Fractal analysis of nuclear histology integrates tumor and stromal features into a single prognostic factor of the oral cancer microenvironment

Computational methods and biomarker discovery strategies for spatial proteomics: a review in immuno-oncology

Advancements in imaging technologies have revolutionized our ability to deeply profile pathological tissue architectures, generating large volumes of imaging data with unparalleled spatial resolution. This type of data collection, namely, spatial proteomics, offers invaluable insights into various human diseases. Simultaneously, computational algorithms have evolved to manage the increasing dimensionality of spatial proteomics inherent in this progress. Numerous imaging-based computational frameworks, such as computational pathology, have been proposed for research and clinical applications. However, the development of these fields demands diverse domain expertise, creating barriers to their integration and further application. This review seeks to bridge this divide by presenting a comprehensive guideline. We consolidate prevailing computational methods and outline a roadmap from image processing to data-driven, statistics-informed biomarker discovery. Additionally, we explore future perspectives as the field moves toward interfacing with other quantitative domains, holding significant promise for precision care in immuno-oncology.

Cyto R-CNN and CytoNuke Dataset: Towards reliable whole-cell segmentation in bright-field histological images

BACKGROUND AND OBJECTIVE

Cell segmentation in bright-field histological slides is a crucial topic in medical image analysis. Having access to accurate segmentation allows researchers to examine the relationship between cellular morphology and clinical observations. Unfortunately, most segmentation methods known today are limited to nuclei and cannot segment the cytoplasm.

METHODS

We present a new network architecture Cyto R-CNN that is able to accurately segment whole cells (with both the nucleus and the cytoplasm) in bright-field images. We also present a new dataset CytoNuke, consisting of multiple thousand manual annotations of head and neck squamous cell carcinoma cells. Utilizing this dataset, we compared the performance of Cyto R-CNN to other popular cell segmentation algorithms, including QuPath's built-in algorithm, StarDist, Cellpose and a multi-scale Attention Deeplabv3+. To evaluate segmentation performance, we calculated AP50, AP75 and measured 17 morphological and staining-related features for all detected cells. We compared these measurements to the gold standard of manual segmentation using the Kolmogorov-Smirnov test.

RESULTS

Cyto R-CNN achieved an AP50 of 58.65% and an AP75 of 11.56% in whole-cell segmentation, outperforming all other methods (QuPath 19.46/0.91%; StarDist 45.33/2.32%; Cellpose 31.85/5.61%, Deeplabv3+ 3.97/1.01%). Cell features derived from Cyto R-CNN showed the best agreement to the gold standard (D¯=0.15) outperforming QuPath (D¯=0.22), StarDist (D¯=0.25), Cellpose (D¯=0.23) and Deeplabv3+ (D¯=0.33).

CONCLUSION

Our newly proposed Cyto R-CNN architecture outperforms current algorithms in whole-cell segmentation while providing more reliable cell measurements than any other model. This could improve digital pathology workflows, potentially leading to improved diagnosis. Moreover, our published dataset can be used to develop further models in the future.

Spatial analyses of immune cell infiltration in cancer: current methods and future directions: A report of the International Immuno-Oncology Biomarker Working Group on Breast Cancer

Modern histologic imaging platforms coupled with machine learning methods have provided new opportunities to map the spatial distribution of immune cells in the tumor microenvironment. However, there exists no standardized method for describing or analyzing spatial immune cell data, and most reported spatial analyses are rudimentary. In this review, we provide an overview of two approaches for reporting and analyzing spatial data (raster versus vector-based). We then provide a compendium of spatial immune cell metrics that have been reported in the literature, summarizing prognostic associations in the context of a variety of cancers. We conclude by discussing two well-described clinical biomarkers, the breast cancer stromal tumor infiltrating lymphocytes score and the colon cancer Immunoscore, and describe investigative opportunities to improve clinical utility of these spatial biomarkers. © 2023 The Pathological Society of Great Britain and Ireland.

Perspective of nuclear fractal dimension in diagnosis and prognosis of oral squamous cell carcinoma

Background:

Owing to the restricted predictive value of conventional prognostic factors and the inconsistent treatment strategies, several oral squamous cell carcinoma (OSCC) patients are still over-treated or under-treated. In recent years, computer-assisted nuclear fractal dimension (nFD) has emerged as an objective approach to predict the outcome of OSCC.

Objective:

This study is an attempt to find out the differences in nFD values of epithelial cells of normal tissue, fibroepithelial hyperplasia, verrucous carcinoma, and OSCC. Further effort to evaluate the predictive potential of nFD of tumor cells for cervical lymph node metastasis (cLNM) was also assessed.

Methodology:

Formalin-fixed paraffin-embedded blocks of OSCC tissues of patients treated with neck dissection were collected. Photomicrographs of H-&E-stained sections were subjected to the image analysis by ImageJ and Python programming to calculate nFD. The association of categorical variables with nFD was studied using cross-tabulation procedure and the Fisher exact test. Receiver operating curve analysis was performed to find out cutoff value of nFD. A logistic regression model was developed to test the individual and combined predictive potential of grading and nFD for cLNM.

Results:

A significant difference between the mean nFD of healthy cells and malignant epithelial cells was observed (P = 0.01). nFD was not found to be an independent predictor of cLNM, although nFD and grading together demonstrated significant predictive potential (P = 0.004).

Conclusion:

nFD combined with grading can predict lymph node metastasis in OSCC. To the best of our knowledge, this is the first study of its kind.

Spatial distribution of B cells and lymphocyte clusters as a predictor of triple-negative breast cancer outcome

While tumor infiltration by CD8+ T cells is now widely accepted to predict outcomes, the clinical significance of intratumoral B cells is less clear. We hypothesized that spatial distribution rather than density of B cells within tumors may provide prognostic significance. We developed statistical techniques (fractal dimension differences and a box-counting method 'occupancy') to analyze the spatial distribution of tumor-infiltrating lymphocytes (TILs) in human triple-negative breast cancer (TNBC). Our results indicate that B cells in good outcome tumors (no recurrence within 5 years) are spatially dispersed, while B cells in poor outcome tumors (recurrence within 3 years) are more confined. While most TILs are located within the stroma, increased numbers of spatially dispersed lymphocytes within cancer cell islands are associated with a good prognosis. B cells and T cells often form lymphocyte clusters (LCs) identified via density-based clustering. LCs consist either of T cells only or heterotypic mixtures of B and T cells. Pure B cell LCs were negligible in number. Compared to tertiary lymphoid structures (TLS), LCs have fewer lymphocytes at lower densities. Both types of LCs are more abundant and more spatially dispersed in good outcomes compared to poor outcome tumors. Heterotypic LCs in good outcome tumors are smaller and more numerous compared to poor outcome. Heterotypic LCs are also closer to cancer islands in a good outcome, with LC size decreasing as they get closer to cancer cell islands. These results illuminate the significance of the spatial distribution of B cells and LCs within tumors.

Physics approaches to the spatial distribution of immune cells in tumors

The goal of immunotherapy is to mobilize the immune system to kill cancer cells. Immunotherapy is more effective and, in general, the prognosis is better, when more immune cells infiltrate the tumor. We explore the question of whether the spatial distribution rather than just the density of immune cells in the tumor is important in forecasting whether cancer recurs. After reviewing previous work on this issue, we introduce a novel application of maximum entropy to quantify the spatial distribution of discrete point-like objects. We apply our approach to B and T cells in images of tumor tissue taken from triple negative breast cancer patients. We find that the immune cells are more spatially dispersed in good clinical outcome (no recurrence of cancer within at least 5 years of diagnosis) compared to poor clinical outcome (recurrence within 3 years of diagnosis). Our results highlight the importance of spatial distribution of immune cells within tumors with regard to clinical outcome, and raise new questions on their role in cancer recurrence.

Feature-driven local cell graph (FLocK): New computational pathology-based descriptors for prognosis of lung cancer and HPV status of oropharyngeal cancers

Local spatial arrangement of nuclei in histopathology images of different cancer subtypes has been shown to have prognostic value. In order to capture localized nuclear architectural information, local cell cluster graph-based measurements have been proposed. However, conventional ways of cell graph construction only utilize nuclear spatial proximity, and do not differentiate between different cell types while constructing the graph. In this paper, we present feature-driven local cell cluster graph (FLocK), a new approach to constructing local cell graphs by simultaneously considering spatial proximity and attributes of the individual nuclei (e.g. shape, size, texture). In addition, we have designed a new set of quantitative graph-derived metrics to be extracted from FLocKs, in turn capturing the interplay between different proximally located clusters of nuclei. We have evaluated the efficacy of FLocK features extracted from H&E stained tissue images in two clinical applications: to classify short-term vs. long-term survival among patients of early stage non-small cell lung cancer (ES-NSCLC), and also to predict human papillomavirus (HPV) status of oropharyngeal squamous cell carcinoma (OP-SCCs). In the classification of long-term vs. short-term survival among patients of ES-NSCLC (training cohort, n = 434), the top 10 discriminative FLocK features related to the variation of FLocK size and intersected FLocK distance were identified, via Minimum Redundancy and Maximum Relevance (MRMR) selection, in 100 runs of 10-fold cross-validation, and in conjunction with a linear discriminant classifier yielded a mean AUC of 0.68 for predicting survival in the training cohort. This is better than other state-of-art histomorphometric and deep learning classifiers (cell cluster graphs (AUC = 0.62), global cell graph (AUC = 0.56), nuclear shape (AUC = 0.54), nuclear orientation (AUC = 0.61), AlexNet (AUC = 0.55), ResNet (AUC = 0.56)). The FLocK-based classifier yielded an AUC of 0.70 in an independent testing cohort (n = 150). The patients identified as "high-risk" had significantly poorer overall survival in the testing cohort, with a hazard ratio (95% confidence interval) of 2.24 (1.24-4.05), p = 0.01144). In the classification of HPV status of OP-SCC, the top three FLocK features pertaining to the portion of intersected FLocKs were used to construct a classifier, which yielded an AUC of 0.80 in the training cohort (n = 50), and an accuracy of 0.78 in an independent testing cohort (n = 35). The combination of FLocK measurements with cell cluster graphs, nuclear orientation, and nuclear shape improved the training AUC to 0.87, 0.91 and 0.85, respectively. Deep learning approaches yielded marginally better performance than the FLocK-based classifier in this application, with AUC = 0.78 for AlexNet, AUC = 0.81 for ResNet, and AUC = 0.76 for FLocK-based classifier in the testing cohort. However, the combination of two hand-crafted features: FLocK and nuclear orientation yielded a better performance (AUC = 0.84). FLocK provides a unique and quantitative way to analyze histology images of solid tumors and interrogate tumor morphology from a different aspect than existing histomorphometrics. The source code can be accessed at https://github.com/hacylu/FLocK.

Reimagining T Staging Through Artificial Intelligence and Machine Learning Image Processing Approaches in Digital Pathology

Tumor stage and grade, visually assessed by pathologists from evaluation of pathology images in conjunction with radiographic imaging techniques, have been linked to outcome, progression, and survival for a number of cancers. The gold standard of staging in oncology has been the TNM (tumor-node-metastasis) staging system. Though histopathological grading has shown prognostic significance, it is subjective and limited by interobserver variability even among experienced surgical pathologists. Recently, artificial intelligence (AI) approaches have been applied to pathology images toward diagnostic-, prognostic-, and treatment prediction-related tasks in cancer. AI approaches have the potential to overcome the limitations of conventional TNM staging and tumor grading approaches, providing a direct prognostic prediction of disease outcome independent of tumor stage and grade. Broadly speaking, these AI approaches involve extracting patterns from images that are then compared against previously defined disease signatures. These patterns are typically categorized as either (1) handcrafted, which involve domain-inspired attributes, such as nuclear shape, or (2) deep learning (DL)-based representations, which tend to be more abstract. DL approaches have particularly gained considerable popularity because of the minimal domain knowledge needed for training, mostly only requiring annotated examples corresponding to the categories of interest. In this article, we discuss AI approaches for digital pathology, especially as they relate to disease prognosis, prediction of genomic and molecular alterations in the tumor, and prediction of treatment response in oncology. We also discuss some of the potential challenges with validation, interpretability, and reimbursement that must be addressed before widespread clinical deployment. The article concludes with a brief discussion of potential future opportunities in the field of AI for digital pathology and oncology.

Occupancy and Fractal Dimension Analyses of the Spatial Distribution of Cytotoxic (CD8+) T Cells Infiltrating the Tumor Microenvironment in Triple Negative Breast Cancer

Favorable outcomes have been associated with high densities of tumor infiltrating lymphocytes (TILs) such as cytotoxic ([Formula: see text]) T cells. However, the clinical significance of the spatial distribution of TILs is less well understood. We have developed novel statistical techniques to characterize the spatial distribution of TILs at various length scales. These include a box counting method that we call “occupancy” and novel applications of fractal dimensions. We apply these techniques to the spatial distribution of [Formula: see text] T cells in the tumor microenvironment of tissue resected from 35 triple negative breast cancer patients. We find that there is a distinct difference in the spatial distribution of [Formula: see text] T cells between good clinical outcome (no recurrence within at least 5 years of diagnosis) and poor clinical outcome (recurrence within 3 years of diagnosis). The statistical significance of the difference between good and poor outcome in the occupancy, fractal dimension (FD), and FD difference of [Formula: see text] T cells is comparable to that of the [Formula: see text] T cell density. Even when we randomly exclude some of the cells so that the images have the same cell density, we still find that the fractal dimension at short length scales is correlated with cancer recurrence, implying that the actual spatial distribution of [Formula: see text] cells, and not just the [Formula: see text] cell density, is associated with clinical outcome. The occupancy and FD difference indicate that the [Formula: see text] T cells are more spatially dispersed in good outcome and more aggregated in poor outcome. We discuss possible interpretations.

Small Cell Lung Cancer Therapeutic Responses Through Fractal Measurements: From Radiology to Mitochondrial Biology

Small cell lung cancer (SCLC) is an aggressive neuroendocrine disease with an overall 5 year survival rate of ~7%. Although patients tend to respond initially to therapy, therapy-resistant disease inevitably emerges. Unfortunately, there are no validated biomarkers for early-stage SCLC to aid in early detection. Here, we used readouts of lesion image characteristics and cancer morphology that were based on fractal geometry, namely fractal dimension (FD) and lacunarity (LC), as novel biomarkers for SCLC. Scanned tumors of patients before treatment had a high FD and a low LC compared to post treatment, and this effect was reversed after treatment, suggesting that these measurements reflect the initial conditions of the tumor, its growth rate, and the condition of the lung. Fractal analysis of mitochondrial morphology showed that cisplatin-treated cells showed a discernibly decreased LC and an increased FD, as compared with control. However, treatment with mdivi-1, the small molecule that attenuates mitochondrial division, was associated with an increase in FD as compared with control. These data correlated well with the altered metabolic functions of the mitochondria in the diseased state, suggesting that morphological changes in the mitochondria predicate the tumor’s future ability for mitogenesis and motogenesis, which was also observed on the CT scan images. Taken together, FD and LC present ideal tools to differentiate normal tissue from malignant SCLC tissue as a potential diagnostic biomarker for SCLC.

Nuclear shape and orientation features from H&E images predict survival in early-stage estrogen receptor-positive breast cancers

Early-stage estrogen receptor-positive (ER+) breast cancer (BCa) is the most common type of BCa in the United States. One critical question with these tumors is identifying which patients will receive added benefit from adjuvant chemotherapy. Nuclear pleomorphism (variance in nuclear shape and morphology) is an important constituent of breast grading schemes, and in ER+ cases, the grade is highly correlated with disease outcome. This study aimed to investigate whether quantitative computer-extracted image features of nuclear shape and orientation on digitized images of hematoxylin-stained and eosin-stained tissue of lymph node-negative (LN-), ER+ BCa could help stratify patients into discrete (<10 years short-term vs. >10 years long-term survival) outcome groups independent of standard clinical and pathological parameters. We considered a tissue microarray (TMA) cohort of 276 ER+, LN- patients comprising 150 patients with long-term and 126 patients with short-term overall survival, wherein 177 randomly chosen cases formed the modeling set, and 99 remaining cases the test set. Segmentation of individual nuclei was performed using multiresolution watershed; subsequently, 615 features relating to nuclear shape/texture and orientation disorder were extracted from each TMA spot. The Wilcoxon's rank-sum test identified the 15 most prognostic quantitative histomorphometric features within the modeling set. These features were then subsequently combined via a linear discriminant analysis classifier and evaluated on the test set to assign a probability of long-term vs. short-term disease-specific survival. In univariate survival analysis, patients identified by the image classifier as high risk had significantly poorer survival outcome: hazard ratio (95% confident interval) = 2.91(1.23-6.92), p = 0.02786. Multivariate analysis controlling for T-stage, histology grade, and nuclear grade showed the classifier to be independently predictive of poorer survival: hazard ratio (95% confident interval) = 3.17(0.33-30.46), p = 0.01039. Our results suggest that quantitative histomorphometric features of nuclear shape and orientation are strongly and independently predictive of patient survival in ER+, LN- BCa.

Is oculofacial surgery complex … or merely complicated?

PURPOSE OF REVIEW

There is confusion in all of healthcare, including oculofacial surgery, as to what is 'complex' and what is 'merely complicated'. Although in common usage, these terms tend to be interchangeable, the distinction is more than trivial. A different and somewhat unfamiliar toolset is needed to successfully navigate complex problems. This review will explore a methodology for the physician to understand what is complex in oculofacial surgery, the tools needed to optimize performance in a complex healthcare system and successfully manage patients with complex diseases.

RECENT FINDINGS

A specific understanding of complexity science in oculofacial surgery is only in its nascent beginnings at this point. Nevertheless, recent advances in closely related fields can provide concrete applications. The practice of oculofacial surgery is optimized within a healthcare network of supporting professionals. Moreover, a newer understanding of the 'complex' nature of disease common to oculofacial surgery, such as neoplasia and inflammation, will direct the physician to recognize the most appropriate therapies.

SUMMARY

Oculofacial surgery, like all of medicine, is a fluid mixture of problems that are complex and those that are merely complicated. As a different toolset is needed to deal with each, physicians need to recognize these differences and acquire those tools.

An oral cavity squamous cell carcinoma quantitative histomorphometric-based image classifier of nuclear morphology can risk stratify patients for disease-specific survival

Oral cavity squamous cell carcinoma is the most common type of head and neck carcinoma. Its incidence is increasing worldwide, and it is associated with major morbidity and mortality. It is often unclear which patients have aggressive, treatment refractory tumors vs those whose tumors will be more responsive to treatment. Better identification of patients with high- vs low-risk cancers could help provide more tailored treatment approaches and could improve survival rates while decreasing treatment-related morbidity. This study investigates computer-extracted image features of nuclear shape and texture on digitized images of H&E-stained tissue sections for risk stratification of oral cavity squamous cell carcinoma patients compared with standard clinical and pathologic parameters. With a tissue microarray cohort of 115 retrospectively identified oral cavity squamous cell carcinoma patients, 50 were randomly chosen as the modeling set, and the remaining 65 constituted the test set. Following nuclear segmentation and feature extraction, the Wilcoxon rank sum test was used to identify the five most prognostic quantitative histomorphometric features from the modeling set. These top ranked features were then combined via a machine learning classifier to construct the oral cavity histomorphometric-based image classifier (OHbIC). The classifier was then validated for its ability to risk stratify patients for disease-specific outcomes on the test set. On the test set, the classifier yielded an area under the receiver operating characteristic curve of 0.72 in distinguishing disease-specific outcomes. In univariate survival analysis, high-risk patients predicted by the classifier had significantly poorer disease-specific survival (P=0.0335). In multivariate analysis controlling for T/N-stage, resection margins, and smoking status, positive classifier results were independently predictive of poorer disease-specific survival: hazard ratio (95% confidence interval)=11.023 (2.62-46.38) and P=0.001. Our results suggest that quantitative histomorphometric features of local nuclear architecture derived from digitized H&E slides of oral cavity squamous cell carcinomas are independently predictive of patient survival.

Spatial Heterogeneity in the Tumor Microenvironment

Recent developments in studies of tumor heterogeneity have provoked new thoughts on cancer management. There is a desperate need to understand influence of the tumor microenvironment on cancer development and evolution. Applying principles and quantitative methods from ecology can suggest novel solutions to fulfil this need. We discuss spatial heterogeneity as a fundamental biological feature of the microenvironment, which has been largely ignored. Histological samples can provide spatial context of diverse cell types coexisting within the microenvironment. Advanced computer-vision techniques have been developed for spatial mapping of cells in histological samples. This has enabled the applications of experimental and analytical tools from ecology to cancer research, generating system-level knowledge of microenvironmental spatial heterogeneity. We focus on studies of immune infiltrate and tumor resource distribution, and highlight statistical approaches for addressing the emerging challenges based on these new approaches.