Tumour Stroma Ratio Assessment Using Digital Image Analysis Predicts Survival in Triple Negative and Luminal Breast Cancer

Mathematical modelling and deep learning algorithms to automate assessment of single and digitally multiplexed immunohistochemical stains in tumoural stroma

Whilst automated analysis of immunostains in pathology research has focused predominantly on the epithelial compartment, automated analysis of stains in the stromal compartment is challenging and therefore requires time-consuming pathological input and guidance to adjust to tissue morphometry as perceived by pathologists. This study aimed to develop a robust method to automate stromal stain analyses using 2 of the commonest stromal stains (SMA and desmin) employed in clinical pathology practice as examples. An effective computational method capable of automatically assessing and quantifying tumour-associated stromal stains was developed and applied on cores of colorectal cancer tissue microarrays. The methodology combines both mathematical models and deep learning techniques with the former requiring no training data and the latter as many inputs as possible. The novel mathematical model was used to produce a digital double marker overlay allowing for fast automated digital multiplex analysis of stromal stains. The results show that deep learning methodologies in combination with mathematical modelling allow for an accurate means of quantifying stromal stains whilst also opening up new possibilities of digital multiplex analyses.

Patient-specific vascularized tumor model: Blocking monocyte recruitment with multispecific antibodies targeting CCR2 and CSF-1R

Tumor-associated inflammation drives cancer progression and therapy resistance, often linked to the infiltration of monocyte-derived tumor-associated macrophages (TAMs), which are associated with poor prognosis in various cancers. To advance immunotherapies, testing on immunocompetent pre-clinical models of human tissue is crucial. We have developed an in vitro model of microvascular networks with tumor spheroids or patient tissues to assess monocyte trafficking into tumors and evaluate immunotherapies targeting the human tumor microenvironment. Our findings demonstrate that macrophages in vascularized breast and lung tumor models can enhance monocyte recruitment via CCL7 and CCL2, mediated by CSF-1R. Additionally, a multispecific antibody targeting CSF-1R, CCR2, and neutralizing TGF-β (CSF1R/CCR2/TGF-β Ab) repolarizes TAMs towards an anti-tumoral M1-like phenotype, reduces monocyte chemoattractant protein secretion, and blocks monocyte migration. This antibody also inhibits monocyte recruitment in patient-specific vascularized tumor models. In summary, this vascularized tumor model recapitulates the monocyte recruitment cascade, enabling functional testing of innovative therapeutic antibodies targeting TAMs in the tumor microenvironment.

Apparent diffusion coefficient and tissue stiffness are associated with different tumor microenvironment features of hepatocellular carcinoma

OBJECTIVES

To investigate associations between tissue diffusion, stiffness, and different tumor microenvironment features in resected hepatocellular carcinoma (HCC).

METHODS

Seventy-two patients were prospectively included for preoperative magnetic resonance (MR) diffusion-weighted imaging and MR elastography examination. The mean apparent diffusion coefficient (ADC) and stiffness value were measured on the central three slices of the tumor and peri-tumor area. Cell density, tumor-stroma ratio (TSR), lymphocyte-rich HCC (LR-HCC), and CD8 + T cell infiltration were estimated in resected tumors. The interobserver agreement of MRI measurements and subjective pathological evaluation was assessed. Variables influencing ADC and stiffness were screened with univariate analyses, and then identified with multivariable linear regression. The potential relationship between explored imaging biomarkers and histopathological features was assessed with linear regression after adjustment for other influencing factors.

RESULTS

Seventy-two patients (male/female: 59/13, mean age: 56 ± 10.2 years) were included for analysis. Inter-reader agreement was good or excellent regarding MRI measurements and histopathological evaluation. No correlation between tumor ADC and tumor stiffness was found. Multivariable linear regression confirmed that cell density was the only factor associated with tumor ADC (Estimate = -0.03, p = 0.006), and tumor-stroma ratio was the only factor associated with tumor stiffness (Estimate = -0.18, p = 0.03). After adjustment for fibrosis stage (Estimate = 0.43, p < 0.001) and age (Estimate = 0.04, p < 0.001) in the multivariate linear regression, intra-tumoral CD8 + T cell infiltration remained a significant factor associated with peri-tumor stiffness (Estimate = 0.63, p = 0.02).

CONCLUSIONS

Tumor ADC surpasses tumor stiffness as a biomarker of cellularity. Tumor stiffness is associated with tumor-stroma ratio and peri-tumor stiffness might be an imaging biomarker of intra-tumoral immune microenvironment.

CLINICAL RELEVANCE STATEMENT

Tissue stiffness could potentially serve as an imaging biomarker of the intra-tumoral immune microenvironment of hepatocellular carcinoma and aid in patient selection for immunotherapy.

KEY POINTS

Apparent diffusion coefficient reflects cellularity of hepatocellular carcinoma. Tumor stiffness reflects tumor-stroma ratio of hepatocellular carcinoma and is associated with tumor-infiltrating lymphocytes. Tumor and peri-tumor stiffness might serve as imaging biomarkers of intra-tumoral immune microenvironment.

Artificial intelligence in digital histopathology for predicting patient prognosis and treatment efficacy in breast cancer

INTRODUCTION

Histological images contain phenotypic information predictive of patient outcomes. Due to the heavy workload of pathologists, the time-consuming nature of quantitatively assessing histological features, and human eye limitations to recognize spatial patterns, manually extracting prognostic information in routine pathological workflows remains challenging. Digital pathology has facilitated the mining and quantification of these features utilizing whole-slide image (WSI) scanners and artificial intelligence (AI) algorithms. AI algorithms to identify image-based biomarkers from the tumor microenvironment (TME) have the potential to revolutionize the field of oncology, reducing delays between diagnosis and prognosis determination, allowing for rapid stratification of patients and prescription of optimal treatment regimes, thereby improving patient outcomes.

AREAS COVERED

In this review, the authors discuss how AI algorithms and digital pathology can predict breast cancer patient prognosis and treatment outcomes using image-based biomarkers, along with the challenges of adopting this technology in clinical settings.

EXPERT OPINION

The integration of AI and digital pathology presents significant potential for analyzing the TME and its diagnostic, prognostic, and predictive value in breast cancer patients. Widespread clinical adoption of AI faces ethical, regulatory, and technical challenges, although prospective trials may offer reassurance and promote uptake, ultimately improving patient outcomes by reducing diagnosis-to-prognosis delivery delays.

Vague-Segment Technique: Automatic Computation of Tumor Stroma Ratio for Breast Cancer on Whole Slides

The calculation of Tumor Stroma Ratio (TSR) is a challenging medical issue that could improve predictions of neoadjuvant chemotherapy benefits and patient prognoses. Although several studies on breast cancer and deep learning methods have achieved promising results, the drawbacks that pixel-level semantic segmentation processes could not extract core tumor regions containing both tumor pixels and stroma pixels make it difficult to accurately calculate TSR. In this paper, we propose a Vague-Segment Technique (VST) consisting of a designed SwinV2UNet module and a modified Suzuki algorithm. Specifically, the SwinV2UNet identifies tumor pixels and generate pixel-level classification results, based on which the modified Suzuki algorithm extracts the contour of core tumor regions in terms of cosine angle. Through this way, VST obtains vaguely segmentation results of core tumor regions containing both tumor pixels and stroma pixels, where the TSR could be calculated by the formula of Intersection over Union (IOU). For the training and evaluation, we utilize the well-known The Cancer Genome Atlas (TCGA) database to create an annotated dataset, while 150 images with TSR annotations from real cases are also collected. The experimental results illustrate that the proposed VST could generate better tumor identification results compared with state-of-the-art methods, where the extracted core tumor regions lead to more consistencies of calculated TSR with senior experts compared to junior pathologists. The experimental results demonstrate the superiority of our proposed pipeline, which has promise for future clinical application.

The Value of Dual-Energy Computed Tomography-Based Radiomics in the Evaluation of Interstitial Fibers of Clear Cell Renal Carcinoma

OBJECTIVE

We investigated the potential of dual-energy computed tomography (DECT) radiomics in assessing cancer-associated fibroblasts in clear cell renal carcinoma (ccRCC).

METHODS

A retrospective analysis was conducted on 132 patients with ccRCC. The arterial and venous phase iodine-based material decomposition images (IMDIs), virtual non-contrast images, 70 keV, 100 keV, and 150 keV virtual monoenergetic images, and mixed energy images (MEIs) were obtained from the DECT datasets. On the Radcloud platform, radiomics feature extraction, feature selection, and model establishment were performed. Seven radiomics models were established using the support vector machine. The predictive performance was evaluated by utilizing receiver operating characteristic and the area under the curve (AUC) was calculated. Nomograms were constructed.

RESULTS

The combined model demonstrated high efficiency in evaluating pseudocapsule thickness with AUC, specificity, and sensitivity of 0.833, 0.870, and 0.750, respectively in the validation set, surpassing those of other models. The precision, F1-score, and Youden index were also higher for the combined model. For evaluating the number of collagen fibers, the combined model exhibited the highest AUC (0.741) among all models, with a specificity of 0.830 and a sensitivity of 0.330. The AUC in the 150 kv model and IMDI model were slightly lower than those in the combined model (0.728 and 0.710, respectively), with corresponding sensitivity and specificity of 0.560/0.780 and 0.670/0.830. The nomogram exhibited that Rad-score had good prediction efficiency.

CONCLUSION

DECT radiomics features have significant value in evaluating the interstitial fibers of ccRCC. The combined model of IMDI + MEI exhibits superior performance in assessing the thickness of the pseudocapsule, while the combined, 150 keV, and IMDI models demonstrate higher efficacy in evaluating collagen fiber number. Radiomics, combined with imaging features and clinical features, has excellent predictive performance. These findings offer crucial support for the clinical diagnosis, treatment, and prognosis of ccRCC and provide valuable insights into the application of DECT.

Feasibility and effectiveness of automatic deep learning network and radiomics models for differentiating tumor stroma ratio in pancreatic ductal adenocarcinoma

OBJECTIVE

This study aims to compare the feasibility and effectiveness of automatic deep learning network and radiomics models in differentiating low tumor stroma ratio (TSR) from high TSR in pancreatic ductal adenocarcinoma (PDAC).

METHODS

A retrospective analysis was conducted on a total of 207 PDAC patients from three centers (training cohort: n = 160; test cohort: n = 47). TSR was assessed on hematoxylin and eosin-stained specimens by experienced pathologists and divided as low TSR and high TSR. Deep learning and radiomics models were developed including ShuffulNetV2, Xception, MobileNetV3, ResNet18, support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF), and logistic regression (LR). Additionally, the clinical models were constructed through univariate and multivariate logistic regression. Kaplan-Meier survival analysis and log-rank tests were conducted to compare the overall survival time between different TSR groups.

RESULTS

To differentiate low TSR from high TSR, the deep learning models based on ShuffulNetV2, Xception, MobileNetV3, and ResNet18 achieved AUCs of 0.846, 0.924, 0.930, and 0.941, respectively, outperforming the radiomics models based on SVM, KNN, RF, and LR with AUCs of 0.739, 0.717, 0.763, and 0.756, respectively. Resnet 18 achieved the best predictive performance. The clinical model based on T stage alone performed worse than deep learning models and radiomics models. The survival analysis based on 142 of the 207 patients demonstrated that patients with low TSR had longer overall survival.

CONCLUSIONS

Deep learning models demonstrate feasibility and superiority over radiomics in differentiating TSR in PDAC. The tumor stroma ratio in the PDAC microenvironment plays a significant role in determining prognosis.

CRITICAL RELEVANCE STATEMENT

The objective was to compare the feasibility and effectiveness of automatic deep learning networks and radiomics models in identifying the tumor-stroma ratio in pancreatic ductal adenocarcinoma. Our findings demonstrate deep learning models exhibited superior performance compared to traditional radiomics models.

KEY POINTS

• Deep learning demonstrates better performance than radiomics in differentiating tumor-stroma ratio in pancreatic ductal adenocarcinoma. • The tumor-stroma ratio in the pancreatic ductal adenocarcinoma microenvironment plays a protective role in prognosis. • Preoperative prediction of tumor-stroma ratio contributes to clinical decision-making and guiding precise medicine.

A Review of AI-Based Radiomics and Computational Pathology Approaches in Triple-Negative Breast Cancer: Current Applications and Perspectives

Breast cancer is one of the most common and deadly cancers worldwide. Approximately, 20% of all breast cancers are characterized as triple negative (TNBC). TNBC typically is associated with a poorer prognosis relative to other breast cancer subtypes. Due to its aggressiveness and lack of response to hormonal therapy, conventional cytotoxic chemotherapy is the usual treatment; however, this treatment is not always effective, and an important percentage of patients develop recurrence. More recently, immunotherapy has started to be used on some populations with TNBC showing promising results. Unfortunately, immunotherapy is only applicable to a minority of patients and responses in metastatic TNBC have overall been modest in comparison to other cancer types. This situation evidences the need for developing effective biomarkers that help to stratify and personalize patient management. Thanks to recent advances in artificial intelligence (AI), there has been an increasing interest in its use for medical applications aiming at supporting clinical decision making. Several works have used AI in combination with diagnostic medical imaging, more specifically radiology and digitized histopathological tissue samples, aiming to extract disease-specific information that is difficult to quantify by the human eye. These works have demonstrated that analysis of such images in the context of TNBC has great potential for (1) risk-stratifying patients to identify those patients who are more likely to experience disease recurrence or die from the disease and (2) predicting pathologic complete response. In this manuscript, we present an overview on AI and its integration with radiology and histopathological images for developing prognostic and predictive approaches for TNBC. We present state of the art approaches in the literature and discuss the opportunities and challenges with developing AI algorithms regarding further development and clinical deployment, including identifying those patients who may benefit from certain treatments (e.g., adjuvant chemotherapy) from those who may not and thereby should be directed toward other therapies, discovering potential differences between populations, and identifying disease subtypes.

AI-enabled routine H&E image based prognostic marker for early-stage luminal breast cancer

Breast cancer (BC) grade is a well-established subjective prognostic indicator of tumour aggressiveness. Tumour heterogeneity and subjective assessment result in high degree of variability among observers in BC grading. Here we propose an objective Haematoxylin & Eosin (H&E) image-based prognostic marker for early-stage luminal/Her2-negative BReAst CancEr that we term as the BRACE marker. The proposed BRACE marker is derived from AI based assessment of heterogeneity in BC at a detailed level using the power of deep learning. The prognostic ability of the marker is validated in two well-annotated cohorts (Cohort-A/Nottingham: n = 2122 and Cohort-B/Coventry: n = 311) on early-stage luminal/HER2-negative BC patients treated with endocrine therapy and with long-term follow-up. The BRACE marker is able to stratify patients for both distant metastasis free survival (p = 0.001, C-index: 0.73) and BC specific survival (p < 0.0001, C-index: 0.84) showing comparable prediction accuracy to Nottingham Prognostic Index and Magee scores, which are both derived from manual histopathological assessment, to identify luminal BC patients that may be likely to benefit from adjuvant chemotherapy.

Deciphering the Morphology of Tumor-Stromal Features in Invasive Breast Cancer Using Artificial Intelligence

Tumor-associated stroma in breast cancer (BC) is complex and exhibits a high degree of heterogeneity. To date, no standardized assessment method has been established. Artificial intelligence (AI) could provide an objective morphologic assessment of tumors and stroma, with the potential to identify new features not discernible by visual microscopy. In this study, we used AI to assess the clinical significance of (1) stroma-to-tumor ratio (S:TR) and (2) the spatial arrangement of stromal cells, tumor cell density, and tumor burden in BC. Whole-slide images of a large cohort (n = 1968) of well-characterized luminal BC cases were examined. Region and cell-level annotation was performed, and supervised deep learning models were applied for automated quantification of tumor and stromal features. S:TR was calculated in terms of surface area and cell count ratio, and the S:TR heterogeneity and spatial distribution were also assessed. Tumor cell density and tumor size were used to estimate tumor burden. Cases were divided into discovery (n = 1027) and test (n = 941) sets for validation of the findings. In the whole cohort, the stroma-to-tumor mean surface area ratio was 0.74, and stromal cell density heterogeneity score was high (0.7/1). BC with high S:TR showed features characteristic of good prognosis and longer patient survival in both the discovery and test sets. Heterogeneous spatial distribution of S:TR areas was predictive of worse outcome. Higher tumor burden was associated with aggressive tumor behavior and shorter survival and was an independent predictor of worse outcome (BC-specific survival; hazard ratio: 1.7, P = .03, 95% CI, 1.04-2.83 and distant metastasis-free survival; hazard ratio: 1.64, P = .04, 95% CI, 1.01-2.62) superior to absolute tumor size. The study concludes that AI provides a tool to assess major and subtle morphologic stromal features in BC with prognostic implications. Tumor burden is more prognostically informative than tumor size.

Computational pathology to improve biomarker testing in breast cancer: how close are we?

The recent advancements in breast cancer precision medicine have highlighted the urgency for the precise and reproducible characterization of clinically actionable biomarkers. Despite numerous standardization efforts, biomarker testing by conventional methodologies is challenged by several issues such as high inter-observer variabilities, the spatial heterogeneity of biomarkers expression, and technological heterogeneity. In this respect, artificial intelligence-based digital pathology approaches are being increasingly recognized as promising methods for biomarker testing and subsequently improved clinical management. Here, we provide an overview on the most recent advances for artificial intelligence-assisted biomarkers testing in breast cancer, with a particular focus on tumor-infiltrating lymphocytes, programmed death-ligand 1, phosphatidylinositol-3 kinase catalytic alpha, and estrogen receptor 1. Challenges and solutions for this integrative analysis in pathology laboratories are also provided.

Reassessing Breast Cancer-Associated Fibroblasts (CAFs) Interactions with Other Stromal Components and Clinico-Pathologic Parameters by Using Immunohistochemistry and Digital Image Analysis (DIA)

BACKGROUND

Breast cancer (BC) stroma has CD34- and αSMA-positive cancer-associated fibroblasts (CAFs) differently distributed. During malignant transformation, CD34-positive fibroblasts decrease while αSMA-positive CAFs increase. The prevalence of αSMA-positive CAFs in BC stroma makes microscopic examination difficult without digital image analysis processing (DIA). DIA was used to compare CD34- and αSMA-positive CAFs among breast cancer molecular subgroups. DIA-derived data were linked to age, survival, tumor stroma vessels, tertiary lymphoid structures (TLS), invasion, and recurrence.

METHODS

Double immunostaining for CD34 and αSMA showed different CAF distribution patterns in normal and BC tissues. Single CD34 immunohistochemistry on supplemental slides quantified tumor stroma CD34_CAFs. Digital image analysis (DIA) data on CAF density, intensity, stromal score, and H-score were correlated with clinico-pathologic factors.

RESULTS

CD34/αSMA CAF proportion was significantly related to age in Luminal A (LA), Luminal B (LB), and HER2 subtypes. CD34_CAF influence on survival, invasion, and recurrence of LA, LB-HER2, and TNBC subtypes was found to be significant. The CD34/αSMA-expressing CAFs exhibited a heterogeneous impact on stromal vasculature and TLS.

CONCLUSION

BC stromal CD34_CAFs/αSMA_CAFs have an impact on survival, invasion, and recurrence differently between BC molecular subtypes. The tumor stroma DIA assessment may have predictive potential to prognosis and long-term follow-up of patients with breast cancer.

Utility of Indigenously Developed Square Grid Method for Evaluation of Tumor-Stroma Ratio and Stromal Tumor-Infiltrating Lymphocytes in Invasive Breast Carcinoma: A Pilot Study

Background & Objective

Invasive breast carcinoma (IBC) is the most commonly diagnosed cancer among women in India. The conventional visual method of evaluation of Tumor-Stroma Ratio (TSR) and Stromal Tumor-Infiltrating Lymphocytes (sTIL) appears to be subjective. The present study aims to evaluate the utility of the indigenously designed square grid method for the evaluation of tumor-stroma ratio and stromal tumor-infiltrating lymphocytes in invasive breast carcinoma by assessing the inter-observer variability.

Methods

This was a retrospective study conducted at a rural tertiary care referral institute from July 2018 to June 2020. In each case, microphotographs were taken from 10 representative fields in H&E-stained sections for evaluating TSR in low-power and sTIL in high-power. Both the parameters were evaluated employing an indigenously designed square grid applied onto microphotographs in the power-point slides by making use of principles of the Pythagorean theorem. Both parameters were separately evaluated by two pathologists. Cohen kappa statistics was the statistical tool used to analyze inter-observer variability.

Results

Thirty cases were analyzed. Invasive breast carcinoma of no special type (IBC-NST) was the most common histopathological type (26 cases (86.67%)). For TRS evaluation, a Kappa value of 0.78 suggested substantial agreement with an agreement of 91.67%. For sTIL evaluation, a Kappa value of 0.51 suggested moderate agreement with an agreement of 88.33%. The P-values were statistically highly significant (P<0.001).

Conclusion

Square grid method is a novel technique for evaluating TSR and sTIL in invasive breast carcinoma. It can be considered an example of the application of Pythagoras' theorem in Pathology.

Artificial intelligence: opportunities and challenges in the clinical applications of triple-negative breast cancer

Triple-negative breast cancer (TNBC) accounts for 15-20% of all invasive breast cancer subtypes. Owing to its clinical characteristics, such as the lack of effective therapeutic targets, high invasiveness, and high recurrence rate, TNBC is difficult to treat and has a poor prognosis. Currently, with the accumulation of large amounts of medical data and the development of computing technology, artificial intelligence (AI), particularly machine learning, has been applied to various aspects of TNBC research, including early screening, diagnosis, identification of molecular subtypes, personalised treatment, and prediction of prognosis and treatment response. In this review, we discussed the general principles of artificial intelligence, summarised its main applications in the diagnosis and treatment of TNBC, and provided new ideas and theoretical basis for the clinical diagnosis and treatment of TNBC.

Tumour-stroma ratio (TSR) in breast cancer: comparison of scoring core biopsies versus resection specimens

PURPOSE

Tumour-stroma ratio (TSR) is an important prognostic and predictive factor in several tumour types. The aim of this study is to determine whether TSR evaluated in breast cancer core biopsies is representative of the whole tumour.

METHOD

Different TSR scoring methods, their reproducibility, and the association of TSR with clinicopathological characteristics were investigated in 178 breast carcinoma core biopsies and corresponding resection specimens. TSR was assessed by two trained scientists on the most representative H&E-stained digitised slides. Patients were treated primarily with surgery between 2010 and 2021 at Semmelweis University, Budapest.

RESULTS

Ninety-one percent of the tumours were hormone receptor (HR)-positive (luminal-like). Interobserver agreement was highest using 100 × magnification (κ_core = 0.906, κ_{resection specimen} = 0.882). The agreement between TSR of core biopsies and resection specimens of the same patients was moderate (κ = 0.514). Differences between the two types of samples were most frequent in cases with TSR scores close to the 50% cut-off point. TSR was strongly correlated with age at diagnosis, pT category, histological type, histological grade, and surrogate molecular subtype. A tendency was identified for more recurrences among stroma-high (SH) tumours (p = 0.07). Significant correlation was detected between the TSR and tumour recurrence in grade 1 HR-positive breast cancer cases (p = 0.03).

CONCLUSIONS

TSR is easy to determine and reproducible on both core biopsies and in resection specimens and is associated with several clinicopathological characteristics of breast cancer. TSR scored on core biopsies is moderately representative for the whole tumour.

Tumor-Stroma Ratio in Colorectal Cancer-Comparison between Human Estimation and Automated Assessment

The tumor-stroma ratio (TSR) has been repeatedly shown to be a prognostic factor for survival prediction of different cancer types. However, an objective and reliable determination of the tumor-stroma ratio remains challenging. We present an easily adaptable deep learning model for accurately segmenting tumor regions in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of colon cancer patients into five distinct classes (tumor, stroma, necrosis, mucus, and background). The tumor-stroma ratio can be determined in the presence of necrotic or mucinous areas. We employ a few-shot model, eventually aiming for the easy adaptability of our approach to related segmentation tasks or other primaries, and compare the results to a well-established state-of-the art approach (U-Net). Both models achieve similar results with an overall accuracy of 86.5% and 86.7%, respectively, indicating that the adaptability does not lead to a significant decrease in accuracy. Moreover, we comprehensively compare with TSR estimates of human observers and examine in detail discrepancies and inter-rater reliability. Adding a second survey for segmentation quality on top of a first survey for TSR estimation, we found that TSR estimations of human observers are not as reliable a ground truth as previously thought.

hist2RNA: An Efficient Deep Learning Architecture to Predict Gene Expression from Breast Cancer Histopathology Images

Gene expression can be used to subtype breast cancer with improved prediction of risk of recurrence and treatment responsiveness over that obtained using routine immunohistochemistry (IHC). However, in the clinic, molecular profiling is primarily used for ER+ breast cancer, which is costly, tissue destructive, requires specialised platforms, and takes several weeks to obtain a result. Deep learning algorithms can effectively extract morphological patterns in digital histopathology images to predict molecular phenotypes quickly and cost-effectively. We propose a new, computationally efficient approach called hist2RNA inspired by bulk RNA sequencing techniques to predict the expression of 138 genes (incorporated from 6 commercially available molecular profiling tests), including luminal PAM50 subtype, from hematoxylin and eosin (H&E)-stained whole slide images (WSIs). The training phase involves the aggregation of extracted features for each patient from a pretrained model to predict gene expression at the patient level using annotated H&E images from The Cancer Genome Atlas (TCGA, n = 335). We demonstrate successful gene prediction on a held-out test set (n = 160, corr = 0.82 across patients, corr = 0.29 across genes) and perform exploratory analysis on an external tissue microarray (TMA) dataset (n = 498) with known IHC and survival information. Our model is able to predict gene expression and luminal PAM50 subtype (Luminal A versus Luminal B) on the TMA dataset with prognostic significance for overall survival in univariate analysis (c-index = 0.56, hazard ratio = 2.16 (95% CI 1.12-3.06), p < 5 × 10^-3), and independent significance in multivariate analysis incorporating standard clinicopathological variables (c-index = 0.65, hazard ratio = 1.87 (95% CI 1.30-2.68), p < 5 × 10^-3). The proposed strategy achieves superior performance while requiring less training time, resulting in less energy consumption and computational cost compared to patch-based models. Additionally, hist2RNA predicts gene expression that has potential to determine luminal molecular subtypes which correlates with overall survival, without the need for expensive molecular testing.

Multimodal ultrasound features of breast cancers: correlation with molecular subtypes

OBJECTIVES

To investigate whether multimodal intratumour and peritumour ultrasound features correlate with specific breast cancer molecular subtypes.

METHODS

From March to November 2021, a total of 85 patients with histologically proven breast cancer underwent B-mode, real-time elastography (RTE), colour Doppler flow imaging (CDFI) and contrast-enhanced ultrasound (CEUS). The time intensity curve (TIC) of CEUS was obtained, and the peak and time to peak (TTP) were analysed. Chi-square and binary logistic regression were used to analyse the connection between multimodal ultrasound imaging features and breast cancer molecular subtype.

RESULTS

Among 85 breast cancers, the subtypes were as follows: luminal A (36 cases, 42.4%), luminal B (20 cases, 23.5%), human epidermal growth factor receptor-2 positive (HER2+) (16 cases, 18.8%), and triple negative breast cancer (TNBC) (13 cases, 15.3%). Binary logistic regression models showed that RTE (P < 0.001) and CDFI (P = 0.036) were associated with the luminal A cancer subtype (C-index: 0.741), RTE (P = 0.016) and the peak ratio between intratumour and corpus mamma (P = 0.036) were related to the luminal B cancer subtype (C-index: 0.788). The peak ratio between peritumour and intratumour (P = 0.039) was related to the HER2 + cancer subtype (C-index: 0.859), and CDFI (P = 0.002) was associated with the TNBC subtype (C-index: 0.847).

CONCLUSIONS

Multimodal ultrasound features could be powerful predictors of specific breast cancer molecular subtypes. The intra- and peritumour CEUS features play assignable roles in separating luminal B and HER2 + breast cancer subtypes.

Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer

Although the tumor-stroma ratio (TSR) has prognostic value in many cancers, the traditional semi-quantitative visual assessment method has inter-observer variability, making it impossible for clinical practice. We aimed to develop a machine learning (ML) algorithm for accurately quantifying TSR in hematoxylin-and-eosin (H&E)-stained whole slide images (WSI) and further investigate its prognostic effect in patients with muscle-invasive bladder cancer (MIBC). We used an optimal cell classifier previously built based on QuPath open-source software and ML algorithm for quantitative calculation of TSR. We retrospectively analyzed data from two independent cohorts to verify the prognostic significance of ML-based TSR in MIBC patients. WSIs from 133 MIBC patients were used as the discovery set to identify the optimal association of TSR with patient survival outcomes. Furthermore, we performed validation in an independent external cohort consisting of 261 MIBC patients. We demonstrated a significant prognostic association of ML-based TSR with survival outcomes in MIBC patients (p < 0.001 for all comparisons), with higher TSR associated with better prognosis. Uni- and multivariate Cox regression analyses showed that TSR was independently associated with overall survival (p < 0.001 for all analyses) after adjusting for clinicopathological factors including age, gender, and pathologic stage. TSR was found to be a strong prognostic factor that was not redundant with the existing staging system in different subgroup analyses (p < 0.05 for all analyses). Finally, the expression of six genes (DACH1, DEEND2A, NOTCH4, DTWD1, TAF6L, and MARCHF5) were significantly associated with TSR, revealing possible potential biological relevance. In conclusion, we developed an ML algorithm based on WSIs of MIBC patients to accurately quantify TSR and demonstrated its prognostic validity for MIBC patients in two independent cohorts. This objective quantitative method allows application in clinical practice while reducing the workload of pathologists. Thus, it might be of significant aid in promoting precise pathology services in MIBC.

Efficient quality control of whole slide pathology images with human-in-the-loop training

Histopathology whole slide images (WSIs) are being widely used to develop deep learning-based diagnostic solutions, especially for precision oncology. Most of these diagnostic softwares are vulnerable to biases and impurities in the training and test data which can lead to inaccurate diagnoses. For instance, WSIs contain multiple types of tissue regions, at least some of which might not be relevant to the diagnosis. We introduce HistoROI, a robust yet lightweight deep learning-based classifier to segregate WSI into 6 broad tissue regions-epithelium, stroma, lymphocytes, adipose, artifacts, and miscellaneous. HistoROI is trained using a novel human in-the-loop and active learning paradigm that ensures variations in training data for labeling efficient generalization. HistoROI consistently performs well across multiple organs, despite being trained on only a single dataset, demonstrating strong generalization. Further, we have examined the utility of HistoROI in improving the performance of downstream deep learning-based tasks using the CAMELYON breast cancer lymph node and TCGA lung cancer datasets. For the former dataset, the area under the receiver operating characteristic curve (AUC) for metastasis versus normal tissue of a neural network trained using weakly supervised learning increased from 0.88 to 0.92 by filtering the data using HistoROI. Similarly, the AUC increased from 0.88 to 0.93 for the classification between adenocarcinoma and squamous cell carcinoma on the lung cancer dataset. We also found that the performance of the HistoROI improves upon HistoQC for artifact detection on a test dataset of 93 annotated WSIs. The limitations of the proposed model are analyzed, and potential extensions are also discussed.

Tumor Microenvironment, Radiology, and Artificial Intelligence: Should We Consider Tumor Periphery?

OBJECTIVES

The tumor microenvironment (TME) consists of cellular and noncellular components which enable the tumor to interact with its surroundings and plays an important role in the tumor progression and how the immune system reacts to the malignancy. In the present study, we investigate the diagnostic potential of the TME in differentiating benign and malignant lesions using image quantification and machine learning.

METHODS

A total of 229 breast lesions and 220 cervical lymph nodes were included in the study. A group of expert radiologists first performed medical imaging and segmented the lesions, after which a rectangular mask was drawn, encompassing all of the contouring. The mask was extended in each axis up to 50%, and 29 radiomics features were extracted from each mask. Radiomics features that showed a significant difference in each contour were used to develop a support vector machine (SVM) classifier for benign and malignant lesions in breast and lymph node images separately.

RESULTS

Single radiomics features extracted from extended contours outperformed radiologists' contours in both breast and lymph node lesions. Furthermore, when fed into the SVM model, the extended models also outperformed the radiologist's contour, achieving an area under the receiver operating characteristic curve of 0.887 and 0.970 in differentiating breast and lymph node lesions, respectively.

CONCLUSIONS

Our results provide convincing evidence regarding the importance of the tumor periphery and TME in medical imaging diagnosis. We propose that the immediate tumor periphery should be considered for differentiating benign and malignant lesions in image quantification studies.

Survival prediction in triple negative breast cancer using multiple instance learning of histopathological images

Computational pathology is a rapidly expanding area for research due to the current global transformation of histopathology through the adoption of digital workflows. Survival prediction of breast cancer patients is an important task that currently depends on histopathology assessment of cancer morphological features, immunohistochemical biomarker expression and patient clinical findings. To facilitate the manual process of survival risk prediction, we developed a computational pathology framework for survival prediction using digitally scanned haematoxylin and eosin-stained tissue microarray images of clinically aggressive triple negative breast cancer. Our results show that the model can produce an average concordance index of 0.616. Our model predictions are analysed for independent prognostic significance in univariate analysis (hazard ratio = 3.12, 95% confidence interval [1.69,5.75], p < 0.005) and multivariate analysis using clinicopathological data (hazard ratio = 2.68, 95% confidence interval [1.44,4.99], p < 0.005). Through qualitative analysis of heatmaps generated from our model, an expert pathologist is able to associate tissue features highlighted in the attention heatmaps of high-risk predictions with morphological features associated with more aggressive behaviour such as low levels of tumour infiltrating lymphocytes, stroma rich tissues and high-grade invasive carcinoma, providing explainability of our method for triple negative breast cancer.

From Immunohistochemistry to New Digital Ecosystems: A State-of-the-Art Biomarker Review for Precision Breast Cancer Medicine

Simple Summary

In this state-of-the-art breast biomarker review, we have tried to imagine and illustrate future, emerging digital breast cancer ecosystems which allow for greater incorporation of traditional immunohistochemical and molecular biomarkers, WSI, and radiomic features.

Abstract

Breast cancers represent complex ecosystem-like networks of malignant cells and their associated microenvironment. Estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) are biomarkers ubiquitous to clinical practice in evaluating prognosis and predicting response to therapy. Recent feats in breast cancer have led to a new digital era, and advanced clinical trials have resulted in a growing number of personalized therapies with corresponding biomarkers. In this state-of-the-art review, we included the latest 10-year updated recommendations for ER, PR, and HER2, along with the most salient information on tumor-infiltrating lymphocytes (TILs), Ki-67, PD-L1, and several prognostic/predictive biomarkers at genomic, transcriptomic, and proteomic levels recently developed for selection and optimization of breast cancer treatment. Looking forward, the multi-omic landscape of the tumor ecosystem could be integrated with computational findings from whole slide images and radiomics in predictive machine learning (ML) models. These are new digital ecosystems on the road to precision breast cancer medicine.

Digital image analysis provides robust tissue microenvironment-based prognosticators in stage I-IV colorectal cancer patients

AIMS

In colorectal cancer (CRC) patients, a promising marker is tumor-stroma ratio (TSR). Quantification issues highlight the importance of precise assessment that might be solved by artificial intelligence (AI)-based digital image analysis systems. Some alternatives have been offered so far, although these platforms are either proprietary developments or require additional programming skills. Our aim was to validate a user-friendly, commercially available software running in everyday computational environment to improve TSR assessment and also to compare the prognostic value of assessing TSR in three distinct regions of interests (ROIs), like hotspot, invasive front and whole tumor. Furthermore, we compared the prognostic power of TSR with newly suggested carcinoma percentage (CP) and carcinoma-stroma percentage (CSP).

METHODS AND RESULTS

Slides of 185 stage I-IV CRC patients with clinical follow up data were scanned and evaluated by a senior pathologist. A machine learning-based digital pathology software was trained to recognize tumoral and stromal compartments. The aforementioned parameters were evaluated in the hotspot, invasive front and whole tumor area, both visually and by machine learning. Patients were classified based on TSR, CP and CSP values. On multivariate analysis, TSR-hotspot was found to be an independent prognostic factor of overall survival (hazard ratio for TSR-hotspot_software: 2.005 (95% confidence interval (CI): 1.146-3.507), p=0.011, for TSR-hostpot_visual: 1.781 (CI: 1.060-2.992) p=0.029). Also, TSR was an independent predictor for distant metastasis and local relapse in most settings. Generally, software performance was comparable to visual evaluation and delivered reliable prognostication in more settings also with CP and CSP values.

CONCLUSIONS

This study presents that software assisted evaluation is a robust prognosticator. Our approach used a less sophisticated and thus easily accessible software without the aid of convolutional neural network; however, it was still effective enough to deliver reliable prognostic information.

Proposal of an automated tumor-stromal ratio assessment algorithm and a nomogram for prognosis in early-stage invasive breast cancer

BACKGROUND

The tumor-stromal ratio (TSR) has been verified to be a prognostic factor in many solid tumors. In most studies, it was manually assessed on routinely stained H&E slides. This study aimed to assess the TSR using image analysis algorithms developed by the Qupath software, and integrate the TSR into a nomogram for prediction of the survival in invasive breast cancer (BC) patients.

METHODS

A modified TSR assessment algorithm based on the recognition of tumor and stroma tissues was developed using the Qupath software. The TSR of 234 invasive BC specimens in H&E-stained tissue microarrays (TMAs) were assessed with the algorithm and categorized as stroma-low or stroma-high. The consistency of TSR estimation between Qupath prediction and pathologist annotation was analyzed. Univariable and multivariable analyses were applied to select potential risk factors and a nomogram for predicting survival in invasive BC patients was constructed and validated. An extra TMA containing 110 specimens was obtained to validate the conclusion as an independent cohort.

RESULTS

In the discovery cohort, stroma-low and stroma-high were identified in 43.6% and 56.4% cases, respectively. Good concordance was observed between the pathologist annotated and Qupath predicted TSR. The Kaplan-Meier curve showed that stroma-high patients were associated with worse 5-DFS compared to stroma-low patients (p = 0.007). Multivariable analysis identified age, T stage, N status, histological grade, ER status, HER-2 gene, and TSR as potential risk predictors, which were included in the nomogram. The nomogram was well calibrated and showed a favorable predictive value for the recurrence of BC. Kaplan-Meier curves showed that the nomogram had a better risk stratification capability than the TNM staging system. In the external validation of the nomogram, the results were further validated.

CONCLUSIONS

Based on H&E-stained TMAs, this study successfully developed image analysis algorithms for TSR assessment and constructed a nomogram for predicting survival in invasive BC.

Protein expression of the gp78 E3-ligase predicts poor breast cancer outcome based on race

Women of African ancestry suffer higher rates of breast cancer mortality compared to all other groups in the United States. Though the precise reasons for these disparities remain unclear, many recent studies have implicated a role for differences in tumor biology. Using an epitope-validated antibody against the endoplasmic reticulum-associated degradation (ERAD) E3 ubiquitin ligase, gp78, we show that elevated levels of gp78 in patient breast cancer cells predict poor survival. Moreover, high levels of gp78 are associated with poor outcomes in both ER-positive and ER-negative tumors, and breast cancers expressing elevated amounts of gp78 protein are enriched in gene expression pathways that influence cell cycle, metabolism, receptor-mediated signaling, and cell stress response pathways. In multivariate analysis adjusted for subtype and grade, gp78 protein is an independent predictor of poor outcomes in women of African ancestry. Furthermore, gene expression signatures, derived from patients stratified by gp78 protein expression, are strong predictors of recurrence and pathological complete response in retrospective clinical trial data and share many common features with gene sets previously identified to be overrepresented in breast cancers based on race. These findings implicate a prominent role for gp78 in tumor progression and offer new insights into our understanding of racial differences in breast cancer outcomes.

Standardization of the tumor-stroma ratio scoring method for breast cancer research

Purpose

The tumor-stroma ratio (TSR) has repeatedly proven to be correlated with patient outcomes in breast cancer using large retrospective cohorts. However, studies validating the TSR often show variability in methodology, thereby hampering comparisons and uniform outcomes.

Method

This paper provides a detailed description of a simple and uniform TSR scoring method using Hematoxylin and Eosin (H&E)-stained core biopsies and resection tissue, specifically focused on breast cancer. Possible histological challenges that can be encountered during scoring including suggestions to overcome them are reported. Moreover, the procedure for TSR estimation in lymph nodes, scoring on digital images and the automatic assessment of the TSR using artificial intelligence are described.

Conclusion

Digitized scoring of tumor biopsies and resection material offers interesting future perspectives to determine patient prognosis and response to therapy. The fact that the TSR method is relatively easy, quick, and cheap, offers great potential for its implementation in routine diagnostics, but this requires high quality validation studies.

3D-bioprinted cancer-on-a-chip: level-up organotypic in vitro models

Combinatorial conjugation of organ-on-a-chip platforms with additive manufacturing technologies is rapidly emerging as a disruptive approach for upgrading cancer-on-a-chip systems towards anatomic-sized dynamic in vitro models. This valuable technological synergy has potential for giving rise to truly physiomimetic 3D models that better emulate tumor microenvironment elements, bioarchitecture, and response to multidimensional flow dynamics. Herein, we showcase the most recent advances in bioengineering 3D-bioprinted cancer-on-a-chip platforms and provide a comprehensive discussion on design guidelines and possibilities for high-throughput analysis. Such hybrid platforms represent a new generation of highly sophisticated 3D tumor models with improved biomimicry and predictability of therapeutics performance.

Combinatory statuses of tumor stromal percentage and tumor infiltrating lymphocytes as prognostic factors in stage III colorectal cancers

BACKGROUND AND AIM

Tumor stroma and tumor-infiltrating lymphocytes (TILs) are major constituents of the tumor microenvironment, although they have different effects on the prognosis of patients with colorectal cancer (CRC). Combinatory statuses of tumor-stromal percentage (TSP) and TILs are expected to provide more powerful prognostic information but have never been studied in CRCs.

METHODS

Stage III CRCs from patients (n = 487) treated with adjuvant chemotherapy were assessed for their TSP and CD3-TIL or CD8-TIL densities using computer-aided methodology. With cut-off values set at median values for intraepithelial TIL (iTIL) and stromal TIL (sTIL) densities, CRCs were sorted into low and high iTIL or sTIL groups. CRCs were classified into five quintile (Q1-Q5) groups according to their TSP and divided into high TSP (Q5) and low TSP (Q1-4) groups.

RESULTS

The combination of CD8 iTIL density and TSP was found to be an independent prognostic parameter in multivariate survival analysis in terms of cancer-specific survival and recurrence-free survival. CRCs with low CD8 iTIL density and high TSP showed the worst survival. The combinatory status showed more prognostic power than CD8 iTIL density or TSP alone. Multivariate survival analysis in an independent cohort of stage III CRC validated the prognostic power of the combinatory statuses.

CONCLUSIONS

The findings suggest that the combinatory status might serve as a prognostic parameter in stage III CRCs. Further research in a large-scale cohort of patients with stage III CRC is needed to validate the prognostic power of the combinatory status.

A Novel Superpixel Approach to the Tumoral Microenvironment in Colorectal Cancer

Colorectal cancer (CRC) is the most common malignancy of the gastrointestinal tract. The stroma and the tumoral microenvironment (TME) represent ecosystem-like biological networks and are new frontiers in CRC. The present study demonstrates the use of a novel machine learning-based superpixel approach for whole slide images to unravel this biology. Findings of significance include the association of low proportionated stromal area, high immature stromal percentage, and high myxoid stromal ratio (MSR) with worse prognostic outcomes in CRC. Overall, stromal computational markers outperformed all others at predicting clinical outcomes. MSR may be able to prognosticate patients independent of pathological stage, representing an optimal way to effectively prognosticate CRC patients which circumvents the need for more extensive molecular and/or computational profiling. The superpixel approaches to the TME demonstrated here can be performed by a trained pathologist and recorded during synoptic cancer reporting with appropriate quality assurance. Future clinical trials will have the ultimate say in determining whether we can better tailor the need for adjuvant therapy in patients with CRC.

Breast cancer-specific mortality in early breast cancer as defined by high-risk clinical and pathologic characteristics

OBJECTIVES

To investigate breast cancer-specific mortality by early breast cancer (EBC; Stages I-IIIC) subtype; incidence of high-risk indicators for recurrence (defined in monarchE trial); and mortality risk difference by those who did/did not meet these criteria.

MATERIALS AND METHODS

Analyses included patients with initial EBC diagnosis between 2010-2015 from Surveillance, Epidemiology, and End Results (SEER) data (n = 342,149). Cox proportional hazards models and Kaplan-Meier estimates examined mortality among 228,031 patients, by subtype (hormone receptor [HR]-positive [+], human epidermal growth factor receptor-2 [HER2] negative [-]; triple negative [TNBC]; HR+, HER2+; HR-, HER2+). Incidence and mortality among patients who did/did not meet monarchE clinicopathological high-risk criteria were examined.

RESULTS

Among patients with HR+, HER2- EBC, histologic Grade 3 (vs. Grade 1) was the most influential factor on mortality (hazard ratio, 3.61; 95%CI, 3.27, 3.98). Among patients with TNBC, ≥4 ipsilateral axillary positive nodes (vs. node negative) was the most influential factor on mortality (hazard ratio, 3.46; 95%CI, 2.87, 4.17). For patients with HR-, HER2+ or HR+, HER2+ EBC, tumor size ≥5 cm (vs. <1 cm) and ≥4 ipsilateral axillary positive nodes were the most influential factors on mortality. The 60-month mortality rate for the 12% of patients within the HR+, HER2- EBC group meeting monarchE clinicopathological high-risk criteria was 16.5%, versus 7.0% (Stage II-III and node positive) and 2.8% (Stage I or node negative) for those not meeting criteria. The 60-month mortality rate for patients with TNBC was 18.5%.

CONCLUSION

Mortality risk and the relative importance of risk factors varied by subtype. monarchE clinicopathological high-risk criteria were associated with increased mortality risk among patients with HR+, HER2- EBC. Patients with HR+, HER2- EBC, and monarchE clinicopathological high-risk criteria experienced risk of mortality similar to patients with early TNBC. These data highlight a high unmet need in this select patient population who may benefit most from therapy escalation.

The Prognostic Role of Intratumoral Stromal Content in Lobular Breast Cancer

Simple Summary

High intratumoral stromal content is related to worse outcomes in several types of cancer. However, its prognostic role in breast cancer seems to differ between different subtypes. High intratumoral stromal content is a negative prognostic marker in triple-negative breast cancer, while the opposite is the case for estrogen-receptor-positive breast cancer, in which higher stromal content is indicative of a better prognosis. Most lobular breast cancers are estrogen-receptor-positive, and the tumor tissue has a clearly defined histological appearance, often with a high intratumoral stromal content. To date, the prognostic role of intratumoral stromal content in lobular breast cancer remains unclear. In this study, we aimed to investigate the prognostic importance of intratumoral stromal content in estrogen-receptor-positive lobular breast cancer. Our results show that high intratumoral stromal content is an easily assessed and clinically useful indicator of a good prognosis in lobular breast cancer.

Abstract

Previous studies have shown that high intratumoral stromal content is associated with a worse prognosis in breast cancer, especially in the triple-negative subtype. However, contradictory results have been reported for estrogen-receptor-positive (ER+) breast cancer, indicating that the prognostic role of intratumoral stromal content may be subtype-dependent. In this study, we investigated the importance of intratumoral stromal content for breast cancer-specific mortality (BCM) in a well-defined subgroup (n = 182) of ER+/human-epidermal growth-factor-receptor-2 negative (HER2−) invasive lobular breast cancer (ILC). The intratumoral stromal content was assessed on hematoxylin–eosin-stained whole sections and graded into high stroma (>50%) or low stroma (≤50%). A total of 82 (45%) patients had high-stroma tumors, and 100 (55%) had low-stroma tumors. High-stroma tumors were associated with a lower Nottingham histological grade, low Ki67, and a luminal A-like subtype. After a 10-year follow-up, the patients with high-stroma tumors had a lower BCM (HR: 0.43, 95% CI: 0.21–0.89, p = 0.023) in univariable analysis. Essentially the same effect was found in both the multivariable analysis (10-year follow-up) and univariable analysis (25-year follow-up), but these findings were not strictly significant. In ER+/HER2− ILC, high intratumoral stromal content is an easily assessable histological indicator of a good prognosis.

Prognostic Efficacy of Tumor-Stroma Ratio in Women With Breast Cancer: A Meta-Analysis of Cohort Studies

Background

Tumor-stroma ratio (TSR) has been suggested as an emerging prognostic predictor in women with breast cancer. However, previous studies evaluating the association between TSR and survival in women with breast cancer showed inconsistent results. We performed a meta-analysis to systematically evaluate the possible prognostic role of TSR in breast cancer.

Methods

Relevant cohort studies were obtained via search of PubMed, Embase, and Web of Science databases. A random-effects model, which incorporated the potential heterogeneity, was used to pool the results.

Results

Twelve cohort studies with 6175 patients were included. Nine of the 12 studies used 50% as the cutoff to divide the patients into those with stroma-rich (low TSR) and stroma-poor (high TSR) tumors. Pooled results showed that compared women with stroma-poor tumor, those with stroma-rich tumor were associated with worse survival outcomes (disease-free survival [DFS]: hazard ratio [HR] = 1.56, 95% confidence interval [CI]: 1.32 to 1.85, P < 0.001; overall survival [OS]: HR = 1.67, 95% CI: 1.46 to 1.91, P < 0.001; and cancer-specific survival [CSS]: HR = 1.75, 95% CI: 1.40 to 2.20, P < 0.001). Analysis limited to women with triple-negative breast cancer (TNBC) showed consistent results (DFS: HR: 2.07, 95% CI: 1.59 to 2.71, P < 0.001; OS: HR: 2.04, 95% CI: 1.52 to 2.73, P < 0.001; and CSS: HR: 2.40, 95% CI: 1.52 to 3.78, P < 0.001).

Conclusions

Current evidence from retrospective studies supports that tumor TSR is a prognostic predictor or poor survival in women with breast cancer.

CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma

Purpose

To develop and validate a machine learning classifier based on multidetector computed tomography (MDCT), for the preoperative prediction of tumor-stroma ratio (TSR) expression in patients with pancreatic ductal adenocarcinoma (PDAC).

Materials and Methods

In this retrospective study, 227 patients with PDAC underwent an MDCT scan and surgical resection. We quantified the TSR by using hematoxylin and eosin staining and extracted 1409 arterial and portal venous phase radiomics features for each patient, respectively. Moreover, we used the least absolute shrinkage and selection operator logistic regression algorithm to reduce the features. The extreme gradient boosting (XGBoost) was developed using a training set consisting of 167 consecutive patients, admitted between December 2016 and December 2017. The model was validated in 60 consecutive patients, admitted between January 2018 and April 2018. We determined the XGBoost classifier performance based on its discriminative ability, calibration, and clinical utility.

Results

We observed low and high TSR in 91 (40.09%) and 136 (59.91%) patients, respectively. A log-rank test revealed significantly longer survival for patients in the TSR-low group than those in the TSR-high group. The prediction model revealed good discrimination in the training (area under the curve [AUC]= 0.93) and moderate discrimination in the validation set (AUC= 0.63). While the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the training set were 94.06%, 81.82%, 0.89, 0.89, and 0.90, respectively, those for the validation set were 85.71%, 48.00%, 0.70, 0.70, and 0.71, respectively.

Conclusions

The CT radiomics-based XGBoost classifier provides a potentially valuable noninvasive tool to predict TSR in patients with PDAC and optimize risk stratification.

Multiplexed immunofluorescence identifies high stromal CD68+PD-L1+ macrophages as a predictor of improved survival in triple negative breast cancer

Triple negative breast cancer (TNBC) comprises 10-15% of all breast cancers and has a poor prognosis with a high risk of recurrence within 5 years. PD-L1 is an important biomarker for patient selection for immunotherapy but its cellular expression and co-localization within the tumour immune microenvironment and associated prognostic value is not well defined. We aimed to characterise the phenotypes of immune cells expressing PD-L1 and determine their association with overall survival (OS) and breast cancer-specific survival (BCSS). Using tissue microarrays from a retrospective cohort of TNBC patients from St George Hospital, Sydney (n = 244), multiplexed immunofluorescence (mIF) was used to assess staining for CD3, CD8, CD20, CD68, PD-1, PD-L1, FOXP3 and pan-cytokeratin on the Vectra Polaris™ platform and analysed using QuPath. Cox multivariate analyses showed high CD68+PD-L1+ stromal cell counts were associated with improved prognosis for OS (HR 0.56, 95% CI 0.33-0.95, p = 0.030) and BCSS (HR 0.47, 95% CI 0.25-0.88, p = 0.018) in the whole cohort and in patients receiving chemotherapy, improving incrementally upon the predictive value of PD-L1+ alone for BCSS. These data suggest that CD68+PD-L1+ status can provide clinically useful prognostic information to identify sub-groups of patients with good or poor prognosis and guide treatment decisions in TNBC.

Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast Cancers

Triple-negative breast cancer (TNBC) is an aggressive and difficult-to-treat cancer type that represents approximately 15% of all breast cancers. Recently, stromal tumor-infiltrating lymphocytes (sTIL) resurfaced as a strong prognostic biomarker for overall survival (OS) for TNBC patients. Manual assessment has innate limitations that hinder clinical adoption, and the International Immuno-Oncology Biomarker Working Group (TIL-WG) has therefore envisioned that computational assessment of sTIL could overcome these limitations and recommended that any algorithm should follow the manual guidelines where appropriate. However, no existing studies capture all the concepts of the guideline or have shown the same prognostic evidence as manual assessment. In this study, we present a fully automated digital image analysis pipeline and demonstrate that our hematoxylin and eosin (H&E)-based pipeline can provide a quantitative and interpretable score that correlates with the manual pathologist-derived sTIL status, and importantly, can stratify a retrospective cohort into two significant distinct prognostic groups. We found our score to be prognostic for OS (HR: 0.81 CI: 0.72-0.92 p = 0.001) independent of age, tumor size, nodal status, and tumor type in statistical modeling. While prior studies have followed fragments of the TIL-WG guideline, our approach is the first to follow all complex aspects, where appropriate, supporting the TIL-WG vision of computational assessment of sTIL in the future clinical setting.

Rapid multi-dynamic algorithm for gray image analysis of the stroma percentage on colorectal cancer

Background: Tumor stroma percentage (TSP), as an independent, low-cost prognostic factor, could complement current pathology and act as a more feasible risk factor for prognosis. However, TSP hadn't been applied into TNM staging. Here, the objective of our study was to investigate the prognostic significance of TSP in a robust rapid multi-dynamic approach with the application of MATLAB and threshold Algorithm for Gray Image analysis.

Methods: Using a retrospective collection of 1539 CRC patients comprising three independent cohorts; one SGH cohort (N=996) and two validation cohorts (N =106, N= 437) from 2 institutions. We investigated 996 CRC of no special type. According to our established thresholds, 357 cases (35.84%) were classified as TSP-high and 639 cases (64.16%) as TSP-low. We determined the gray image area as the stromal part of the WSI and calculated the stroma percentage with our proposed method on MATLAB software.

Results: In both TSP-cad(50%) and TSP-cad(median), multivariate analysis showed the TSP-cad was an independent prognostic factor for the vessel invasion and tumor location. For OS, TSP-manual HR=1.512 (95% CI 1.045-2.187); TSP-cad HR=1.443 (95% CI 0.993-2.097) and TSP-cad(median) HR=1.632 (95% CI 1.105-2.410). Fortunately, TSP-manual and TSP-cad were also found independent prognostic factor in all the cohorts. It was found that TSP-cad had slightly higher HR and wider CI than TSP-manual.

Conclusions: Our research showed that TSP was an independent prognostic factor in CRC. Moreover, threshold algorithm for the quantitation of TSP could be established. In conclusion, with this Rapid multi-dynamic threshold Algorithm for Gray Image counting of TSP, which showed a higher accuracy than manual evaluation by pathologists and could be a practical method for CRC to guide clinical decision making.