Integration of clinical features and deep learning on pathology for the prediction of breast cancer recurrence assays and risk of recurrence

Prediction of one-year recurrence among breast cancer patients undergone surgery using artificial intelligence-based algorithms: a retrospective study on prognostic factors

BACKGROUND AND AIM

Breast cancer is highly prevalent, with an increasing trend in women globally. Although the survival of breast cancer is relatively high, the recurrence rate is also high, demanding effective predictive solutions to breast cancer prognosis among post-operative patients. So far, Artificial intelligence algorithms integrated with various clinical data have demonstrated potential predictive capability regarding breast cancer recurrence.

OBJECTIVE

This study aims to specifically conduct a predictive analysis of one-year recurrence of breast cancer by comparing and analyzing different machine learning and deep learning algorithms trained by structural prognostic data.

MATERIALS AND METHODS

This retrospective study was carried out using one database, including 1156 post-operative breast cancer data from 30 January 2020 to 30 December 2022, in three clinical centers in Tehran City. The inclusion criteria were patients who had undergone at least one surgery, had at least one year of medical records, and did not have other conditions. The patients who were diagnosed with malignant BC and had undergone adjuvant therapies without surgery were excluded from the study. Twenty-three prognostic factors were utilized to train algorithms to establish prediction models for the one-year recurrence of breast cancer. The data were analyzed using univariate and adjusted correlation-based methods and chosen machine learning and deep learning algorithms. The discrimination, calibration, and clinical utility were leveraged to assess the algorithms' performance efficiency. The SHapley Additive exPlanations plot was generated to identify the prominent prognostic factors affecting the one-year recurrence of breast cancer.

RESULTS

Totally, 445 relapsed and 711 non-relapsed cases were utilized in this study. Our empirical study showed that the random forest with a positive predictive value of 0.96, negative predictive value of 0.92, sensitivity of 0.92, specificity of 0.96, accuracy of 0.94, F-score of 0.94, area under the receiver operator characteristics curve of 0.919 was the best-performing model for predicting the breast cancer recurrence. As the analysis of SHapley Additive exPlanations indicated, the tumor grade, HER-2, and the number of lymph nodes involved were more significant predictors.

CONCLUSION

The current study demonstrated the potential predictive power of the random forest for early predicting tumors among breast cancer patients who have undergone surgery and its utility in enhancing decision-making in clinical environments. It is crucial in promoting the prognosis, more effectively choosing therapies, augmenting post-operative breast cancer patients' survival, and controlling the limited healthcare resources.

CLINICAL TRIAL NUMBER

Not applicable.

Deep learning-based interpretable prediction of recurrence of diffuse large B-cell lymphoma

BACKGROUND

The heterogeneous and aggressive nature of diffuse large B-cell lymphoma (DLBCL) presents significant treatment challenges as up to 50% of patients experience recurrence of disease after chemotherapy. Upfront detection of recurring patients could offer alternative treatments. Deep learning has shown potential in predicting recurrence of various cancer types but suffers from lack of interpretability. Particularly in prediction of recurrence, an understanding of the model's decision could eventually result in novel treatments.

METHODS

We developed a deep learning-based pipeline to predict recurrence of DLBCL based on histological images of a publicly available cohort. We utilized attention-based classification to highlight areas within the images that were of high relevance for the model's classification. Subsequently, we segmented the nuclei within these areas, calculated morphological features, and statistically analyzed them to find differences between recurred and non-recurred patients.

RESULTS

We achieved an f1 score of 0.88 indicating that our model can distinguish non-recurred from recurred patients. Additionally, we found that features that are the most predictive of recurrence include large and irregularly shaped tumor cell nuclei.

DISCUSSION

Our work underlines the value of histological images in predicting treatment outcomes and enhances our understanding of complex biological processes in aggressive, heterogeneous cancers like DLBCL.

AI in Breast Cancer Imaging: An Update and Future Trends

Breast cancer is one of the most common types of cancer affecting women worldwide. Artificial intelligence (AI) is transforming breast cancer imaging by enhancing diagnostic capabilities across multiple imaging modalities including mammography, digital breast tomosynthesis, ultrasound, magnetic resonance imaging, and nuclear medicines techniques. AI is being applied to diverse tasks such as breast lesion detection and classification, risk stratification, molecular subtyping, gene mutation status prediction, and treatment response assessment, with emerging research demonstrating performance levels comparable to or potentially exceeding those of radiologists. The large foundation models are showing remarkable potential in different breast cancer imaging tasks. Self-supervised learning gives an insight into data inherent correlation, and federated learning is an alternative way to maintain data privacy. While promising results have been obtained so far, data standardization from source, large-scale annotated multimodal datasets, and extensive prospective clinical trials are still needed to fully explore and validate deep learning's clinical utility and address the legal and ethical considerations, which will ultimately determine its widespread adoption in breast cancer care. We hereby provide a review of the most up-to-date knowledge on AI in breast cancer imaging.

Current controversies in the use of Oncotype DX in early breast cancer

Multigene prognostic genomic assays have become essential tools in the management of early breast cancer (BC), providing information that help in risk-stratification, to provide risk-adapted decision-making of adjuvant treatments. Clinical practice guidelines recommend refining the prognostic information provided by clinical and pathology features with the use of genomic tests, such as Oncotype DX®, to classify cancers into risk groups and inform adjuvant treatment strategies. However, the clinical value (i.e., prognostic and/or predictive) and applicability of these assays vary due to differences in the clinical setting, especially in those populations that were underrepresented in pivotal clinical trials. Oncotype DX® is a broadly utilized genomic test for breast cancer, having the highest level of supporting evidence to inform clinical practice. Our manuscript provides a comprehensive overview on this recurrence score assay, evaluates supporting evidence across patient populations, and discusses their impact on treatment decisions in those groups of patients underrepresented in pivotal clinical trials, where evidence is limited with the use of Oncotype DX.

Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological features

BACKGROUND

In HR+/HER2- early breast cancer (EBC) patients, approximately one-third of stage II and 50% of stage III patients experience recurrence, with poor outcomes after recurrence. Given that these patients commonly undergo adjuvant chemo-endocrine therapy (C-ET), accurately predicting the recurrence risk is crucial for optimizing treatment strategies and improving patient outcomes.

METHODS

We collected postoperative histopathological slides from 1095 HR+/HER2- EBC who received C-ET and were followed for more than five years at West China Hospital, Sichuan University. Two deep learning pipelines were developed and validated: ACMIL-based and CLAM-based. Both pipelines, designed to predict recurrence risk post-treatment, were based on pretrained feature encoders and multi-instance learning with attention mechanisms. Model performance was evaluated using a five-fold cross-validation approach and externally validated on HR+/HER2- EBC patients from the TCGA cohort.

RESULTS

Both ACMIL-based and CLAM-based pipelines performed well in predicting recurrence risk, with UNI-ACMIL demonstrating superior performance across multiple metrics. The average area under the curve (AUC) for the UNI-ACMIL pipeline in the five-fold cross-validation test set was 0.86 ± 0.02, and 0.80 ± 0.04 in the TCGA cohort. In the five-fold cross-validation test sets, effectively stratified patients into high-risk and low-risk groups, demonstrating significant prognostic differences. Hazard ratios for recurrence-free survival (RFS) ranged from 5.32 (95% CI 1.86-15.12) to 15.16 (95% CI 3.61-63.56). Moreover, among six different multimodal recurrence risk models, the WSI-based risk score was identified as the most significant contributor.

CONCLUSION

Our multimodal recurrence risk prediction model is a practical and reliable tool that enhances the predictive power of existing systems relying solely on clinicopathological parameters. It offers improved recurrence risk prediction for HR+/HER2- EBC patients following adjuvant C-ET, supporting personalized treatment and better patient outcomes.

Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging

Predicting long-term recurrence of disease in breast cancer (BC) patients remains a significant challenge for patients with early stage disease who are at low to intermediate risk of relapse as determined using current clinical tools. Prognostic assays which utilize bulk transcriptomics ignore the spatial context of the cellular material and are, therefore, of limited value in the development of mechanistic models. In this study, Fourier-transform infrared (FTIR) chemical images of BC tissue were used to train deep learning models to predict future disease recurrence. A number of deep learning models were employed, with champion models employing two-dimensional and two-dimensional-separable convolutional networks found to have predictive performance of a ROC AUC of approximately 0.64, which compares well to other clinically used prognostic assays in this space. All-digital chemical imaging may therefore provide a label-free platform for histopathological prognosis in breast cancer, opening new horizons for future deployment of these technologies.

From ductal carcinoma in situ to invasive breast cancer: the prognostic value of the extracellular microenvironment

Ductal carcinoma in situ (DCIS) is a noninvasive breast disease that variably progresses to invasive breast cancer (IBC). Given the unpredictability of this progression, most DCIS patients are aggressively managed similar to IBC patients. Undoubtedly, this treatment paradigm places many DCIS patients at risk of overtreatment and its significant consequences. Historically, prognostic modeling has included the assessment of clinicopathological features and genomic markers. Although these provide valuable insights into tumor biology, they remain insufficient to predict which DCIS patients will progress to IBC. Contemporary work has begun to focus on the microenvironment surrounding the ductal cells for molecular patterns that might predict progression. In this review, extracellular microenvironment alterations occurring with the malignant transformation from DCIS to IBC are detailed. Not only do changes in collagen abundance, organization, and localization mediate the transition to IBC, but also the discrete post-translational regulation of collagen fibers is understood to promote invasion. Other extracellular matrix proteins, such as matrix metalloproteases, decorin, and tenascin C, have been characterized for their role in invasive transformation and further demonstrate the prognostic value of the extracellular matrix. Importantly, these extracellular matrix proteins influence immune cells and fibroblasts toward pro-tumorigenic phenotypes. Thus, the progressive changes in the extracellular microenvironment play a key role in invasion and provide promise for prognostic development.

Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features

Artificial intelligence models have been increasingly used in the analysis of tumor histology to perform tasks ranging from routine classification to identification of molecular features. These approaches distill cancer histologic images into high-level features, which are used in predictions, but understanding the biologic meaning of such features remains challenging. We present and validate a custom generative adversarial network-HistoXGAN-capable of reconstructing representative histology using feature vectors produced by common feature extractors. We evaluate HistoXGAN across 29 cancer subtypes and demonstrate that reconstructed images retain information regarding tumor grade, histologic subtype, and gene expression patterns. We leverage HistoXGAN to illustrate the underlying histologic features for deep learning models for actionable mutations, identify model reliance on histologic batch effect in predictions, and demonstrate accurate reconstruction of tumor histology from radiographic imaging for a "virtual biopsy."

Nanomedicine for cancer patient-centered care

Cancer is a leading cause of morbidity and mortality worldwide, and an increase in incidence is estimated in the next future, due to population aging, which requires the development of highly tolerable and low-toxicity cancer treatment strategies. The use of nanotechnology to tailor treatments according to the genetic and immunophenotypic characteristics of a patient's tumor, and to allow its targeted release, can meet this need, improving the efficacy of treatment and minimizing side effects. Nanomedicine-based approach for the diagnosis and treatment of cancer is a rapidly evolving field. Several nanoformulations are currently in clinical trials, and some have been approved and marketed. However, their large-scale production and use are still hindered by an in-depth debate involving ethics, intellectual property, safety and health concerns, technical issues, and costs. Here, we survey the key approaches, with specific reference to organ-on chip technology, and cutting-edge tools, such as CRISPR/Cas9 genome editing, through which nanosystems can meet the needs for personalized diagnostics and therapy in cancer patients. An update is provided on the nanopharmaceuticals approved and marketed for cancer therapy and those currently undergoing clinical trials. Finally, we discuss the emerging avenues in the field and the challenges to be overcome for the transfer of nano-based precision oncology into clinical daily life.

A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk

Breast cancer is the most common malignancy affecting women worldwide and is notable for its morphologic and biologic diversity, with varying risks of recurrence following treatment. The Oncotype DX Breast Recurrence Score test is an important predictive and prognostic genomic assay for estrogen receptor positive/HER2 negative breast cancer that guides therapeutic strategies; however, such tests can be expensive, delay care, and are not widely available. The aim of this study was to develop a multi-model approach integrating the analysis of whole-slide images and clinicopathologic data to predict their associated breast cancer recurrence risks and categorize these patients into two risk groups according to the predicted score: low-risk and high-risk. The proposed novel methodology uses convolutional neural networks for feature extraction and vision transformers for contextual aggregation, complemented by a logistic regression model that analyzes clinicopathologic data for classification into two risk categories. This method was trained and tested on 956 hematoxylin and eosin-stained whole-slide images of 950 ER+/HER2- breast cancer patients with corresponding clinicopathological features that had prior Oncotype DX testing. The model's performance was evaluated using an internal test set of 192 patients from Dartmouth Health and an external test set of 405 patients from the University of Chicago. The multi-model approach achieved an AUC of 0.91 (95% CI: 0.87-0.95) on the internal set and an AUC of 0.84 (95% CI: 0.78-0.89) on the external cohort for predicting low- and high-breast cancer recurrence risk categories based on the Oncotype DX recurrence score. With further validation, the proposed methodology could provide an alternative to assist clinicians in personalizing treatment for breast cancer patients and potentially improving their outcomes.

Artificial Intelligence Applications in Oral Cancer and Oral Dysplasia

Oral squamous cell carcinoma (OSCC) is a highly unpredictable disease with devastating mortality rates that have not changed over the past decades, in the face of advancements in treatments and biomarkers, which have improved survival for other cancers. Delays in diagnosis are frequent, leading to more disfiguring treatments and poor outcomes for patients. The clinical challenge lies in identifying those patients at the highest risk of developing OSCC. Oral epithelial dysplasia (OED) is a precursor of OSCC with highly variable behavior across patients. There is no reliable clinical, pathological, histological, or molecular biomarker to determine individual risk in OED patients. Similarly, there are no robust biomarkers to predict treatment outcomes or mortality in OSCC patients. This review aims to highlight advancements in artificial intelligence (AI)-based methods to develop predictive biomarkers of OED transformation to OSCC or predictive biomarkers of OSCC mortality and treatment response. Biomarkers such as S100A7 demonstrate promising appraisal for the risk of malignant transformation of OED. Machine learning-enhanced multiplex immunohistochemistry workflows examine immune cell patterns and organization within the tumor immune microenvironment to generate outcome predictions in immunotherapy. Deep learning (DL) is an AI-based method using an extended neural network or related architecture with multiple "hidden" layers of simulated neurons to combine simple visual features into complex patterns. DL-based digital pathology is currently being developed to assess OED and OSCC outcomes. The integration of machine learning in epigenomics aims to examine the epigenetic modification of diseases and improve our ability to detect, classify, and predict outcomes associated with epigenetic marks. Collectively, these tools showcase promising advancements in discovery and technology, which may provide a potential solution to addressing the current limitations in predicting OED transformation and OSCC behavior, both of which are clinical challenges that must be addressed in order to improve OSCC survival.

Deep Learning Model for Predicting Lung Adenocarcinoma Recurrence from Whole Slide Images

Lung cancer is the leading cause of cancer-related death in the United States. Lung adenocarcinoma (LUAD) is one of the most common subtypes of lung cancer that can be treated with resection. While resection can be curative, there is a significant risk of recurrence, which necessitates close monitoring and additional treatment planning. Traditionally, microscopic evaluation of tumor grading in resected specimens is a standard pathologic practice that informs subsequent therapy and patient management. However, this approach is labor-intensive and subject to inter-observer variability. To address the challenge of accurately predicting recurrence, we propose a deep learning-based model to predict the 5-year recurrence of LUAD in patients following surgical resection. In our model, we introduce an innovative dual-attention architecture that significantly enhances computational efficiency. Our model demonstrates excellent performance in recurrent risk stratification, achieving a hazard ratio of 2.29 (95% CI: 1.69-3.09, p < 0.005), which outperforms several existing deep learning methods. This study contributes to ongoing efforts to use deep learning models for automatically learning histologic patterns from whole slide images (WSIs) and predicting LUAD recurrence risk, thereby improving the accuracy and efficiency of treatment decision making.

Developing a low-cost, open-source, locally manufactured workstation and computational pipeline for automated histopathology evaluation using deep learning

BACKGROUND

Deployment and access to state-of-the-art precision medicine technologies remains a fundamental challenge in providing equitable global cancer care in low-resource settings. The expansion of digital pathology in recent years and its potential interface with diagnostic artificial intelligence algorithms provides an opportunity to democratize access to personalized medicine. Current digital pathology workstations, however, cost thousands to hundreds of thousands of dollars. As cancer incidence rises in many low- and middle-income countries, the validation and implementation of low-cost automated diagnostic tools will be crucial to helping healthcare providers manage the growing burden of cancer.

METHODS

Here we describe a low-cost ($230) workstation for digital slide capture and computational analysis composed of open-source components. We analyze the predictive performance of deep learning models when they are used to evaluate pathology images captured using this open-source workstation versus images captured using common, significantly more expensive hardware. Validation studies assessed model performance on three distinct datasets and predictive models: head and neck squamous cell carcinoma (HPV positive versus HPV negative), lung cancer (adenocarcinoma versus squamous cell carcinoma), and breast cancer (invasive ductal carcinoma versus invasive lobular carcinoma).

FINDINGS

When compared to traditional pathology image capture methods, low-cost digital slide capture and analysis with the open-source workstation, including the low-cost microscope device, was associated with model performance of comparable accuracy for breast, lung, and HNSCC classification. At the patient level of analysis, AUROC was 0.84 for HNSCC HPV status prediction, 1.0 for lung cancer subtype prediction, and 0.80 for breast cancer classification.

INTERPRETATION

Our ability to maintain model performance despite decreased image quality and low-power computational hardware demonstrates that it is feasible to massively reduce costs associated with deploying deep learning models for digital pathology applications. Improving access to cutting-edge diagnostic tools may provide an avenue for reducing disparities in cancer care between high- and low-income regions.

FUNDING

Funding for this project including personnel support was provided via grants from NIH/NCIR25-CA240134, NIH/NCIU01-CA243075, NIH/NIDCRR56-DE030958, NIH/NCIR01-CA276652, NIH/NCIK08-CA283261, NIH/NCI-SOAR25CA240134, SU2C (Stand Up to Cancer) Fanconi Anemia Research Fund - Farrah Fawcett Foundation Head and Neck Cancer Research Team Grant, and the European UnionHorizon Program (I3LUNG).

Artificial intelligence breakthroughs in pioneering early diagnosis and precision treatment of breast cancer: A multimethod study

This article delves into the potential of artificial intelligence (AI) to enhance early breast cancer (BC) detection for improved treatment outcomes and patient care. Utilizing a multimethod approach comprising literature review and experiments, the study systematically reviewed 310 articles utilizing 30 diverse datasets. Among the techniques assessed, recurrent neural network (RNN) emerged as the most accurate, achieving 98.58 % accuracy, followed by genetic principles (GP), transfer learning (TL), and artificial neural networks (ANNs), with accuracies exceeding 96 %. While conventional machine learning (ML) methods demonstrated accuracies above 90 %, DL techniques outperformed them. Evaluation of BC diagnostic models using the Wisconsin breast cancer dataset (WBCD) highlighted logistic regression (LR) and support vector machine (SVM) as the most accurate predictors, with minimal errors for clinical data. Conversely, decision trees (DT) exhibited higher error rates due to overfitting, emphasizing the importance of algorithm selection for complex datasets. Analysis of ultrasound images underscored the significance of preprocessing, while histopathological image analysis using convolutional neural networks (CNNs) demonstrated robust classification capabilities. These findings underscore the transformative potential of ML and DL in BC diagnosis, offering automated, accurate, and accessible diagnostic tools. Collaboration among stakeholders is crucial for further advancements in BC detection methods.

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.

Development and validation of a clinical breast cancer tool for accurate prediction of recurrence

Given high costs of Oncotype DX (ODX) testing, widely used in recurrence risk assessment for early-stage breast cancer, studies have predicted ODX using quantitative clinicopathologic variables. However, such models have incorporated only small cohorts. Using a cohort of patients from the National Cancer Database (NCDB, n = 53,346), we trained machine learning models to predict low-risk (0-25) or high-risk (26-100) ODX using quantitative estrogen receptor (ER)/progesterone receptor (PR)/Ki-67 status, quantitative ER/PR status alone, and no quantitative features. Models were externally validated on a diverse cohort of 970 patients (median follow-up 55 months) for accuracy in ODX prediction and recurrence. Comparing the area under the receiver operating characteristic curve (AUROC) in a held-out set from NCDB, models incorporating quantitative ER/PR (AUROC 0.78, 95% CI 0.77-0.80) and ER/PR/Ki-67 (AUROC 0.81, 95% CI 0.80-0.83) outperformed the non-quantitative model (AUROC 0.70, 95% CI 0.68-0.72). These results were preserved in the validation cohort, where the ER/PR/Ki-67 model (AUROC 0.87, 95% CI 0.81-0.93, p = 0.009) and the ER/PR model (AUROC 0.86, 95% CI 0.80-0.92, p = 0.031) significantly outperformed the non-quantitative model (AUROC 0.80, 95% CI 0.73-0.87). Using a high-sensitivity rule-out threshold, the non-quantitative, quantitative ER/PR and ER/PR/Ki-67 models identified 35%, 30% and 43% of patients as low-risk in the validation cohort. Of these low-risk patients, fewer than 3% had a recurrence at 5 years. These models may help identify patients who can forgo genomic testing and initiate endocrine therapy alone. An online calculator is provided for further study.

Addressing Social Determinants in the Era of Precision Medicine in Breast Cancer: Is It Sufficient to Reduce Disparities?

The Oncotype DX (ODX) assay predicts recurrence risk and demonstrates the benefits of adjuvant therapy in patients with early-stage, hormone receptor (HR)-positive/HER2-negative breast cancer. ODX uptake varies by patients' racial/ethnic backgrounds and socioeconomic status (SES). However, community-level variability remains unknown, and research regarding the association between testing status and receipt of adjuvant chemotherapy is limited. To fill these knowledge gaps, Van Alsten and colleagues found a 6% lower prevalence of ODX uptake among patients residing in high SES-deprived areas than among those residing in low SES-deprived areas. Among patients with low and median ODX recurrence scores, those who underwent testing were 28% and 21% less likely to receive adjuvant chemotherapy than those who did not, respectively. The findings emphasize the role of social determinants of health. However, to further reduce or eliminate racial/ethnic disparities and SES inequities, we would need sufficient and effective multi-level approaches. These involve lower ODX testing costs, health insurance coverage expansion, re-classification and validation of ODX recurrence scores in patients of minority ancestry, and the development of a faster, more accurate, and affordable test. See related article by Van Alsten et al., p. 654.

A population-level digital histologic biomarker for enhanced prognosis of invasive breast cancer

Breast cancer is a heterogeneous disease with variable survival outcomes. Pathologists grade the microscopic appearance of breast tissue using the Nottingham criteria, which are qualitative and do not account for noncancerous elements within the tumor microenvironment. Here we present the Histomic Prognostic Signature (HiPS), a comprehensive, interpretable scoring of the survival risk incurred by breast tumor microenvironment morphology. HiPS uses deep learning to accurately map cellular and tissue structures to measure epithelial, stromal, immune, and spatial interaction features. It was developed using a population-level cohort from the Cancer Prevention Study-II and validated using data from three independent cohorts, including the Prostate, Lung, Colorectal, and Ovarian Cancer trial, Cancer Prevention Study-3, and The Cancer Genome Atlas. HiPS consistently outperformed pathologists in predicting survival outcomes, independent of tumor-node-metastasis stage and pertinent variables. This was largely driven by stromal and immune features. In conclusion, HiPS is a robustly validated biomarker to support pathologists and improve patient prognosis.

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.

A comparative study on the features of breast sclerosing adenosis and invasive ductal carcinoma via ultrasound and establishment of a predictive nomogram

Objective

To analyze the clinical and ultrasonic characteristics of breast sclerosing adenosis (SA) and invasive ductal carcinoma (IDC), and construct a predictive nomogram for SA.

Materials and methods

A total of 865 patients were recruited at the Second Hospital of Shandong University from January 2016 to November 2022. All patients underwent routine breast ultrasound examinations before surgery, and the diagnosis was confirmed by histopathological examination following the operation. Ultrasonic features were recorded using the Breast Imaging Data and Reporting System (BI-RADS). Of the 865 patients, 203 (252 nodules) were diagnosed as SA and 662 (731 nodules) as IDC. They were randomly divided into a training set and a validation set at a ratio of 6:4. Lastly, the difference in clinical characteristics and ultrasonic features were comparatively analyzed.

Result

There was a statistically significant difference in multiple clinical and ultrasonic features between SA and IDC (P<0.05). As age and lesion size increased, the probability of SA significantly decreased, with a cut-off value of 36 years old and 10 mm, respectively. In the logistic regression analysis of the training set, age, nodule size, menopausal status, clinical symptoms, palpability of lesions, margins, internal echo, color Doppler flow imaging (CDFI) grading, and resistance index (RI) were statistically significant (P<0.05). These indicators were included in the static and dynamic nomogram model, which showed high predictive performance, calibration and clinical value in both the training and validation sets.

Conclusion

SA should be suspected in asymptomatic young women, especially those younger than 36 years of age, who present with small-size lesions (especially less than 10 mm) with distinct margins, homogeneous internal echo, and lack of blood supply. The nomogram model can provide a more convenient tool for clinicians.

HistoMIL: A Python package for training multiple instance learning models on histopathology slides

Hematoxylin and eosin (H&E) stained slides are widely used in disease diagnosis. Remarkable advances in deep learning have made it possible to detect complex molecular patterns in these histopathology slides, suggesting automated approaches could help inform pathologists' decisions. Multiple instance learning (MIL) algorithms have shown promise in this context, outperforming transfer learning (TL) methods for various tasks, but their implementation and usage remains complex. We introduce HistoMIL, a Python package designed to streamline the implementation, training and inference process of MIL-based algorithms for computational pathologists and biomedical researchers. It integrates a self-supervised learning module for feature encoding, and a full pipeline encompassing TL and three MIL algorithms: ABMIL, DSMIL, and TransMIL. The PyTorch Lightning framework enables effortless customization and algorithm implementation. We illustrate HistoMIL's capabilities by building predictive models for 2,487 cancer hallmark genes on breast cancer histology slides, achieving AUROC performances of up to 85%.

Artificial Intelligence in the Pathology of Gastric Cancer

Recent advances in artificial intelligence (AI) have provided novel tools for rapid and precise pathologic diagnosis. The introduction of digital pathology has enabled the acquisition of scanned slide images that are essential for the application of AI. The application of AI for improved pathologic diagnosis includes the error-free detection of potentially negligible lesions, such as a minute focus of metastatic tumor cells in lymph nodes, the accurate diagnosis of potentially controversial histologic findings, such as very well-differentiated carcinomas mimicking normal epithelial tissues, and the pathological subtyping of the cancers. Additionally, the utilization of AI algorithms enables the precise decision of the score of immunohistochemical markers for targeted therapies, such as human epidermal growth factor receptor 2 and programmed death-ligand 1. Studies have revealed that AI assistance can reduce the discordance of interpretation between pathologists and more accurately predict clinical outcomes. Several approaches have been employed to develop novel biomarkers from histologic images using AI. Moreover, AI-assisted analysis of the cancer microenvironment showed that the distribution of tumor-infiltrating lymphocytes was related to the response to the immune checkpoint inhibitor therapy, emphasizing its value as a biomarker. As numerous studies have demonstrated the significance of AI-assisted interpretation and biomarker development, the AI-based approach will advance diagnostic pathology.

Deep learning generates synthetic cancer histology for explainability and education

Artificial intelligence methods including deep neural networks (DNN) can provide rapid molecular classification of tumors from routine histology with accuracy that matches or exceeds human pathologists. Discerning how neural networks make their predictions remains a significant challenge, but explainability tools help provide insights into what models have learned when corresponding histologic features are poorly defined. Here, we present a method for improving explainability of DNN models using synthetic histology generated by a conditional generative adversarial network (cGAN). We show that cGANs generate high-quality synthetic histology images that can be leveraged for explaining DNN models trained to classify molecularly-subtyped tumors, exposing histologic features associated with molecular state. Fine-tuning synthetic histology through class and layer blending illustrates nuanced morphologic differences between tumor subtypes. Finally, we demonstrate the use of synthetic histology for augmenting pathologist-in-training education, showing that these intuitive visualizations can reinforce and improve understanding of histologic manifestations of tumor biology.