Search

Timely disease diagnosis is challenging due to increasing disease burdens and limited clinician availability. AI shows promise in diagnosis accuracy but faces real-world application issues due to insufficient validation in clinical workflows and diverse populations. This study addresses gaps in medical AI downstream accountability through a case study on age-related macular degeneration (AMD) diagnosis and severity classification. We designed and implemented an AI-assisted diagnostic workflow for AMD, comparing diagnostic performance with and without AI assistance among 24 clinicians from 12 institutions with real patient data sampled from the Age-Related Eye Disease Study (AREDS). Additionally, we demonstrated continual enhancement of an existing AI model by incorporating approximately 40,000 additional medical images (named AREDS2 dataset). The improved model was then systematically evaluated using both AREDS and AREDS2 test sets, as well as an external test set from Singapore. AI assistance markedly enhanced diagnostic accuracy and classification for 23 out of 24 clinicians, with the average F1-score increasing by 20% from 37.71 (Manual) to 45.52 (Manual + AI) (P-value < 0.0001), achieving an improvement of over 50% in some cases. In terms of efficiency, AI assistance reduced diagnostic times for 17 out of the 19 clinicians tracked, with time savings of up to 40%. Furthermore, a model equipped with continual learning showed robust performance across three independent datasets, recording a 29% increase in accuracy, and elevating the F1-score from 42 to 54 in the Singapore population.

Transcriptional noise, or heterogeneity, is important in cellular development and in disease. The molecular mechanisms driving it are, however, elusive and ill-understood. Here, we use computer simulations to explore the role of 3D chromatin structure in driving transcriptional noise. We study a simple polymer model where proteins - modeling complexes of transcription factors and polymerases - bind multivalently to transcription units - modeling regulatory elements such as promoters and enhancers. We also include cohesin-like factors which extrude chromatin loops that are important for the physiological folding of chromosomes. We find that transcription factor binding creates spatiotemporal patterning and a highly variable correlation time in transcriptional dynamics, providing a mechanism for intrinsic noise within a single cell. Instead, loop extrusion contributes to extrinsic noise, as the stochastic nature of this process leads to different networks of cohesin loops in different cells in our simulations. Our results could be tested with single-cell experiments and provide a pathway to understanding the principles underlying transcriptional plasticity in vivo.

Multiphase field models have emerged as an important computational tool for understanding biological tissue while resolving single-cell properties. While they have successfully reproduced many experimentally observed behaviors of living tissue, the theoretical underpinnings have not been fully explored. We show that a two-dimensional version of the model, which is commonly employed to study tissue monolayers, can be derived from a three-dimensional version in the presence of a substrate. We also show how viscous forces, which arise from friction between different cells, can be included in the model. Finally, we numerically simulate a tissue monolayer, and find that intercellular friction tends to solidify the tissue., Comment: 16 pages, 4 figures

Spatiotemporal patterns in multicellular systems are important to understanding tissue dynamics, for instance, during embryonic development and disease. Here, we use a multiphase field model to study numerically the behavior of a near-confluent monolayer of deformable cells with intercellular friction. Varying friction and cell motility drives a solid-liquid transition, and near the transition boundary, we find the emergence of nematic order of cell deformation driven by shear-aligning cellular flows. Intercellular friction endows the monolayer with a finite viscosity, which significantly increases the spatial correlation in the flow and, concomitantly, the extent of nematic order. We also show that hexatic and nematic order are tightly coupled and propose a mechanical-geometric model for the colocalization of +1/2 nematic defects and 5-7 disclination pairs, which are the structural defects in the hexatic phase. Such topological defects coincide with regions of high cell-cell overlap, suggesting that they may mediate cellular extrusion from the monolayer, as found experimentally. Our results delineate a mechanical basis for the recent observation of nematic and hexatic order in multicellular collectives in experiments and simulations and pinpoint a generic pathway to couple topological and physical effects in these systems.

Using a multi-phase field model, we examine how particle deformability, which is a proxy for cell stiffness, affects motility induced phase separation (MIPS). We show that purely repulsive deformable, i.e., squishy, cells phase separate more effectively than their rigid counterparts. This can be understood as due to the fact that deformability increases the effective duration of collisions. In addition, the dense regions become increasingly disordered as deformability increases. Our results contextualize the applicability of MIPS to biological systems and have implications for how cells in biological systems may self-organize, Comment: 7 pages, 6 figures

Many variables of interest in clinical medicine, like disease severity, are recorded using discrete ordinal categories such as normal/mild/moderate/severe. These labels are used to train and evaluate disease severity prediction models. However, ordinal categories represent a simplification of an underlying continuous severity spectrum. Using continuous scores instead of ordinal categories is more sensitive to detecting small changes in disease severity over time. Here, we present a generalized framework that accurately predicts continuously valued variables using only discrete ordinal labels during model development. We found that for three clinical prediction tasks, models that take the ordinal relationship of the training labels into account outperformed conventional multi-class classification models. Particularly the continuous scores generated by ordinal classification and regression models showed a significantly higher correlation with expert rankings of disease severity and lower mean squared errors compared to the multi-class classification models. Furthermore, the use of MC dropout significantly improved the ability of all evaluated deep learning approaches to predict continuously valued scores that truthfully reflect the underlying continuous target variable. We showed that accurate continuously valued predictions can be generated even if the model development only involves discrete ordinal labels. The novel framework has been validated on three different clinical prediction tasks and has proven to bridge the gap between discrete ordinal labels and the underlying continuously valued variables.

The rheology of biological tissue plays an important role in many processes, from organ formation to cancer invasion. Here, we use a multi-phase field model of motile cells to simulate active microrheology within a tissue monolayer. When unperturbed, the tissue exhibits a transition between a solid-like state and a fluid-like state tuned by cell motility and deformability - the ratio of the energetic costs of steric cell-cell repulsion and cell surface tension. When perturbed, solid tissues exhibit yield-stress behavior, with a threshold force for the onset of motion of a probe particle that vanishes upon approaching the solid-to-liquid transition. This onset of motion is qualitatively different in the low and high deformability regimes. At high deformability, the tissue is amorphous when solid, it responds compliantly to deformations, and the probe transition to motion is smooth. At low deformability, the monolayer is more ordered translationally and stiffer, and the onset of motion appears discontinuous. Our results suggest that cellular or nanoparticle transport in different types of tissues can be fundamentally different, and point to ways in which it can be controlled., Comment: Main text (6 pages, 4 figures) plus SM (8 pages, 9 figures)

Background: Artificial intelligence (AI) may demonstrate racial bias when skin or choroidal pigmentation is present in medical images. Recent studies have shown that convolutional neural networks (CNNs) can predict race from images that were not previously thought to contain race-specific features. We evaluate whether grayscale retinal vessel maps (RVMs) of patients screened for retinopathy of prematurity (ROP) contain race-specific features. Methods: 4095 retinal fundus images (RFIs) were collected from 245 Black and White infants. A U-Net generated RVMs from RFIs, which were subsequently thresholded, binarized, or skeletonized. To determine whether RVM differences between Black and White eyes were physiological, CNNs were trained to predict race from color RFIs, raw RVMs, and thresholded, binarized, or skeletonized RVMs. Area under the precision-recall curve (AUC-PR) was evaluated. Findings: CNNs predicted race from RFIs near perfectly (image-level AUC-PR: 0.999, subject-level AUC-PR: 1.000). Raw RVMs were almost as informative as color RFIs (image-level AUC-PR: 0.938, subject-level AUC-PR: 0.995). Ultimately, CNNs were able to detect whether RFIs or RVMs were from Black or White babies, regardless of whether images contained color, vessel segmentation brightness differences were nullified, or vessel segmentation widths were normalized. Interpretation: AI can detect race from grayscale RVMs that were not thought to contain racial information. Two potential explanations for these findings are that: retinal vessels physiologically differ between Black and White babies or the U-Net segments the retinal vasculature differently for various fundus pigmentations. Either way, the implications remain the same: AI algorithms have potential to demonstrate racial bias in practice, even when preliminary attempts to remove such information from the underlying images appear to be successful., Comment: 31 pages, 6 figures

Lamina-associated domains (LADs) cover a large part of the human genome and are thought to play a major role in shaping the nuclear architectural landscape. Here, we perform polymer simulations, microscopy and mass spectrometry to dissect the roles played by heterochromatin- and lamina-mediated interactions in nuclear organisation. Our model explains the conventional organisation of heterochromatin and euchromatin in growing cells and the pathological organisation found in oncogene-induced senescence and progeria. We show that the experimentally observed changes in the locality of contacts in senescent and progeroid cells can be explained as arising due to phase transitions in the system. Within our simulations LADs are highly stochastic, as in experiments. Our model suggests that, once established, the senescent phenotype should be metastable even if lamina-mediated interactions were reinstated. Overall, our simulations uncover a generic physical mechanism that can regulate heterochromatin segregation and LAD formation in a wide range of mammalian nuclei., Comment: 20 pages, 8 figures

Experiments and theory have shown that cell monolayers and epithelial tissues exhibit solid-liquid and glass-liquid transitions. These transitions are biologically relevant to our understanding of embryonic development, wound healing, and cancer. Current models typically consider purely two-dimensional monolayers with no overlaps between neighboring cells. In reality, overlaps are important, and they may be precursors of cell extrusion -- a key biophysical process to maintain homeostasis in epithelial tissues. Here, we use a multi-phase field model to study the solid-liquid transition in a confluent monolayer of deformable cells which can overlap. When cells overlap rather than deform, we find that the melting transition changes from continuous to discontinuous, and that there is an intermittent regime close to the transition, where solid and liquid states alternate over time. By studying the dynamics of $5$- and $7$-fold disclinations in the hexagonal lattice formed by the cell centers, we observe that these correlate with spatial fluctuations in the cellular overlap, and that cell extrusion tends to initiate near $5$-fold disclinations., Comment: Figures have been updated and the text expanded. Main text (6 pages, 4 figures) plus SM (12 pages, 16 figures). Supplementary movies can be found at https://drive.google.com/open?id=1yfMf0aFqFlgjsGGjE0Zr3zo_eiIcREB9

Convolutional neural networks (CNNs) have enabled significant performance leaps in medical image classification tasks. However, translating neural network models for clinical applications remains challenging due to data privacy issues. Fully Homomorphic Encryption (FHE) has the potential to address this challenge as it enables the use of CNNs on encrypted images. However, current HE technology poses immense computational and memory overheads, particularly for high-resolution images such as those seen in the clinical context. We present CaRENets: Compact and Resource-Efficient CNNs for high performance and resource-efficient inference on high-resolution encrypted images in practical applications. At the core, CaRENets comprises a new FHE compact packing scheme that is tightly integrated with CNN functions. CaRENets offers dual advantages of memory efficiency (due to compact packing of images and CNN activations) and inference speed (due to the reduction in the number of ciphertexts created and the associated mathematical operations) over standard interleaved packing schemes. We apply CaRENets to perform homomorphic abnormality detection with 80-bit security level in two clinical conditions - Retinopathy of Prematurity (ROP) and Diabetic Retinopathy (DR). The ROP dataset comprises 96 x 96 grayscale images, while the DR dataset comprises 256 x 256 RGB images. We demonstrate over 45x improvement in memory efficiency and 4-5x speedup in inference over the interleaved packing schemes. As our approach enables memory-efficient low-latency HE inference without imposing additional communication burden, it has implications for practical and secure deep learning inference in clinical imaging.

Pairwise comparison labels are more informative and less variable than class labels, but generating them poses a challenge: their number grows quadratically in the dataset size. We study a natural experimental design objective, namely, D-optimality, that can be used to identify which $K$ pairwise comparisons to generate. This objective is known to perform well in practice, and is submodular, making the selection approximable via the greedy algorithm. A na\"ive greedy implementation has $O(N^2d^2K)$ complexity, where $N$ is the dataset size, $d$ is the feature space dimension, and $K$ is the number of generated comparisons. We show that, by exploiting the inherent geometry of the dataset--namely, that it consists of pairwise comparisons--the greedy algorithm's complexity can be reduced to $O(N^2(K+d)+N(dK+d^2) +d^2K).$ We apply the same acceleration also to the so-called lazy greedy algorithm. When combined, the above improvements lead to an execution time of less than 1 hour for a dataset with $10^8$ comparisons; the na\"ive greedy algorithm on the same dataset would require more than 10 days to terminate.