Machine learning survival models trained on clinical data to identify high risk patients with hormone responsive HER2 negative breast cancer.

For endocrine-positive Her2 negative breast cancer patients at an early stage, the benefit of adding chemotherapy to adjuvant endocrine therapy is not still confirmed. Several genomic tests are available on the market but are very expensive. Therefore, there is the urgent need to explore novel reliable and less expensive prognostic tools in this setting. In this paper, we shown a machine learning survival model to estimate Invasive Disease-Free Events trained on clinical and histological data commonly collected in clinical practice. We collected clinical and cytohistological outcomes of 145 patients referred to Istituto Tumori "Giovanni Paolo II". Three machine learning survival models are compared with the Cox proportional hazards regression according to time-dependent performance metrics evaluated in cross-validation. The c-index at 10 years obtained by random survival forest, gradient boosting, and component-wise gradient boosting is stabled with or without feature selection at approximately 0.68 in average respect to 0.57 obtained to Cox model. Moreover, machine learning survival models have accurately discriminated low- and high-risk patients, and so a large group which can be spared additional chemotherapy to hormone therapy. The preliminary results obtained by including only clinical determinants are encouraging. The integrated use of data already collected in clinical practice for routine diagnostic investigations, if properly analyzed, can reduce time and costs of the genomic tests.

Analyzing breast cancer invasive disease event classification through explainable artificial intelligence.

Introduction: Recently, accurate machine learning and deep learning approaches have been dedicated to the investigation of breast cancer invasive disease events (IDEs), such as recurrence, contralateral and second cancers. However, such approaches are poorly interpretable. Methods: Thus, we designed an Explainable Artificial Intelligence (XAI) framework to investigate IDEs within a cohort of 486 breast cancer patients enrolled at IRCCS Istituto Tumori "Giovanni Paolo II" in Bari, Italy. Using Shapley values, we determined the IDE driving features according to two periods, often adopted in clinical practice, of 5 and 10 years from the first tumor diagnosis. Results: Age, tumor diameter, surgery type, and multiplicity are predominant within the 5-year frame, while therapy-related features, including hormone, chemotherapy schemes and lymphovascular invasion, dominate the 10-year IDE prediction. Estrogen Receptor (ER), proliferation marker Ki67 and metastatic lymph nodes affect both frames. Discussion: Thus, our framework aims at shortening the distance between AI and clinical practice.

Robustness Evaluation of a Deep Learning Model on Sagittal and Axial Breast DCE-MRIs to Predict Pathological Complete Response to Neoadjuvant Chemotherapy.

To date, some artificial intelligence (AI) methods have exploited Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) to identify finer tumor properties as potential earlier indicators of pathological Complete Response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). However, they work either for sagittal or axial MRI protocols. More flexible AI tools, to be used easily in clinical practice across various institutions in accordance with its own imaging acquisition protocol, are required. Here, we addressed this topic by developing an AI method based on deep learning in giving an early prediction of pCR at various DCE-MRI protocols (axial and sagittal). Sagittal DCE-MRIs refer to 151 patients (42 pCR; 109 non-pCR) from the public I-SPY1 TRIAL database (DB); axial DCE-MRIs are related to 74 patients (22 pCR; 52 non-pCR) from a private DB provided by Istituto Tumori "Giovanni Paolo II" in Bari (Italy). By merging the features extracted from baseline MRIs with some pre-treatment clinical variables, accuracies of 84.4% and 77.3% and AUC values of 80.3% and 78.0% were achieved on the independent tests related to the public DB and the private DB, respectively. Overall, the presented method has shown to be robust regardless of the specific MRI protocol.

A ultrasound-based radiomic approach to predict the nodal status in clinically negative breast cancer patients.

In breast cancer patients, an accurate detection of the axillary lymph node metastasis status is essential for reducing distant metastasis occurrence probabilities. In case of patients resulted negative at both clinical and instrumental examination, the nodal status is commonly evaluated performing the sentinel lymph-node biopsy, that is a time-consuming and expensive intraoperative procedure for the sentinel lymph-node (SLN) status assessment. The aim of this study was to predict the nodal status of 142 clinically negative breast cancer patients by means of both clinical and radiomic features extracted from primary breast tumor ultrasound images acquired at diagnosis. First, different regions of interest (ROIs) were segmented and a radiomic analysis was performed on each ROI. Then, clinical and radiomic features were evaluated separately developing two different machine learning models based on an SVM classifier. Finally, their predictive power was estimated jointly implementing a soft voting technique. The experimental results showed that the model obtained by combining clinical and radiomic features provided the best performances, achieving an AUC value of 88.6%, an accuracy of 82.1%, a sensitivity of 100% and a specificity of 78.2%. The proposed model represents a promising non-invasive procedure for the SLN status prediction in clinically negative patients.

Prognostic Value of NLRP3 Inflammasome and TLR4 Expression in Breast Cancer Patients.

Inflammasome complexes play a pivotal role in different cancer types. NOD-like receptor protein 3 (NLRP3) inflammasome is one of the most well-studied inflammasomes. Activation of the NLRP3 inflammasome induces abnormal secretion of soluble cytokines, generating advantageous inflammatory surroundings that support tumor growth. The expression levels of the NLRP3, PYCARD and TLR4 were determined by immunohistochemistry in a cohort of primary invasive breast carcinomas (BCs). We observed different NLRP3 and PYCARD expressions in non-tumor vs tumor areas (p<0.0001). All the proteins were associated to more aggressive clinicopathological characteristics (tumor size, grade, tumor proliferative activity etc.). Univariate analyses were carried out and related Kaplan-Meier curves plotted for NLRP3, PYCARD and TLR4 expression. Patients with higher NLRP3 and TLR4 expression had worse 5-year disease-free survival (DFS) compared to patients with lower NLRP3 and TLR4 expression (p =0.021 and p = 0.009, respectively). In multivariate analysis, TLR4 was confirmed as independent prognostic factors for DFS (HR = 2.03, 95% CI 1.16-3.57, p = 0.014), and high NLRP3 expression showed a slight association with DFS (HR = 1.75, 95% CI 0.98-3.15, p = 0.06). In conclusion, we showed TLR4 expression as independent prognostic factors and we highlighted for the first time that high expression of NLRP3 is linked to a poor prognosis in BC patients. These results suggest that NLRP3 and TLR4 could be two new good prognostic factor for BC patients.

The role of rapid on site evaluation on touch imprint cytology and brushing during conventional bronchoscopy.

BACKGROUND: The increase in immunohistochemical and molecular predictive tests in lung cancer requires new strategies for managing small samples taken during bronchoscopic procedures. The value of Rapid On Site Evaluation (ROSE) during conventional bronchoscopic procedures on endobronchial neoplasms in optimizing small biopsies and cytologlogical tissue specimens for diagnostic testing, and ancillary studies was evaluated. METHOD: ROSE on touch imprint cytology (TIC) and brushing was performed on 690 consecutive cases of patients undergoing biopsies, using fiber optic bronchoscopy. Immunohistochemical assay for PD-L1, ALK, and ROS1 and molecular testing, via next generation technique for EGFR, KRAS, and BRAF, were performed. RESULTS: The concordance between ROSE and final diagnoses was almost perfect for brushing (sensitivity: 0.84; specificity: 0.96), and less so for touch preparations (sensitivity: 0.77; specificity: 0.89). Immunohistochemical assay for PD-L1 was evaluated on 256 bioptic cases with only six unsuitable samples. Material available for immunohistochemistry for ALK was sufficient in 151 biopsies with no inadequate cases. ROS1 was evaluated in 132 biopsies, with only two unsuitable samples. Molecular analysis was performed on 128 biopsies, 29 TIC, and 17 brushing. Out of these, only ten were considered to be unsuitable. CONCLUSIONS: ROSE is an effective procedure for monitoring the quality and quantity of material taken during conventional bronchoscopic procedures for evaluating the suitability of small samples that must undergo immunohistochemical and molecular assay.

Predicting of Sentinel Lymph Node Status in Breast Cancer Patients with Clinically Negative Nodes: A Validation Study.

In the absence of lymph node abnormalities detectable on clinical examination or imaging, the guidelines provide for the dissection of the first axillary draining lymph nodes during surgery. It is not always possible to arrive at surgery without diagnostic doubts, and machine learning algorithms can support clinical decisions. The web calculator CancerMath (CM) allows you to estimate the probability of having positive lymph nodes valued on the basis of tumor size, age, histologic type, grading, expression of estrogen receptor, and progesterone receptor. We collected 993 patients referred to our institute with clinically negative results characterized by sentinel lymph node status, prognostic factors defined by CM, and also human epidermal growth factor receptor 2 (HER2) and Ki-67. Area Under the Curve (AUC) values obtained by the online CM application were comparable with those obtained after training its algorithm on our database. Nevertheless, by training the CM model on our dataset and using the same feature, we reached a sensitivity median value of 72%, whereas the online one was equal to 46%, despite a specificity reduction. We found that the addition of the prognostic factors Her2 and Ki67 could help improve performances on the classification of particular types of patients with the aim of reducing as much as possible the false positives that lead to axillary dissection. As showed by our experimental results, it is not particularly suitable for use as a support instrument for the prediction of metastatic lymph nodes on clinically negative patients.

Radiomic Analysis in Contrast-Enhanced Spectral Mammography for Predicting Breast Cancer Histological Outcome.

Contrast-Enhanced Spectral Mammography (CESM) is a recently introduced mammographic method with characteristics particularly suitable for breast cancer radiomic analysis. This work aims to evaluate radiomic features for predicting histological outcome and two cancer molecular subtypes, namely Human Epidermal growth factor Receptor 2 (HER2)-positive and triple-negative. From 52 patients, 68 lesions were identified and confirmed on histological examination. Radiomic analysis was performed on regions of interest (ROIs) selected from both low-energy (LE) and ReCombined (RC) CESM images. Fourteen statistical features were extracted from each ROI. Expression of estrogen receptor (ER) was significantly correlated with variation coefficient and variation range calculated on both LE and RC images; progesterone receptor (PR) with skewness index calculated on LE images; and Ki67 with variation coefficient, variation range, entropy and relative smoothness indices calculated on RC images. HER2 was significantly associated with relative smoothness calculated on LE images, and grading tumor with variation coefficient, entropy and relative smoothness calculated on RC images. Encouraging results for differentiation between ER+/ER-, PR+/PR-, HER2+/HER2-, Ki67+/Ki67-, High-Grade/Low-Grade and TN/NTN were obtained. Specifically, the highest performances were obtained for discriminating HER2+/HER2- (90.87%), ER+/ER- (83.79%) and Ki67+/Ki67- (84.80%). Our results suggest an interesting role for radiomics in CESM to predict histological outcomes and particular tumors' molecular subtype.

Biomarker phenotyping drives clinical management in axillary sentinel node: A retrospective study on women with primary breast cancer in 2002.

The current study examined if cancer biomarker phenotyping could predict the clinical/pathological status of axillary nodes in women with primary breast cancer. Primary breast cancers from 2002 were analyzed for tumor size, estrogen receptor (ER), progesterone receptor (PgR), Ki-67MIB expression and Her2/neu amplification. Relationships between the clinical and pathological status of the axilla and the biological subtypes classification were analyzed using univariate, multivariate and regression tree analysis. A total of 65% of women with axillary nodes clinically involved had complete axillary node dissection (ALND) while 705 women with clinically negative axillary underwent sentinel lymph node biopsy (SLNB), 18.5% of the latter had at least one pathologically SLNB involved node. Multivariate analysis revealed that the Luminal A subtype was significantly associated (OR 0.62; P<10-9) with clinical negative axilla while HER2pos/not Luminal was associated with clinical positivity (OR 1.71; P<0.01). No significant association between biological subtypes and SLNB status was demonstrated. Regression tree analysis revealed that subgroups with significantly different probability of SLNB status were separated according to tumor size and PgR values. In conclusion, the current study demonstrated that biomarker breast cancer phenotyping is significantly associated with clinical status of axillary nodes but not with pathological involvement of nodes at SLNB. Regression tree analysis could represent a valid attempt to individualize some patients subgroups candidate to different surgical axilla approaches.

Tumor Infiltrating Lymphocytes and NHERF1 Impact on Prognosis of Breast Cancer Patients.

BACKGROUND: Breast cancer (BC) is a heterogeneous disease, and patients with apparently similar clinicopathological characteristics in clinical practice show different outcome. This study evaluated in primary BCs and in the subgroup of the triple-negative breast cancers (TNBCs) the level of tumor infiltrating lymphocytes (TILs), Na+/H+ exchanger regulatory factor 1 (NHERF1) expression, and their association respect to the clinical outcome of patients. MATERIAL AND METHODS: NHERF1 expression was assessed by immunohistochemistry in 338 BC samples; the analysis of TILs was examined using hematoxylin and eosin stained slides, according to International TILs Working Group 2014. RESULTS: Multivariate analysis identified TILs as an independent prognostic factor for DFS in the entire cohort and in the TNBC subgroup (HR, 0.32; 95% CI, 0.12-0.87; P = 0.026; and HR, 0.22; 95% CI, 0.06-0.80; P = 0.022, respectively). Univariate and survival analysis by Kaplan-Meier method revealed that patients with cytoplasmic (c) NHERF1-/TILs+ expression had better DFS than other patients (P = 0.049), and this result was also found in the TNBC subgroup (P = 0.031). Moreover, TNBC patients with cNHERF1-/TILs- expression had a worse DFS and OS than other patients (P = 0.057 and P = 0.002, respectively). CONCLUSIONS: In the complex scenario of BC and in the era of tumor immunogenicity and immunotherapy, we found an association of TIL levels and cNHERF1 expression that could be useful to identify BCs and particularly TNBC patients with different prognosis and clinical outcome.

NHERF1 and tumor microenvironment: a new scene in invasive breast carcinoma.

BACKGROUND: Tumor microenvironment (TME) includes many factors such as tumor associated inflammatory cells, vessels, and lymphocytes, as well as different signaling molecules and extracellular matrix components. These aspects can be de-regulated and consequently lead to a worsening of cancer progression. In recent years an association between the scaffolding protein Na+/H+ exchanger regulatory factor 1 (NHERF1) and tumor microenvironment changes in breast cancer (BC) has been reported. METHODS: Subcellular NHERF1 localization, vascular endothelial growth factor (VEGF), its receptor VEGFR1, hypoxia inducible factor 1 alpha (HIF-1α), TWIST1 expression and microvessel density (MVD) in 183 invasive BCs were evaluated, using immunohistochemistry on tissue microarrays (TMA). Immunofluorescence was employed to explore protein interactions. RESULTS: Cytoplasmic NHERF1(cNHERF1) expression was directly related to cytoplasmic VEGF and VEGFR1 expression (p = 0.001 and p = 0.027 respectively), and inversely to nuclear HIF-1α (p = 0.021) and TWIST1 (p = 0.001). Further, immunofluorescence revealed an involvement of tumor cells with NHERF1 positive staining in neo-vascular formation, suggesting a "mosaic" structure development of these neo-vessels. Survival analyses showed that loss of nuclear TWIST1 (nTWIST1) expression was related to a decrease of disease free survival (DFS) (p < 0.001), while nTWIST1-/mNHERF1+ presented an increased DFS with respect to nTWIST1+/mNHERF1- phenotype (p < 0.001). Subsequently, the analyses of nTWIST1+/cNHERF1+ phenotype selected a subgroup of patients with a worse DFS compared to nTWIST1-/cNHERF1- patients (p = 0.004). CONCLUSION: Resulting data suggested a dynamic relation between NHERF1 and TME markers, and confirmed both the oncosuppressor role of membranous NHERF1 expression and the oncogene activity of cytoplasmic NHERF1.