Deep learning identification of stiffness markers in breast cancer

Integrating finite element analysis and physics-informed neural networks for biomechanical modeling of the human lumbar spine

Background

Comprehending the biomechanical characteristics of the human lumbar spine is crucial for managing and preventing spinal disorders. Precise material properties derived from patient-specific CT scans are essential for simulations to accurately mimic real-life scenarios, which is invaluable in creating effective surgical plans. The integration of Finite Element Analysis (FEA) with Physics-Informed Neural Networks (PINNs) offers significant clinical benefits by automating lumbar spine segmentation and meshing.

Methods

We developed a FEA model of the lumbar spine incorporating detailed anatomical and material properties derived from high-quality CT and MRI scans. The model includes vertebrae and intervertebral discs, segmented and meshed using advanced imaging and computational techniques. PINNs were implemented to integrate physical laws directly into the neural network training process, ensuring that the predictions of material properties adhered to the governing equations of mechanics.

Results

The model achieved an accuracy of 94.30% in predicting material properties such as Young's modulus (14.88 GPa for cortical bone and 1.23 MPa for intervertebral discs), Poisson's ratio (0.25 and 0.47, respectively), bulk modulus (9.87 GPa and 6.56 MPa, respectively), and shear modulus (5.96 GPa and 0.42 MPa, respectively). We developed a lumbar spine FEA model using anatomical and material properties from CT and MRI scans. Vertebrae and discs were segmented and meshed with advanced imaging techniques, while PINNs ensured material predictions followed mechanical laws.

Conclusions

The integration of FEA and PINNs allows for accurate, automated prediction of material properties and mechanical behaviors of the lumbar spine, significantly reducing manual input and enhancing reliability. This approach ensures dependable biomechanical simulations and supports the development of personalized treatment plans and surgical strategies, ultimately improving clinical outcomes for spinal disorders. This method improves surgical planning and outcomes, contributing to better patient care and recovery in spinal disorders.

Interpretable deep learning method to predict wound healing progress based on collagen fibers in wound tissue

BACKGROUND AND OBJECTIVE

The dynamic evolution of collagen fibers during wound healing is crucial for assessing repair progression, guiding clinical treatment, and drug screening. Current quantitative methods analyzing collagen spatial patterns (density, orientation variance) lack established criteria to both stratify distinct healing periods and detect delayed healing conditions, necessitating the establishment of a novel classification method for wound healing status based on collagen fibers.

METHODS

We propose a deep learning method to classify various time points of wound healing and delayed healing using histological images of skin tissue. We fine-tune a pre-trained VGG16 model and enhance it with an interpretable framework that combines LayerCAM and Guided Backpropagation, leveraging model gradients and features to visually identify the tissue regions driving model predictions.

RESULTS

Our model achieved 85 % accuracy in a five-class classification task (normal skin, wound skin at 0, 3, 7, and 10 days) and 78 % in a three-class task (normal skin, wound skin at 0 days, diabetic wound skin at 10 days). Our interpretable framework accurately localizes collagen fibers without pixel-level annotations, demonstrating that our model classifies healing periods and delayed healing based on collagen regions in histological images rather than other less relevant tissue structures.

CONCLUSIONS

Our deep learning method leverages collagen fiber features to predict various time points of wound healing and delayed healing with high accuracy and visual interpretability, enhancing doctors' trust in model decisions. This could lead to more precise and effective wound treatment practices.

Combined assembloid modeling and 3D whole-organ mapping captures the microanatomy and function of the human fallopian tube

The fallopian tubes play key roles in processes from pregnancy to ovarian cancer where three-dimensional (3D) cellular and extracellular interactions are important to their pathophysiology. Here, we develop a 3D multicompartment assembloid model of the fallopian tube that molecularly, functionally, and architecturally resembles the organ. Global label-free proteomics, innovative assays capturing physiological functions of the fallopian tube (i.e., oocyte transport), and whole-organ single-cell resolution mapping are used to validate these assembloids through a multifaceted platform with direct comparisons to fallopian tube tissue. These techniques converge at a unique combination of assembloid parameters with the highest similarity to the reference fallopian tube. This work establishes (i) an optimized model of the human fallopian tubes for in vitro studies of their pathophysiology and (ii) an iterative platform for customized 3D in vitro models of human organs that are molecularly, functionally, and microanatomically accurate by combining tunable assembloid and tissue mapping methods.

Tumor-associated fibrosis: a unique mechanism promoting ovarian cancer metastasis and peritoneal dissemination

Epithelial ovarian cancer (EOC) is often diagnosed in advanced stage with peritoneal dissemination. Recent studies indicate that aberrant accumulation of collagen fibers in tumor stroma has a variety of effects on tumor progression. We refer to remodeled fibrous stroma with altered expression of collagen molecules, increased stiffness, and highly oriented collagen fibers as tumor-associated fibrosis (TAF). TAF contributes to EOC cell invasion and metastasis in the intraperitoneal cavity. However, an understanding of molecular events involved is only just beginning to emerge. Further development in this field will lead to new strategies to treat EOC. In this review, we focus on the recent findings on how the TAF contributes to EOC malignancy. Furthermore, we will review the recent initiatives and future therapeutic strategies for targeting TAF in EOC.

Elastic parameter identification of three-dimensional soft tissue based on deep neural network

In the field of virtual surgery and deformation simulation, the identification of elastic parameters of human soft tissues is a critical technology that directly affects the accuracy of deformation simulation. Current research on soft tissue deformation simulation predominantly assumes that the elasticity of tissues is fixed and already known, leading to the difficulty in populating with the elasticity measured or identified from specific tissues of real patients. Existing elasticity modeling efforts struggle to be implemented on irregularly structured soft tissues, failing to adapt to clinical surgical practices. Therefore, this paper proposes a new method for identifying human soft tissue elastic parameters based on the finite element method and the deep neural network, UNet. This method requires only the full-field displacement data of soft tissues under external loads to predict their elastic distribution. The performance and validity of the algorithm are assessed using test data and clinical data from rhinoplasty surgeries. Experiments demonstrate that the method proposed in this paper can achieve an accuracy of over 99% in predicting elastic parameters. Clinical data validation shows that the predicted elastic distribution can reduce the error in finite element deformation simulations by more than 80% at the maximum compared to the error with traditional uniform elastic parameters, effectively enhancing the computational accuracy in virtual surgery simulations and soft tissue deformation modeling.

Small Extracellular Vesicles Promote Stiffness-mediated Metastasis

Tissue stiffness is a critical prognostic factor in breast cancer and is associated with metastatic progression. Here we show an alternative and complementary hypothesis of tumor progression whereby physiologic matrix stiffness affects the quantity and protein cargo of small extracellular vesicles (EV) produced by cancer cells, which in turn aid cancer cell dissemination. Primary patient breast tissue released by cancer cells on matrices that model human breast tumors (25 kPa; stiff EVs) feature increased adhesion molecule presentation (ITGα2β1, ITGα6β4, ITGα6β1, CD44) compared with EVs from softer normal tissue (0.5 kPa; soft EVs), which facilitates their binding to extracellular matrix proteins including collagen IV, and a 3-fold increase in homing ability to distant organs in mice. In a zebrafish xenograft model, stiff EVs aid cancer cell dissemination. Moreover, normal, resident lung fibroblasts treated with stiff and soft EVs change their gene expression profiles to adopt a cancer-associated fibroblast phenotype. These findings show that EV quantity, cargo, and function depend heavily on the mechanical properties of the extracellular microenvironment.

SIGNIFICANCE

Here we show that the quantity, cargo, and function of breast cancer-derived EVs vary with mechanical properties of the extracellular microenvironment.

Atomic force microscopy in disease-related studies: Exploring tissue and cell mechanics

Despite significant progress in human medicine, certain diseases remain challenging to promptly diagnose and treat. Hence, the imperative lies in the development of more exhaustive criteria and tools. Tissue and cellular mechanics exhibit distinctive traits in both normal and pathological states, suggesting that "force" represents a promising and distinctive target for disease diagnosis and treatment. Atomic force microscopy (AFM) holds great promise as a prospective clinical medical device due to its capability to concurrently assess surface morphology and mechanical characteristics of biological specimens within a physiological setting. This review presents a comprehensive examination of the operational principles of AFM and diverse mechanical models, focusing on its applications in investigating tissue and cellular mechanics associated with prevalent diseases. The findings from these studies lay a solid groundwork for potential clinical implementations of AFM. RESEARCH HIGHLIGHTS: By examining the surface morphology and assessing tissue and cellular mechanics of biological specimens in a physiological setting, AFM shows promise as a clinical device to diagnose and treat challenging diseases.

Small extracellular vesicles promote stiffness-mediated metastasis

Tissue stiffness is a critical prognostic factor in breast cancer and is associated with metastatic progression. Here we show an alternative and complementary hypothesis of tumor progression whereby physiological matrix stiffness affects the quantity and protein cargo of small EVs produced by cancer cells, which in turn drive their metastasis. Primary patient breast tissue produces significantly more EVs from stiff tumor tissue than soft tumor adjacent tissue. EVs released by cancer cells on matrices that model human breast tumors (25 kPa; stiff EVs) feature increased adhesion molecule presentation (ITGα 2 β 1 , ITGα 6 β 4 , ITGα 6 β 1 , CD44) compared to EVs from softer normal tissue (0.5 kPa; soft EVs), which facilitates their binding to extracellular matrix (ECM) protein collagen IV, and a 3-fold increase in homing ability to distant organs in mice. In a zebrafish xenograft model, stiff EVs aid cancer cell dissemination through enhanced chemotaxis. Moreover, normal, resident lung fibroblasts treated with stiff and soft EVs change their gene expression profiles to adopt a cancer associated fibroblast (CAF) phenotype. These findings show that EV quantity, cargo, and function depend heavily on the mechanical properties of the extracellular microenvironment.

Collagen fiber centerline tracking in fibrotic tissue via deep neural networks with variational autoencoder-based synthetic training data generation

The role of fibrillar collagen in the tissue microenvironment is critical in disease contexts ranging from cancers to chronic inflammations, as evidenced by many studies. Quantifying fibrillar collagen organization has become a powerful approach for characterizing the topology of collagen fibers and studying the role of collagen fibers in disease progression. We present a deep learning-based pipeline to quantify collagen fibers' topological properties in microscopy-based collagen images from pathological tissue samples. Our method leverages deep neural networks to extract collagen fiber centerlines and deep generative models to create synthetic training data, addressing the current shortage of large-scale annotations. As a part of this effort, we have created and annotated a collagen fiber centerline dataset, with the hope of facilitating further research in this field. Quantitative measurements such as fiber orientation, alignment, density, and length can be derived based on the centerline extraction results. Our pipeline comprises three stages. Initially, a variational autoencoder is trained to generate synthetic centerlines possessing controllable topological properties. Subsequently, a conditional generative adversarial network synthesizes realistic collagen fiber images from the synthetic centerlines, yielding a synthetic training set of image-centerline pairs. Finally, we train a collagen fiber centerline extraction network using both the original and synthetic data. Evaluation using collagen fiber images from pancreas, liver, and breast cancer samples collected via second-harmonic generation microscopy demonstrates our pipeline's superiority over several popular fiber centerline extraction tools. Incorporating synthetic data into training further enhances the network's generalizability. Our code is available at https://github.com/uw-loci/collagen-fiber-metrics.

Mechano-induced homotypic patterned domain formation by monocytes

Matrix stiffness and corresponding mechano-signaling play indispensable roles in cellular phenotypes and functions. How tissue stiffness influences the behavior of monocytes, a major circulating leukocyte of the innate system, and how it may promote the emergence of collective cell behavior is less understood. Here, using tunable collagen-coated hydrogels of physiological stiffness, we show that human primary monocytes undergo a dynamic local phase separation to form highly regular, reversible, multicellular, multi-layered domains on soft matrix. Local activation of the β2 integrin initiates inter-cellular adhesion, while global soluble inhibitory factors maintain the steady state domain pattern over days. Patterned domain formation generated by monocytes is unique among other key immune cells, including macrophages, B cells, T cells, and NK cells. While inhibiting their phagocytic capability, domain formation promotes monocytes' survival. We develop a computational model based on the Cahn-Hilliard equation of phase separation, combined with a Turing mechanism of local activation and global inhibition suggested by our experiments, and provides experimentally validated predictions of the role of seeding density and both chemotactic and random cell migration on domain pattern formation. This work reveals that, unlike active matters, cells can generate complex cell phases by exploiting their mechanosensing abilities and combined short-range interactions and long-range signals to enhance their survival.

Mechano-induced homotypic patterned domain formation by monocytes

Matrix stiffness and corresponding mechano-signaling play indispensable roles in cellular phenotypes and functions. How tissue stiffness influences the behavior of monocytes, a major circulating leukocyte of the innate system, and how it may promote the emergence of collective cell behavior is less understood. Here, using tunable collagen-coated hydrogels of physiological stiffness, we show that human primary monocytes undergo a dynamic local phase separation to form highly patterned multicellular multi-layered domains on soft matrix. Local activation of the β2 integrin initiates inter-cellular adhesion, while global soluble inhibitory factors maintain the steady-state domain pattern over days. Patterned domain formation generated by monocytes is unique among other key immune cells, including macrophages, B cells, T cells, and NK cells. While inhibiting their phagocytic capability, domain formation promotes monocytes' survival. We develop a computational model based on the Cahn-Hilliard equation, which includes combined local activation and global inhibition mechanisms of intercellular adhesion suggested by our experiments, and provides experimentally validated predictions of the role of seeding density and both chemotactic and random cell migration on pattern formation.

Precision-engineered biomimetics: the human fallopian tube

The fallopian tube has an essential role in several physiological and pathological processes from pregnancy to ovarian cancer. However, there are no biologically relevant models to study its pathophysiology. The state-of-the-art organoid model has been compared to two-dimensional tissue sections and molecularly assessed providing only cursory analyses of the model's accuracy. We developed a novel multi-compartment organoid model of the human fallopian tube that was meticulously tuned to reflect the compartmentalization and heterogeneity of the tissue's composition. We validated this organoid's molecular expression patterns, cilia-driven transport function, and structural accuracy through a highly iterative platform wherein organoids are compared to a three-dimensional, single-cell resolution reference map of a healthy, transplantation-quality human fallopian tube. This organoid model was precision-engineered to match the human microanatomy.

One sentence summary

Tunable organoid modeling and CODA architectural quantification in tandem help design a tissue-validated organoid model.

A hybrid breast cancer classification algorithm based on meta-learning and artificial neural networks

The incidence of breast cancer in women has surpassed that of lung cancer as the world’s leading new cancer case. Regular screening and measures become an effective way to prevent breast cancer and also provide a good foundation for later treatment. Women should receive regular checkups in the hospital after reaching a certain age. The use of computer-aided technology can improve the accuracy and efficiency of physicians’ decision-making. Data pre-processing is required before data analysis, and 16 features are selected using a correlation-based feature selection method. In this paper, meta-learning and Artificial Neural Networks (ANN) are combined to create a hybrid algorithm. The proposed hybrid algorithm for predicting breast cancer was attempted to achieve 98.74% accuracy and 98.02% F1-score by creating a combination of various meta-learning models whose output was used as input features for creating ANN models. Therefore, the hybrid algorithm proposed in this paper can obtain better prediction results than a single model.

Extracellular matrix mechanobiology in cancer cell migration

The extracellular matrix (ECM) is pivotal in modulating tumor progression. Besides chemically stimulating tumor cells, it also offers physical support that orchestrates the sequence of events in the metastatic cascade upon dynamically modulating cell mechanosensation. Understanding this translation between matrix biophysical cues and intracellular signaling has led to rapid growth in the interdisciplinary field of cancer mechanobiology in the last decade. Substantial efforts have been made to develop novel in vitro tumor mimicking platforms to visualize and quantify the mechanical forces within the tissue that dictate tumor cell invasion and metastatic growth. This review highlights recent findings on tumor matrix biophysical cues such as fibrillar arrangement, crosslinking density, confinement, rigidity, topography, and non-linear mechanics and their implications on tumor cell behavior. We also emphasize how perturbations in these cues alter cellular mechanisms of mechanotransduction, consequently enhancing malignancy. Finally, we elucidate engineering techniques to individually emulate the mechanical properties of tumors that could help serve as toolkits for developing and testing ECM-targeted therapeutics on novel bioengineered tumor platforms. STATEMENT OF SIGNIFICANCE: Disrupted ECM mechanics is a driving force for transitioning incipient cells to life-threatening malignant variants. Understanding these ECM changes can be crucial as they may aid in developing several efficacious drugs that not only focus on inducing cytotoxic effects but also target specific matrix mechanical cues that support and enhance tumor invasiveness. Designing and implementing an optimal tumor mimic can allow us to predictively map biophysical cue-modulated cell behaviors and facilitate the design of improved lab-grown tumor models with accurately controlled structural features. This review focuses on the abnormal changes within the ECM during tumorigenesis and its implications on tumor cell-matrix mechanoreciprocity. Additionally, it accentuates engineering approaches to produce ECM features of varying levels of complexity which is critical for improving the efficiency of current engineered tumor tissue models.