Transcriptional intra-tumour heterogeneity predicted by deep learning in routine breast histopathology slides provides independent prognostic information

DCE-MRI based deep learning analysis of intratumoral subregion for predicting Ki-67 expression level in breast cancer

OBJECTIVE

To evaluate whether deep learning (DL) analysis of intratumor subregion based on dynamic contrast-enhanced MRI (DCE-MRI) can help predict Ki-67 expression level in breast cancer.

MATERIALS AND METHODS

A total of 290 breast cancer patients from two hospitals were retrospectively collected. A k-means clustering algorithm confirmed subregions of tumor. DL features of whole tumor and subregions were extracted from DCE-MRI images based on 3D ResNet18 pre-trained model. The logistic regression model was constructed after dimension reduction. Model performance was assessed using the area under the curve (AUC), and clinical value was demonstrated through decision curve analysis (DCA).

RESULTS

The k-means clustering method clustered the tumor into two subregions (habitat 1 and habitat 2) based on voxel values. Both the habitat 1 model (validation set: AUC = 0.771, 95 %CI: 0.642-0.900 and external test set: AUC = 0.794, 95 %CI: 0.696-0.891) and the habitat 2 model (AUC = 0.734, 95 %CI: 0.605-0.862 and AUC = 0.756, 95 %CI: 0.646-0.866) showed better predictive capabilities for Ki-67 expression level than the whole tumor model (AUC = 0.686, 95 %CI: 0.550-0.823 and AUC = 0.680, 95 %CI: 0.555-0.804). The combined model based on the two subregions further enhanced the predictive capability (AUC = 0.808, 95 %CI: 0.696-0.921 and AUC = 0.842, 95 %CI: 0.758-0.926), and it demonstrated higher clinical value than other models in DCA.

CONCLUSIONS

The deep learning model derived from subregion of tumor showed better performance for predicting Ki-67 expression level in breast cancer patients. Additionally, the model that integrated two subregions further enhanced the predictive performance.

A large histological images dataset of gastric cancer with tumour microenvironment annotation for AI

Gastric cancer (GC) is the third leading cause of cancer death worldwide. Its clinical course varies considerably due to the highly heterogeneous tumour microenvironment (TME). Decomposing the complex TME from histological images into its constituent parts is crucial for evaluating its patterns and enhancing GC therapies. Although various deep learning methods were developed in medical field, their applications on this task are hindered by the lack of well-annotated histological images of GC. Through this work, we seek to provide a large database of histological images of GC completely annotated for 8 tissue classes in TME. The dataset consists of nearly 31 K histological images from 300 whole slide images. Additionally, we explained two deep learning models used as validation examples using this dataset.

Prediction of gene expression-based breast cancer proliferation scores from histopathology whole slide images using deep learning

BACKGROUND

In breast cancer, several gene expression assays have been developed to provide a more personalised treatment. This study focuses on the prediction of two molecular proliferation signatures: an 11-gene proliferation score and the MKI67 proliferation marker gene. The aim was to assess whether these could be predicted from digital whole slide images (WSIs) using deep learning models.

METHODS

WSIs and RNA-sequencing data from 819 invasive breast cancer patients were included for training, and models were evaluated on an internal test set of 172 cases as well as on 997 cases from a fully independent external test set. Two deep Convolutional Neural Network (CNN) models were optimised using WSIs and gene expression readouts from RNA-sequencing data of either the proliferation signature or the proliferation marker, and assessed using Spearman correlation (r). Prognostic performance was assessed through Cox proportional hazard modelling, estimating hazard ratios (HR).

RESULTS

Optimised CNNs successfully predicted the proliferation score and proliferation marker on the unseen internal test set (ρ = 0.691(p < 0.001) with R2 = 0.438, and ρ = 0.564 (p < 0.001) with R2 = 0.251 respectively) and on the external test set (ρ = 0.502 (p < 0.001) with R2 = 0.319, and ρ = 0.403 (p < 0.001) with R2 = 0.222 respectively). Patients with a high proliferation score or marker were significantly associated with a higher risk of recurrence or death in the external test set (HR = 1.65 (95% CI: 1.05-2.61) and HR = 1.84 (95% CI: 1.17-2.89), respectively).

CONCLUSIONS

The results from this study suggest that gene expression levels of proliferation scores can be predicted directly from breast cancer morphology in WSIs using CNNs and that the predictions provide prognostic information that could be used in research as well as in the clinical setting.

Characterization of Breast Cancer Intra-Tumor Heterogeneity Using Artificial Intelligence

Intra-tumor heterogeneity (ITH) is a fundamental characteristic of breast cancer (BC), influencing tumor progression, prognosis, and therapeutic responses. However, the complexity of ITH in BC makes its accurate characterization challenging. This study leverages deep learning (DL) techniques to comprehensively evaluate ITH in early-stage luminal BC and provide a nuanced understanding of its impact on tumor behavior and patient outcomes. A large cohort (n = 2561) of early-stage luminal BC was evaluated using whole slide images (WSIs) of hematoxylin and eosin-stained slides of excision specimens. Morphological features of both the tumor and stromal components were meticulously annotated by a panel of pathologists in a subset of cases. A DL model was applied to develop an algorithm to assess the degree of heterogeneity of various morphological features per individual case utilizing defined patches. The results of extracted features were used to generate an overall heterogeneity score that was correlated with the clinicopathological features and outcome. Overall, 162 features were quantified and a significant positive correlation between these features was identified. Specifically, there was a significant association between a high degree of intra-tumor heterogeneity and larger tumor size, poorly differentiated tumors, highly proliferative tumors, tumors of no special type (NST), and those with low estrogen receptor (ER) expression. When all features are considered in combination, a high overall heterogeneity score was significantly associated with parameters characteristic of aggressive tumor behavior, and it was an independent predictor of poor patient outcome. In conclusion, DL models can be used to accurately decipher the complexity of ITH and provide extra information for outcome prediction.

Construction of a combined prognostic model for pancreatic ductal adenocarcinoma based on deep learning and digital pathology images

BACKGROUND

Deep learning has made significant advancements in the field of digital pathology, and the integration of multiple models has further improved accuracy. In this study, we aimed to construct a combined prognostic model using deep learning-extracted features from digital pathology images of pancreatic ductal adenocarcinoma (PDAC) alongside clinical predictive indicators and to explore its prognostic value.

METHODS

A retrospective analysis was conducted on 142 postoperative pathologically confirmed PDAC cases. These cases were divided into training (n = 114) and testing sets (n = 28) at an 8:2 ratio. Tumor whole-slide imaging features were extracted and screened to construct a pathological risk model based on a pre-trained deep learning model. Clinical and pathological data from the training set were used to select independent predictive factors for PDAC and establish a clinical risk model using LASSO, univariate, and multivariate Cox regression analyses. Based on the pathological and clinical risk models, a combined model was developed. The Harrell concordance index (C-index) was computed to assess the predictive performance of each model for PDAC survival prognosis.

RESULTS

For the training and testing sets, the C-index values for the clinical risk model were 0.76 and 0.75, respectively; for the pathological risk model, they were 0.82 and 0.73, respectively; and for the combined model, they were 0.86 and 0.77, respectively. The combined model exhibited appropriate calibration at 1-, 3-, and 5-year time points, as well as a superior area under the curve of the receiver operating characteristic curve and clinical net benefit compared to the single models.

CONCLUSIONS

Integrating the pathological and clinical risk models may provide a higher predictive value for survival prognosis.

Clinical evaluation of deep learning-based risk profiling in breast cancer histopathology and comparison to an established multigene assay

PURPOSE

To evaluate the Stratipath Breast tool for image-based risk profiling and compare it with an established prognostic multigene assay for risk profiling in a real-world case series of estrogen receptor (ER)-positive and human epidermal growth factor receptor 2 (HER2)-negative early breast cancer patients categorized as intermediate risk based on classic clinicopathological variables and eligible for chemotherapy.

METHODS

In a case series comprising 234 invasive ER-positive/HER2-negative tumors, clinicopathological data including Prosigna results and corresponding HE-stained tissue slides were retrieved. The digitized HE slides were analysed by Stratipath Breast.

RESULTS

Our findings showed that the Stratipath Breast analysis identified 49.6% of the clinically intermediate tumors as low risk and 50.4% as high risk. The Prosigna assay classified 32.5%, 47.0% and 20.5% tumors as low, intermediate and high risk, respectively. Among Prosigna intermediate-risk tumors, 47.3% were stratified as Stratipath low risk and 52.7% as high risk. In addition, 89.7% of Stratipath low-risk cases were classified as Prosigna low/intermediate risk. The overall agreement between the two tests for low-risk and high-risk groups (N = 124) was 71.0%, with a Cohen's kappa of 0.42. For both risk profiling tests, grade and Ki67 differed significantly between risk groups.

CONCLUSION

The results from this clinical evaluation of image-based risk stratification shows a considerable agreement to an established gene expression assay in routine breast pathology.

Deep learning-based risk stratification of preoperative breast biopsies using digital whole slide images

BACKGROUND

Nottingham histological grade (NHG) is a well established prognostic factor in breast cancer histopathology but has a high inter-assessor variability with many tumours being classified as intermediate grade, NHG2. Here, we evaluate if DeepGrade, a previously developed model for risk stratification of resected tumour specimens, could be applied to risk-stratify tumour biopsy specimens.

METHODS

A total of 11,955,755 tiles from 1169 whole slide images of preoperative biopsies from 896 patients diagnosed with breast cancer in Stockholm, Sweden, were included. DeepGrade, a deep convolutional neural network model, was applied for the prediction of low- and high-risk tumours. It was evaluated against clinically assigned grades NHG1 and NHG3 on the biopsy specimen but also against the grades assigned to the corresponding resection specimen using area under the operating curve (AUC). The prognostic value of the DeepGrade model in the biopsy setting was evaluated using time-to-event analysis.

RESULTS

Based on preoperative biopsy images, the DeepGrade model predicted resected tumour cases of clinical grades NHG1 and NHG3 with an AUC of 0.908 (95% CI: 0.88; 0.93). Furthermore, out of the 432 resected clinically-assigned NHG2 tumours, 281 (65%) were classified as DeepGrade-low and 151 (35%) as DeepGrade-high. Using a multivariable Cox proportional hazards model the hazard ratio between DeepGrade low- and high-risk groups was estimated as 2.01 (95% CI: 1.06; 3.79).

CONCLUSIONS

DeepGrade provided prediction of tumour grades NHG1 and NHG3 on the resection specimen using only the biopsy specimen. The results demonstrate that the DeepGrade model can provide decision support to identify high-risk tumours based on preoperative biopsies, thus improving early treatment decisions.

Cost-effective prognostic evaluation of breast cancer: using a STAR nomogram model based on routine blood tests

Background

Breast cancer (BC) is the most common and prominent deadly disease among women. Predicting BC survival mainly relies on TNM staging, molecular profiling and imaging, hampered by subjectivity and expenses. This study aimed to establish an economical and reliable model using the most common preoperative routine blood tests (RT) data for survival and surveillance strategy management.

Methods

We examined 2863 BC patients, dividing them into training and validation cohorts (7:3). We collected demographic features, pathomics characteristics and preoperative 24-item RT data. BC risk factors were identified through Cox regression, and a predictive nomogram was established. Its performance was assessed using C-index, area under curves (AUC), calibration curve and decision curve analysis. Kaplan-Meier curves stratified patients into different risk groups. We further compared the STAR model (utilizing HE and RT methodologies) with alternative nomograms grounded in molecular profiling (employing second-generation short-read sequencing methodologies) and imaging (utilizing PET-CT methodologies).

Results

The STAR nomogram, incorporating subtype, TNM stage, age and preoperative RT data (LYM, LYM%, EOSO%, RDW-SD, P-LCR), achieved a C-index of 0.828 in the training cohort and impressive AUCs (0.847, 0.823 and 0.780) for 3-, 5- and 7-year OS rates, outperforming other nomograms. The validation cohort showed similar impressive results. The nomogram calculates a patient's total score by assigning values to each risk factor, higher scores indicating a poor prognosis. STAR promises potential cost savings by enabling less intensive surveillance in around 90% of BC patients. Compared to nomograms based on molecular profiling and imaging, STAR presents a more cost-effective, with potential savings of approximately $700-800 per breast cancer patient.

Conclusion

Combining appropriate RT parameters, STAR nomogram could help in the detection of patient anemia, coagulation function, inflammation and immune status. Practical implementation of the STAR nomogram in a clinical setting is feasible, and its potential clinical impact lies in its ability to provide an early, economical and reliable tool for survival prediction and surveillance strategy management. However, our model still has limitations and requires external data validation. In subsequent studies, we plan to mitigate the potential impact on model robustness by further updating and adjusting the data and model.