Bridging Histopathology and Radiomics Toward Prognosis of Metastasis in Early Breast Cancer.

Tumor histomorphology is crucial for the prognostication of breast cancer outcomes because it contains histological, cellular, and molecular tumor heterogeneity related to metastatic potential. To enhance breast cancer prognosis, we aimed to apply radiomics analysis-traditionally used in 3D scans-to 2D histopathology slides. This study tested radiomics analysis in a cohort of 92 breast tumor specimens for outcome prognosis, addressing -omics dimensionality by comparing models with moderate and high feature counts, using least absolute shrinkage and selection operator for feature selection and machine learning for prognostic modeling. In the test folds, models with radiomics features [area under the curves (AUCs) range 0.799-0.823] significantly outperformed the benchmark model, which only included clinicopathological (CP) parameters (AUC = 0.584). The moderate-dimensionality model with 11 CP + 93 radiomics features matched the performance of the highly dimensional models with 1,208 radiomics or 11 CP + 1,208 radiomics features, showing average AUCs of 0.823, 0.799, and 0.807 and accuracies of 79.8, 79.3, and 76.6%, respectively. In conclusion, our application of deep texture radiomics analysis to 2D histopathology showed strong prognostic performance with a moderate-dimensionality model, surpassing a benchmark based on standard CP parameters, indicating that this deep texture histomics approach could potentially become a valuable prognostic tool.

Fractals in the Neurosciences: A Translational Geographical Approach.

The chapter presents three new fractal indices (fractal fragmentation index, fractal tentacularity index, and fractal anisotropy index) and normalized Kolmogorov complexity with proven applicability in geographic research, developed by the authors, and the possibility of their future use in neuroscience. The research demonstrates the relevance of fractal analysis in different fields and the basic concepts and principles of fractal geometry being sufficient for the development of models relevant to the studied reality. Also, the research highlighted the need to continue interdisciplinary research based on known fractal indicators, as well as the development of new analysis methods with the translational potential between fields.

Performance and Dimensionality of Pretreatment MRI Radiomics in Rectal Carcinoma Chemoradiotherapy Prediction.

(1) Background: This study aimed to develop a machine learning model based on radiomics of pretreatment magnetic resonance imaging (MRI) 3D T2W contrast sequence scans combined with clinical parameters (CP) to predict neoadjuvant chemoradiotherapy (nCRT) response in patients with locally advanced rectal carcinoma (LARC). The study also assessed the impact of radiomics dimensionality on predictive performance. (2) Methods: Seventy-five patients were prospectively enrolled with clinicopathologically confirmed LARC and nCRT before surgery. Tumor properties were assessed by calculating 2141 radiomics features. Least absolute shrinkage selection operator (LASSO) and multivariate regression were used for feature selection. (3) Results: Two predictive models were constructed, one starting from 72 CP and 107 radiomics features, and the other from 72 CP and 1862 radiomics features. The models revealed moderately advantageous impact of increased dimensionality, with their predictive respective AUCs of 0.86 and 0.90 in the entire cohort and 0.84 within validation folds. Both models outperformed the CP-only model (AUC = 0.80) which served as the benchmark for predictive performance without radiomics. (4) Conclusions: Predictive models developed in this study combining pretreatment MRI radiomics and clinicopathological features may potentially provide a routine clinical predictor of chemoradiotherapy responders, enabling clinicians to personalize treatment strategies for rectal carcinoma.

First basin scale spatial-temporal characterization of underwater sound in the Mediterranean Sea.

Anthropogenic underwater noise is an emergent pollutant. Despite several worldwide monitoring programs, only few data are available for the Mediterranean Sea, one of the global biodiversity hotspots. The results of the first continuous acoustic programme run at a transnational basin scale in the Mediterranean Sea are here presented. Recordings were done from March 2020 to June 2021, including the COVID-19 lockdown, at nine stations in the Northern Adriatic Sea. Spatial-temporal variations of the underwater sound are described, having one third octave band sound pressure levels (SPLs) from 10 Hz to 20 kHz as metrics. Higher and more variable SPLs, mainly related to vessel traffic, were found close to harbours, whereas Natura 2000 stations experienced lower SPLs. Lower values were recorded during the lockdown in five stations. Median yearly SPLs ranged between 64 and 95 as well as 70 and 100 dB re 1 µPa for 63 and 125 Hz bands, respectively. These values are comparable with those previously found in busy shallow EU basins but higher levels are expected during a business-as-usual period. This is a baseline assessment for a highly impacted and environmental valuable area, that needs to be managed in a new sustainable blue growth strategy.

Vascular endothelial growth factor (VEGF) -A, -C and VE-cadherin as potential biomarkers in early breast cancer patients.

BACKGROUND: Vascular endothelial growth factor (VEGF) -A and -C act as multifunctional molecules and growth factors, while VE-cadherin (cadherin 5, CDH5) is the endothelial junction protein. AIM: To assess the relationship between intratumoral VEGF -A, -C and CDH5 levels and clinical outcome, in primary, early-stage, breast cancer patients. PATIENTS AND METHODS: The study included 69 node-negative (N0) breast cancer patients, all of whom had not received any prior hormonal or chemotherapeutic systemic therapy that would affect the course of disease. The median follow-up period was 144 months. Intratumoral mRNA levels of VEGF -A, -C and CDH5 were determined by RT-qPCR. Prognostic performance was evaluated by Cox proportional hazards regression, Kaplan-Meier analysis, as well as by the multivariable approach based on the least absolute shrinkage and selection operator (LASSO) logit regression. Classification of patients into the low and high subgroups was performed using the outcome-oriented cut-off point categorization approach. RESULTS: Of the measured mRNAs, only CDH5 mRNA (t = -2.17; p = 0.04) and VEGF-C mRNA (t = -2.41; p = 0.03) showed significant differences between values in patient subgroups with distant metastasis and those without recurrences, respectively. These t-test results were in agreement with the Cox regression by which CDH5 mRNA reached the most pronounced hazard ratio (HR=2.07; p = 0.05), followed by VEGF-C mRNA (HR=1.59; p = 0.005). HR values above 1.0 indicate that high levels of either CDH5 or VEGF-C mRNAs associated with a higher risk of poor clinical outcome. Distant recurrence incidence was 26% for the CDH5high and 3% for the CDH5low subgroup (Kaplan-Meier analysis). Distant recurrence incidence was 23% for the VEGF-Chigh and 0% for VEGF-Clow subgroup. The independent prognostic value of VEGF-C mRNA was confirmed by LASSO regression. CONCLUSION: Intratumoral VEGF-A levels did not associate with disease outcome in primary, early-stage, breast cancer patients, whilst raised levels of either CDH5 or VEGF-C prognosticated a high risk of distant metastasis.

ComsystanJ: A collection of Fiji/ImageJ2 plugins for nonlinear and complexity analysis in 1D, 2D and 3D.

Complex systems such as the global climate, biological organisms, civilisation, technical or social networks exhibit diverse behaviours at various temporal and spatial scales, often characterized by nonlinearity, feedback loops, and emergence. These systems can be characterized by physical quantities such as entropy, information, chaoticity or fractality rather than classical quantities such as time, velocity, energy or temperature. The drawback of these complexity quantities is that their definitions are not always mathematically exact and computational algorithms provide estimates rather than exact values. Typically, evaluations can be cumbersome, necessitating specialized tools. We are therefore introducing ComsystanJ, a novel and user-friendly software suite, providing a comprehensive set of plugins for complex systems analysis, without the need for prior programming knowledge. It is platform independent, end-user friendly and extensible. ComsystanJ combines already known algorithms and newer methods for generalizable analysis of 1D signals, 2D images and 3D volume data including the generation of data sets such as signals and images for testing purposes. It is based on the framework of the open-source image processing software Fiji and ImageJ2. ComsystanJ plugins are macro recordable and are maintained as open-source software. ComsystanJ includes effective surrogate analysis in all dimensions to validate the features calculated by the different algorithms. Future enhancements of the project will include the implementation of parallel computing for image stacks and volumes and the integration of artificial intelligence methods to improve feature recognition and parameter calculation.

First assessment of underwater sound levels in the Northern Adriatic Sea at the basin scale.

The protection of marine habitats from human-generated underwater noise is an emerging challenge. Baseline information on sound levels, however, is poorly available, especially in the Mediterranean Sea. To bridge this knowledge gap, the SOUNDSCAPE project ran a basin-scale, cross-national, long-term underwater monitoring in the Northern Adriatic Sea. A network of nine monitoring stations, characterized by different natural conditions and anthropogenic pressures, ensured acoustic data collection from March 2020 to June 2021, including the full lockdown period related to the COVID-19 pandemic. Calibrated stationary recorders featured with an omnidirectional Neptune Sonar D60 Hydrophone recorded continuously 24 h a day (48 kHz sampling rate, 16 bit resolution). Data were analysed to Sound Pressure Levels (SPLs) with a specially developed and validated processing app. Here, we release the dataset composed of 20 and 60 seconds averaged SPLs (one-third octave, base 10) output files and a Python script to postprocess them. This dataset represents a benchmark for scientists and policymakers addressing the risk of noise impacts on marine fauna in the Mediterranean Sea and worldwide.

Directionally Sensitive Fractal Radiomics Compatible With Irregularly Shaped Magnetic Resonance Tumor Regions of Interest: Association With Osteosarcoma Chemoresistance.

BACKGROUND: Computational analysis of routinely acquired MRI has potential to improve the tumor chemoresistance prediction and to provide decision support in precision medicine, which may extend patient survival. Most radiomic analytical methods are compatible only with rectangular regions of interest (ROIs) and irregular tumor shape is therefore an important limitation. Furthermore, the currently used analytical methods are not directionally sensitive. PURPOSE: To implement a tumor analysis that is directionally sensitive and compatible with irregularly shaped ROIs. STUDY TYPE: Retrospective. SUBJECTS: A total of 54 patients with histopathologic diagnosis of primary osteosarcoma on tubular long bones and with prechemotherapy MRI. FIELD STRENGTH/SEQUENCE: A 1.5 T, T2-weighted-short-tau-inversion-recovery-fast-spin-echo. ASSESSMENT: A model to explore associations with osteosarcoma chemo-responsiveness included MRI data obtained before OsteoSa MAP neoadjuvant cytotoxic chemotherapy. Osteosarcoma morphology was analyzed in the MRI data by calculation of the nondirectional two-dimensional (2D) and directional and nondirectional one-dimensional (1D) Higuchi dimensions (Dh). MAP chemotherapy response was assessed by histopathological necrosis. STATISTICAL TESTS: The area under the receiver operating characteristic (ROC) curve (AUC) evaluated the association of the calculated features with the actual chemoresponsiveness, using tumor histopathological necrosis (95%) as the endpoint. Least absolute shrinkage and selection operator (LASSO) machine learning and multivariable regression were used for feature selection. Significance was set at <0.05. RESULTS: The nondirectional 1D Dh reached an AUC of 0.88 in association with the 95% tumor necrosis, while the directional 1D analysis along 180 radial lines significantly improved this association according to the Hanley/McNeil test, reaching an AUC of 0.95. The model defined by variable selection using LASSO reached an AUC of 0.98. The directional analysis showed an optimal predictive range between 90° and 97° and revealed structural osteosarcoma anisotropy manifested by its directionally dependent textural properties. DATA CONCLUSION: Directionally sensitive radiomics had superior predictive performance in comparison to the standard nondirectional image analysis algorithms with AUCs reaching 0.95 and full compatibility with irregularly shaped ROIs. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 1.

The Magnetic Resonance Imaging Pattern of the Lesions Caused by Knee Overuse in the Pediatric Population.

Background and Objectives: Excessive use of the knee in patients with immature locomotor systems leads to a whole spectrum of morphological changes with possible consequences in adulthood. This study aimed to examine the morphological pattern in magnetic resonance imaging (MRI) that is associated with recurrent pain due to increased physical activity in children. Materials and Methods: This was a retrospective study conducted among pediatric patients treated at the University Children's Hospital in Belgrade in 2018 and 2019. MRI findings of patients who reported recurrent pain in the knee joint during physical activity and who were without any pathological findings on both clinical examination and knee radiographs were included in the study. Results: MRI findings of 168 patients (73 boys and 95 girls, mean age 14.07 ± 3.34 years) were assessed. Meniscus and cartilage lesions were the most commonly detected morphological findings: meniscus lesions in 49.4%, cartilage ruptures in 44.6%, and cartilage edema in 26.2% of patients. The medial meniscus was more often injured in girls (p = 0.030), while boys were more prone to other joint injuries (p = 0.016), re-injury of the same joint (p = 0.036), bone bruises (p < 0.001), and ligament injuries (p = 0.001). In children older than 15 years, tibial plateau cartilage edema (p = 0.016), chondromalacia patellae (p = 0.005), and retropatellar effusion (p = 0.011) were detected more frequently compared to younger children. Conclusions: Children reporting recurrent knee pain due to increased physical activity, without any detected pathological findings on clinical examination and knee radiography, may have morphological changes that can be detected on MRI. Timely diagnosis of joint lesions should play a significant role in preventing permanent joint dysfunction in the pediatric population as well as in preventing the development of musculoskeletal diseases in adulthood.

Characterization of the underwater noise produced by recreational and small fishing boats (<14 m) in the shallow-water of the Cres-Losinj Natura 2000 SCI.

Recreational boats are a dominant source of underwater noise in coastal areas, but reliable boat noise assessment is generally lacking. Here the Underwater Radiated Noise (URN) of seven recreational and small fishing boats moving at two different speeds was measured in the shallow waters of the Cres-Losinj Natura 2000 SCI (Croatia). Measurements were undertaken considering the internationally recognized standards and published guidelines for shallow waters. URN was provided in 1/3 octave band spectra and in narrow band spectra, to highlight the tonal components. Engine power and type rather than the boat length and design result to be more predictive of URN. Highest speeds induce highest noise levels only in a very limited frequency range and different boats with similar speed but different engines show a shift in the spectra. Relevance of the achieved results for the tested area is further discussed.

Can granulysin provide prognostic value in primary breast cancer?

BACKGROUND: Granulysin (GNLY) is a cytolytic and proinflammatory molecule which also acts as an immune alarmin. The multifunctional nature of this molecule has made it challenging to define its full potential as a biomarker in breast cancer. AIM: To evaluate the prognostic value of intratumoral GNLY in primary breast cancer patients and its association with established clinicopathological parameters. PATIENTS AND METHODS: The study included 69 node-negative breast cancer patients with known clinicopathological parameters, all of whom had not received any prior hormonal or chemotherapeutic systemic therapy that would interfere with the course of disease. The median follow-up period was 144 months. Steroid hormone receptor status was determined by ligand-binding assay and HER2 status by chromogenic in situ hybridisation (CISH). Intratumoral GNLY mRNA levels were determined by RT-qPCR. Prognostic performance was evaluated by the receiver operating characteristic (ROC), Cox proportional hazards regression and Kaplan-Meier analysis. Classification of patients into GNLYlow and GNLYhigh subgroups was performed by the use of the outcome-oriented cut-off point categorisation approach. RESULTS: There was a significant difference between GNLY values of patients without any recurrences and those with local or distant recurrences (Mann-Whitney test, p = 0.05 and p = 0.02, respectively). None of the tested parameters showed prognostic significance for local and distant recurrences when combined. When distant metastases and local recurrences were separated as events, the best prognostic performance was observed for GNLY as compared with any clinicopathological parameter (AUC=0.24 and p = 0.04 for local events; AUC=0.71 and p = 0.03 for distant events). Local recurrence incidence was 0% for the GNLYhigh subgroup and 19% for the GNLYlow subgroup; however distant recurrence incidence was 24% for the GNLYhigh subgroup but only 3% for the GNLYlow subgroup (Kaplan-Meier analysis). A significant positive correlation was found between intratumoral ER and GNLY levels, and a significant negative correlation between tumour grade and GNLY levels. CONCLUSION: High levels of granulysin prognosticate low risk of local recurrence but a high risk of distant metastasis in primary, untreated, breast cancer patients.

Kolmogorov compression complexity may differentiate different schools of Orthodox iconography.

The complexity in the styles of 1200 Byzantine icons painted between 13th and 16th from Greece, Russia and Romania was investigated through the Kolmogorov algorithmic information theory. The aim was to identify specific quantitative patterns which define the key characteristics of the three different painting schools. Our novel approach using the artificial surface images generated with Inverse FFT and the Midpoint Displacement (MD) algorithms, was validated by comparison of results with eight fractal and non-fractal indices. From the analyzes performed, normalized Kolmogorov compression complexity (KC) proved to be the best solution because it had the best complexity pattern differentiations, is not sensitive to the image size and the least affected by noise. We conclude that normalized KC methodology does offer capability to differentiate the icons within a School and amongst the three Schools.

MRI radiomics in the prediction of the volumetric response in meningiomas after gamma knife radiosurgery.

PURPOSE: This report presents the first investigation of the radiomics value in predicting the meningioma volumetric response to gamma knife radiosurgery (GKRS). METHODS: The retrospective study included 93 meningioma patients imaged by three Tesla MRI. Tumor morphology was quantified by calculating 337 shape, first- and second-order radiomic features from MRI obtained before GKRS. Analysis was performed on original 3D MR images and after their laplacian of gaussian (LoG), logarithm and exponential filtering. The prediction performance was evaluated by Pearson correlation, linear regression and ROC analysis, with meningioma volume change per month as the outcome. RESULTS: Sixty calculated features significantly correlated with the outcome. The feature selection based on LASSO and multivariate regression started from all available 337 radiomic and 12 non-radiomic features. It selected LoG-sigma-1-0-mm-3D_firstorder_InterquartileRange and logarithm_ngtdm_Busyness as the predictively most robust and non-redundant features. The radiomic score based on these two features produced an AUC = 0.81. Adding the non-radiomic karnofsky performance status (KPS) to the score has increased the AUC to 0.88. Low values of the radiomic score defined a homogeneous subgroup of 50 patients with consistent absence (0%) of tumor progression. CONCLUSION: This is the first report of a strong association between MRI radiomic features and volumetric meningioma response to radiosurgery. The clinical importance of the early and reliable prediction of meningioma responsiveness to radiosurgery is based on its potential to aid individualized therapy decision making.

The prognostic significance of serum interferon-gamma (IFN-γ) in hormonally dependent breast cancer.

BACKGROUND: Interferon-γ (IFN-γ) is a pleiotropic immunomodulatory cytokine. Because of its contradictory and even dualistic roles in malignancies, its potential as a biomarker remains to be unraveled. AIM: To evaluate the prognostic significance of serum IFN-γ in hormonally treated breast cancer patients. MATERIAL AND METHODS: The study included 72 premenopausal breast cancer patients with known clinicopathological characteristics. All patients received adjuvant hormonal therapy based on hormone receptor-positivity. The median follow-up period was 93 months. IFN-γ serum protein levels were determined by quantitative ELISA. Prognostic performance was evaluated by the receiver operating characteristic (ROC), Cox proportional hazards regression and Kaplan-Meier analyses. Classification of patients into IFN-γlow and IFN-γhigh subgroups was performed by the use of the outcome-oriented cut-off point categorization approach. RESULTS: The best prognostic performance was achieved by IFN-γ (AUC = 0.24 and p = 0.01 for distant events, AUC = 0.29 and p = 0.01 for local and distant events combined). Age and IFN-γ were prognostically significant in instances of all types of outcomes and IFN-γ was the independent prognostic parameter (Cox regression). There was a significant difference between IFN-γ values of patients without any events and those with distant metastases (Mann-Whitney test, p = 0.007). IFN-γ levels correlated significantly with nodal status and tumor stage (Spearman's rank order, r = -0.283 and r = -0.238, respectively). Distant recurrence incidence was 4% for the IFN-γhigh subgroup and 33% for the IFN-γlow subgroup (Kaplan-Meier analysis). CONCLUSIONS: Raised serum IFN-γ levels associate independently with favorable disease outcome in hormonally dependent breast cancer.

The significance of HOXB7 and IL17RB serum levels in prognosis of hormonally dependent breast cancer: A pilot study.

PURPOSE: Improved prognostication of a patient's outcome could allow for personalized treatment decisions in breast cancer. Homeobox B7 (HOXB7) and interleukin 17 receptor B (IL17RB) are proteins reportedly involved in the development of hormonal therapy resistance. Their prognostic value was previously investigated in tumor tissue but recent mass spectrometric detection of HOXB7 and IL17RB proteins in serum has prompted us to perform the first prognostic evaluation of their serum levels. PATIENTS AND METHODS: The study included 81 premenopausal breast cancer patients that received adjuvant hormonal therapy. The median follow-up period was 61 months. HOXB7 and IL17RB serum protein levels were measured by quantitative sandwich ELISA and prognostically evaluated by Cox proportional hazards regression analysis. RESULTS: HOXB7 protein was detected in 96.3% and IL17RB in 33.3% of serum samples. Higher levels of serum HOXB7 significantly associated with favorable disease outcome by prognosticating distant (by HR â€‹= â€‹0.04; P â€‹= â€‹0.001) and local recurrence (by HR â€‹= â€‹0.03, P â€‹= â€‹0.001). The recurrence rates in the HOXB7high and HOXB7low subgroups of patients (cut-off 81.5 â€‹pg/mL) were 0% and 17%, respectively. Serum IL17RB levels did not significantly associate with either local or distant events. The multivariate analysis highlighted estrogen receptor, histological grade, nodal status and HOXB7 as independent prognostic parameters. CONCLUSIONS: Our findings validate the previous mass-spectrometry data by showing that HOXB7 and IL17RB cellular proteins are detectable in serum by a standard ELISA assay. Furthermore, we show that HOXB7 serum levels are the relevant prognosticator of response to hormonal therapy.

Computational analysis of MRIs predicts osteosarcoma chemoresponsiveness.

Aim: This study aimed to improve osteosarcoma chemoresponsiveness prediction by optimization of computational analysis of MRIs. Patients & methods: Our retrospective predictive model involved osteosarcoma patients with MRI scans performed before OsteoSa MAP neoadjuvant cytotoxic chemotherapy. Results: We found that several monofractal and multifractal algorithms were able to classify tumors according to their chemoresponsiveness. The predictive clues were defined as morphological complexity, homogeneity and fractality. The monofractal feature CV for Λ'(G) provided the best predictive association (area under the ROC curve = 0.88; p <0.001), followed by   Y-axis intersection of the regression line  for â€Šbox fractal dimension, r²â€Š for  FDM and tumor circularity. Conclusion: This is the first full-scale study to indicate that computational analysis of pretreatment MRIs could provide imaging biomarkers for the classification of osteosarcoma according to their chemoresponsiveness.

The prognostic value of cyclin D1 in breast cancer patients treated with hormonal therapy: A pilot study.

THE AIM: of the study was to determine the clinical relevance of cyclin D1 (cD1) and its association with clinicopathological parameters in breast cancer patients treated with hormonal therapy. MATERIAL AND METHODS: The study included 96 primary breast cancer patients with known clinicopathological parameters. In adjuvant setting, 44 patients were tamoxifen-treated and 52 were treated with ovarian irradiation/ablation. The cD1 status (gene amplified/nonamplified) was determined on formalin-fixed paraffin-embedded tumor tissue sections by chromogenic in situ hybridization. Associations between parameters were analyzed by Chi-square and Spearman's rank order correlation tests. Cox proportional hazards regression test was performed. Survival curves for relapse-free survival were constructed according to the Kaplan-Meier method. RESULTS: There were no significant associations between cyclin D1 and clinicopathological parameters in either patient group. Amplified cyclin D1 associated significantly with the actual relapse incidence in the ovarian ablation patient group (p = 0.01, HR = 3.1), but not in the tamoxifen-treated patient group. Estrogen receptor and cyclin D1 have proven to be independent parameters of poor outcome in the ovarian ablation patient group (p = 0.03, HR = 2.9; and p = 0.009, HR = 2.5; respectively). CONCLUSIONS: Cyclin D1 might be a candidate biomarker of poor outcome in breast cancer patients treated with ovarian ablation, suggesting its possible involvement in acquirement of hormonal resistance. The role of cyclin D1 as potential parameter of response to tamoxifen was not as pronounced.

Analysis of Spatial Distribution and Prognostic Value of Different Pan Cytokeratin Immunostaining Intensities in Breast Tumor Tissue Sections.

Cancer risk prognosis could improve patient survival through early personalized treatment decisions. This is the first systematic analysis of the spatial and prognostic distribution of different pan cytokeratin immunostaining intensities in breast tumors. The prognostic model included 102 breast carcinoma patients, with distant metastasis occurrence as the endpoint. We segmented the full intensity range (0-255) of pan cytokeratin digitized immunostaining into seven discrete narrow grey level ranges: 0-130, 130-160, 160-180, 180-200, 200-220, 220-240, and 240-255. These images were subsequently examined by 33 major (GLCM), fractal and first-order statistics computational analysis features. Interestingly, while moderate intensities were strongly associated with metastasis outcome, high intensities of pan cytokeratin immunostaining provided no prognostic value even after an exhaustive computational analysis. The intense pan cytokeratin immunostaining was also relatively rare, suggesting the low differentiation state of epithelial cells. The observed variability in immunostaining intensities highlighted the intratumoral heterogeneity of the malignant cells and its association with a poor disease outcome. The prognostic importance of the moderate intensity range established by complex computational morphology analyses was supported by simple measurements of its immunostaining area which was associated with favorable disease outcome. This study reveals intratumoral heterogeneity of the pan cytokeratin immunostaining together with the prognostic evaluation and spatial distribution of its discrete intensities.