Search

Rituximab, a chimeric monoclonal antibody directed against the CD20 antigen, has been shown to be active in newly diagnosed and relapsed patients with follicular lymphoma (FL), both as monotherapy and in combination with chemotherapy. Many studies suggest that the prognosis of patients with FL may improve when it is used in combination with chemotherapy. Despite these advances, the disease remains essentially incurable with standard therapy, and novel approaches to treatment are needed because optimal therapy is not defined. The combination of chlorambucil-rituximab is one of several standard treatment options for FL. Here, we considered data arising from 75 patients with newly diagnosed FL at the European Institute of Oncology treated with the combination of rituximab plus chlorambucil. The aim of this study was to evaluate the efficacy and safety of chlorambucil and rituximab, delivered 6 mg/m(2) /day orally for 6 weeks and 375 mg/m(2) in a standard 4-weekly schedule, respectively. Patients responding to the induction therapy received a prolonged therapy with four additional cycles of chlorambucil plus rituximab. Seventy-one patients (94.6%) completed the treatment; four patients discontinued treatment because of grade 3-4 hematological toxicity. The overall response rate was 97.3% including 74.7% of complete responses. Only two patients had a stable disease at revaluation after treatment. With a median follow-up of 57 months, 72 patients (96%) are alive. Median event-free survival (EFS) and median overall survival (OS) were not reached; 5-year OS rate was 98.4%. The 5-year EFS was 71.3%. By univariate and multivariate analyses, elevated beta-2 microglobulin levels and partial responses to therapy were correlated with worse EFS. These results suggest that the combination of chlorambucil and rituximab is an active and safe regimen in patients with newly diagnosed FL, principally in those with low tumour burden and favourable prognostic factors. [ABSTRACT FROM AUTHOR]

Here, we present the results of a randomised clinical trial carried out between 1998 and 2004, evaluating the possible role of radiotherapy (RT) as consolidation treatment after induction chemotherapy (CT) in diffuse large B-cell (DLBC) gastric lymphoma. Fifty-four patients were enrolled and all received anthracycline containing regimens as induction CT. Patients were evaluated after four to six cycles and those in complete remission (CR) were randomised to receive gastric involved field (IF) RT or two addition cycles of the same CT. Forty-five patients (83%) were randomised after the induction CT. Clinical results of patients allocated to the RT arm showed a significant reduction in incidence of local relapse versus patients who received CT alone. However, overall survival was not different between the two arms. Our results confirm that CT could be considered as first line therapy for newly diagnosed gastric DLBC lymphoma; IF RT delivered in those patients achieving CR after induction CT is able to prevent local relapse. [ABSTRACT FROM AUTHOR]

Background: Lymphocyte-predominant Hodgkin disease (LPHD) differs in biology and clinical behaviour from classic Hodgkin disease. Almost 100% of LPHD neoplastic cells express CD20 and thus rituximab could be effective; yet limited data are available. Patients and Methods: We performed a retrospective analysis on patients with LPHD who were treated with rituximab at our institution to determine the magnitude of benefit offered by this drug. Results: Seven patients were identified; 4 received the drug as single agent while the rest received it in combination with chemotherapy. All except 2 received the drug in the salvage setting. Response rate was 100% with 6 of 7 patients achieving complete remission. At a median follow-up of 2 years, 4 patients are still disease free while the rest relapsed at a median time of 27 months. Conclusion: Rituximab is effective in LPHD and should be considered; however, the optimal schedule remains to be determined. Copyright © 2008 S. Karger AG, Basel [ABSTRACT FROM AUTHOR]

Carpal tunnel release for compression of the median nerve at the wrist is a common procedure, often resulting in good clinical outcomes. There are, however, many anatomical variations in and around the carpal tunnel and it is important to be aware of these during carpal tunnel release. After surgery, recurrent carpal tunnel syndrome is uncommon, but difficult to diagnose and treat. Ultrasonography is often necessary for the evaluation of the anatomical variations before carpal tunnel release and to evaluate the most common complications after carpal tunnel release. [ABSTRACT FROM AUTHOR]

Disorders affecting the ulnar nerve in the elbow are common in clinical practice. The diagnosis is based on clinical evaluation and electrodiagnostic tests, but imaging examinations are frequently necessary, particularly for the identification of the structures associated with nerve compression. The purpose of this video article is to review the anatomy, the pathology, scanning techniques, and sonographic appearance of the ulnar nerve in the elbow. [ABSTRACT FROM AUTHOR]

This article describes how the transcriptional alterations of the innate immune system divide dysplasias into aggressive forms that, despite the treatment, relapse quickly and more easily, and others where the progression is slow and more treatable. It elaborates on how the immune system can change the extracellular matrix, favoring neoplastic progression, and how infections can enhance disease progression by increasing epithelial damage due to the loss of surface immunoglobulin and amplifying the inflammatory response. We investigated whether these dysregulated genes were linked to disease progression, delay, or recovery. These transcriptional alterations were observed using the RNA-based next-generation sequencing (NGS) panel Oncomine Immune Response Research Assay (OIRRA) to measure the expression of genes associated with lymphocyte regulation, cytokine signaling, lymphocyte markers, and checkpoint pathways. During the analysis, it became apparent that certain alterations divide dysplasia into two categories: progressive or not. In the future, these biological alterations are the first step to provide new treatment modalities with different classes of drugs currently in use in a systemic or local approach, including classical chemotherapy drugs such as cisplatin and fluorouracile, older drugs like fenretinide, and new checkpoint inhibitor drugs such as nivolumab and pembrolizumab, as well as newer options like T cell therapy (CAR-T). Following these observed alterations, it is possible to differentiate which dysplasias progress or not or relapse quickly. This information could, in the future, be the basis for determining a close follow-up, minimizing surgical interventions, planning a correct and personalized treatment protocol for each patient and, after specific clinical trials, tailoring new drug treatments. [ABSTRACT FROM AUTHOR]

Simple Summary: Cutaneous squamous cell carcinoma is among the most frequent cutaneous tumors. Over the years, the understanding and diagnostic sensitivity has increased due to the introduction and improved knowledge of dermoscopy, as well as of more recent noninvasive technologies, such as reflectance confocal microscopy and line-field confocal optical coherence. Imaging plays a central role in the staging of the disease; however, its role in the follow-up, as well as the choice of the best technique in each patient, is still not fully clarified. Cutaneous squamous cell carcinoma (SCC) is the second most frequent skin cancer, accounting for approximately 20% of all cutaneous malignancies, and with an increasing incidence due to the progressive increment of the average age of life. The diagnosis is usually firstly suspected based on clinical manifestations; however, dermoscopic features may improve diagnostic sensitivity in cases of an uncertain diagnosis and may guide the biopsy, which should be performed to histopathologically prove the tumor. New diagnostic strategies may improve the sensitivity of the cutaneous SCC, such as reflectance confocal microscopy and line-field confocal optical coherence, for which increasing data have been recently published. Imaging has a central role in the staging of the diseases, while its exact role, as well as the choice of the best techniques, during the follow-up are not fully clarified. The aim of this literature review is to describe diagnostic clinical and instrumental tools of cutaneous SCC, with an insight into the role of imaging in the diagnosis and follow-up of cutaneous SCC. [ABSTRACT FROM AUTHOR]

Simple Summary: Raman spectroscopy, a light scattering technique that provides the biochemical fingerprint of a sample, was used on samples taken from patients with cancer and precancerous lesions. This information was then used to build a classifier to identify cancer and the precancerous phases. The ability to distinguish cancerous tissue from normal and precancerous tissue is diagnostically crucial as it can alter the patients' prognosis and management. Moreover, as cellular changes are often present at the tumour margin, the ability to distinguish these changes from cancer can help in preserving more of the tissue and maintaining aesthetics and functionality for the patient. Early diagnosis, treatment and/or surveillance of oral premalignant lesions are important in preventing progression to oral squamous cell carcinoma (OSCC). The current gold standard is through histopathological diagnosis, which is limited by inter- and intra-observer errors and sampling errors. The objective of this work was to use Raman spectroscopy to discriminate between benign, mild, moderate and severe dysplasia and OSCC in formalin fixed paraffin preserved (FFPP) tissues. The study included 72 different pathologies from which 17 were benign lesions, 20 mildly dysplastic, 20 moderately dysplastic, 10 severely dysplastic and 5 invasive OSCC. The glass substrate and paraffin wax background were digitally removed and PLSDA with LOPO cross-validation was used to differentiate the pathologies. OSCC could be differentiated from the other pathologies with an accuracy of 70%, while the accuracy of the classifier for benign, moderate and severe dysplasia was ~60%. The accuracy of the classifier was lowest for mild dysplasia (~46%). The main discriminating features were increased nucleic acid contributions and decreased protein and lipid contributions in the epithelium and decreased collagen contributions in the connective tissue. Smoking and the presence of inflammation were found to significantly influence the Raman classification with respective accuracies of 76% and 94%. [ABSTRACT FROM AUTHOR]

Background: Benign nerve sheath tumors presenting as solitary retroperitoneal masses (RBNSTs) pose a complex diagnostic challenge for multidisciplinary teams regarding differential diagnosis, staging, and treatment planning. This article reviews the role played by different imaging techniques in assessing RBNSTs and elucidates their typical pathological features with a particular emphasis on the correlation between imaging and histological findings. Furthermore, some examples of retroperitoneal tumors that merit consideration in the process of differential diagnosis based on cross-sectional investigations (CSIs) are reported. The correlation between tissue architecture and appearance on imaging can help increase the accuracy of differential diagnosis with other retroperitoneal neoplasms at CSIs. Critical relevance statement: This educational review critically examines the correlation between imaging and histological features in solitary retroperitoneal benign nerve sheath tumors, offering valuable insights for improving the accuracy of differential diagnosis in clinical radiology. Key Points: RBNSTs are challenging to diagnose because they lack specific radiological features. Differential diagnosis of RBNSTs from other retroperitoneal neoplasms on imaging is complex. Surgical removal of RBNSTs is recommended for an accurate diagnosis. [ABSTRACT FROM AUTHOR]

Background: Pancreatic adenocarcinoma is a high-mortality neoplasm with a documented 5-years-overall survival around 5%. In the last decades, a real breakthrough in the treatment of the disease has not been achieved. Here we propose a prospective, phase II, multicentre, single-arm study aiming to assess the efficacy and the feasibility of a therapeutic protocol combining chemotherapy, carbon ion therapy and surgery for resectable and borderline resectable pancreatic adenocarcinoma.Method: The purpose of this trial (PIOPPO Protocol) is to assess the efficacy and the feasibility of 3 cycles of FOLFIRINOX neoadjuvant chemotherapy followed by a short-course of carbon ion radiotherapy (CIRT) for resectable or borderline resectable pancreatic adenocarcinoma patients. Primary outcome of this study is the assessment of local progression free survival (L-PFS). The calculation of sample size is based on the analysis of the primary endpoint "progression free survival" according to Fleming's Procedure.Discussion: Very preliminary results provide initial evidence of the feasibility of the combined chemotherapy and CIRT in the neoadjuvant setting for resectable or borderline resectable pancreatic cancer. Completion of the accrual and long term results are awaited to see if this combination of treatment is advisable and will provide the expected benefits.Trial Registration: ClinicalTrials.gov Identifier: NCT03822936 registered on January 2019. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) approaches have been introduced in various disciplines but remain rather unused in head and neck (H&N) cancers. This survey aimed to infer the current applications of and attitudes toward AI in the multidisciplinary care of H&N cancers. From November 2020 to June 2022, a web-based questionnaire examining the relationship between AI usage and professionals' demographics and attitudes was delivered to different professionals involved in H&N cancers through social media and mailing lists. A total of 139 professionals completed the questionnaire. Only 49.7% of the respondents reported having experience with AI. The most frequent AI users were radiologists (66.2%). Significant predictors of AI use were primary specialty (V = 0.455; p < 0.001), academic qualification and age. AI's potential was seen in the improvement of diagnostic accuracy (72%), surgical planning (64.7%), treatment selection (57.6%), risk assessment (50.4%) and the prediction of complications (45.3%). Among participants, 42.7% had significant concerns over AI use, with the most frequent being the 'loss of control' (27.6%) and 'diagnostic errors' (57.0%). This survey reveals limited engagement with AI in multidisciplinary H&N cancer care, highlighting the need for broader implementation and further studies to explore its acceptance and benefits. [ABSTRACT FROM AUTHOR]

Simple Summary: T1 and T2 mapping are MRI techniques that are routinely used in the evaluation of both benign and malignant lesions in different organs and tissues. Immunohistochemical analysis is the gold standard method to assess the programmed death-ligand 1 protein (PD-L1) expression status in patients diagnosed with non-small cell lung cancer (NSCLC) to guide immunotherapy. There have been no studies on the correlation between T1 and T2 mapping values and PD-L1 expression of NSCLCs nor on the correlation between T2 mapping values and histological subtypes of lung tumors. Therefore, we present our preliminary results on the evaluation of the possible association of T1 and T2 mapping values with PD-L1 TPS and of their potential in distinguishing between the different histological subtypes of NSCLCs. In the future, T1 values could offer the possibility to help in the diagnosis and pathological classification of NSCLC through a non-invasive MRI exam. We investigated the association of T1/T2 mapping values with programmed death-ligand 1 protein (PD-L1) expression in lung cancer and their potential in distinguishing between different histological subtypes of non-small cell lung cancers (NSCLCs). Thirty-five patients diagnosed with stage III NSCLC from April 2021 to December 2022 were included. Conventional MRI sequences were acquired with a 1.5 T system. Mean T1 and T2 mapping values were computed for six manually traced ROIs on different areas of the tumor. Data were analyzed through RStudio. Correlation between T1/T2 mapping values and PD-L1 expression was studied with a Wilcoxon–Mann–Whitney test. A Kruskal–Wallis test with a post-hoc Dunn test was used to study the correlation between T1/T2 mapping values and the histological subtypes: squamocellular carcinoma (SCC), adenocarcinoma (ADK), and poorly differentiated NSCLC (PD). There was no statistically significant correlation between T1/T2 mapping values and PD-L1 expression in NSCLC. We found statistically significant differences in T1 mapping values between ADK and SCC for the periphery ROI (p-value 0.004), the core ROI (p-value 0.01), and the whole tumor ROI (p-value 0.02). No differences were found concerning the PD NSCLCs. [ABSTRACT FROM AUTHOR]

Pulmonary hypertension (PH) is a pathophysiological disorder, defined by a mean pulmonary arterial pressure (mPAP) > 20 mmHg at rest, as assessed by right heart catheterization (RHC). PH is not a specific disease, as it may be observed in multiple clinical conditions and may complicate a variety of thoracic diseases. Conditions associated with the risk of developing PH are categorized into five different groups, according to similar clinical presentations, pathological findings, hemodynamic characteristics, and treatment strategy. Most chronic lung diseases that may be complicated by PH belong to group 3 (interstitial lung diseases, chronic obstructive pulmonary disease, combined pulmonary fibrosis, and emphysema) and are associated with the lowest overall survival among all groups. However, some of the chronic pulmonary diseases may develop PH with unclear/multifactorial mechanisms and are included in group 5 PH (sarcoidosis, pulmonary Langerhans' cell histiocytosis, and neurofibromatosis type 1). This paper focuses on PH associated with chronic lung diseases, in which radiological imaging—particularly computed tomography (CT)—plays a crucial role in diagnosis and classification. Radiologists should become familiar with the hemodynamical, physiological, and radiological aspects of PH and chronic lung diseases in patients at risk of developing PH, whose prognosis and treatment depend on the underlying disease. [ABSTRACT FROM AUTHOR]

An aberrant subclavian artery (ASA) (or lusoria) is the most common congenital anomaly of the aortic arch (0.5%-2.2%; female-to-male ratio 2:1 to 3:1). ASA can become aneurysmal and result in dissection, involving Kommerell's diverticulum when present and the aorta. Data of its significance in genetic arteriopathies are not available. The purpose of this study was to assess the prevalence and complications of ASA in gene-positive and -negative nonatherosclerotic arteriopathies. The series includes 1,418 consecutive patients with gene-positive (n = 854) and gene-negative arteriopathies (n = 564) diagnosed as part of institutional work-up for nonatherosclerotic syndromic and nonsyndromic arteriopathies. Comprehensive evaluation includes genetic counseling, next-generation sequencing multigene testing, cardiovascular and multidisciplinary assessment, and whole-body computed tomography angiography. ASA was found in 34 of 1,418 cases (2.4%), with a similar prevalence in gene-positive (n = 21 of 854, 2.5%) and gene-negative (n = 13 of 564, 2.3%) arteriopathies. Of the former 21 patients, 14 had Marfan syndrome, 5 had Loeys-Dietz syndrome, 1 had type-IV Ehlers-Danlos syndrome, and 1 had periventricular heterotopia type 1. ASA did not segregate with genetic defects. Dissection occurred in 5 of 21 patients with genetic arteriopathies (23.8%; 2 Marfan syndrome and 3 Loeys-Dietz syndrome), all with associated Kommerell's diverticulum. No dissections occurred in gene-negative patients. At baseline, none of the 5 patients with ASA dissection fulfilled criteria for elective repair according to guidelines. The risk of complications of ASA is higher in patients with genetic arteriopathies and is difficult to predict. In these diseases, imaging of the supra-aortic trunks should enter baseline investigations. Determination of precise indications for repair can prevent unexpected acute events such as those described. [Display omitted] [ABSTRACT FROM AUTHOR]

Arrhythmogenic cardiomyopathy with left ventricular involvement (ACM-LV), particularly in case of isolated left ventricular involvement (i.e. left dominant arrhythmogenic cardiomyopathy, LDAC) and previous infectious myocarditis (pIM) may have overlapping clinical and cardiac magnetic resonance (CMR) features. To date, there are no validated CMR criteria for the differential diagnosis between these conditions. The present study aimed to identify CMR characteristics to distinguish ACM-LV from pIM. This observational, retrospective, single-centre study included 30 pIM patients and 30 ACM-LV patients. In ACM-LV patients CMR was performed at diagnosis; in patients with pIM, CMR was performed six months after acute infection. CMR analysis included quantitative assessment of left ventricle (LV) volumes, systolic function and wall thicknesses, qualitative and quantitative assessment of late gadolinium enhancement (LGE) sequences. Compared with pIM, ACM-LV patients showed slightly larger LV volumes, more frequent regional wall motion anomalies and reduced wall thicknesses. ACM-LV patients had higher amounts of LV LGE and extension. Notably, the LDAC subgroup had the highest amount of LV LGE. LV LGE amount > 15 g and a LV LGE percentage > 30% of LV mass discriminated ACM-LV from pIM with a 100% specificity. LGE segmental distribution was superimposable among the groups, except for septal segments that were more frequently involved in ACM-LV and LDAC patients. A great extension of LV LGE (a cut-off of LGE >15 g and a percentage above 30% of LV LGE in relation to total myocardial mass) discriminates ACM-LV from pIM with extremely high specificity. • Quantification of late gadolinium enhancement is crucial in the differential diagnosis between arrhythmogenic cardiomyopathy with left ventricular involvement and previous infectious myocarditis. • Integration of several morpho-functional parameters together with late gadolinium enhancement analysis can help in distinguishing left dominant arrhythmogenic cardiomyopathy from previous infectious myocarditis. • Both the layer location and the distribution pattern of the late gadolinium enhancement are not useful elements in the differential diagnosis between arrhythmogenic cardiomyopathy with left ventricular involvement and previous myocarditis. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) is a widely used diagnostic technique. Patients wearing orthodontic devices are often requested to remove their appliances before an MRI exam, even when the exam involves anatomical areas far from the head, in order to prevent the heating and detachment of the appliances. The present report aims to evaluate changes in temperature and adhesive forces of molar bands after MRI at two different strength outputs. Sixty stainless steel molar bands were bonded on permanent human upper molars using two different cements: Unitek Multi-Cure Glass Ionomer Band Cement (3M Unitek, Monrovia, CA, USA) and Transbond Plus Light Cure Band Adhesive (3M Unitek). Appliances were subjected to MRI with two different strengths (1.5 Tesla and 3 Tesla). Tubes and band temperature was measured before and after MRI. Subsequently, the shear bond strength (SBS) test was calculated. Data underwent statistical analysis (p < 0.05). After MRI, molar bands exhibited significant heating, even though not clinically relevant, with a temperature increase ranging between 0.48 °C and 1.25 °C (p < 0.05). SBS did not show significant differences (p > 0.05). The present study suggests that, under MRI, the molar bands tested are safe; therefore, their removal could be not recommended for non-head and neck MRI exams. Removal would be necessary just in artifact risk areas. [ABSTRACT FROM AUTHOR]

Simple Summary: Intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) is an advanced magnetic resonance imaging (MRI) technique able to distinguish true diffusion from microcirculation-related perfusion without the use of contrast medium. Immunohistochemical analysis is the gold standard method to assess the programmed death-ligand 1 protein (PD-L1) expression status in patients affected by non-small cell lung cancer (NSCLC) to guide immunotherapy. We present our preliminary results on the evaluation of IVIM-DWI parameters and their correlation with the PD-L1 expression status in patients affected by stage III NSCLC. Since PD-L1 expression is very heterogeneous in NSCLCs, and an invasive biopsy of the tumor is necessary for immunohistochemical analysis, a non-invasive alternative method to quantify PD-L1 expression should be considered to provide information on the whole tumor. In the future, IVIM-DWI parameters could offer the possibility to perform diagnosis, pathological classification, to guide therapy, and to assess therapeutic responses. This study aims to investigate the correlation between intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) parameters in magnetic resonance imaging (MRI) and programmed death-ligand 1 (PD-L1) expression in non-small cell lung cancer (NSCLC). Twenty-one patients diagnosed with stage III NSCLC from April 2021 to April 2022 were included. The tumors were distinguished into two groups: no PD-L1 expression (<1%), and positive PD-L1 expression (≥1%). Conventional MRI and IVIM-DWI sequences were acquired with a 1.5-T system. Both fixed-size ROIs and freehand segmentations of the tumors were evaluated, and the data were analyzed through a software using four different algorithms. The diffusion (D), pseudodiffusion (D*), and perfusion fraction (pf) were obtained. The correlation between IVIM parameters and PD-L1 expression was studied with Pearson correlation coefficient. The Wilcoxon–Mann–Whitney test was used to study IVIM parameter distributions in the two groups. Twelve patients (57%) had PD-L1 ≥1%, and 9 (43%) <1%. There was a statistically significant correlation between D* values and PD-L1 expression in images analyzed with algorithm 0, for fixed-size ROIs (189.2 ± 65.709 µm²/s × 104 in no PD-L1 expression vs. 122.0 ± 31.306 µm²/s × 104 in positive PD-L1 expression, p = 0.008). The values obtained with algorithms 1, 2, and 3 were not significantly different between the groups. The IVIM-DWI MRI parameter D* can reflect PD-L1 expression in NSCLC. [ABSTRACT FROM AUTHOR]

Radiology reports are typically written in a free-text format, making clinical information difficult to extract and use. Recently, the adoption of structured reporting (SR) has been recommended by various medical societies thanks to the advantages it offers, e.g. standardization, completeness, and information retrieval. We propose a pipeline to extract information from Italian free-text radiology reports that fits with the items of the reference SR registry proposed by a national society of interventional and medical radiology, focusing on CT staging of patients with lymphoma. Our work aims to leverage the potential of Natural Language Processing and Transformer-based models to deal with automatic SR registry filling. With the availability of 174 Italian radiology reports, we investigate a rule-free generative Question Answering approach based on the Italian-specific version of T5: IT5. To address information content discrepancies, we focus on the six most frequently filled items in the annotations made on the reports: three categorical (multichoice), one free-text (free-text), and two continuous numerical (factual). In the preprocessing phase, we encode also information that is not supposed to be entered. Two strategies (batch-truncation and ex-post combination) are implemented to comply with the IT5 context length limitations. Performance is evaluated in terms of strict accuracy, f1, and format accuracy, and compared with the widely used GPT-3.5 Large Language Model. Unlike multichoice and factual, free-text answers do not have 1-to-1 correspondence with their reference annotations. For this reason, we collect human-expert feedback on the similarity between medical annotations and generated free-text answers, using a 5-point Likert scale questionnaire (evaluating the criteria of correctness and completeness). The combination of fine-tuning and batch splitting allows IT5 ex-post combination to achieve notable results in terms of information extraction of different types of structured data, performing on par with GPT-3.5. Human-based assessment scores of free-text answers show a high correlation with the AI performance metrics f1 (Spearman's correlation coefficients>0.5, p -values<0.001) for both IT5 ex-post combination and GPT-3.5. The latter is better at generating plausible human-like statements, even if it systematically provides answers even when they are not supposed to be given. In our experimental setting, a fine-tuned Transformer-based model with a modest number of parameters (i.e., IT5, 220 M) performs well as a clinical information extraction system for automatic SR registry filling task. It can extract information from more than one place in the report, elaborating it in a manner that complies with the response specifications provided by the SR registry (for multichoice and factual items), or that closely approximates the work of a human-expert (free-text items); with the ability to discern when an answer is supposed to be given or not to a user query. • Reshaping free-text radiology notes into structured reports using transformers. • Generative QA approach to extract different types of data (including free-text). • Greater impact of in-domain data fine-tuning combined with batch partitioning. • Human-expert based evaluation of free-text answers generated by models. • Small fine-tuned model ensures answer's appropriateness and fair plausibility. [ABSTRACT FROM AUTHOR]