Systematic review and feasibility study on pre-analytical factors and genomic analyses on archival formalin-fixed paraffin-embedded breast cancer tissue.

Formalin-fixed paraffin-embedded (FFPE) tissue represents a valuable source for translational cancer research. However, the widespread application of various downstream methods remains challenging. Here, we aimed to assess the feasibility of a genomic and gene expression analysis workflow using FFPE breast cancer (BC) tissue. We conducted a systematic literature review for the assessment of concordance between FFPE and fresh-frozen matched tissue samples derived from patients with BC for DNA and RNA downstream applications. The analytical performance of three different nucleic acid extraction kits on FFPE BC clinical samples was compared. We also applied a newly developed targeted DNA Next-Generation Sequencing (NGS) 370-gene panel and the nCounter BC360® platform on simultaneously extracted DNA and RNA, respectively, using FFPE tissue from a phase II clinical trial. Of the 3701 initial search results, 40 articles were included in the systematic review. High degree of concordance was observed in various downstream application platforms. Moreover, the performance of simultaneous DNA/RNA extraction kit was demonstrated with targeted DNA NGS and gene expression profiling. Exclusion of variants below 5% variant allele frequency was essential to overcome FFPE-induced artefacts. Targeted genomic analyses were feasible in simultaneously extracted DNA/RNA from FFPE material, providing insights for their implementation in clinical trials/cohorts.

Validation of an AI-based solution for breast cancer risk stratification using routine digital histopathology images.

BACKGROUND: Stratipath Breast is a CE-IVD marked artificial intelligence-based solution for prognostic risk stratification of breast cancer patients into high- and low-risk groups, using haematoxylin and eosin (H&E)-stained histopathology whole slide images (WSIs). In this validation study, we assessed the prognostic performance of Stratipath Breast in two independent breast cancer cohorts. METHODS: This retrospective multi-site validation study included 2719 patients with primary breast cancer from two Swedish hospitals. The Stratipath Breast tool was applied to stratify patients based on digitised WSIs of the diagnostic H&E-stained tissue sections from surgically resected tumours. The prognostic performance was evaluated using time-to-event analysis by multivariable Cox Proportional Hazards analysis with progression-free survival (PFS) as the primary endpoint. RESULTS: In the clinically relevant oestrogen receptor (ER)-positive/human epidermal growth factor receptor 2 (HER2)-negative patient subgroup, the estimated hazard ratio (HR) associated with PFS between low- and high-risk groups was 2.76 (95% CI: 1.63-4.66, p-value < 0.001) after adjusting for established risk factors. In the ER+/HER2- Nottingham histological grade (NHG) 2 subgroup, the HR was 2.20 (95% CI: 1.22-3.98, p-value = 0.009) between low- and high-risk groups. CONCLUSION: The results indicate an independent prognostic value of Stratipath Breast among all breast cancer patients, as well as in the clinically relevant ER+/HER2- subgroup and the NHG2/ER+/HER2- subgroup. Improved risk stratification of intermediate-risk ER+/HER2- breast cancers provides information relevant for treatment decisions of adjuvant chemotherapy and has the potential to reduce both under- and overtreatment. Image-based risk stratification provides the added benefit of short lead times and substantially lower cost compared to molecular diagnostics and therefore has the potential to reach broader patient groups.

Inferring clonal somatic mutations directed by X chromosome inactivation status in single cells.

Analysis of clonal dynamics in human tissues is enabled by somatic genetic variation. Here, we show that analysis of mitochondrial mutations in single cells is dramatically improved in females when using X chromosome inactivation to select informative clonal mutations. Applying this strategy to human peripheral mononuclear blood cells reveals clonal structures within T cells that otherwise are blurred by non-informative mutations, including the separation of gamma-delta T cells, suggesting this approach can be used to decipher clonal dynamics of cells in human tissues.

Ensemble-based deep learning improves detection of invasive breast cancer in routine histopathology images.

Accurate detection of invasive breast cancer (IC) can provide decision support to pathologists as well as improve downstream computational analyses, where detection of IC is a first step. Tissue containing IC is characterized by the presence of specific morphological features, which can be learned by convolutional neural networks (CNN). Here, we compare the use of a single CNN model versus an ensemble of several base models with the same CNN architecture, and we evaluate prediction performance as well as variability across ensemble based model predictions. Two in-house datasets comprising 587 whole slide images (WSI) are used to train an ensemble of ten InceptionV3 models whose consensus is used to determine the presence of IC. A novel visualisation strategy was developed to communicate ensemble agreement spatially. Performance was evaluated in an internal test set with 118 WSIs, and in an additional external dataset (TCGA breast cancer) with 157 WSI. We observed that the ensemble-based strategy outperformed the single CNN-model alternative with respect to accuracy on tile level in 89 % of all WSIs in the test set. The overall accuracy was 0.92 (DICE coefficient, 0.90) for the ensemble model, and 0.85 (DICE coefficient, 0.83) for the single CNN alternative in the internal test set. For TCGA the ensemble outperformed the single CNN in 96.8 % of the WSI, with an accuracy of 0.87 (DICE coefficient 0.89), the single model provides an accuracy of 0.75 (DICE coefficient 0.78). The results suggest that an ensemble-based modeling strategy for breast cancer invasive cancer detection consistently outperforms the conventional single model alternative. Furthermore, visualisation of the ensemble agreement and confusion areas provide direct visual interpretation of the results. High performing cancer detection can provide decision support in the routine pathology setting as well as facilitate downstream computational analyses.

The ACROBAT 2022 challenge: Automatic registration of breast cancer tissue.

The alignment of tissue between histopathological whole-slide-images (WSI) is crucial for research and clinical applications. Advances in computing, deep learning, and availability of large WSI datasets have revolutionised WSI analysis. Therefore, the current state-of-the-art in WSI registration is unclear. To address this, we conducted the ACROBAT challenge, based on the largest WSI registration dataset to date, including 4,212 WSIs from 1,152 breast cancer patients. The challenge objective was to align WSIs of tissue that was stained with routine diagnostic immunohistochemistry to its H&E-stained counterpart. We compare the performance of eight WSI registration algorithms, including an investigation of the impact of different WSI properties and clinical covariates. We find that conceptually distinct WSI registration methods can lead to highly accurate registration performances and identify covariates that impact performances across methods. These results provide a comparison of the performance of current WSI registration methods and guide researchers in selecting and developing methods.

Prelude to malignancy: A gene expression signature in normal mammary gland from breast cancer patients suggests pre-tumorous alterations and is associated with adverse outcomes.

Despite advances in early detection and treatment strategies, breast cancer recurrence and mortality remain a significant health issue. Recent insights suggest the prognostic potential of microscopically healthy mammary gland, in the vicinity of the breast lesion. Nonetheless, a comprehensive understanding of the gene expression profiles in these tissues and their relationship to patient outcomes remain missing. Furthermore, the increasing trend towards breast-conserving surgery may inadvertently lead to the retention of existing cancer-predisposing mutations within the normal mammary gland. This study assessed the transcriptomic profiles of 242 samples from 83 breast cancer patients with unfavorable outcomes, including paired uninvolved mammary gland samples collected at varying distances from primary lesions. As a reference, control samples from 53 mammoplasty individuals without cancer history were studied. A custom panel of 634 genes linked to breast cancer progression and metastasis was employed for expression profiling, followed by whole-transcriptome verification experiments and statistical analyses to discern molecular signatures and their clinical relevance. A distinct gene expression signature was identified in uninvolved mammary gland samples, featuring key cellular components encoding keratins, CDH1, CDH3, EPCAM cell adhesion proteins, matrix metallopeptidases, oncogenes, tumor suppressors, along with crucial genes (FOXA1, RAB25, NRG1, SPDEF, TRIM29, and GABRP) having dual roles in cancer. Enrichment analyses revealed disruptions in epithelial integrity, cell adhesion, and estrogen signaling. This signature, named KAOS for Keratin-Adhesion-Oncogenes-Suppressors, was significantly associated with reduced tumor size but increased mortality rates. Integrating molecular assessment of non-malignant mammary tissue into disease management could enhance survival prediction and facilitate personalized patient care.

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.

Unveiling the Power of Model-Agnostic Multiscale Analysis for Enhancing Artificial Intelligence Models in Breast Cancer Histopathology Images.

Developing AI models for digital pathology has traditionally relied on single-scale analysis of histopathology slides. However, a whole slide image is a rich digital representation of the tissue, captured at various magnification levels. Limiting our analysis to a single scale overlooks critical information, spanning from intricate high-resolution cellular details to broad low-resolution tissue structures. In this study, we propose a model-agnostic multiresolution feature aggregation framework tailored for the analysis of histopathology slides in the context of breast cancer, on a multicohort dataset of 2038 patient samples. We have adapted 9 state-of-the-art multiple instance learning models on our multi-scale methodology and evaluated their performance on grade prediction, TP53 mutation status prediction and survival prediction. The results prove the dominance of the multiresolution methodology, and specifically, concatenating or linearly transforming via a learnable layer the feature vectors of image patches from a high (20x) and low (10x) magnification factors achieve improved performance for all prediction tasks across domain-specific and imagenet-based features. On the contrary, the performance of uniresolution baseline models was not consistent across domain-specific and imagenet-based features. Moreover, we shed light on the inherent inconsistencies observed in models trained on whole-tissue-sections when validated against biopsy-based datasets. Despite these challenges, our findings underscore the superiority of multiresolution analysis over uniresolution methods. Finally, cross-scale analysis also benefits the explainability aspects of attention-based architectures, since one can extract attention maps at the tissue- and cell-levels, improving the interpretation of the model's decision.

Real-world overall survival and characteristics of patients with ER-zero and ER-low HER2-negative breast cancer treated as triple-negative breast cancer: a Swedish population-based cohort study.

Background: Estrogen receptor-low (ER-low) HER2-negative breast cancer has similar pathological and molecular characteristics as triple-negative breast cancer (TNBC), and it is questionable whether it should be considered a separate entity. When the international guidelines lowered the cutoff for ER positivity to ≥1% in 2010, the ≥10% threshold was kept in Sweden. ER-low breast cancer (ER 1-9%) is thus in Sweden treated as TNBC. We aimed to describe patient and tumor characteristics, treatment patterns and overall survival in a Swedish population-based cohort of patients with ER-zero and ER-low HER2-negative breast cancer treated as TNBC. Methods: All TNBC cases diagnosed in Sweden 2008-2020 were included in a population-based cohort study. Patient, tumor and treatment characteristics were analyzed by ER-status (ER 0% vs 1-9%), and associations between subgroups compared using χ2 test. Survival endpoint was overall survival (OS), and Kaplan-Meier curves were estimated. Cox proportional hazards models were used to estimate adjusted hazard ratios comparing ER-low to ER-zero. Findings: Of the 5655 tumors, 90.1% had an ER expression of 0%, while 9.9% were ER-low. ER-low tumors were grade III in 69.4% (80.8% in ER-zero tumors, p-value = 0.001), with a median Ki67 of 60% (63% in ER-zero tumors, p-value = 0.005). There were no significant differences in given chemotherapy (p = 0.546). A pathological complete response (pCR) was achieved in 28.1% of ER-low tumors (25.1% in ER-zero tumors). In the unadjusted analysis of OS, women with ER-low disease had a borderline but not significantly better OS than those with ER-zero disease (HR 0.84 (95% CI 0.71-1.00), p = 0.052). ER-status 1-9% vs 0% was not associated with OS in the multivariable analysis (HR 1.11 (0.90-1.36)). Distant disease-free survival did not differ by ER-status 0% vs 1-9% (HR 0.97 for ER-zero vs ER-low (0.62-1.53), p = 0.905). After preoperative treatment, the impact of pCR for OS did not significantly differ between ER-zero or ER-low disease. Interpretation: ER-low HER2-negative breast cancer has characteristics and prognosis similar to TNBC, when treated in the same way. Therefore, it seems reasonable to use a ≥10% threshold for ER positivity. This would provide patients with ER-low tumors the same treatment opportunities as patients with TNBC, within studies and within clinical routine. Funding: This work was financially supported by Merck Sharp & Dohme LLC, a subsidiary of Merck & Co., Inc., Rahway, NJ, USA, in accordance with terms and conditions of a Master Collaboration Agreement between the company and Karolinska Institutet.

Tumor-associated NK cells drive MDSC-mediated tumor immune tolerance through the IL-6/STAT3 axis.

Apart from their killer identity, natural killer (NK) cells have integral roles in shaping the tumor microenvironment. Through immune gene deconvolution, the present study revealed an interplay between NK cells and myeloid-derived suppressor cells (MDSCs) in nonresponders of immune checkpoint therapy. Given that the mechanisms governing the outcome of NK cell-to-myeloid cell interactions remain largely unknown, we sought to investigate the cross-talk between NK cells and suppressive myeloid cells. Upon contact with tumor-experienced NK cells, monocytes and neutrophils displayed increased expression of MDSC-related suppressive factors along with increased capacities to suppress T cells. These changes were accompanied by impaired antigen presentation by monocytes and increased ER stress response by neutrophils. In a cohort of patients with sarcoma and breast cancer, the production of interleukin-6 (IL-6) by tumor-infiltrating NK cells correlated with S100A8/9 and arginase-1 expression by MDSCs. At the same time, NK cell-derived IL-6 was associated with tumors with higher major histocompatibility complex class I expression, which we further validated with b2m-knockout (KO) tumor mice models. Similarly in syngeneic wild-type and IL-6 KO mouse models, we then demonstrated that the accumulation of MDSCs was influenced by the presence of such regulatory NK cells. Inhibition of the IL-6/signal transducer and activator of transcription 3 (STAT3) axis alleviated suppression of T cell responses, resulting in reduced tumor growth and metastatic dissemination. Together, these results characterize a critical NK cell-mediated mechanism that drives the development of MDSCs during tumor immune escape.

PIK3CA mutations in endocrine-resistant breast cancer.

Around 75% of breast cancer (BC) patients have tumors expressing the predictive biomarker estrogen receptor α (ER) and are offered endocrine therapy. One-third eventually develop endocrine resistance, a majority with retained ER expression. Mutations in the phosphatidylinositol bisphosphate 3-kinase (PI3K) catalytic subunit encoded by PIK3CA is a proposed resistance mechanism and a pharmacological target in the clinical setting. Here we explore the frequency of PIK3CA mutations in endocrine-resistant BC before and during treatment and correlate to clinical features. Patients with ER-positive (ER +), human epidermal growth factor receptor 2 (HER2)-negative primary BC with an ER + relapse within 5 years of ongoing endocrine therapy were retrospectively assessed. Tissue was collected from primary tumors (n = 58), relapse tumors (n = 54), and tumor-free lymph nodes (germline controls, n = 62). Extracted DNA was analyzed through panel sequencing. Somatic mutations were observed in 50% (31/62) of the patients, of which 29% occurred outside hotspot regions. The presence of PIK3CA mutations was significantly associated with nodal involvement and mutations were more frequent in relapse than primary tumors. Our study shows the different PIK3CA mutations in endocrine-resistant BC and their fluctuations during therapy. These results may aid investigations of response prediction, facilitating research deciphering the mechanisms of endocrine resistance.

A phenotypic screening approach to target p60AmotL2-expressing invasive cancer cells.

BACKGROUND: Tumor cells have the ability to invade and form small clusters that protrude into adjacent tissues, a phenomenon that is frequently observed at the periphery of a tumor as it expands into healthy tissues. The presence of these clusters is linked to poor prognosis and has proven challenging to treat using conventional therapies. We previously reported that p60AmotL2 expression is localized to invasive colon and breast cancer cells. In vitro, p60AmotL2 promotes epithelial cell invasion by negatively impacting E-cadherin/AmotL2-related mechanotransduction. METHODS: Using epithelial cells transfected with inducible p60AmotL2, we employed a phenotypic drug screening approach to find compounds that specifically target invasive cells. The phenotypic screen was performed by treating cells for 72 h with a library of compounds with known antitumor activities in a dose-dependent manner. After assessing cell viability using CellTiter-Glo, drug sensitivity scores for each compound were calculated. Candidate hit compounds with a higher drug sensitivity score for p60AmotL2-expressing cells were then validated on lung and colon cell models, both in 2D and in 3D, and on colon cancer patient-derived organoids. Nascent RNA sequencing was performed after BET inhibition to analyse BET-dependent pathways in p60AmotL2-expressing cells. RESULTS: We identified 60 compounds that selectively targeted p60AmotL2-expressing cells. Intriguingly, these compounds were classified into two major categories: Epidermal Growth Factor Receptor (EGFR) inhibitors and Bromodomain and Extra-Terminal motif (BET) inhibitors. The latter consistently demonstrated antitumor activity in human cancer cell models, as well as in organoids derived from colon cancer patients. BET inhibition led to a shift towards the upregulation of pro-apoptotic pathways specifically in p60AmotL2-expressing cells. CONCLUSIONS: BET inhibitors specifically target p60AmotL2-expressing invasive cancer cells, likely by exploiting differences in chromatin accessibility, leading to cell death. Additionally, our findings support the use of this phenotypic strategy to discover novel compounds that can exploit vulnerabilities and specifically target invasive cancer cells.

CopyVAE: a variational autoencoder-based approach for copy number variation inference using single-cell transcriptomics.

MOTIVATION: Copy number variations (CNVs) are common genetic alterations in tumour cells. The delineation of CNVs holds promise for enhancing our comprehension of cancer progression. Moreover, accurate inference of CNVs from single-cell sequencing data is essential for unravelling intratumoral heterogeneity. However, existing inference methods face limitations in resolution and sensitivity. RESULTS: To address these challenges, we present CopyVAE, a deep learning framework based on a variational autoencoder architecture. Through experiments, we demonstrated that CopyVAE can accurately and reliably detect CNVs from data obtained using single-cell RNA sequencing. CopyVAE surpasses existing methods in terms of sensitivity and specificity. We also discussed CopyVAE's potential to advance our understanding of genetic alterations and their impact on disease advancement. AVAILABILITY AND IMPLEMENTATION: CopyVAE is implemented and freely available under MIT license at https://github.com/kurtsemih/copyVAE.

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.

Human Epidermal Growth Factor Receptor 2 (HER2) PET Imaging of HER2-Low Breast Cancer with [68Ga]Ga-ABY-025: Results from a Pilot Study.

Patients with HER2-low metastatic breast cancer (mBC), defined as an immunohistochemistry (IHC) score of 1+ or 2+ without HER2 gene amplification, may benefit from HER2 antibody-drug conjugates. Identifying suitable candidates is a clinical challenge because of spatial and temporal heterogeneity in HER2 expression and discrepancies in pathologic reporting. We aimed to investigate the feasibility and safety of HER2-specific PET imaging with [68Ga]Ga-ABY-025 for visualization of HER2-low mBC. Methods: A prospective pilot study was done with 10 patients who had HER2-low mBC, as part of a phase 2 basket imaging study with [68Ga]Ga-ABY-025 in HER2-expressing solid tumors. Patients were recruited at the Breast Clinic at the Karolinska University Hospital, Stockholm, Sweden. PET/CT images were acquired 3 h after injection of 200 MBq of [68Ga]Ga-ABY-025. The SUVmax was used to quantify tracer uptake. Ultrasound-guided tumor biopsies were guided by results from the HER2 PET. The main outcome-the safety and feasibility of HER2 PET in patients with HER2-low mBC, measured the occurrence of possible procedure-related adverse events. Results: Ten patients with HER2-low mBC underwent [68Ga]Ga-ABY-025 PET/CT with paired tumor biopsies. No adverse events occurred. In all patients, [68Ga]Ga-ABY-025-avid lesions with substantial intra- and interindividual heterogeneity in tracer uptake were noted. In 8 of 10 patients with ABY-025-avid lesions, the HER2-low status of the corresponding lesions was confirmed by IHC or in situ hybridization. Two patients had an IHC score of 0 in the tumor biopsies:1 in a cutaneous lesion with a low SUVmax and 1 in a liver metastasis with a high SUVmax but a "cold" core. Conclusion: The visualization of HER2-low mBC with [68Ga]Ga-ABY-025 PET/CT was feasible and safe. Areas of tracer uptake showed varying levels of HER2 expression on IHC. The observed intra- and interindividual heterogeneity in [68Ga]Ga-ABY-025 uptake suggested that HER2 PET might be used as a tool for the noninvasive assessment of disease heterogeneity and has the potential to identify patients in whom HER2-targeted drugs can have a clinical benefit.

Immune cell infiltrate in ductal carcinoma in situ and the risk of dying from breast cancer: case-control study.

BACKGROUND: Studies identifying risk factors for death from breast cancer after ductal carcinoma in situ (DCIS) are rare. In this retrospective nested case-control study, clinicopathological factors in women treated for DCIS and who died from breast cancer were compared with those of patients with DCIS who were free from metastatic disease. METHODS: The study included patients registered with DCIS without invasive carcinoma in Sweden between 1992 and 2012. This cohort was linked to the National Cause of Death Registry. Of 6964 women with DCIS, 96 were registered with breast cancer as cause of death (cases). For each case, up to four controls (318; women with DCIS, alive and without metastatic breast cancer at the time of death of the corresponding case) were selected randomly by incidence density sampling. Whole slides of tumour tissue were evaluated for DCIS grade, comedo necrosis, and intensity of periductal lymphocytic infiltrate. Composition of the immune cell infiltrate, expression of oestrogen receptor, progesterone receptor, human epidermal growth factor receptor 2, and proliferation marker Ki-67 were scored on tissue microarrays. Clinical information was obtained from medical records. Information on date, site, and histological characteristics of local and distant recurrences was obtained from medical records for both cases and controls. RESULTS: Tumour tissue was analysed from 65 cases and 195 controls. Intense periductal lymphocytic infiltrate around DCIS was associated with an increased risk of later dying from breast cancer (OR 2.21. 95% c.i. 1.01 to 4.84). Tumours with more intense lymphocytic infiltrate had a lower T cell/B cell ratio. None of the other biomarkers correlated with increased risk of breast cancer death. CONCLUSION: The immune response to DCIS may influence the risk of dying from breast cancer.

Prognostic impact of HER2 biomarker levels in trastuzumab-treated early HER2-positive breast cancer.

BACKGROUND: Overexpression of human epidermal growth factor receptor 2 (HER2) caused by HER2 gene amplification is a driver in breast cancer tumorigenesis. We aimed to investigate the prognostic significance of manual scoring and digital image analysis (DIA) algorithm assessment of HER2 copy numbers and HER2/CEP17 ratios, along with ERBB2 mRNA levels among early-stage HER2-positive breast cancer patients treated with trastuzumab. METHODS: This retrospective study comprised 371 early HER2-positive breast cancer patients treated with adjuvant trastuzumab, with HER2 re-testing performed on whole tumor sections. Digitized tumor tissue slides were manually scored and assessed with uPath HER2 Dual ISH image analysis, breast algorithm. Targeted ERBB2 mRNA levels were assessed by the Xpert® Breast Cancer STRAT4 Assay. HER2 copy number and HER2/CEP17 ratio from in situ hybridization assessment, along with ERBB2 mRNA levels, were explored in relation to recurrence-free survival (RFS). RESULTS: The analysis showed that patients with tumors with the highest and lowest manually counted HER2 copy number levels had worse RFS than those with intermediate levels (HR = 2.7, CI 1.4-5.3, p = 0.003 and HR = 2.1, CI 1.1-3.9, p = 0.03, respectively). A similar trend was observed for HER2/CEP17 ratio, and the DIA algorithm confirmed the results. Moreover, patients with tumors with the highest and the lowest values of ERBB2 mRNA had a significantly worse prognosis (HR = 2.7, CI 1.4-5.1, p = 0.003 and HR = 2.8, CI 1.4-5.5, p = 0.004, respectively) compared to those with intermediate levels. CONCLUSIONS: Our findings suggest that the association between any of the three HER2 biomarkers and RFS was nonlinear. Patients with tumors with the highest levels of HER2 gene amplification or ERBB2 mRNA were associated with a worse prognosis than those with intermediate levels, which is of importance to investigate in future clinical trials studying HER2-targeted therapy.

Development and prognostic validation of a three-level NHG-like deep learning-based model for histological grading of breast cancer.

BACKGROUND: Histological grade is a well-known prognostic factor that is routinely assessed in breast tumours. However, manual assessment of Nottingham Histological Grade (NHG) has high inter-assessor and inter-laboratory variability, causing uncertainty in grade assignments. To address this challenge, we developed and validated a three-level NHG-like deep learning-based histological grade model (predGrade). The primary performance evaluation focuses on prognostic performance. METHODS: This observational study is based on two patient cohorts (SöS-BC-4, N = 2421 (training and internal test); SCAN-B-Lund, N = 1262 (test)) that include routine histological whole-slide images (WSIs) together with patient outcomes. A deep convolutional neural network (CNN) model with an attention mechanism was optimised for the classification of the three-level histological grading (NHG) from haematoxylin and eosin-stained WSIs. The prognostic performance was evaluated by time-to-event analysis of recurrence-free survival and compared to clinical NHG grade assignments in the internal test set as well as in the fully independent external test cohort. RESULTS: We observed effect sizes (hazard ratio) for grade 3 versus 1, for the conventional NHG method (HR = 2.60 (1.18-5.70 95%CI, p-value = 0.017)) and the deep learning model (HR = 2.27, 95%CI 1.07-4.82, p-value = 0.033) on the internal test set after adjusting for established clinicopathological risk factors. In the external test set, the unadjusted HR for clinical NHG 2 versus 1 was estimated to be 2.59 (p-value = 0.004) and clinical NHG 3 versus 1 was estimated to be 3.58 (p-value < 0.001). For predGrade, the unadjusted HR for predGrade 2 versus 1 HR = 2.52 (p-value = 0.030), and 4.07 (p-value = 0.001) for preGrade 3 versus 1 was observed in the independent external test set. In multivariable analysis, HR estimates for neither clinical NHG nor predGrade were found to be significant (p-value > 0.05). We tested for differences in HR estimates between NHG and predGrade in the independent test set and found no significant difference between the two classification models (p-value > 0.05), confirming similar prognostic performance between conventional NHG and predGrade. CONCLUSION: Routine histopathology assessment of NHG has a high degree of inter-assessor variability, motivating the development of model-based decision support to improve reproducibility in histological grading. We found that the proposed model (predGrade) provides a similar prognostic performance as clinical NHG. The results indicate that deep CNN-based models can be applied for breast cancer histological grading.

Multiresolution Self-Supervised Feature Integration via Attention Multiple Instance Learning for Histopathology Analysis.

Digital histopathology image analysis of tumor tissue sections has seen great research interest for automating standard diagnostic tasks, but also for developing novel prognostic biomarkers. However, research has mainly been focused on developing uniresolution models, capturing either high-resolution cellular features or low-resolution tissue architectural features. In addition, in the patch-based weakly-supervised training of deep learning models, the features which represent the intratumoral heterogeneity are lost. In this study, we propose a multiresolution attention-based multiple instance learning framework that can capture cellular and contextual features from the whole tissue for predicting patient-level outcomes. Several basic mathematical operations were examined for integrating multiresolution features, i.e. addition, mean, multiplication and concatenation. The proposed multiplication-based multiresolution model performed the best (AUC=0.864), while all multiresolution models outperformed the uniresolution baseline models (AUC=0.669, 0.713) for breast-cancer grading. (Implementation: https://github.com/tsikup/multiresolution-clam).

Spatial transcriptomics of B cell and T cell receptors reveals lymphocyte clonal dynamics.

The spatial distribution of lymphocyte clones within tissues is critical to their development, selection, and expansion. We have developed spatial transcriptomics of variable, diversity, and joining (VDJ) sequences (Spatial VDJ), a method that maps B cell and T cell receptor sequences in human tissue sections. Spatial VDJ captures lymphocyte clones that match canonical B and T cell distributions and amplifies clonal sequences confirmed by orthogonal methods. We found spatial congruency between paired receptor chains, developed a computational framework to predict receptor pairs, and linked the expansion of distinct B cell clones to different tumor-associated gene expression programs. Spatial VDJ delineates B cell clonal diversity and lineage trajectories within their anatomical niche. Thus, Spatial VDJ captures lymphocyte spatial clonal architecture across tissues, providing a platform to harness clonal sequences for therapy.