Explainable 3D CNN based on baseline breast DCE-MRI to give an early prediction of pathological complete response to neoadjuvant chemotherapy.

BACKGROUND: So far, baseline Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) has played a key role for the application of sophisticated artificial intelligence-based models using Convolutional Neural Networks (CNNs) to extract quantitative imaging information as earlier indicators of pathological Complete Response (pCR) achievement in breast cancer patients treated with neoadjuvant chemotherapy (NAC). However, these models did not exploit the DCE-MRI exams in their full geometry as 3D volume but analysed only few individual slices independently, thus neglecting the depth information. METHOD: This study aimed to develop an explainable 3D CNN, which fulfilled the task of pCR prediction before the beginning of NAC, by leveraging the 3D information of post-contrast baseline breast DCE-MRI exams. Specifically, for each patient, the network took in input a 3D sequence containing the tumor region, which was previously automatically identified along the DCE-MRI exam. A visual explanation of the decision-making process of the network was also provided. RESULTS: To the best of our knowledge, our proposal is competitive than other models in the field, which made use of imaging data alone, reaching a median AUC value of 81.8%, 95%CI [75.3%; 88.3%], a median accuracy value of 78.7%, 95%CI [74.8%; 82.5%], a median sensitivity value of 69.8%, 95%CI [59.6%; 79.9%] and a median specificity value of 83.3%, 95%CI [82.6%; 84.0%], respectively. The median and CIs were computed according to a 10-fold cross-validation scheme for 5 rounds. CONCLUSION: Finally, this proposal holds high potential to support clinicians on non-invasively early pursuing or changing patient-centric NAC pathways.

Treatment of Thoracic SMARCA4-Deficient Undifferentiated Tumors: Where We Are and Where We Will Go.

Recently, the fifth edition of the WHO classification recognized the thoracic SMARCA4-deficient undifferentiated tumor (SMARCA4-UT) as a separate entity from conventional non-small cell lung cancer with SMARCA4 deficiency because of the different clinicopathological characteristics of these two diseases. SMARCA4-UT mainly occurs in young to middle-aged adults and involves a large mass compressing the tissues surrounding the mediastinum and lung parenchyma. Unfortunately, SMARCA4-UT shows a high probability of recurrence after upfront surgery as well as radiotherapy resistance; moreover, chemotherapy has low efficacy. Moreover, given the recent classification of SMARCA4-UT, no data concerning specific clinical trials are currently available. However, several case reports show immunotherapy efficacy in patients with this disease not only in a metastatic setting but also in a neoadjuvant manner, supporting the development of clinical trials. In addition, preclinical data and initial clinical experiences suggest that inhibiting pathways such as CDK4/6, AURKA, ATR, and EZH2 may be a promising therapeutic approach to SMARCA4-UT.

Comparison between vision transformers and convolutional neural networks to predict non-small lung cancer recurrence.

Non-Small cell lung cancer (NSCLC) is one of the most dangerous cancers, with 85% of all new lung cancer diagnoses and a 30-55% of recurrence rate after surgery. Thus, an accurate prediction of recurrence risk in NSCLC patients during diagnosis could be essential to drive targeted therapies preventing either overtreatment or undertreatment of cancer patients. The radiomic analysis of CT images has already shown great potential in solving this task; specifically, Convolutional Neural Networks (CNNs) have already been proposed providing good performances. Recently, Vision Transformers (ViTs) have been introduced, reaching comparable and even better performances than traditional CNNs in image classification. The aim of the proposed paper was to compare the performances of different state-of-the-art deep learning algorithms to predict cancer recurrence in NSCLC patients. In this work, using a public database of 144 patients, we implemented a transfer learning approach, involving different Transformers architectures like pre-trained ViTs, pre-trained Pyramid Vision Transformers, and pre-trained Swin Transformers to predict the recurrence of NSCLC patients from CT images, comparing their performances with state-of-the-art CNNs. Although, the best performances in this study are reached via CNNs with AUC, Accuracy, Sensitivity, Specificity, and Precision equal to 0.91, 0.89, 0.85, 0.90, and 0.78, respectively, Transformer architectures reach comparable ones with AUC, Accuracy, Sensitivity, Specificity, and Precision equal to 0.90, 0.86, 0.81, 0.89, and 0.75, respectively. Based on our preliminary experimental results, it appears that Transformers architectures do not add improvements in terms of predictive performance to the addressed problem.

A CT-based transfer learning approach to predict NSCLC recurrence: The added-value of peritumoral region.

Non-small cell lung cancer (NSCLC) represents 85% of all new lung cancer diagnoses and presents a high recurrence rate after surgery. Thus, an accurate prediction of recurrence risk in NSCLC patients at diagnosis could be essential to designate risk patients to more aggressive medical treatments. In this manuscript, we apply a transfer learning approach to predict recurrence in NSCLC patients, exploiting only data acquired during its screening phase. Particularly, we used a public radiogenomic dataset of NSCLC patients having a primary tumor CT image and clinical information. Starting from the CT slice containing the tumor with maximum area, we considered three different dilatation sizes to identify three Regions of Interest (ROIs): CROP (without dilation), CROP 10 and CROP 20. Then, from each ROI, we extracted radiomic features by means of different pre-trained CNNs. The latter have been combined with clinical information; thus, we trained a Support Vector Machine classifier to predict the NSCLC recurrence. The classification performances of the devised models were finally evaluated on both the hold-out training and hold-out test sets, in which the original sample has been previously divided. The experimental results showed that the model obtained analyzing CROP 20 images, which are the ROIs containing more peritumoral area, achieved the best performances on both the hold-out training set, with an AUC of 0.73, an Accuracy of 0.61, a Sensitivity of 0.63, and a Specificity of 0.60, and on the hold-out test set, with an AUC value of 0.83, an Accuracy value of 0.79, a Sensitivity value of 0.80, and a Specificity value of 0.78. The proposed model represents a promising procedure for early predicting recurrence risk in NSCLC patients.

A Machine Learning Approach for Predicting Capsular Contracture after Postmastectomy Radiotherapy in Breast Cancer Patients.

In recent years, immediate breast reconstruction after mastectomy surgery has steadily increased in the treatment pathway of breast cancer (BC) patients due to its potential impact on both the morpho-functional and aesthetic type of the breast and the quality of life. Although recent studies have demonstrated how recent radiotherapy techniques have allowed a reduction of adverse events related to breast reconstruction, capsular contracture (CC) remains the main complication after post-mastectomy radio-therapy (PMRT). In this study, we evaluated the association of the occurrence of CC with some clinical, histological and therapeutic parameters related to BC patients. We firstly performed bivariate statistical tests and we then evaluated the prognostic predictive power of the collected data by using machine learning techniques. Out of a sample of 59 patients referred to our institute, 28 patients (i.e., 47%) showed contracture after PMRT. As a result, only estrogen receptor status (ER) and molecular subtypes were significantly associated with the occurrence of CC after PMRT. Different machine learning models were trained on a subset of clinical features selected by a feature importance approach. Experimental results have shown that collected features have a non-negligible predictive power. The extreme gradient boosting classifier achieved an area under the curve (AUC) value of 68% and accuracy, sensitivity, and specificity values of 68%, 64%, and 74%, respectively. Such a support tool, after further suitable optimization and validation, would allow clinicians to identify the best therapeutic strategy and reconstructive timing.

Immunotherapy in Elderly Patients Affected by Non-Small Cell Lung Cancer: A Narrative Review.

Lung cancer is the leading cause of cancer-related deaths worldwide. Non-small cell lung cancer (NSCLC) accounts for approximately 80% of all lung cancers, and most NSCLC is diagnosed in the advanced stage. The advent of immune check point inhibitors (ICIs) changed the therapeutic scenario both in metastatic disease (in first and subsequent lines) and earlier settings. Comorbidities, reduced organ function, cognitive deterioration, and social impairment give reasons for a greater probability of adverse events, making the treatment of elderly patients challenging. The reduced toxicity of ICIs compared to standard chemotherapy makes this approach attractive in this population. The effectiveness of ICIs varies according to age, and patients older than 75 years may benefit less than younger patients. This may be related to the so-called immunosenescence, a phenomenon that refers to the reduced activity of immunity with older age. Elders are often under-represented in clinical trials, even if they are a large part of the patients in a clinical practice. In this review, we aim to explore the biological aspects of immunosenescence and to report and analyze the most relevant and recent literature findings on the role of immunotherapy in elderly patients with NSCLC.

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.

Consolidative thoracic radiation therapy for extensive-stage small cell lung cancer in the era of first-line chemoimmunotherapy: preclinical data and a retrospective study in Southern Italy.

Background: Consolidative thoracic radiotherapy (TRT) has been commonly used in the management of extensive-stage small cell lung cancer (ES-SCLC). Nevertheless, phase III trials exploring first-line chemoimmunotherapy have excluded this treatment approach. However, there is a strong biological rationale to support the use of radiotherapy (RT) as a boost to sustain anti-tumor immune responses. Currently, the benefit of TRT after chemoimmunotherapy remains unclear. The present report describes the real-world experiences of 120 patients with ES-SCLC treated with different chemoimmunotherapy combinations. Preclinical data supporting the hypothesis of anti-tumor immune responses induced by RT are also presented. Methods: A total of 120 ES-SCLC patients treated with chemoimmunotherapy since 2019 in the South of Italy were retrospectively analyzed. None of the patients included in the analysis experienced disease progression after undergoing first-line chemoimmunotherapy. Of these, 59 patients underwent TRT after a multidisciplinary decision by the treatment team. Patient characteristics, chemoimmunotherapy schedule, and timing of TRT onset were assessed. Safety served as the primary endpoint, while efficacy measured in terms of overall survival (OS) and progression-free survival (PFS) was used as the secondary endpoint. Immune pathway activation induced by RT in SCLC cells was explored to investigate the biological rationale for combining RT and immunotherapy. Results: Preclinical data supported the activation of innate immune pathways, including the STimulator of INterferon pathway (STING), gamma-interferon-inducible protein (IFI-16), and mitochondrial antiviral-signaling protein (MAVS) related to DNA and RNA release. Clinical data showed that TRT was associated with a good safety profile. Of the 59 patients treated with TRT, only 10% experienced radiation toxicity, while no ≥ G3 radiation-induced adverse events occurred. The median time for TRT onset after cycles of chemoimmunotherapy was 62 days. Total radiation dose and fraction dose of TRT include from 30 Gy in 10 fractions, up to definitive dose in selected patients. Consolidative TRT was associated with a significantly longer PFS than systemic therapy alone (one-year PFS of 61% vs. 31%, p<0.001), with a trend toward improved OS (one-year OS of 80% vs. 61%, p=0.027). Conclusion: Multi-center data from establishments in the South of Italy provide a general confidence in using TRT as a consolidative strategy after chemoimmunotherapy. Considering the limits of a restrospective analysis, these preliminary results support the feasibility of the approach and encourage a prospective evaluation.

A machine learning ensemble approach for 5- and 10-year breast cancer invasive disease event classification.

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.

An Invasive Disease Event-Free Survival Analysis to Investigate Ki67 Role with Respect to Breast Cancer Patients' Age: A Retrospective Cohort Study.

Characterization of breast cancer into intrinsic molecular profiles has allowed women to live longer, undergoing personalized treatments. With the aim of investigating the relation between different values of ki67 and the predisposition to develop a breast cancer-related IDE at different ages, we enrolled 900 patients with a first diagnosis of invasive breast cancer, and we partitioned the dataset into two sub-samples with respect to an age value equal to 50 years. For each sample, we performed a Kaplan−Meier analysis to compare the IDE-free survival curves obtained with reference to different ki67 values. The analysis on patients under 50 years old resulted in a p-value < 0.001, highlighting how the behaviors of patients characterized by a ki67 ranging from 10% to 20% and greater than 20% were statistically significantly similar. Conversely, patients over 50 years old characterized by a ki67 ranging from 10% to 20% showed an IDE-free survival probability significantly greater than patients with a ki67 greater than 20%, with a p-value of 0.01. Our work shows that the adoption of two different ki67 values, namely, 10% and 20%, might be discriminant in designing personalized treatments for patients under 50 years old and over 50 years old, respectively.

Cemiplimab in an Elderly Frail Population of Patients With Locally Advanced or Metastatic Cutaneous Squamous Cell Carcinoma: A Single-Center Real-Life Experience From Italy.

BACKGROUND: Cutaneous squamous cell carcinoma (CSCC) is the second most common skin cancer whose incidence is growing parallel to the lengthening of the average lifespan. Cemiplimab, an antiPD-1 monoclonal antibody, is the first approved immunotherapy for patients with locally advanced CSCC (laCSCC) or metastatic CSCC (mCSCC) thanks to phase I and II studies showing high antitumor activity and good tolerability. Nevertheless, at present, very few data are available regarding cemiplimab in real-life experience and in frail, elderly, and immunosuppressed patients as well as regarding biomarkers able to predict response so as to guide therapeutic choices. PATIENTS AND METHODS: We built a retroprospective cohort study including 30 non-selected patients with laCSCC (25) and mCSCC (five) treated with cemiplimab from August 2019 to November 2020. Clinical outcomes, toxicity profile, and correlations with disease, patients, and peripheral blood parameters are explored. RESULTS: The median age was 81 years (range, 36-95), with 24 males and five patients having an immunosuppressive condition, while the frailty prevalence was 83% based on index derived from age, Eastern Cooperative Oncology Group performance status, and Charlson Comorbidity Index. We reported 23 responses (76.7%) with nine complete responses (30%). A statistically significant higher response rate was observed in head and neck primary tumors and in patients with hemoglobin level >12 g/dl. No difference was observed with respect to frailty, median age, sex, and body mass index. The baseline low neuthophil/lymphocyte ratio and low platelet/lymphocyte ratio resulted to be also correlated with a better response. Moreover, lymphocyte, neutrophil, and monocyte behaviors had an opposite trend in responders and non-responders. An overall response was reported in four of five immunosuppressed patients. Seventeen patients (57.6%) have an ongoing response and are still alive. Six responders had interrupted treatment (two for toxicity and four for personal choice) but maintained their response. The treatment was well tolerated by the majority of patients. The most common adverse events were fatigue in seven patients (23.3%) and skin toxicity in 10 patients (33.3%), including pruritus in six patients, rash in three patients, and bullous erythema in one patient. CONCLUSIONS: In our real-life experience, cemiplimab showed a high antitumor activity with acceptable safety profile similar to those in trials with selected patients. Moreover, its antitumor activity resulted to be not impaired in very elderly patients and in those with immunocompromised status.

Advancement study of CancerMath model as prognostic tools for predicting Sentinel lymph node metastasis in clinically negative T1 breast cancer patients.

PURPOSE: Sentinel lymph node biopsy (SLNB) is an invasive surgical procedure and although it has fewer complications and is less severe than axillary lymph node dissection, it is not a risk-free procedure. Large prospective trials have documented SLNB that it is considered non-therapeutic in early stage breast cancer. METHODS: Web-calculator CancerMath (CM) allows you to estimate the probability of having positive lymph nodes valued on the basis of tumour size, age, histologic type, grading, expression of estrogen receptor, progesterone receptor. We collected 595 patients referred to our Institute resulting clinically negative T1 breast cancer characterized by sentinel lymph node status, prognostic factors defined by CM and also HER2 and Ki-67. We have compared classification performances obtained by online CM application with those obtained after training its algorithm on our database. RESULTS: By training CM model on our dataset and using the same feature, adding HER2 or ki67 we reached a sensitivity median value of 71.4%, 73%, 70.4%, respectively, whereas the online one was equal to 61%, without losing specificity. The introduction of the prognostic factors Her2 and Ki67 could help improving performances on the classification of particularly type of patients. CONCLUSIONS: Although the training of the model on the sample of T1 patients has brought a significant improvement in performance, the general performance does not yet allow a clinical application of the algorithm. However, the experimental results encourage future developments aimed at introducing features of a different nature in the CM model.

Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs.

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.

Radiomic Feature Reduction Approach to Predict Breast Cancer by Contrast-Enhanced Spectral Mammography Images.

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.

A Clinical Decision Support System for Predicting Invasive Breast Cancer Recurrence: Preliminary Results.

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.

Examining the Relationship between Circulating CD4- CD8- Double-Negative T Cells and Outcomes of Immuno-Checkpoint Inhibitor Therapy-Looking for Biomarkers and Therapeutic Targets in Metastatic Melanoma.

BACKGROUND: The role of circulating CD4-/CD8- double-negative T cells (DNTs) in the immune response to melanoma is poorly understood, as are the effects of checkpoint inhibitors on T cell subpopulations. METHODS: We performed a basal and longitudinal assessment of circulating immune cells, including DNTs, in metastatic melanoma patients treated with checkpoint blockade in a single-center cohort, and examined the correlations levels of immune cells with clinical features and therapy outcomes. RESULTS: Sixty-eight patients (48 ipilimumab, 20 PD1 inhibitors) were enrolled in the study. Our analysis indicated that better outcomes were associated with normal LDH, fewer than three metastatic sites, an ECOG performance status of 0, M1a stage, lower WBC and a higher lymphocyte count. The increase in lymphocyte count and decrease of DNTs were significantly associated with the achievement of an overall response. The median value of DNT decreased while the CD4+ and NK cells increased in patients that responded to treatment compare to those who did not respond to treatment. CONCLUSIONS: DNT cells change during treatment with checkpoint inhibitors and may be adept at sensing the immune response to melanoma. The complementary variation of DNT cells with respect to CD4+ and other immune actors may improve the reliability of lymphocyte assessment. Further investigation of DNT as a potential target in checkpoint inhibitor resistant melanoma is warranted.

The Management of Oligoprogression in the Landscape of New Therapies for Metastatic Melanoma.

Background: A limited degree of progression after a response to treatment is labelled as oligoprogression and is a hot topic of metastatic melanoma (MM) management. Rogue progressive metastases could benefit from local treatment, which could allow the continuation of ongoing systemic therapy, also known as treatment beyond progression (TBP). Methods: We retrospectively reviewed 214 selected MM patients who developed oligoprogression during treatment with v-Raf murine sarcoma viral oncogene homolog B (BRAF)/mitogen-activated-extracellular signal-regulated kinase (MEK) or programmed cell death protein 1 (PD-1) inhibitors and received a local treatment continuing TBP. We performed univariate and multivariable analyses to assess the association between therapy outcomes and a series of clinical and biological features. Results: We identified 27 (10%) oligoprogressed patients treated locally with surgery (14), radiosurgery (11), and electrochemotherapy (2). TBP included PD-1 inhibitors (13) and BRAF/MEK inhibitors (14). The median progression-free survival post oligoprogression (PFSPO) was 14 months (5-19 95% confidence interval (C.I.)). In the univariate analysis, a significantly longer PFSPO was associated with complete response (CR), Eastern Cooperative Oncology Group (ECOG) performance status (PS) of 0, neutrophils/lymphocytes ratio (N/L) <2, and progression-free survival (PFS) at oligoprogression >11 months. Nevertheless, in the multivariable analysis, only CR and N/L <2 were found to be associated with longer PFSPO. Conclusions: In selected patients, local treatments contribute to controlling oligoprogression for a long time, allowing the continuation of systemic treatment and prolongation of overall survival (OS). Increasing biological and clinical knowledge is improving the accuracy in identifying patients to apply for local ablative therapies.