanical properties of aponeurosis: Experimentation, modeling, and tissue microstructure.

Aponeuroses are stiff sheath-like components of the muscle-tendon unit that play a vital role in force transmission and thus locomotion. There is clear importance of the aponeurosis in musculoskeletal function, but there have been relatively few studies of aponeurosis material properties to date. The goals of this work were to: 1) perform tensile stress-relaxation tests, 2) perform planar biaxial tests, 3) employ computational modeling to the data from 1 to 2, and 4) perform scanning electron microscopy to determine collagen fibril organization for aponeurosis tissue. Viscoelastic modeling and statistical analysis of stress-relaxation data showed that while relaxation rate differed statistically between strain levels (p = 0.044), functionally the relaxation behavior was nearly the same. Biaxial testing and associated modeling highlighted the nonlinear (toe region of ~2-3% strain) and anisotropic (longitudinal direction linear modulus ~50 MPa, transverse ~2.5 MPa) tensile mechanical behavior of aponeurosis tissue. Comparisons of various constitutive formulations showed that a transversely isotropic Ogden approach balanced strong fitting (goodness of fit 0.984) with a limited number of parameters (five), while damage modeling parameters were also provided. Scanning electron microscopy showed a composite structure of highly aligned, partially wavy collagen fibrils with more random collagen cables for aponeurosis microstructure. Future work to expand microstructural analysis and use these data to inform computational modeling would benefit this work and the field.

An experimental and computational investigation of the effects of volumetric boundary conditions on the compressive mechanics of passive skeletal muscle.

Computational modeling, such as finite element analysis, is employed in a range of biomechanics specialties, including impact biomechanics and surgical planning. These models rely on accurate material properties for skeletal muscle, which comprises roughly 40% of the human body. Due to surrounding tissues, compressed skeletal muscle in vivo likely experiences a semi-confined state. Nearly all previous studies investigating passively compressed muscle at the tissue level have focused on muscle in unconfined compression. The goals of this study were to (1) examine the stiffness and time-dependent material properties of skeletal muscle subjected to both confined and unconfined compression (2) develop a model that captures passive muscle mechanics under both conditions and (3) determine the extent to which different assumptions of volumetric behavior affect model results. Muscle in confined compression exhibited stiffer behavior, agreeing with previous assumptions of near-incompressibility. Stress relaxation was found to be faster under unconfined compression, suggesting there may be different mechanisms that support load these two conditions. Finite element calibration was achieved through nonlinear optimization (normalized root mean square error <6%) and model validation was strong (normalized root mean square error <17%). Comparisons to commonly employed assumptions of bulk behavior showed that a simple one parameter approach does not accurately simulate confined compression. We thus recommend the use of a properly calibrated, nonlinear bulk constitutive model for modeling of skeletal muscle in vivo. Future work to determine mechanisms of passive muscle stiffness would enhance the efforts presented here.