Search

Abstract Background About 15%–20% of breast cancer (BC) cases is classified as Human Epidermal growth factor Receptor type 2 (HER2) positive. The Neoadjuvant chemotherapy (NAC) was initially introduced for locally advanced and inflammatory BC patients to allow a less extensive surgical resection, whereas now it represents the current standard for early‐stage and operable BC. However, only 20%–40% of patients achieve pathologic complete response (pCR). According to the results of practice‐changing clinical trials, the addition of trastuzumab to NAC brings improvements to pCR, and recently, the use of pertuzumab plus trastuzumab has registered further statistically significant and clinically meaningful improvements in terms of pCR. The goal of our work is to propose a machine learning model to predict the pCR to NAC in HER2‐positive patients based on a subset of clinical features. Method First, we evaluated the significant association of clinical features with pCR on the retrospectively collected data referred to 67 patients afferent to Istituto Tumori “Giovanni Paolo II.” Then, we performed a feature selection procedure to identify a subset of features to be used for training a machine learning‐based classification algorithm. As a result, pCR to NAC was associated with ER status, Pgr status, and HER2 score. Results The machine learning model trained on a subgroup of essential features reached an AUC of 73.27% (72.44%–73.66%) and an accuracy of 71.67% (71.64%–73.13%). According to our results, the clinical features alone are not enough to define a support system useful for clinical pathway. Conclusion Our results seem worthy of further investigation in large validation studies and this work could be the basis of future study that will also involve radiomics analysis of biomedical images.

Abstract Background A timely diagnosis is essential for improving breast cancer patients’ survival and designing targeted therapeutic plans. For this purpose, the screening timing, as well as the related waiting lists, are decisive. Nonetheless, even in economically advanced countries, breast cancer radiology centres fail in providing effective screening programs. Actually, a careful hospital governance should encourage waiting lists reduction programs, not only for improving patients care, but also for minimizing costs associated with the treatment of advanced cancers. Thus, in this work, we proposed a model to evaluate several scenarios for an optimal distribution of the resources invested in a Department of Breast Radiodiagnosis. Materials and methods Particularly, we performed a cost-benefit analysis as a technology assessment method to estimate both costs and health effects of the screening program, to maximise both benefits related to the quality of care and resources employed by the Department of Breast Radiodiagnosis of Istituto Tumori “Giovanni Paolo II” of Bari in 2019. Specifically, we determined the Quality-Adjusted Life Year (QALY) for estimating health outcomes, in terms of usefulness of two hypothetical screening strategies with respect to the current one. While the first hypothetical strategy adds one team made up of a doctor, a technician and a nurse, along with an ultrasound and a mammograph, the second one adds two afternoon teams. Results This study showed that the most cost-effective incremental ratio could be achieved by reducing current waiting lists from 32 to 16 months. Finally, our analysis revealed that this strategy would also allow to include more people in the screening programs (60,000 patients in 3 years).

Abstract 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.

BackgroundIn triple negative breast cancer patients treated with neoadjuvant chemotherapy, residual disease at surgery is the most relevant unfavorable prognostic factor. Current guidelines consider the use of adjuvant capecitabine, based on the results of the randomized CREATE-X study, carried out in Asian patients and including a small subset of triple negative tumors. Thus far, evidence on Caucasian patients is limited, and no real-world data are available.MethodsWe carried out a multicenter, observational study, involving 44 oncologic centres. Triple negative breast cancer patients with residual disease, treated with adjuvant capecitabine from January 2017 through June 2021, were recruited. We primarily focused on treatment tolerability, with toxicity being reported as potential cause of treatment discontinuation. Secondarily, we assessed effectiveness in the overall study population and in a subset having a minimum follow-up of 2 years.ResultsOverall, 270 patients were retrospectively identified. The 50.4% of the patients had residual node positive disease, 7.8% and 81.9% had large or G3 residual tumor, respectively, and 80.4% a Ki-67 >20%. Toxicity-related treatment discontinuation was observed only in 10.4% of the patients. In the whole population, at a median follow-up of 15 months, 2-year disease-free survival was 62%, 2 and 3-year overall survival 84.0% and 76.2%, respectively. In 129 patients with a median follow-up of 25 months, 2-year disease-free survival was 43.4%, 2 and 3-year overall survival 78.0% and 70.8%, respectively. Six or more cycles of capecitabine were associated with more favourable outcomes compared with less than six cycles.ConclusionThe CaRe study shows an unexpectedly good tolerance of adjuvant capecitabine in a real-world setting, although effectiveness appears to be lower than that observed in the CREATE-X study. Methodological differences between the two studies impose significant limits to comparability concerning effectiveness, and strongly invite further research.

Abstract 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.

IntroductionRecently, 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.MethodsThus, 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.ResultsAge, 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.DiscussionThus, our framework aims at shortening the distance between AI and clinical practice

Objective: Bladder cancer (BC) is considered one of the malignancies with moderate-high incidence, high rate of recurrence and costly management. Diagnosis and staging are thus important for therapeutic purposes. Considering the risk of residual tumour and understaging, in specific cases, international guidelines recommend performing a second transurethral resection of the bladder (reTURB). Our study aimed to evaluate the impact of hexaminolevulinate Photodynamic Diagnostics (PDD) at first TURB on the rate of residual tumour. Materials and Methods: We retrospectively analysed patients undergoing TURB in our centre between 2012 and 2020. Eightytwo patients had a re-TURB after a first complete TURB with a delay < 3 months. Patients who had an incomplete first resection were excluded. We compared patients who underwent standard white light cystoscopy/TURB and then hexaminolevulinate PDDguided reTURB (group A, n = 49) and patients with PDD-cystoscopy/ TURB at the first procedure then white light cystoscopy/reTURB (group B, n = 33). The residual tumour rate at reTURB as well as median recurrence-free survival (RFS) were compared between the two groups. Results: Residual tumour at reTURB was detected in 48.8% of cases in our cohort, with a significant difference between the two groups (71.4% in group A versus 12.5% in group B, p < 0.001). After a median follow-up of 22 months, the median RFS was 15 months in Group A and 32 months in Group B, but this difference was not significant (p = 0.7). Conclusions: Using PDD at the time of the initial TURB had a statistically significant impact on the rate of residual tumour at the reTURB. Nevertheless, the percentage of residual tumour even with the use of PDD does not allow for safely omitting second resection. Performing a reTURB with PDD for patients who did not have it initially, provides the same benefit in terms of recurrence-free survival.

Objective: To evaluate the impact on erectile and ejaculatory function following transrectal ultrasound-guided biopsies of the prostate (TRUS-Bx) in sexually active men. Methods: Monocentric prospective study from May 2021 to January 2022 of consecutive patients with suspected prostate cancer [elevated prostate specific antigen (PSA) level and/or abnormal digital rectal examination] undergoing TRUS-Bx. The 15-item version of the International Index of Erectile Function (IIEF-15), Premature Ejaculation Diagnostic Tool (PDET) and short form of Male Sexual Health Questionnaire (MSHQ-EjD Short Form) were assessed before, one and three months after TRUS-Bx. The primary endpoint was to evaluate the risk of temporary post-biopsy erectile and/or ejaculatory dysfunctions. The statistical significance was set as p value < 0.05. Results: A total of 276 consecutive patients were included in the study. The median age, PSA and biopsy cores were 65 years (IQR 59-69), 7 ng/ml (IQR 5-9.7) and 16 (IQR 12-16), respectively. We compared the IIEF subdomains before TRUS-Bx vs. one or three months: the erectile function (EF) decreased after one month (p

The treatment of HR+/HER2- metastatic breast cancer with cyclin-dependent kinases 4 and 6 inhibitors combined with endocrine therapy has recently emerged as the most relevant therapeutic strategy. However, in routine clinical practice, the best therapeutic approach in patients with comorbidities at early relapsing or ab initio metastatic disease, PI3KCA mutation, is still debated among oncologists. Given these areas of uncertainty, we conducted a Delphi survey to describe and confront the level of agreement or disagreement between clinicians working in referral vs local spoke oncological hospitals and summarize a consensus on these debated topics. In total, 56 items were drafted using the Nominal Group Technique and used for the Delphi Survey. A total of 46 clinicians participated in the survey. Overall, the consensus threshold among all participants was reached in 46/56 items (82%), and Delphi Survey results showed a high level of consensus. For the 10 items (18%) that did not reach the consensus threshold, possible explanations considering differences in clinical practice and recent findings from literature are provided in the Discussion. Outcomes from the present survey may help guide treatment in multiple comorbidities, early recurring and ab initio metastatic disease, and PI3KCA mutation, where evidence from randomized trials and level 1 evidence is currently missing.

Abstract The dynamic contrast-enhanced MR imaging plays a crucial role in evaluating the effectiveness of neoadjuvant chemotherapy (NAC) even since its early stage through the prediction of the final pathological complete response (pCR). In this study, we proposed a transfer learning approach to predict if a patient achieved pCR (pCR) or did not (non-pCR) by exploiting, separately or in combination, pre-treatment and early-treatment exams from I-SPY1 TRIAL public database. First, low-level features, i.e., related to local structure of the image, were automatically extracted by a pre-trained convolutional neural network (CNN) overcoming manual feature extraction. Next, an optimal set of most stable features was detected and then used to design an SVM classifier. A first subset of patients, called fine-tuning dataset (30 pCR; 78 non-pCR), was used to perform the optimal choice of features. A second subset not involved in the feature selection process was employed as an independent test (7 pCR; 19 non-pCR) to validate the model. By combining the optimal features extracted from both pre-treatment and early-treatment exams with some clinical features, i.e., ER, PgR, HER2 and molecular subtype, an accuracy of 91.4% and 92.3%, and an AUC value of 0.93 and 0.90, were returned on the fine-tuning dataset and the independent test, respectively. Overall, the low-level CNN features have an important role in the early evaluation of the NAC efficacy by predicting pCR. The proposed model represents a first effort towards the development of a clinical support tool for an early prediction of pCR to NAC.

Abstract In metastatic breast cancer (mBC), the change of human epidermal growth factor receptor 2 (HER2) status between primary and metastatic lesions is widely recognized, however clinical implications are unknown. Our study address the question if relevant differences exist between subjects who preserve the HER2 status and those who gain the HER2 positivity when relapsed. Data of patients affected by HER2-positive mBC, treated with pertuzumab and/or trastuzumab-emtansine (T-DM1) in a real-world setting at 45 Italian cancer centers were retrospectively collected and analyzed. From 2003 to 2017, 491 HER2‐positive mBC patients were included. Of these, 102 (20.7%) had been initially diagnosed as HER2-negative early BC. Estrogen and/or progesterone receptor were more expressed in patients with HER2-discordance compared to patients with HER2-concordant status (p

Dislocation or wrong placement of central venous catheters into the pleural cavity is rare, but if undiagnosed, may cause major, sometimes life-threatening, complications (pneumothorax, hemothorax, infection, and migration) and accidental pleural effusion due to intravenous injection of fluids containing drugs (i.e. chemotherapy, antibiotics, parenteral nutrition, other). We report a rare case of pleural effusion consisting of chemotherapy (chemothorax) directly injected into the pleural cavity due to the wrong placement of a central venous catheter (Porth-A-Cath) in a woman with breast cancer. A multidisciplinary management consisting of antidote administration, followed by removal of the venous device and washing of the pleural cavity through video-assisted thoracic surgery (VATS), avoided any major complication related to the adverse event.

Epidermal growth factor receptor 2 (EGFR2, also known as HER2) overexpression and/or amplification confers a more aggressive clinical behavior but also represents a therapeutic opportunity for targeted therapies in breast cancer (BC). Over the last 2 decades, the prognosis of HER2-positive metastatic BC patients has improved due to the introduction of anti-HER2 agents including trastuzumab and novel, emerging drugs and combinations such as trastuzumab deruxtecan and tucatinib – trastuzumab - capecitabine. Herein, we provide a critical overview of current clinical recommendations and emerging treatment options for metastatic HER2-positive BC, especially focusing on recently presented and published clinical trials in this setting.

Background. The combination of chemotherapy plus anti HER-2 agents is the mainstay of HER-2 positive advanced breast cancer (ABC) therapy. We conducted a phase II trial testing activity and safety of trastuzumab and metronomic capecitabine/cyclophosphamide (HEX) as first-line therapy in HER-2 positive ABC. Methods. Patients at first relapse or with synchronous metastasis were treated with trastuzumab (4 mg/kg, biweekly) plus oral capecitabine (1500 mg/daily) and cyclophosphamide (50 mg/daily). Primary endpoint was objective response rate (ORR), secondary endpoints progression-free survival (PFS), clinical benefit rate (CBR; PR + CR + SD for ≥ 24 weeks) and tolerability. Optimal two-stage design was applied. Results. Sixty patients with measurable ABC, tumors scored as +3 for HER-2 or FISH +, untreated for advanced disease were enrolled. Median age was 62.5 years, visceral metastases were present in most patients (57.9%). Median number of cycles was 16 (range 1–98). ORR was 56.7% (95% CI, 44.1–68.4%), with 5 CR (8.3%) and 29 PR (48.3%). Fifteen patients had SD (25%). The CBR was 78.2%. Nine progressions were observed (15%). Median PFS was 11 months. One year PFS was 47.7%. Median OS was 45.9 months. Worst toxicities were grade 3 hand-foot syndrome in 2 pts (3.3%), grade 3 anaemia in 2 pts (3.3%), grade 2 nausea in 2 pts (3.3%) and grade 3–4 diarrhea in 2 pts (3.3%). Cardiac toxicity grade 1 was reported in 1 pt. Conclusions. Combination of trastuzumab and metronomic oral chemotherapy has clinical activity. The tolerability was excellent and allowed the prolonged delivery of treatment.

Designing targeted treatments for breast cancer patients after primary tumor removal is necessary to prevent the occurrence of invasive disease events (IDEs), such as recurrence, metastasis, contralateral and second tumors, over time. However, due to the molecular heterogeneity of this disease, predicting the outcome and efficacy of the adjuvant therapy is challenging. A novel ensemble machine learning classification approach was developed to address the task of producing prognostic predictions of the occurrence of breast cancer IDEs at both 5- and 10-years. The method is based on the concept of voting among multiple models to give a final prediction for each individual patient. Promising results were achieved on a cohort of 529 patients, whose data, related to primary breast cancer, were provided by Istituto Tumori “Giovanni Paolo II” in Bari, Italy. Our proposal greatly improves the performances returned by the baseline original model, i.e., without voting, finally reaching a median AUC value of 77.1% and 76.3% for the IDE prediction at 5-and 10-years, respectively. Finally, the proposed approach allows to promote more intelligible decisions and then a greater acceptability in clinical practice since it returns an explanation of the IDE prediction for each individual patient through the voting procedure.

Background: The evolution of therapeutic landscape of human epidermal growth factor receptor-2 (HER2)-positive breast cancer (BC) has led to an unprecedented outcome improvement, even if the optimal sequence strategy is still debated. To address this issue and to provide a picture of the advancement of anti-HER2 treatments, we performed a large, multicenter, retrospective study of HER2-positive BC patients. Methods: The observational PANHER study included 1,328 HER2-positive advanced BC patients treated with HER2 blocking agents since June 2000 throughout July 2020. Endpoints of efficacy were progression-free survival (PFS) and overall survival (OS). Results: Patients who received a first-line pertuzumab-based regimen showed better PFS ( p < 0.0001) and OS ( p = 0.004) than those receiving other treatments. Median PFS and mOS from second-line starting were 8 and 28 months, without significant differences among various regimens. Pertuzumab-pretreated patients showed a mPFS and a mOS from second-line starting not significantly affected by type of second line, that is, T-DM1 or lapatinib/capecitabine ( p = 0.80 and p = 0.45, respectively). Conversely, pertuzumab-naïve patients receiving second-line T-DM1 showed a significantly higher mPFS compared with that of patients treated with lapatinib/capecitabine ( p = 0.004). Median OS from metastatic disease diagnosis was higher in patients treated with trastuzumab-based first line followed by second-line T-DM1 in comparison to pertuzumab-based first-line and second-line T-DM1 ( p = 0.003), although these data might be partially influenced by more favorable prognostic characteristics of patients in the pre-pertuzumab era . No significant differences emerged when comparing patients treated with ‘old’ or ‘new’ drugs ( p = 0.43), even though differences in the length of the follow-up between the two cohorts should be taken into account. Conclusion: Our results confirmed a relevant impact of first-line pertuzumab-based treatment and showed lower efficacy of second-line T-DM1 in trastuzumab/pertuzumab pretreated, as compared with pertuzumab-naïve patients. Our findings may help delineate a more appropriate therapeutic strategy in HER2-positive metastatic BC. Prospective randomized trials addressing this topic are awaited.

Segmental testicular infarction is rare, and the etiology is mostly idiopathic. We report a case series of four young patients, one of them with metachronous bilateral disease, presenting with an acute scrotum and treated with a testis-sparing approach, if feasible, after a negative intraoperative biopsy. Etiology, differential diagnosis, and management are reviewed. To be aware of clinical and imaging features of this benign testicular pathology, it is crucial to avoid unnecessary orchiectomies to preserve vital testicular tissue left.

The current guidelines recommend the sentinel lymph node biopsy to evaluate the lymph node involvement for breast cancer patients with clinically negative lymph nodes on clinical or radiological examination. Machine learning (ML) models have significantly improved the prediction of lymph nodes status based on clinical features, thus avoiding expensive, time-consuming and invasive procedures. However, the classification of sentinel lymph node status represents a typical example of an unbalanced classification problem. In this work, we developed a ML framework to explore the effects of unbalanced populations on the performance and stability of feature ranking for sentinel lymph node status classification in breast cancer. Our results indicate state-of-the-art AUC (Area under the Receiver Operating Characteristic curve) values on a hold-out set (67%) while providing particularly stable features related to tumor size, histological subtype and estrogen receptor expression, which should therefore be considered as potential biomarkers.

Immune checkpoint inhibitors (ICIs) have made a breakthrough in the systemic treatment for metastatic triple-negative breast cancer (TNBC) patients. However, results of phase II and III clinical trials assessing ICIs plus chemotherapy as neoadjuvant treatment were controversial and conflicting. We performed a meta-analysis aimed at assessing the Odds Ratio (OR) of the pathological complete response (pCR) rate in trials assessing neoadjuvant chemoimmunotherapy in TNBC. According to our results, the use of neoadjuvant chemoimmunotherapy was associated with higher pCR (OR 1.95; 95% Confidence Intervals, 1.27–2.99). In addition, we highlighted that this benefit was observed regardless of PD-L1 status since the analysis reported a statistically significant and clinically meaningful benefit in both PD-L1 positive and PD-L1 negative patients. These findings further support the exploration of the role of ICIs plus chemotherapy in early-stage TNBC, given the potentially meaningful clinical impact of these agents. Further studies aimed at more deeply investigating this emerging topic in breast cancer immunotherapy are warranted.

The mortality associated to breast cancer is in many cases related to metastasization and recurrence. Personalized treatment strategies are critical for the outcomes improvement of BC patients and the Clinical Decision Support Systems can have an important role in medical practice. In this paper, we present the preliminary results of a prediction model of the Breast Cancer Recurrence (BCR) within five and ten years after diagnosis. The main breast cancer-related and treatment-related features of 256 patients referred to Istituto Tumori “Giovanni Paolo II” of Bari (Italy) were used to train machine learning algorithms at the-state-of-the-art. Firstly, we implemented several feature importance techniques and then we evaluated the prediction performances of BCR within 5 and 10 years after the first diagnosis by means different classifiers. By using a small number of features, the models reached highly performing results both with reference to the BCR within 5 years and within 10 years with an accuracy of 77.50% and 80.39% and a sensitivity of 92.31% and 95.83% respectively, in the hold-out sample test. Despite validation studies are needed on larger samples, our results are promising for the development of a reliable prognostic supporting tool for clinicians in the definition of personalized treatment plans.

Abstract Background It is frequently asked whether chemotherapy can still play a role in metastatic melanoma considering the effectiveness of the available drugs today, including antiCTLA4/antiPD1 immunotherapy and antiBRAF/antiMEK inhibitors. However, only approximately half of patients respond to these drugs, and the majority progress after 6–11 months. Therefore, a need for other therapeutic options is still very much apparent. We report the first large trial of a sequential full dose of fotemustine (FM) preceded by a low dose of temozolomide (TMZ) as a chemo-modulator in order to inactivate the DNA repair action of O(6)-methylguanine DNA-methyltransferase (MGMT). Primary endpoints were overall response and safety. We also evaluated specific biological parameters aiming to tailor these chemotherapies to selected patients. Methods A total of 69 consecutive patients were enrolled. The main features included a median age of 60 years (21–81) and M1c stage, observed in 74% of the patients, with brain metastases in 15% and high LDH levels in 42% of the patients. The following schedule was used: oral TMZ 100 mg/m2 on days 1 and 2 and FM iv 100 mg/m2 on day 2, 4 h after TMZ; A translational study aiming to analyse MGMT methylation status and base-excision repair (BER) gene expression was performed in a subset of 14 patients. Results We reported an overall response rate of 30.3% with 3 complete responses and a disease control rate of 50.5%. The related toxicity rate was low and mainly of haematological types. Although our population had a very poor prognosis, we observed a PFS of 6 months and an OS of 10 months. A non-significant correlation with response was found with the mean expression level of the three genes involved in the BER pathway (APE1, XRCC1 and PARP1), whereas no association was found with MGMT methylation status. Conclusion This schedule could represent a good alternative for patients who are not eligible for immune or targeted therapy or whose previous therapies have failed. Trial registration EUDRACT 2009–016487-36l; date of registration 23 June 2010.

The reported incidence of node metastasis at sentinel lymph node biopsy is generally low, so that the majority of women underwent unnecessary invasive axilla surgery. Although the sentinel lymph node biopsy is time consuming and expensive, it is still the intra-operative exam with the highest performance, but sometimes surgery is achieved without a clear diagnosis and also with possible serious complications. In this work, we developed a machine learning model to predict the sentinel lymph nodes positivity in clinically negative patients. Breast cancer clinical and immunohistochemical features of 907 patients characterized by a clinically negative lymph node status were collected. We trained different machine learning algorithms on the retrospective collected data and selected an optimal subset of features through a sequential forward procedure. We found comparable performances for different classification algorithms: on a hold-out training set, the logistics regression classifier with seven features, i.e., tumor diameter, age, histologic type, grading, multiplicity, in situ component and Her2-neu status reached an AUC value of 71.5% and showed a better trade-off between sensitivity and specificity (69.4 and 66.9%, respectively) compared to other two classifiers. On the hold-out test set, the performance dropped by five percentage points in terms of accuracy. Overall, the histological characteristics alone did not allow us to develop a support tool suitable for actual clinical application, but it showed the maximum informative power contained in the same for the resolution of the clinical problem. The proposed study represents a starting point for future development of predictive models to obtain the probability for lymph node metastases by using histopathological features combined with other features of a different nature.

Several retrospective analyses of large amounts of contemporary data have shown the superiority of breast conservative surgery (BCS) over mastectomy carried out in the early stage of breast cancer. The characteristics of the patients and cancers that are most likely to benefit from BCS remain unclear. In our work, we analyzed the disease-free survival (DFS) of a cohort of patients treated with BCS or mastectomy between 1995 and 2018 in our institute with pT1-2, pN0, or cM0 breast cancer. The DFS curves of patients treated with both mastectomy and quadrantectomy were compared in the different subsamples with respect to the clinical and histopathological characteristics. We identified 188 eligible patients treated with BCS and 64 patients treated with mastectomy. DFS was not found to be statistically higher in patients treated with BCS compared to those treated with mastectomy, who achieved a 5-year DFS of 89.9% vs. 81.3% and a 10-year DFS of 78.9% vs. 79.3%, respectively. No significant differences were detected for the DFS curves when patients were differentiated by the type of surgical treatment received, age, and the tumor histological characteristics. We verified a p-value just above the 10% significance threshold for patients with tumor dimensions between 20 mm and 50 mm and molecular sub-type Luminal B. In our experience, treatment with mastectomy is not associated with improved DFS compared to treatment with BCS in women with early-stage tumors.

In recent years personalized medicine reached an increasing importance, especially in the design of oncological therapies. In particular, the development of patients’ profiling strategies suggests the possibility of promising rewards. In this work, we present an explainable artificial intelligence (XAI) framework based on an adaptive dimensional reduction which (i) outlines the most important clinical features for oncological patients’ profiling and (ii), based on these features, determines the profile, i.e., the cluster a patient belongs to. For these purposes, we collected a cohort of 267 breast cancer patients. The adopted dimensional reduction method determines the relevant subspace where distances among patients are used by a hierarchical clustering procedure to identify the corresponding optimal categories. Our results demonstrate how the molecular subtype is the most important feature for clustering. Then, we assessed the robustness of current therapies and guidelines; our findings show a striking correspondence between available patients’ profiles determined in an unsupervised way and either molecular subtypes or therapies chosen according to guidelines, which guarantees the interpretability characterizing explainable approaches to machine learning techniques. Accordingly, our work suggests the possibility to design data-driven therapies to emphasize the differences observed among the patients.

Primary urethral lymphoma is a rare entity without a standardized treatment protocol. We report a case of an elderly woman presenting with a caruncle associated with vaginal spotting and intermittent dysuria. She underwent surgical excision of the lesion. Histological analysis revealed a blastoid variant of mantle cell lymphoma, a previously unreported subtype. The patient received chlorambucil assisting a rapid local disease progression. She died of disseminated disease 6 months after diagnosis. A review of the lymphomas of the urethra is included.

Contrast-enhanced spectral mammography (CESM) is an advanced instrument for breast care that is still operator dependent. The aim of this paper is the proposal of an automated system able to discriminate benign and malignant breast lesions based on radiomic analysis. We selected a set of 58 regions of interest (ROIs) extracted from 53 patients referred to Istituto Tumori “Giovanni Paolo II” of Bari (Italy) for the breast cancer screening phase between March 2017 and June 2018. We extracted 464 features of different kinds, such as points and corners of interest, textural and statistical features from both the original ROIs and the ones obtained by a Haar decomposition and a gradient image implementation. The features data had a large dimension that can affect the process and accuracy of cancer classification. Therefore, a classification scheme for dimension reduction was needed. Specifically, a principal component analysis (PCA) dimension reduction technique that includes the calculation of variance proportion for eigenvector selection was used. For the classification method, we trained three different classifiers, that is a random forest, a naïve Bayes and a logistic regression, on each sub-set of principal components (PC) selected by a sequential forward algorithm. Moreover, we focused on the starting features that contributed most to the calculation of the related PCs, which returned the best classification models. The method obtained with the aid of the random forest classifier resulted in the best prediction of benign/malignant ROIs with median values for sensitivity and specificity of 88.37% and 100%, respectively, by using only three PCs. The features that had shown the greatest contribution to the definition of the same were almost all extracted from the LE images. Our system could represent a valid support tool for radiologists for interpreting CESM images.

Learning tasks are implemented via mappings of the sampled data set, including both the classical and the quantum framework. Biomedical data characterizing complex diseases such as cancer typically require an algorithmic support for clinical decisions, especially for early stage tumors that typify breast cancer patients, which are still controllable in a therapeutic and surgical way. Our case study consists of the prediction during the pre-operative stage of lymph node metastasis in breast cancer patients resulting in a negative diagnosis after clinical and radiological exams. The classifier adopted to establish a baseline is characterized by the result invariance for the order permutation of the input features, and it exploits stratifications in the training procedure. The quantum one mimics support vector machine mapping in a high-dimensional feature space, yielded by encoding into qubits, while being characterized by complexity. Feature selection is exploited to study the performances associated with a low number of features, thus implemented in a feasible time. Wide variations in sensitivity and specificity are observed in the selected optimal classifiers during cross-validations for both classification system types, with an easier detection of negative or positive cases depending on the choice between the two training schemes. Clinical practice is still far from being reached, even if the flexible structure of quantum-inspired classifier circuits guarantees further developments to rule interactions among features: this preliminary study is solely intended to provide an overview of the particular tree tensor network scheme in a simplified version adopting just product states, as well as to introduce typical machine learning procedures consisting of feature selection and classifier performance evaluation.

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.

The typification of breast lumps with fine-needle biopsies is often affected by inconclusive results that extend diagnostic time. Many breast centers have progressively substituted cytology with micro-histology. The aim of this study is to assess the performance of a 13G-needle biopsy using cable-free vacuum-assisted breast biopsy (VABB) technology. Two of our operators carried out 200 micro-histological biopsies using the Elite 13G-needle VABB and 1314 14–16G-needle core biopsies (CBs) on BI-RADS 3, 4, and 5 lesions. Thirty-one of the procedures were repeated following CB, eighteen following cytological biopsy, and three after undergoing both procedures. The VABB Elite procedure showed high diagnostic performance with an accuracy of 94.00%, a sensitivity of 92.30%, and a specificity of 100%, while the diagnostic underestimation was 11.00%, all significantly comparable to of the CB procedure. The VABB Elite 13G system has been shown to be a simple, rapid, reliable, and well-tolerated biopsy procedure, without any significant complications and with a diagnostic performance comparable to traditional CB procedures. The histological class change in an extremely high number of samples would suggest the use of this procedure as a second-line biopsy for suspect cases or those with indeterminate cyto-histological results.

Enzymatic activation of irinotecan (CPT-11) is due to carboxylesterase (CES), and its pharmacological behavior is influenced by drug resistance-related proteins. We previously reported that the clinical response and prognosis of metastatic colorectal cancer (mCRC) patients did not differ in tumors with different thymidylate synthase (TS) or topoisomerase-I (Topo-I) expression. Using immunohistochemistry (IHC), we evaluated the biological role of CES2 and the expression of breast cancer resistance protein (BCRP/ABCG2) in 58 consecutive mCRC patients, who had undergone a first-line CPT-11/5-FU/leucovirin (FOLFIRI) regimen. The expression of these proteins was also examined in a group of synchronous lymph nodes and liver metastases. Furthermore, all samples were revaluated for TS and Topo-I expression. High expression of CES2, ABCG2, TS and Topo-I was observed in 55%, 56%, 38% and 49% of patients, respectively. There was a significant association between high TS and high ABCG2 expression (p = 0.049). Univariate analysis showed that only TS expression significantly impacted on time to progression (p = 0.005). Moreover, Cox’ multivariate analysis revealed that TS expression was significantly associated with overall survival (p = 0.01). No significant correlation was found between investigated markers expression and clinical response. Topo-I expression resulted in being significantly higher in liver metastases with respect to the corresponding primary tumors (p < 0.0001), emphasizing the role of Topo-I expression in metastatic cancer biology. In primary tumor tissues, CES2 expression tended to be higher than that observed in liver metastasis tissues (p = 0.05). These preliminary data may suggest CES2 over-expression as a potential marker of malignant phenotype. In light of these findings, we suggest that Topo-I expression together with TS expression could be associated with metastatic progression of CRC. Further studies are warranted with the aim of evaluating the potential predictive and prognostic role of CES2 and ABCG2 in larger series of patients.

Objective: to estimate the impact of lapatinib utilization within the Italian National Health Service (NHS) resources consumption. Lapatinib is an oral inhibitor of kinase protein, approved as dual therapy with capecitabine for the treatment of metastatic breast cancer patients with HER2 overexpression who experience disease progression despite trastuzumab treatment. Methods: the analysis is based on a model, which structure can be summarized as follows: a) national cancer registries-based estimate of the yearly number of HER2+ breast cancer patients who develop metastatic disease in Italy; b) literature-based identification of the rate of patients eligible to receive lapatinib; c) identification of the current therapeutic strategy-mix; d) costing of the alternatives, and e) calculation of budget impact. Direct NHS costs (drug acquisition and administration, and monitoring for 8 cycles of 21 days) are estimated based on current Italian prices and tariffs. Results: the annual number of patients eligible for lapatinib-based therapy can vary from 1,676 to 2,172, according to the expected extent of the trastuzumab use as adjuvant therapy. The current strategy-mix beyond progression is based on drugs used in the clinical practice, with a portion of patients continuing trastuzumab. Pharmaceutical cost of lapatinib results higher than the average cost of the current pattern of treatments. This cost increase would be partially offset by the reduction of laboratory tests and hospital personnel work for the oral administration of lapatinib, as compared to intravenous strategies. Furthermore, a risk sharing agreement has been adopted by NHS and manufacturer, according to which the NHS pays only for responding patients. As a consequence, lapatinib-based therapy would increase yearly NHS expenditure by about 3.8-4.9 millions of euro. Conclusions: lapatinib is the only treatment option specifically indicated for the management of HER2+, metastatic breast cancer in patients who received prior treatments including trastuzumab and is estimated to induce a low budget impact for the Italian NHS.

Vito LorussoOncologic Institute, Vito Fazzi Hospital, Lecce, ItalyAbstract: Angiogenesis has a clear and definite role in the breast cancer progression process, making antivascular endothelial growth factor (VEGF) therapies an attractive option for the treatment of metastatic breast cancer (MBC). Bevacizumab is a potent humanized monoclonal antibody to VEGF, which has shown regression of breast cancer in preclinical and clinical setting, either alone or in combination with cytotoxic treatment. Additionally, bevacizumab potentially increases the effectiveness of other anticancer therapies through the normalization of tumor vasculature, reduction of intratumoral pressure and improved tumor oxygenation. Phase 1/2 trials showed significant antitumor effects of bevacizumab in MBC, in particular in tumors not expressing HER2 receptor. A first phase 3 trial in pre-treated MBC patients showed better response rates but no survival benefit from the addition of bevacizumab to capecitabine. However, in two phase 2 trial in first-line setting in patients with MBC, bevacizumab improved progression-free survival in combination with weekly paclitaxel in comparison to paclitaxel alone or in combination with 3-weekly docetaxel in comparison with docetaxel alone, respectively. Bevacizumab in combination with taxanes seems to be a highly effective first-line treatment for MBC patients. Future research will investigate bevacizumab in the neoadjuvant or adjuvant setting, where even more potential may exist for these patients.Keywords: bevacizumab, breast cancer, HER2, HER2-negative breast cancer

BackgroundBone is an uncommon site of metastasis in patients with advanced hepatocellular carcinoma (HCC). Therefore, there are few studies concerning the natural history of bone metastasis in patients with HCC.Patients and methodsData on clinicopathology, survival, skeletal-related events (SREs), and bone-directed therapies for 211 deceased HCC patients with evidence of bone metastasis were statistically analyzed.ResultsThe median age was 70 years; 172 patients were male (81.5%). The median overall survival was 19 months. The median time to the onset of bone metastasis was 13 months (22.2% at HCC diagnosis); 64.9% patients had multiple bone metastases. Spine was the most common site of bone metastasis (59.7%). Most of these lesions were osteolytic (82.4%); 88.5% of them were treated with zoledronic acid. At multivariate analysis, only the Child Score was significantly correlated with a shorter time to diagnosis of bone metastases (p = 0.001, HR = 1.819). The median survival from bone metastasis was 7 months. At multivariate analysis, HCC etiology (p = 0.005), ECOG performance status (p = 0.002) and treatment with bisphosphonate (p = 0.024) were associated with shorter survival after bone disease occurrence. The site of bone metastasis but not the number of bone lesions was associated with the survival from first skeletal related event (SRE) (p = 0.021) and OS (p = 0.001).ConclusionsThis study provides a significant improvement in the understanding the natural history of skeletal disease in HCC patients. An early and appropriate management of these patients is dramatically needed in order to avoid subsequent worsening of their quality of life.

Rituximab is a chimeric monoclonal antibody directed against human CD20 antigen, which is expressed on B-cell lymphocytes and on the majority of B-cell lymphoid malignancies. Herein we report the conjugate of rituximab with the near-infrared (NIR) fluorophore Cy5.5 (RI-Cy5.5) as a tool for in vitro, in vivo, and ex vivo NIR time-domain (TD) optical imaging. In vitro, RI-Cy5.5 retained biologic activity and led to elevated cell-associated fluorescence on tumor cells. In vivo, TD optical imaging analysis of RI-Cy5.5 injected into lymphoma-bearing mice revealed a slow tumor uptake and a specific long-lasting persistence of the probe within the tumor. Biodistribution studies after intraperitoneal and endovenous administration were undertaken to evaluate differences in the tumor uptake. RI-Cy5.5 concentration in the organs after intraperitoneal injection was not as high as after endovenous injection. Ex vivo analysis of biologic tissues and organs by both TD optical imaging and immunohistochemistry confirmed the probe distribution, as demonstrated by imaging experiment in vivo, showing that RI-Cy5.5 selectively accumulated in the tumor tissue and major excretion organs. In summary, the study indicates that NIR TD optical imaging is a powerful tool for rituximab-targeting investigation, furthering understanding of its administration outcome in lymphoma treatment.