Early GLS changes detection after chemoradiation in locally advanced non-small cell lung cancer (NSCLC).

PURPOSE: Chemoradiation is the standard treatment in patients with locally advanced non-small-cell lung cancer (LA-NSCLC), and thanks to the recent combination with immunotherapy, median survival has unexpectedly improved. This study aims to evaluate early changes in cardiac function after chemoradiotherapy (CRT) in LA-NSCLC by multimodal use of advanced imaging techniques. MATERIALS AND METHODS: This is a prospective, observational cohort study. At the beginning of combined treatment, screening tests including blood samples, electrocardiogram (ECG), echocardiographic examination (TTE), and cardiac magnetic resonance were performed in all patients with LA-NSCLC. ECG and cardiac marker assays were performed weekly during treatment. ECG and TTE were performed at month 1 (M1) and month 3 (M3) after the end of CRT. RESULTS: This preliminary analysis included thirty-four patients with a mean age of 69.5 years. The median follow-up was 27.8 months. 62% of patients were in stage IIIA. Radiation therapy was delivered with a median total dose of 60 Gy with conventional fractionation. All patients were treated with concurrent CRT, and 65% of cases were platinum-based therapy. Global longitudinal strain (GLS) and ejection fraction (EF) progressively decreased from baseline to M1 and M3. There was a strong correlation between GLS and EF reduction (at M1: p = 0.034; at M3: p = 0.018). Cardiac arrhythmias occurred in eight patients (23.5%) at a mean follow-up of 15.8 months after CRT. CONCLUSIONS: Reduction in GLS is an early sign occurring after the end of CRT for LA-NSCLC. Future studies are needed to identify variables that can increase the risk of cardiac events in this patient population to implement adequate damage prevention strategies.

18F-choline PET/CT driven salvage radiotherapy in prostate cancer patients: up-date analysis with 5-year median follow-up.

PURPOSE: Salvage radiotherapy is generally considered as the standard treatment for biochemical relapse after surgery. Best results have been obtained with a PSA value < 0.5 ng/ml at relapse, while 60-66 Gy is deemed as standard total dose. Modern imaging, as dynamic-18F-choline PET/CT may identify site of recurrence, allowing dose escalation to a biological target volume. METHODS: Hundred and fifty patients showed a local relapse at dynamic-18F-choline PET/CT at time of biochemical recurrence. High-dose salvage radiotherapy was delivered up to total dose of 80 Gy to 18F-choline PET/CT positive area. Toxicity and relapse-free survival were recorded. RESULTS: Median PSA value at the beginning of salvage radiotherapy was 0.47 ng/ml (range 0.2-17.5 ng/ml). One-hundred and thirty nine patients (93%) completed salvage radiotherapy without interruptions. Acute gastrointestinal grade ≥ 2 toxicity was recorded in 13 patients (9%), acute genitourinary grade ≥ 2 toxicity in 2 patients (1.4%). One patient (0.7%) experienced late gastrointestinal grade 4 toxicity and 2 patients (1.4%) late acute genitourinary grade 3 toxicity. With a median follow-up of 63.5 months, 5 and 7-years relapse-free survival were 70% and 60.7%, respectively. CONCLUSION: With a median follow-up of 5 years the present study confirms that high-dose salvage radiotherapy to a biological target volume is feasible, with low rate of late toxicity and promising activity.

Deep pathomics: A new image-based tool for predicting response to treatment in stage III non-small cell lung cancer.

Despite the advantages offered by personalized treatments, there is presently no way to predict response to chemoradiotherapy in patients with non-small cell lung cancer (NSCLC). In this exploratory study, we investigated the application of deep learning techniques to histological tissue slides (deep pathomics), with the aim of predicting the response to therapy in stage III NSCLC. We evaluated 35 digitalized tissue slides (biopsies or surgical specimens) obtained from patients with stage IIIA or IIIB NSCLC. Patients were classified as responders (12/35, 34.7%) or non-responders (23/35, 65.7%) based on the target volume reduction shown on weekly CT scans performed during chemoradiation treatment. Digital tissue slides were tested by five pre-trained convolutional neural networks (CNNs)-AlexNet, VGG, MobileNet, GoogLeNet, and ResNet-using a leave-two patient-out cross validation approach, and we evaluated the networks' performances. GoogLeNet was globally found to be the best CNN, correctly classifying 8/12 responders and 10/11 non-responders. Moreover, Deep-Pathomics was found to be highly specific (TNr: 90.1) and quite sensitive (TPr: 0.75). Our data showed that AI could surpass the capabilities of all presently available diagnostic systems, supplying additional information beyond that currently obtainable in clinical practice. The ability to predict a patient's response to treatment could guide the development of new and more effective therapeutic AI-based approaches and could therefore be considered an effective and innovative step forward in personalised medicine.

Deep Reinforcement Learning for Fractionated Radiotherapy in Non-Small Cell Lung Carcinoma.

Lung cancer is by far the leading cause of cancer death among both men and women. Radiation therapy is one of the main approaches to lung cancer treatment, and its planning is crucial for the therapy outcome. However, the current practice that uniformly delivers the dose does not take into account the patient-specific tumour features that may affect treatment success. Since radiation therapy is by its very nature a sequential procedure, Deep Reinforcement Learning (DRL) is a well-suited methodology to overcome this limitation. In this respect, in this work we present a DRL controller optimizing the daily dose fraction delivered to the patient on the basis of CT scans collected over time during the therapy, offering a personalized treatment not only for volume adaptation, as currently intended, but also for daily fractionation. Furthermore, this contribution introduces a virtual radiotherapy environment based on a set of ordinary differential equations modelling the tissue radiosensitivity by combining both the effect of the radiotherapy treatment and cell growth. Their parameters are estimated from CT scans routinely collected using the Particle Swarm Optimization algorithm. This permits the DRL to learn the optimal behaviour through an iterative trial and error process with the environment. We performed several experiments considering three rewards functions modelling treatment strategies with different tissue aggressiveness and two exploration strategies for the exploration-exploitation dilemma. The results show that our DRL approach can adapt to radiation therapy treatment, optimizing its behaviour according to the different reward functions and outperforming the current clinical practice.

A radiomic approach for adaptive radiotherapy in non-small cell lung cancer patients.

The primary goal of precision medicine is to minimize side effects and optimize efficacy of treatments. Recent advances in medical imaging technology allow the use of more advanced image analysis methods beyond simple measurements of tumor size or radiotracer uptake metrics. The extraction of quantitative features from medical images to characterize tumor pathology or heterogeneity is an interesting process to investigate, in order to provide information that may be useful to guide the therapies and predict survival. This paper discusses the rationale supporting the concept of radiomics and the feasibility of its application to Non-Small Cell Lung Cancer in the field of radiation oncology research. We studied 91 stage III patients treated with concurrent chemoradiation and adaptive approach in case of tumor reduction during treatment. We considered 12 statistics features and 230 textural features extracted from the CT images. In our study, we used an ensemble learning method to classify patients' data into either the adaptive or non-adaptive group during chemoradiation on the basis of the starting CT simulation. Our data supports the hypothesis that a specific signature can be identified (AUC 0.82). In our experience, a radiomic signature mixing semantic and image-based features has shown promising results for personalized adaptive radiotherapy in non-small cell lung cancer.