No abstract

Neoadjuvant chemotherapy (NAC) is becoming the standard of care for locally advanced breast cancer, aiming to reduce tumor size before surgery. Unfortunately, less than 30% of patients generally achieve a pathological complete response and approximately 5% of patients show disease progression while receiving NAC. Accurate assessment of the response to NAC is crucial for subsequent surgical planning. Furthermore, early prediction of tumor response could avoid patients being overtreated with useless chemotherapy sections, which are not free from side effects and psychological implications. In this review, we first analyze and compare the accuracy of conventional and advanced imaging techniques as well as discuss the application of artificial intelligence tools in the assessment of tumor response after NAC. Thereafter, the role of advanced imaging techniques, such as MRI, nuclear medicine, and new hybrid PET/MRI imaging in the prediction of the response to NAC is described in the second part of the review. Finally, future perspectives in NAC response prediction, represented by AI applications, are discussed.

Purpose To systematically review and evaluate the methodological quality of studies using radiomics for diagnostic and predictive purposes in patients with intracranial meningioma. To perform a meta-analysis of machine learning studies for the prediction of intracranial meningioma grading from pre-operative brain MRI. Methods Articles published from the year 2000 on radiomics and machine learning applications in brain imaging of meningioma patients were included. Their methodological quality was assessed by three readers with the radiomics quality score, using the intra-class correlation coefficient (ICC) to evaluate inter-reader reproducibility. A meta-analysis of machine learning studies for the preoperative evaluation of meningioma grading was performed and their risk of bias was assessed with the Quality Assessment of Diagnostic Accuracy Studies tool. Results In all, 23 studies were included in the systematic review, 8 of which were suitable for the meta-analysis. Total (possible range, −8 to 36) and percentage radiomics quality scores were respectively 6.96 ± 4.86 and 19 ± 13% with a moderate to good inter-reader reproducibility (ICC = 0.75, 95% confidence intervals, 95%CI = 0.54–0.88). The meta-analysis showed an overall AUC of 0.88 (95%CI = 0.84–0.93) with a standard error of 0.02. Conclusions Machine learning and radiomics have been proposed for multiple applications in the imaging of meningiomas, with promising results for preoperative lesion grading. However, future studies with adequate standardization and higher methodological quality are required prior to their introduction in clinical practice.

Autoimmune hemolytic anemia (AIHA) is an uncommon disease of childhood caused by the premature destruction of erythrocytes by autoantibodies. In this rare disease both diagnostic criteria and therapeutic approaches are not well standardized. The Red Cell Working Group of the Pediatric Italian Hematogy and Oncology Association (AIEOP) developed specific recommendations to help Physicians for AIHA management. The document is available on the AIEOP website since November 1st 2013. The Italian Pediatric AIHA Group began an observational, retrospective and prospective study in order to monitor the management of children with AIHA diagnosed from 2010 to 2018, and to assess whether the availability of AIEOP recommendations had an impact on the clinical management of such patients in AIEOP Centers. We collected a national cohort of 159 children with AIHA from 21 AIEOP Centers; 48 patients were diagnosed before November 2013 and 111 patients after that date. Gender was 56% males and 44% females; median age at diagnosis was 47 months, with 11.9% under 12 months of age; 8.2% of children were born prematurely and 3.9% showed congenital malformations. 23.2 % of patients had a familiar history of immunological, hematological or oncological diseases. The median hemoglobin level at diagnosis was 6.1 gr/dL. Table 1 reports the distribution of our cases, according to the different type of autoantibodies. The comparison between the retrospective and prospective study did not reveal significative differences in clinical and biological presentation. The cold IgM forms were mainly post infective (38.4%) or primary forms (53.8%), only one patient had a secondary form due to a primitive immunodeficiency. These patients did not develop other diseases during follow up (median follow up: 28,6 months). The preliminary results of treatment and follow up of the 146 patients with warm antibody AIHA revealed the following: The treatment with conventional dose of steroids (median dose 2 mg/Kg, range 0.7- 3.5 mg/Kg) was started in 94.4% of patients, in 53% of cases on the same day of diagnosis. A high number of children used additional treatment: red blood cell transfusions (51.4%), high dose Prednisolone (59.7%), high dose i.v. Immunoglobulin (49.7%) and Plasma Exchange (1.4%). 9.5% of patients, with poor responsive disease, needed alternative drugs during the first four weeks of therapy. Response criteria were so defined: a complete response was defined as the achievement of an Hb concentration greater than or equal to the lower normal limit for age with no signs of haemolysis, i.e. normal reticulocyte count and bilirubine concentration. A partial response was defined as an increase of Hb >2 g/dL without the Hb concentration reaching a normal value for the patient age and no response as an increase of Hb< 2 g/dL and/or dependence on transfusion. A complete response was reached by 62.5%, 79.3%, 85.1% at 3, 4, 6 weeks respectively. 14.9% of patients had either a partial response or a resistant disease at 6 weeks. IgG/IgG+C3d positivity was a negative prognostic factor, as compared to positivity to C3d only, with the need of a second line treatment (prevalently Mabthera or Mycophenolate Mofetil) in 31.7% vs 0, respectively (p 0.009). Currently 6.1% of the patients were lost to follow up, 1.3% died, 55,8% are in Complete Response without events and 21.9% of the patients are still on treatment . At the last follow up, in the whole "cohort" of warm AIHA, 58% have a Primary form, 15.7% an isolated post infective form and 27.7% a Secondary form (56% Evans Syndrome). The management of the patients diagnosed after November 2013 was mostly in agreement with our recommendations, whose comprehensive therapeutic algorithm is reported in table 2, with prolonged steroid tapering in order to extend the treatment for at least 6 months. The most important difference between the retrospective and prospective study was the duration of first line treatment: 6 months or more, for steroid dependence, in 71.6% of patients in the prospective study versus 52.3% of the retrospective (p 0.031) and, more importantly, the percentage of relapsed patients: 8.3% in the prospective study versus 29.8% of the retrospective (p 0.001), these data need a longer follow up (median follow up: 24 months in the prospective study versus 63 in the retrospective) Disclosures Colombatti: Global Blood Therapeutics: Consultancy; Novartis: Consultancy; AddMedica: Consultancy.

Purpose Cerebellar ataxias are a large and heterogeneous group of disorders. The evaluation of brain parenchyma via MRI plays a central role in the diagnostic assessment of these conditions, being mandatory to exclude the presence of other underlying causes in determining the clinical phenotype. Once these possible causes are ruled out, the diagnosis is usually researched in the wide range of hereditary or sporadic ataxias. Methods We here propose a review of the main clinical and conventional imaging findings of the most common hereditary degenerative ataxias, to help neuroradiologists in the evaluation of these patients. Results Hereditary degenerative ataxias are all usually characterized from a neuroimaging standpoint by the presence, in almost all cases, of cerebellar atrophy. Nevertheless, a proper assessment of imaging data, extending beyond the mere evaluation of cerebellar atrophy, evaluating also the pattern of volume loss as well as concomitant MRI signs, is crucial to achieve a proper diagnosis. Conclusion The integration of typical neuroradiological characteristics, along with patient’s clinical history and laboratory data, could allow the neuroradiologist to identify some conditions and exclude others, addressing the neurologist to the more appropriate genetic testing.