Nuclear Morphological Features Research Articles

Multiscale Optical Imaging Fusion for Cervical Precancer Diagnosis: Integrating Widefield Colposcopy and High-Resolution Endomicroscopy.

Early detection and treatment of cervical precancers can prevent disease progression. However, in low-resource communities with a high incidence of cervical cancer, high equipment costs and a shortage of specialists hinder preventative strategies. This manuscript presents a low-cost multiscale in vivo optical imaging system coupled with a computer-aided diagnostic system that could enable accurate, real-time diagnosis of high-grade cervical precancers. The system combines portable colposcopy and high-resolution endomicroscopy (HRME) to acquire spatially registered widefield and microscopy videos. A multiscale imaging fusion network (MSFN) was developed to identify cervical intraepithelial neoplasia grade 2 or more severe (CIN 2+). The MSFN automatically identifies and segments the ectocervix and lesions from colposcopy images, extracts nuclear morphology features from HRME videos, and integrates the colposcopy and HRME information. With a threshold value set to achieve sensitivity equal to clinical impression (0.98 [p = 1.0]), the MSFN achieved a significantly higher specificity than clinical impression (0.75 vs. 0.43, p = 0.000006). Our findings show that multiscale optical imaging of the cervix allows the highly sensitive and specific detection of high-grade precancers. The multiscale imaging system and MSFN could facilitate the accurate, real-time diagnosis of cervical precancers in low-resource settings.

Deep Residual Learning-Based Classification with Identification of Incorrect Predictions and Quantification of Cellularity and Nuclear Morphological Features in Digital Pathological Images of Common Astrocytic Tumors.

Interobserver variations in the pathology of common astrocytic tumors impact diagnosis and subsequent treatment decisions. This study leveraged a residual neural network-50 (ResNet-50) in digital pathological images of diffuse astrocytoma, anaplastic astrocytoma, and glioblastoma to recognize characteristic pathological features and perform classification at the patch and case levels with identification of incorrect predictions. In addition, cellularity and nuclear morphological features, including axis ratio, circularity, entropy, area, irregularity, and perimeter, were quantified via a hybrid task cascade (HTC) framework and compared between different characteristic pathological features with importance weighting. A total of 95 cases, including 15 cases of diffuse astrocytoma, 11 cases of anaplastic astrocytoma, and 69 cases of glioblastoma, were collected in Taiwan Hualien Tzu Chi Hospital from January 2000 to December 2021. The results revealed that an optimized ResNet-50 model could recognize characteristic pathological features at the patch level and assist in diagnosis at the case level with accuracies of 0.916 and 0.846, respectively. Incorrect predictions were mainly due to indistinguishable morphologic overlap between anaplastic astrocytoma and glioblastoma tumor cell area, zones of scant vascular lumen with compact endothelial cells in the glioblastoma microvascular proliferation area mimicking the glioblastoma tumor cell area, and certain regions in diffuse astrocytoma with too low cellularity being misrecognized as the glioblastoma necrosis area. Significant differences were observed in cellularity and each nuclear morphological feature among different characteristic pathological features. Furthermore, using the extreme gradient boosting (XGBoost) algorithm, we found that entropy was the most important feature for classification, followed by cellularity, area, circularity, axis ratio, perimeter, and irregularity. Identifying incorrect predictions provided valuable feedback to machine learning design to further enhance accuracy and reduce errors in classification. Moreover, quantifying cellularity and nuclear morphological features with importance weighting provided the basis for developing an innovative scoring system to achieve objective classification and precision diagnosis among common astrocytic tumors.

Significance of Combined Immuno-histochemical Expression of P63 & CD56 in Papillary and Follicular Thyroid Carcinoma

Background: Thyroid neoplasm is the commonest endocrine neoplasm. More than 80% of thyroid malignancies are papillary thyroid carcinoma (PTC) followed by follicular carcinoma (FC). The diagnosis of papillary thyroid carcinoma is based on characteristic nuclear morphology of a thyroid neoplasm. In contrast, follicular variant of PTC may cause, if the nuclear features of PTC are insufficiently appreciated, severe problems in differentiating from follicular thyroid carcinoma. Several immunohistochemical (IHC) markers such as P63 and CD56 have been recommended to differentiate between this two thyroid malignancies with overlapping histomorphology. Objectives: Our aim was to identify the possible diagnostic role of P63 and CD56 immunoexpression that distinguish PTC, including the follicular variant from follicular thyroid carcinoma. Methods: This cross-sectional descriptive study was conducted in the Department of Pathology, Rajshahi Medical College from March 2020 to February 2022. A total of 44 cases, histologically confirmed as papillary and follicular thyroid carcinoma were included in the study. Immunohistochemistry was done for P63 and CD56 from selected paraffin blocks. Results: Histologically, 39 cases were diagnosed as papillary thyroid carcinoma (27 were classical PTC & 12 were FVPTC) and the rest 5 were follicular thyroid carcinoma. In this study, mean age of the patients was 40.86 ± 6.57 years (SD) and male to female ratio was 1:2.4. P63 showed 74.4% positivity with papillary thyroid carcinoma. Positive immunoreactivity of P63 was highly significant in distinguishing papillary from follicular thyroid carcinoma (P=0.003). Combined P63 positive CD56 negative (P=0.048) and P63 negative CD56 negative immunoexpression (P=0.039) were statistically significant in differentiating papillary from follicular thyroid carcinoma. Conclusion: This study suggested that the use of P63 and CD56 may be helpful in the diagnosis of papillary and follicular thyroid carcinoma along with histopathological examination and their combination may also help in this purpose.

Automatic analysis of nuclear features reveals a non-tumoral predictor of tumor grade in bladder cancer

Background & objectivesTumor grade determines prognosis in urothelial carcinoma. The classification of low and high grade is based on nuclear morphological features that include nuclear size, hyperchromasia and pleomorphism. These features are subjectively assessed by the pathologists and are not numerically measured, which leads to high rates of interobserver variability. The purpose of this study is to assess the value of a computer-based image analysis tool for identifying predictors of tumor grade in bladder cancer.MethodsFour hundred images of urothelial tumors were graded by five pathologists and two expert genitourinary pathologists using a scale of 1 (lowest grade) to 5 (highest grade). A computer algorithm was used to automatically segment the nuclei and to provide morphometric parameters for each nucleus, which were used to establish the grading algorithm. Grading algorithm was compared to pathologists’ agreement.ResultsComparison of the grading scores of the five pathologists with the expert genitourinary pathologists score showed agreement rates between 88.5% and 97.5%.The agreement rate between the two expert genitourinary pathologists was 99.5%. The quantified algorithm based conventional parameters that determine the grade (nuclear size, pleomorphism and hyperchromasia) showed > 85% agreement with the expert genitourinary pathologists. Surprisingly, the parameter that was most associated with tumor grade was the 10th percentile of the nuclear area, and high grade was associated with lower 10th percentile nuclei, caused by the presence of more inflammatory cells in the high-grade tumors.ConclusionQuantitative nuclear features could be applied to determine urothelial carcinoma grade and explore new biologically explainable parameters with better correlation to grade than those currently used.

Focal adhesion and actin orientation regulated by cellular geometry determine stem cell differentiation via mechanotransduction

Tuning cell adhesion geometry can affect cytoskeleton organization and the distribution of cytoskeleton forces, which play critical roles in controlling cell functions. To elucidate the geometrical relationship with cytoskeleton force distribution, it is necessary to control cell morphology. In this study, a series of dextral vortex micropatterns were prepared to precisely control cell morphology for investigating the influence of the curvature degree of adhesion curves on intracellular force distribution and stem cell differentiation at a sub-cellular level. Peripherial actin filaments of micropatterned cells were assembled along the adhesion curves and showed different orientations, filament thicknesses and densities. Focal adhesion and cytoskeleton force distribution were dependent on the curvature degree. Intracellular force distribution was also regulated by adhesion curves. The cytoskeleton and force distribution affected the osteogenic differentiation of mesenchymal stem cells through a YAP/TAZ-mediated mechanotransduction process. Thus, regulation of cell adhesion curvature, especially at cytoskeletal filament level, is critical for cell function manipulation. Statement of significanceIn this study, a series of dextral micro-vortexes were prepared and used for the culture of human mesenchymal stem cells (hMSCs) to precisely control adhesive curvatures (0°, 30°, 60°, and 90°). The single MSCs on the micropatterns had the same size and shape but showed distinct focal adhesion (FA) and cytoskeleton orientations. Cellular nanomechanics were observed to be correlated with the curvature degrees, subsequently influencing nuclear morphological features. As a consequence, the localization of the mechanotransduction sensor and activator-YAP/TAZ was affected, influencing osteogenic differentiation. The results revealed the pivotal role of adhesive curvatures in the manipulation of stem cell differentiation via the machanotransduction process, which has rarely been investigated.

Synthesis and anti-tumor activities of three newly designed organotin(IV) carboxylates complexes

Three distinctive end group-containing organotin (IV) carboxylates complexes (YDCOOSn, CLCOOSn and BZCOOSn) were designed and synthesized. Together with theoretical calculations, a thorough examination was carried out to investigate the photophysical properties of these compounds. The cytotoxicity of the synthesized compounds was tested using normal cell line GES-1 and was assessed against four cancer cell lines (A549, Hela, H1299 and HepG2). The outcomes of the experiments demonstrated that these complexes had superior selectivity than cisplatin towards cancerous cells, particularly in the A549 cell line. BZCOOSn was selected as a candidate compound for additional research because it exhibited the lowest IC50 value and the most impressive inducing effect on cell death and G2/M phase arrest. Increased caspase-3 and -9 enzyme activity, a decline in mitochondrial membrane potential (MMP), characteristic nuclear apoptotic morphology, and an accumulation of intracellular reactive oxygen species (ROS) were seen in A549 exposed to BZCOOSn. These findings demonstrated that BZCOOSn exhibited strong cytotoxicity by triggering cell death in A549 via the mitochondrial route. Furthermore, using the scratch wound healing assay, it was discovered that BZCOOSn reduced the migration of A549 cancerous cells. These data all pointed to BZCOOSn as a possible candidate for more research and development as a chemotherapeutic drug.

Detection of senescence using machine learning algorithms based on nuclear features

Cellular senescence is a stress response with broad pathophysiological implications. Senotherapies can induce senescence to treat cancer or eliminate senescent cells to ameliorate ageing and age-related pathologies. However, the success of senotherapies is limited by the lack of reliable ways to identify senescence. Here, we use nuclear morphology features of senescent cells to devise machine-learning classifiers that accurately predict senescence induced by diverse stressors in different cell types and tissues. As a proof-of-principle, we use these senescence classifiers to characterise senolytics and to screen for drugs that selectively induce senescence in cancer cells but not normal cells. Moreover, a tissue senescence score served to assess the efficacy of senolytic drugs and identified senescence in mouse models of liver cancer initiation, ageing, and fibrosis, and in patients with fatty liver disease. Thus, senescence classifiers can help to detect pathophysiological senescence and to discover and validate potential senotherapies.

Application of artificial intelligence (AI) features of nuclear morphology from BLASST-1 (Bladder Cancer Signal Seeking Trial) of nivolumab, gemcitabine, and cisplatin in patients with MIBC undergoing cystectomy.

674 Background: BLASST-1 is a multi-center phase II trial evaluating neoadjuvant nivolumab (N) with gemcitabine-cisplatin (GC) for patients (pts) with MIBC undergoing radical cystectomy (RC) (NCT03294304). 41 pts with MIBC (cT2-T4a, N≤1, M0) were enrolled between Feb 2018 and June 2019; (cT2N0 90%, cT3N0 7%, cT4N1 3%). Pts received C (70mg/m2) IV on D1, G (1000mg/m2) on D1, D8, and N (360 mg) IV on D8 every 21 days for 4 cycles followed by RC within 8 wks. The primary endpoint was pathologic downstaging (PaR; ≤pT1N0). Safety, Relapse-free survival (RFS), Progression-free survival (PFS) and biomarker analyses were secondary endpoints. PaR rate was 65.8%, the pCR (≤pT is N0) rate was 49% and there were no safety concerns or delays to RC. Morphometric characteristics of the cell nucleus can be used to assess bladder cancer grading and gain insights into cellular functionalities. In this study, we sought to evaluate the ability of the AI model to identify non-responders to neoadjuvant chemo-immunotherapy. in the BLASST-1 cohort based on computerized image features of nuclear morphology and architecture on pre-treatment transurethral resection of bladder tumor (TURBT) tissues. Methods: Of the 41 pts, we had H&E images available for 34 pts, of which 23 had PaR and 11 did not have PaR and these were classified as responder (R) and non-responder (NR) groups. A machine learning model (U-net) was developed and invoked for tumor segmentation on the H&E images from the BLASST-1 cohort. A second machine learning model (HoVer-Net) was employed to segment and classify individual nuclei. A total of 408 features relating to the textural and spatial arrangement of individual cancer nuclei were extracted. The 17 most significant features, identified through the least absolute shrinkage and selection operator, were used to train a Cox regression model to predict the risk of death using 361 MIBC pts from the Cancer Genome Atlas (TCGA). This Cox model was then applied to assign a risk score to pts in BLASST-1, using a threshold learned from TCGA pts, the individual pts in BLASST-1 were assigned as either low-risk or high-risk. Results: The top identified prognostic features described the textural appearance of individual nuclei with more texture. This model accurately predicted PaR in BLASST-1, with an area under a receiver operating characteristic curve of 0.83. Overall, the pts with the same nuclear angle direction within the tumor tissue had a high chance of response to the neoadjuvant chemo-IO combination in the BLASST-1 trial. Conclusions: A computerized AI model relying on nuclear morphologic and architecture features demonstrated prognostic capability in MIBC within the TCGA dataset and predictive capability for the PaR in the BLASST-1 trial. These findings support further validation studies.

Single-cell morphological and topological atlas reveals the ecosystem diversity of human breast cancer

Digital pathology allows computerized analysis of tumor ecosystem using whole slide images (WSIs). Here, we present single-cell morphological and topological profiling (sc-MTOP) to characterize tumor ecosystem by extracting the features of nuclear morphology and intercellular spatial relationship for individual cells. We construct a single-cell atlas comprising 410 million cells from 637 breast cancer WSIs and dissect the phenotypic diversity within tumor, inflammatory and stroma cells respectively. Spatially-resolved analysis identifies recurrent micro-ecological modules representing locoregional multicellular structures and reveals four breast cancer ecotypes correlating with distinct molecular features and patient prognosis. Further analysis with multiomics data uncovers clinically relevant ecosystem features. High abundance of locally-aggregated inflammatory cells indicates immune-activated tumor microenvironment and favorable immunotherapy response in triple-negative breast cancers. Morphological intratumor heterogeneity of tumor nuclei correlates with cell cycle pathway activation and CDK inhibitors responsiveness in hormone receptor-positive cases. sc-MTOP enables using WSIs to characterize tumor ecosystems at the single-cell level.

Recurrence prediction in clear cell renal cell carcinoma using machine learning of quantitative nuclear features

The recurrence of non-metastatic renal cell carcinoma (RCC) may occur early or late after surgery. This study aimed to develop a recurrence prediction machine learning model based on quantitative nuclear morphologic features of clear cell RCC (ccRCC). We investigated 131 ccRCC patients who underwent nephrectomy (T1-3N0M0). Forty had recurrence within 5 years and 22 between 5 and 10 years; thirty-seven were recurrence-free during 5–10 years and 32 were for more than 10 years. We extracted nuclear features from regions of interest (ROIs) using a digital pathology technique and used them to train 5- and 10-year Support Vector Machine models for recurrence prediction. The models predicted recurrence at 5/10 years after surgery with accuracies of 86.4%/74.1% for each ROI and 100%/100% for each case, respectively. By combining the two models, the accuracy of the recurrence prediction within 5 years was 100%. However, recurrence between 5 and 10 years was correctly predicted for only 5 of the 12 test cases. The machine learning models showed good accuracy for recurrence prediction within 5 years after surgery and may be useful for the design of follow-up protocols and patient selection for adjuvant therapy.

Single-Cell, High-Content Microscopy Analysis of BK Polyomavirus Infection.

By adulthood, the majority of the population is persistently infected with BK polyomavirus (BKPyV). Only a subset of the population, generally transplant recipients on immunosuppressive drugs, will experience disease from BKPyV, but those who do have few treatment options and, frequently, poor outcomes, because to date there are no effective antivirals to treat or approved vaccines to prevent BKPyV. Most studies of BKPyV have been performed on bulk populations of cells, and the dynamics of infection at single-cell resolution have not been explored. As a result, much of our knowledge is based upon the assumption that all cells within a greater population are behaving the same way with respect to infection. The present study examines BKPyV infection on a single-cell level using high-content microscopy to measure and analyze the viral protein large T antigen (TAg), promyelocytic leukemia protein (PML), DNA, and nuclear morphological features. We observed significant heterogeneity among infected cells, within and across time points. We found that the levels of TAg within individual cells did not necessarily increase with time and that cells with the same TAg levels varied in other ways. Overall, high-content, single-cell microscopy is a novel approach to studying BKPyV that enables experimental insight into the heterogenous nature of the infection. IMPORTANCE BK polyomavirus (BKPyV) is a human pathogen that infects nearly everyone by adulthood and persists throughout a person's life. Only people with significant immune suppression develop disease from the virus, however. Until recently the only practical means of studying many viral infections was to infect a group of cells in the laboratory and measure the outcomes in that group. However, interpreting these bulk population experiments requires the assumption that infection influences all cells within a group similarly. This assumption has not held for multiple viruses tested so far. Our study establishes a novel single-cell microscopy assay for BKPyV infection. Using this assay, we discovered differences among individual infected cells that have not been apparent in bulk population studies. The knowledge gained in this study and the potential for future use demonstrate the power of this assay as a tool for understanding the biology of BKPyV.

MEF2B is the ideal immunohistochemical marker to highlight neoplastic LP cells in nodular lymphocyte-predominant Hodgkin lymphoma.

MEF2B is the ideal immunohistochemical marker to highlight neoplastic LP cells in nodular lymphocyte-predominant Hodgkin lymphoma.

Abstract 5815: Nucleus positioning and composition dictate the invasion performance of E-cadherin mutant cells

Abstract Introduction: Cell invasion is a critical step for tumor progression and dissemination into neighboring and distant tissues, which constitute the foremost cause of cancer mortality. Loss of the cell-cell adhesion molecule E-cadherin occurs in 70% of carcinomas and is widely described as an initiating event in the invasion process. Recently, data has emerged demonstrating that this milestone phenomenon is accompanied by an abnormal affair between cancer cells and the extracellular matrix (ECM). In fact, cancer cells display increased plasticity and a remarkable ability to overcome the fibrous structure of the ECM. Since the nucleus is the largest and stiffest organelle in the cell, we hypothesize that it represents a major determinant of cell reshaping and spreading capacity. Our main aim is thus to dissect the mechanisms through which the nucleus supports invasion of cancer cells. Material and Methods: To determine alterations in nuclear composition and architecture that are distinctive of cells with E-cadherin impairment, we have used cell lines and Drosophila strains expressing either wild-type E-cadherin or the Y755C variant identified in Hereditary Diffuse Gastric Cancer (HDGC) patients. Nuclear morphological features and migratory rates were assessed by fluorescent markers coupled with confocal microscopy and advanced bioimaging techniques. The molecular profile of nuclei envelope from E-cadherin mutant and wild-type cells was subsequently investigated by implementation of a proteomic workflow, encompassing cellular fractionation and processing through high-resolution Mass Spectrometry (LC-MS). Results: We have shown that the Y755C E-cadherin mutation induces evident changes in nuclear morphology, and an increased migration performance of border cells in Drosophila. In particular, detailed quantitative measurements revealed differences in nuclear area, mean intensity, perimeter, solidity and relative position to basal surface of E-cadherin mutant cells, when compared with those expressing the wild-type protein. Further, proteomic analysis of enriched nuclear fractions disclosed that the composition of the nuclear envelope from E-cadherin mutant cells is significantly different from that of the wild-type counterparts. Differentially abundant molecules include proteins relevant for spatial and structural integrity of the nucleus. Conclusion: Overall, this work provides evidence that cells with E-cadherin loss of function activate a specific mechanotransduction program that imposes nuclear remodeling at physical and biochemical levels, endowing cells with a pro-invasive signature. Citation Format: Joana Figueiredo, Joana Pereira, Rui M. Ferreira, Luísa Carvalho, Margarida Gonçalves, Soraia Melo, Patrícia Carneiro, Parry Guilford, Eurico Morais-de-Sá, Raquel Seruca. Nucleus positioning and composition dictate the invasion performance of E-cadherin mutant cells [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5815.

Abstract P2-11-16: Computerized Measurements of Nuclear Morphology Features, Mitosis Rate, and Tubule Formation from H&E Images Predicts Disease-Free Survival in Patients with HR+ & LN+ Invasive Breast Cancer from SWOG S8814

Abstract Background: Lymph node (LN) involvement is a strong indicator of poor prognosis for breast cancer (BC), with adjuvant chemotherapy remaining fundamental to management of these patients. SWOG S8814 was a Phase III randomized trial of postmenopausal patients with pathologic LN-positive BC who were hormone receptor positive (HR+). The objectives of the clinical trial were to compare disease free survival (DFS) and overall survival (OS) of 1) these postoperative patients treated with a combination of cyclophosphamide, doxorubicin, fluorouracil (CAF) plus tamoxifen versus tamoxifen alone; and 2) patients treated with CAF followed by tamoxifen versus CAF plus concurrent tamoxifen. In this study we sought to evaluate the potential of applying computational image analysis on whole slide images (WSI) for predicting DFS and OS in SWOG S8814. Methods: A cohort of 135 patients (N=53 DFS event) diagnosed with HR+ & LN+ BC from clinical trial ECOG 2197 was utilized as training set D1. Validation set D2 comprised 630 patients (N=260 DFS event, N=195 death) with HR+& LN+ BC from SWOG S8814. Three deep learning models were employed to respectively detect nuclei, mitosis, and tubules in WSIs. Subsequently, a total of 1,810 features relating to nuclear morphology (e.g., spatial distribution, shape, texture, orientation), mitotic activity (e.g., mitosis hotspot, mitotic rates) and tubule formation (e.g., tubular nuclei distribution, ratio of tubule to non-tubule area) were extracted from each WSI. A lasso regularized Cox regression model (IbRiS) was trained on D1 to respectively identify four features from each of the feature categories (nuclei morphology, mitotic activity, and tubule formation) most strongly associated with DFS, a continuous risk score based on the selected features was then constructed. An optimal risk threshold was identified on D1 to dichotomize the risk scores into high vs. low risk of recurrence categories. Blinded validation of the machine learning model on SWOG S8814 using Cox regression was performed by SWOG to evaluate its performance in terms of DFS and OS. Results: In D2, patients identified as high risk of recurrence by IbRiS had a significantly worse prognosis in terms of DFS with hazard ratio=1.30 (p=0.039, 95% CI=1.01-1.66). IbRiS was also found to be significantly prognostic of OS with hazard ratio=1.38 (p=0.026, 95% CI=1.04-1.83). IbRiS was however, neither prognostic of DFS (HR = 1.20; 95% CI 0.93-1.54) nor OS (HR = 1.28; 95% CI 0.96-1.71) in multivariable analysis adjusting for treatment, tumor size, and number of positive nodes. IbRiS was also not a significant predictor of chemotherapy benefit (DFS p=0.45; OS p=0.25). Conclusion: We developed a prognostic model (IbRiS) based on the combined features of nuclear morphology, mitosis count, and tubule formation that can help further risk stratify HR+ & LN+ BC patients by only using H&E slides. Citation Format: Yuli Chen, William E. Barlow, Haojia Li, Cheng Lu, Andrew Janowczyk, German Corredor, Shridar Ganesan, Michael Feldman, Pingfu Fu, Hannah Gilmore, Kathy S. Albain, Lajos Pusztai, James Rae, Daniel Hayes, Andrew K. Godwin, Alastair M. Thompson, Anant Madabhushi. Computerized Measurements of Nuclear Morphology Features, Mitosis Rate, and Tubule Formation from H&E Images Predicts Disease-Free Survival in Patients with HR+ & LN+ Invasive Breast Cancer from SWOG S8814 [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P2-11-16.

Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features

AbstractRecurrence is the key factor affecting the prognosis of osteosarcoma. Currently, there is a lack of clinically useful tools to predict osteosarcoma recurrence. The application of pathological images for artificial intelligence‐assisted accurate prediction of tumour outcomes is increasing. Thus, the present study constructed a quantitative histological image classifier with tumour nuclear features to predict osteosarcoma outcomes using haematoxylin and eosin (H&E)‐stained whole‐slide images (WSIs) from 150 osteosarcoma patients. We first segmented eight distinct tissues in osteosarcoma H&E‐stained WSIs, with an average accuracy of 90.63% on the testing set. The tumour areas were automatically and accurately acquired, facilitating the tumour cell nuclear feature extraction process. Based on six selected tumour nuclear features, we developed an osteosarcoma histological image classifier (OSHIC) to predict the recurrence and survival of osteosarcoma following standard treatment. The quantitative OSHIC derived from tumour nuclear features independently predicted the recurrence and survival of osteosarcoma patients, thereby contributing to precision oncology. Moreover, we developed a fully automated workflow to extract quantitative image features, evaluate the diagnostic values of feature sets and build classifiers to predict osteosarcoma outcomes. Thus, the present study provides a novel tool for predicting osteosarcoma outcomes, which has a broad application prospect in clinical practice.

Automated analysis of computerized morphological features of cell clusters associated with malignancy on bile duct brushing whole slide images.

Bile duct brush specimens are difficult to interpret as they often present inflammatory and reactive backgrounds due to the local effects of stricture, atypical reactive changes, or previously installed stents, and often have low to intermediate cellularity. As a result, diagnosis of biliary adenocarcinomas is challenging and often results in large interobserver variability and low sensitivity OBJECTIVE: In this work, we used computational image analysis to evaluate the role of nuclear morphological and texture features of epithelial cell clusters to predict the presence of pancreatic and biliary tract adenocarcinoma on digitized brush cytology specimens. Whole slide images from 124 patients, either diagnosed as benign or malignant based on clinicopathological correlation, were collected and randomly split into training (ST , N= 58) and testing (Sv , N= 66) sets, with the exception of cases diagnosed as atypical on cytology were included in Sv . Nuclear boundaries on cell clusters extracted from each image were segmented via a watershed algorithm. A total of 536 quantitative morphometric features pertaining to nuclear shape, size, and aggregate cluster texture were extracted from within the cell clusters. The most predictive features from patients in ST were selected via rank-sum, t-test, and minimum redundancy maximum relevance (mRMR) schemes. The selected features were then used to train three machine-learning classifiers. Malignant clusters tended to exhibit lower textural homogeneity within the nucleus, greater textural entropy around the nuclear membrane, and longer minor axis lengths. The sensitivity of cytology alone was 74% (without atypicals) and 46% (with atypicals). With machine diagnosis, the sensitivity improved to 68% from 46% when atypicals were included and treated as nonmalignant false negatives. The specificity of our model was 100% within the atypical category. We achieved an area under the receiver operating characteristic curve (AUC) of 0.79 on Sv , which included atypical cytological diagnosis.

A Matched-Pair Analysis of Nuclear Morphologic Features Between Core Needle Biopsy and Surgical Specimen in Thyroid Tumors Using a Deep Learning Model.

Core needle biopsy (CNB) is a method that can be used as an alternative to fine-needle aspiration for the sampling of thyroid nodules to provide a preoperative diagnosis. Nuclear atypia is of paramount importance in diagnosing thyroid tumors. We aimed to identify the differences in nuclear morphologic features between CNB and surgical specimens. Quantitative image analysis was performed on whole slide images (WSI) of paired CNB and surgical specimens from 50 follicular cell-derived tumors including adenoma, non-invasive follicular thyroid neoplasm with papillary-like nuclear features, and carcinoma. The nuclear features of tumor cells were extracted from WSI using a pre-trained deep-learning model. In matched-pair analysis, the ratios (surgical specimens-to-CNB) of the mean nuclear diameters and the areas of the tumor cells were 1:0.75-0.85 and 1:0.54-0.73 according to the tumor types, respectively. The ratio of the nuclear optical density of tumor cells was 1.68-2.44 times higher in CNB specimens than it was in their corresponding surgical specimens. The significant nuclear size reduction and optical density increase in CNB were most prominent in papillary carcinoma cells. Normal follicular cells showed nuclear size reduction in CNB but no change in nuclear optical density between CNB and surgical specimens. Nuclear vacuolar artifacts mimicking nuclear pseudoinclusions were frequently seen in CNB regardless of the tumor types. In conclusion, tumor cells in CNB showed marked nuclear shrinkage, darker nuclear staining, and nuclear vacuolar changes. Awareness of the morphological differences according to the sampling types can facilitate correct diagnosis in thyroid histopathology.

Computer-extracted features of nuclear morphology in hematoxylin and eosin images distinguish stage II and IV colon tumors.

We assessed the utility of quantitative features of colon cancer nuclei, extracted from digitized hematoxylin and eosin‐stained whole slide images (WSIs), to distinguish between stage II and stage IV colon cancers. Our discovery cohort comprised 100 stage II and stage IV colon cancer cases sourced from the University Hospitals Cleveland Medical Center (UHCMC). We performed initial (independent) model validation on 51 (143) stage II and 79 (54) stage IV colon cancer cases from UHCMC (The Cancer Genome Atlas's Colon Adenocarcinoma, TCGA‐COAD, cohort). Our approach comprised the following steps: (1) a fully convolutional deep neural network with VGG‐18 architecture was trained to locate cancer on WSIs; (2) another deep‐learning model based on Mask‐RCNN with Resnet‐50 architecture was used to segment all nuclei from within the identified cancer region; (3) a total of 26 641 quantitative morphometric features pertaining to nuclear shape, size, and texture were extracted from within and outside tumor nuclei; (4) a random forest classifier was trained to distinguish between stage II and stage IV colon cancers using the five most discriminatory features selected by the Wilcoxon rank‐sum test. Our trained classifier using these top five features yielded an AUC of 0.81 and 0.78, respectively, on the held‐out cases in the UHCMC and TCGA validation sets. For 197 TCGA‐COAD cases, the Cox proportional hazards model yielded a hazard ratio of 2.20 (95% CI 1.24–3.88) with a concordance index of 0.71, using only the top five features for risk stratification of overall survival. The Kaplan–Meier estimate also showed statistically significant separation between the low‐risk and high‐risk patients, with a log‐rank P value of 0.0097. Finally, unsupervised clustering of the top five features revealed that stage IV colon cancers with peritoneal spread were morphologically more similar to stage II colon cancers with no long‐term metastases than to stage IV colon cancers with hematogenous spread. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

A deep hybrid learning pipeline for accurate diagnosis of ovarian cancer based on nuclear morphology.

Nuclear morphological features are potent determining factors for clinical diagnostic approaches adopted by pathologists to analyze the malignant potential of cancer cells. Considering the structural alteration of the nucleus in cancer cells, various groups have developed machine learning techniques based on variation in nuclear morphometric information like nuclear shape, size, nucleus-cytoplasm ratio and various non-parametric methods like deep learning have also been tested for analyzing immunohistochemistry images of tissue samples for diagnosing various cancers. We aim to correlate the morphometric features of the nucleus along with the distribution of nuclear lamin proteins with classical machine learning to differentiate between normal and ovarian cancer tissues. It has already been elucidated that in ovarian cancer, the extent of alteration in nuclear shape and morphology can modulate genetic changes and thus can be utilized to predict the outcome of low to a high form of serous carcinoma. In this work, we have performed exhaustive imaging of ovarian cancer versus normal tissue and developed a dual pipeline architecture that combines the matrices of morphometric parameters with deep learning techniques of auto feature extraction from pre-processed images. This novel Deep Hybrid Learning model, though derived from classical machine learning algorithms and standard CNN, showed a training and validation AUC score of 0.99 whereas the test AUC score turned out to be 1.00. The improved feature engineering enabled us to differentiate between cancerous and non-cancerous samples successfully from this pilot study.

Expression Levels of Lamin A or C Are Critical to Nuclear Maturation, Functional Responses, and Gene Expression Profiles in Differentiating Mouse Neutrophils.

Neutrophils mediate critical innate immune responses by migrating to sites of infection or inflammation, phagocytosing microorganisms, and releasing an arsenal of antimicrobial agents, including reactive oxygen species. These functions are shared by other innate immune cell types, but an interesting feature of neutrophils is their hallmark lobulated nuclei. Although why this bizarre nuclear shape forms is still being elucidated, studies of two intermediate filament proteins that associate with the nuclear envelope, lamin A and C, indicate that expression levels of these proteins govern nuclear maturation. These A-type lamins also modulate nuclear stiffness, the loss of which may be critical to the migration of not only neutrophils but also cancer cells that become prone to metastasis. We investigated whether increased expression of either lamin A or C affects neutrophil nuclear morphologic maturation, but more importantly we tested whether overexpression of either lamin also affects neutrophil functional responses, using two mouse myeloid progenitor models that can be induced toward functionally responsive neutrophil-like cells. Collectively, our results demonstrate that overexpression of either lamin A or C not only disrupts nuclear lobulation but also causes aberrant functional responses critical to innate immunity, including chemotaxis, phagocytosis, and reactive oxygen species production. Moreover, the lamin A-overexpressing cells exhibit decreased expression of a critical NADPH oxidase complex factor, gp91phox, and transcriptomic profiling demonstrated differential expression of a number of myeloid differentiation and functional pathway components. Taken together, these data demonstrate that A-type lamin expression levels modulate not only nuclear morphologic features but also gene expression changes as neutrophils mature.