High Incidence of Invasive Fungal Diseases in Patients with FLT3-Mutated AML Treated with Midostaurin: Results of a Multicenter Observational SEIFEM Study.

The potential drug-drug interactions of midostaurin may impact the choice of antifungal (AF) prophylaxis in FLT3-positive acute myeloid leukemia (AML) patients. To evaluate the incidence of invasive fungal diseases (IFD) during the treatment of FLT3-mutated AML patients and to correlate it to the different AF prophylaxis strategies, we planned a multicenter observational study involving 15 SEIFEM centers. One hundred fourteen patients treated with chemotherapy + midostaurin as induction/reinduction, consolidation or both were enrolled. During induction, the incidence of probable/proven and possible IFD was 10.5% and 9.7%, respectively; no statistically significant difference was observed according to the different AF strategy adopted. The median duration of neutropenia was similar in patients with or without IFD. Proven/probable and possible IFD incidence was 2.4% and 1.8%, respectively, during consolidation. Age was the only risk factor for IFD (OR, 95% CI, 1.10 [1.03-1.19]) and complete remission achievement after first induction the only one for survival (OR, 95% CI, 5.12 [1.93-13.60]). The rate of midostaurin discontinuation was similar across different AF strategies. The IFD attributable mortality during induction was 8.3%. In conclusion, the 20.2% overall incidence of IFD occurring in FLT3-mutated AML during induction with chemotherapy + midostaurin, regardless of AF strategy type, was noteworthy, and merits further study, particularly in elderly patients.

Long-Term Follow-Up of Elderly Patients with Acute Myeloid Leukemia Treated with Decitabine: A Real-World Study of the Apulian Hematological Network.

Decitabine, a DNA hypomethylating agent, was approved for use in adults with acute myeloid leukemia (AML) not eligible for standard chemotherapy and is now widely accepted as standard treatment. Although a number of clinical trials demonstrated its benefits in elderly AML patients, older adults and patients with frequent comorbidities are typically under-represented in such settings. Thus, the aim of the present study is to evaluate, in a real-world setting, the effectiveness and toxicity of decitabine administered as a single agent in unselected previously untreated elderly AML patients not eligible for intensive chemotherapy. In nine hematological departments of the Apulian Hematological Network (REP), we enrolled 199 patients (median age: 75.4 years; range: 61-91) with de novo (n = 94) or secondary/therapy-related (n = 105) AML treated with decitabine 20 mg/m2 for five days every 4 weeks. Hazard ratios (HR) and their 95% confidence intervals (CI) were estimated using multivariate Cox regression. The average number of cycles administered per patient was 6.3 (SD: 6.0; median: 5 cycles). Complete response was achieved by 31 patients (15.6%) and partial response by 57 (28.6%), for a total of 88 responders overall (44.2%). After a median follow-up of 33.6 months, median OS was 8.7 months (95% CI: 7.4-10.3), and the 6-month, 1-year, and 3-year OS rates were 62.7%, 37.0%, and 7.1%, respectively. Mortality was increased in AML patients with ≥3 comorbidities (HR = 2.45; 95% CI: 1.18-5.08) vs. no comorbidities and in those with adverse karyotype (HR = 1.58; 95% CI: 1.05-2.38) vs. favourable or intermediate profile. Infection was the main registered adverse event (46.0%). In conclusion, this REP real-life study demonstrates, after a follow-up of almost 3 years, how decitabine administered to AML patients not suitable for intensive chemotherapy is effective and well tolerated, even in a population of truly elderly patients with frequent comorbidities.

Combining computed tomography and biologically effective dose in radiomics and deep learning improves prediction of tumor response to robotic lung stereotactic body radiation therapy.

PURPOSE: The aim of this study is to improve the performance of machine learning (ML) models in predicting response of non-small cell lung cancer (NSCLC) to stereotactic body radiation therapy (SBRT) by integrating image features from pre-treatment computed tomography (CT) with features from the biologically effective dose (BED) distribution. MATERIALS AND METHODS: Image features, consisting of crafted radiomic features or machine-learned features extracted using a convolutional neural network, were calculated from pre-treatment CT data and from dose distributions converted into BED for 80 NSCLC lesions over 76 patients treated with robotic guided SBRT. ML models using different combinations of features were trained to predict complete or partial response according to response criteria in solid tumors, including radiomics CT (RadCT ), radiomics CT and BED (RadCT,BED ), deep learning (DL) CT (DLCT ), and DL CT and BED (DLCT,BED ). Training of ML included feature selection by neighborhood component analysis followed by ensemble ML using robust boosting. A model was considered as acceptable when the sum of average sensitivity and specificity on test data in repeated cross validations was at least 1.5. RESULTS: Complete or partial response occurred in 58 out of 80 lesions. The best models to predict the tumor response were those using BED variables, achieving significantly better area under curve (AUC) and accuracy than those using only features from CT, including a RadCT,BED model using three radiomic features from BED, which scored an accuracy of 0.799 (95% confidence intervals (0.75-0.85)) and AUC of 0.773 (0.688-0.846), and a DLCT,BED model also using three variables with an accuracy of 0.798 (0.649-0.829) and AUC of 0.812 (0.755-0.867). CONCLUSION: According to our results, the inclusion of BED features improves the response prediction of ML models for lung cancer patients undergoing SBRT, regardless of the use of radiomic or DL features.

Distant metastasis time to event analysis with CNNs in independent head and neck cancer cohorts.

Deep learning models based on medical images play an increasingly important role for cancer outcome prediction. The standard approach involves usage of convolutional neural networks (CNNs) to automatically extract relevant features from the patient's image and perform a binary classification of the occurrence of a given clinical endpoint. In this work, a 2D-CNN and a 3D-CNN for the binary classification of distant metastasis (DM) occurrence in head and neck cancer patients were extended to perform time-to-event analysis. The newly built CNNs incorporate censoring information and output DM-free probability curves as a function of time for every patient. In total, 1037 patients were used to build and assess the performance of the time-to-event model. Training and validation was based on 294 patients also used in a previous benchmark classification study while for testing 743 patients from three independent cohorts were used. The best network could reproduce the good results from 3-fold cross validation [Harrell's concordance indices (HCIs) of 0.78, 0.74 and 0.80] in two out of three testing cohorts (HCIs of 0.88, 0.67 and 0.77). Additionally, the capability of the models for patient stratification into high and low-risk groups was investigated, the CNNs being able to significantly stratify all three testing cohorts. Results suggest that image-based deep learning models show good reliability for DM time-to-event analysis and could be used for treatment personalisation.

What Is New in the Treatment of Smoldering Multiple Myeloma?

Smoldering multiple myeloma (SMM), an asymptomatic plasma cell neoplasm, is currently diagnosed according to the updated IMWG criteria, which reflect an intermediate tumor mass between monoclonal gammopathy of undetermined significance (MGUS) and active MM. However, SMM is a heterogeneous entity and individual case may go from an "MGUS-like" behavior to "early MM" with rapid transformation into symptomatic disease. This wide range of clinical outcomes poses challenges for prognostication and management of individual patients. However, initial studies showed a benefit in terms of progression or even survival for early treatment of high-risk SMM patients. While outside of clinical trials the conventional approach to SMM generally remains that of close observation, these studies raised the question of whether early treatment should be offered in high-risk patients, prompting evaluation of several different therapeutic approaches with different goals. While delay of progression to MM with a non-toxic treatment is clearly achievable by early treatment, a convincing survival benefit still needs to be proven by independent studies. Furthermore, if SMM is to be considered less biologically complex than MM, early treatment may offer the chance of cure that is currently not within reach of any active MM treatment. In this paper, we present updated results of completed or ongoing clinical trials in SMM treatment, highlighting areas of uncertainty and critical issues that will need to be addressed in the near future before the "watch and wait" paradigm in SMM is abandoned in favor of early treatment.

TRIMAGE: A dedicated trimodality (PET/MR/EEG) imaging tool for schizophrenia.

Simultaneous PET/MR/EEG (Positron Emission Tomography - Magnetic Resonance - Electroencephalography), a new tool for the investigation of neuronal networks in the human brain, is presented here within the framework of the European Union Project TRIMAGE. The trimodal, cost-effective PET/MR/EEG imaging tool makes use of cutting edge technology both in PET and in MR fields. A novel type of magnet (1.5T, non-cryogenic) has been built together with a PET scanner that makes use of the most advanced photodetectors (i.e., SiPM matrices), scintillators matrices (LYSO) and digital electronics. The combined PET/MR/EEG system is dedicated to brain imaging and has an inner diameter of 260 mm and an axial Field-of-View of 160 mm. It enables the acquisition and assessment of molecular metabolic information with high spatial and temporal resolution in a given brain simultaneously. The dopaminergic system and the glutamatergic system in schizophrenic patients are investigated via PET, the same physiological/pathophysiological conditions with regard to functional connectivity, via fMRI, and its electrophysiological signature via EEG. In addition to basic neuroscience questions addressing neurovascular-metabolic coupling, this new methodology lays the foundation for individual physiological and pathological fingerprints for a wide research field addressing healthy aging, gender effects, plasticity and different psychiatric and neurological diseases. The preliminary performances of two components of the imaging tool (PET and MR) are discussed. Initial results of the search of possible candidates for suitable schizophrenia biomarkers are also presented as obtained with PET/MR systems available to the collaboration.