The role of contrast-enhanced mammography in the preoperative evaluation of invasive lobular carcinoma of the breast.

AIM: To assess the performance of contrast-enhanced mammography (CEM) in the preoperative staging of invasive lobular carcinoma (ILC) of the breast. MATERIALS AND METHODS: The present study was a multicentre, multivendor, multinational retrospective study of women with a histological diagnosis of ILC who had undergone CEM from December 2013 to December 2021. Index lesion size and multifocality were recorded for two-dimensional (2D) mammography, CEM, and when available magnetic resonance imaging (MRI). Comparison with histological data was undertaken for women treated by primary surgical excision. Pearson correlation coefficients and Bland-Altman's analysis of agreement were used to assess differences with a significance level of 0.05. RESULTS: One hundred and fifteen ILC lesions were included, 46 (40%) presented symptomatically and 69 were screening detected. CEM demonstrated superior sensitivity when compared to standard mammography. The correlation between the histological size measured on the surgical excision specimen size was greater than with standard mammography (r=0.626 and 0.295 respectively, p=0.001), with 19% of lobular carcinomas not visible without a contrast agent. The sensitivity of CEM for multifocal disease was greater than standard mammography (70% and 20% respectively, p<0.0001). CEM overestimated tumour size by an average of 1.5 times, with the size difference increasing for larger tumour. When MRI was performed (n=22), tumour size was also overestimated by an average of 1.3 times. The degree of size overestimation was similar for both techniques, with the tumour size on CEM being on average 0.5 cm larger than MRI. CONCLUSION: CEM is a useful tool for the local staging of lobular carcinomas and could be an alternative to breast MRI.

Adherence to prescription medication during pregnancy: Do pregnant women use pharmacological treatment as prescribed?

AIMS: Pregnant women are hypothesized to have low adherence to prescribed medication, because of concerns about harmful effects on the unborn child. However, very little is known about the actual adherence to prescribed medication during pregnancy. We determined to what extent women follow treatment recommendations regarding prescribed medication use in mid-pregnancy. METHODS: Dutch women participating in the PRIDE Study completed a 6-week diary on medication use. Additionally, pharmacy records were obtained. For each medication dispensed, we determined 3 measures of adherence: (i) whether use was reported in the diary (actual use); (ii) difference between dispensing date and date of first reported use (initiation time); and (iii) proportion of days with at least the correct number of doses taken (implementation adherence). RESULTS: During the 6-week study period, 235 of 816 women (29%) were dispensed medication. Actual use was highest for medications used for chronic conditions (88%; 95% confidence interval [95% CI] 81-93), followed by medication for pregnancy-related conditions (79%; 95% CI 71-86) and medication for occasional and short-time use (69%; 95% CI 60-77). We observed a ≥1-day delay in treatment initiation for 42% of medications dispensed for the first time in the study period. Mean implementation adherence was 74.2% (95% CI 69.3-79.2) for medications that were actually used. CONCLUSION: Although actual use of medications dispensed was high, many pregnant women did not adhere to treatment recommendations. This nonadherence may impact maternal and child health and lead to overestimation of medication use in studies in perinatal pharmacoepidemiology relying on administrative databases.

Guiding future paediatric drug studies based on existing pharmacokinetic and efficacy data: Cardiovascular drugs as a proof of concept.

INTRODUCTION: Off-label drug use in the paediatric population is common, and the lack of high-quality efficacy studies poses patients at risk for failing pharmacotherapy. Next to efficacy studies, pharmacokinetic (PK) studies are increasingly used to inform paediatric dose selection. As resources for paediatric trials are limited, we aimed to summarize existing PK and efficacy studies to identify knowledge gaps in available evidence supporting paediatric dosing recommendations, thereby taking paediatric cardiovascular drugs as proof of concept. METHODS: For each cardiovascular drug, paediatric indication and prespecified age group, together comprising one record, the authorized state was assessed. Next, for off-label records, the highest level of evidence was scored. High-quality efficacy studies were defined as meta-analysis or randomized controlled trials. Other comparative research, noncomparative research or consensus-based expert opinions were considered low quality. The level of evidence for PK studies was scored per drug and per age group, but regardless of indication. RESULTS: A total of 58 drugs included 417 records, of which 279 (67%) were off-label. Of all off-label records, the majority (81%) were not supported by high-quality efficacy studies, but for 140 of these records (62%) high-quality PK studies were available. CONCLUSION: We demonstrated that for the majority of off-label cardiovascular drugs, only low-quality efficacy studies were available. However, high-quality PK studies were frequently available. Combining these PK data with extrapolation of efficacy data from adults may help to close the current information gap and prioritize the drugs for which clinical studies and safety data are urgently needed.

Proenkephalin A as a marker for glomerular filtration rate in critically ill children: validation against gold standard iohexol GFR measurements.

OBJECTIVES: Accurate determination of glomerular filtration rate (GFR) is important. Several endogenous biomarkers exist for estimating GFR, yet, they have limited accuracy, especially in the paediatric population. Proenkephalin A 119-159 (PENK) is a novel and promising GFR marker, but its relation with age in children remains unknown. Also, the value of PENK has never been validated against measured GFR (mGFR) in children when compared to traditional GFR markers including serum creatinine (SCr), SCr-based estimated GFR (eGFR) and cystatin C (cysC). METHODS: Critically ill children and term-born neonates were included in this single-centre, prospective study. Iohexol-based mGFR, SCr, and cysC were determined in each patient. eGFR was calculated using the bedside Schwartz equation, incorporating SCr and height. Spearman correlation coefficients were calculated to determine the correlation between mGFR and PENK, SCr, cysC and eGFR. RESULTS: For 97 patients (56 children and 41 neonates), mGFR, SCr, cysC and PENK levels were available. PENK levels were higher in young children and decreased to adult PENK reference values around two years of age. PENK levels were highly correlated with mGFR (ρ=-0.88, p<0.001), and similar to mGFR-eGFR correlation (ρ=-0.87, p<0.001). For cysC and SCr the correlation with mGFR was lower (ρ=-0.77 and ρ=-0.46, respectively. Both p<0.001). CONCLUSIONS: The correlation of PENK with mGFR was as good as SCr-based eGFR-mGFR correlation. To determine the added value of PENK in paediatric clinical care and prior to implementation, PENK reference values are needed and the development and validation of a paediatric PENK-based eGFR equation is necessary.

Glomerular filtration rate in critically ill neonates and children: creatinine-based estimations versus iohexol-based measurements.

BACKGROUND: Acute kidney injury (AKI) and augmented renal clearance (ARC), both alterations of the glomerular filtration rate (GFR), are prevalent in critically ill children and neonates. AKI and ARC prevalence estimates are based on estimation of GFR (eGFR) using serum creatinine (SCr), which is known to be inaccurate. We aimed to test our hypothesis that AKI prevalence will be higher and ARC prevalence will be lower in critically ill children when using iohexol-based measured GFR (mGFR), rather than using eGFR. Additionally, we aimed to investigate the performance of different SCr-based eGFR methods. METHODS: In this single-center prospective study, critically ill term-born neonates and children were included. mGFR was calculated using a plasma disappearance curve after parenteral administration of iohexol. AKI diagnosis was based on the KDIGO criteria, SCr-based eGFR, and creatinine clearance (CrCL). Differences between eGFR and mGFR were determined using Wilcoxon signed-rank tests and by calculating bias and accuracy (percentage of eGFR values within 30% of mGFR values). RESULTS: One hundred five children, including 43 neonates, were included. AKI prevalence was higher based on mGFR (48%), than with KDIGO or eGFR (11-40%). ARC prevalence was lower with mGFR (24%) compared to eGFR (38-51%). eGFR equations significantly overestimated mGFR (60-71 versus 41 ml/min/1.73 m2, p < 0.001-0.002). Accuracy was highest with eGFR equations based on age- and sex-dependent equations (up to 59%). CONCLUSION: Iohexol-based AKI prevalence was higher and ARC prevalence lower compared to standard SCr-based eGFR methods. Age- and sex-dependent equations for eGFR (eGFR-Smeets for neonates and eGFR-Pierce for children) best approached measured GFR and should preferably be used to optimize diagnosis of AKI and ARC in this population. A higher resolution version of the Graphical abstract is available as Supplementary information.

Maturation of GFR in Term-Born Neonates: An Individual Participant Data Meta-Analysis.

BACKGROUND: The evidence from individual studies to support the maturational pattern of GFR in healthy, term-born neonates is inconclusive. We performed an individual participant data (IPD) meta-analysis of reported measured GFR (mGFR) data, aiming to establish neonatal GFR reference values. Furthermore, we aimed to optimize neonatal creatinine-based GFR estimations. METHODS: We identified studies reporting mGFR measured by exogenous markers or creatinine clearance (CrCL) in healthy, term-born neonates. The relationship between postnatal age and clearance was investigated using cubic splines with generalized additive linear mixed models. From our reference values, we estimated an updated coefficient for the Schwartz equation (eGFR [ml/min per 1.73 m2]=(k×height [cm])/serum creatinine [mg/dl]). RESULTS: Forty-eight out of 1521 screened articles reported mGFR in healthy, term-born neonates, and 978 mGFR values from 881 neonates were analyzed. IPD were available for 367 neonates, and the other 514 neonates were represented by 41 aggregated data points as means/medians per group. GFR doubled in the first 5 days after birth, from 19.6 (95% CI, 14.7 to 24.6) to 40.6 (95% CI, 36.7 to 44.5) ml/min per 1.73 m2, and then increased more gradually to 59.4 (95% CI, 45.9 to 72.9) ml/min per 1.73 m2 by 4 weeks of age. A coefficient of 0.31 to estimate GFR best fitted the data. CONCLUSIONS: These reference values for healthy, term-born neonates show a biphasic increase in GFR, with the largest increase between days 1 and 5. Together with the re-examined Schwartz equation, this can help identify altered GFR in term-born neonates. To enable widespread implementation of our proposed eGFR equation, validation in a large cohort of neonates is required.

Assessing causality by means of the Naranjo scale in a paediatric patient with life threatening respiratory failure after alemtuzumab administration: a case report.

BACKGROUND: Alemtuzumab is a T cell depleting antibody agent used as induction immunosuppressant therapy in solid organ transplant recipients. In addition, it is being increasingly used to treat severe or glucocorticoid-resistant graft rejection. Despite the effectiveness of the treatment, severe adverse events have been reported related to alemtuzumab administration. We present a similar event illustrating the severity of this adverse drug reaction (ADR) and we highlight the structure causality assessment provides in approaching such a case. CASE PRESENTATION: We report a case of life-threatening respiratory failure after alemtuzumab administration in a 17 year old paediatric kidney transplant recipient. He developed near fatal severe respiratory and circulatory failure based on acute respiratory distress syndrome (ARDS) with diffuse alveolar oedema and haemoptysis hours after his second alemtuzumab administration. As it was questionable whether alemtuzumab could be regarded as the origin of his reaction and in order to assess the causality of this reaction as well as to structure clinical reasoning, we applied a widely used ADR probability scale to systematically review our case. DISCUSSION AND CONCLUSIONS: Our case shows a severe ADR after alemtuzumab administration. It illustrates the importance of proper causality assessment, the structure it provides and the benefit of a clinical pharmacology consultation when a severe reaction is suspected to be an ADR. By taking our case as an example, we demonstrate the added value of structured causality assessment to clinical reasoning and in generating differential diagnoses.

Secondary thrombotic microangiopathy with severely reduced ADAMTS13 activity in a patient with Capnocytophaga canimorsus sepsis: a case report.

BACKGROUND: The Gram-negative bacillus Capnocytophaga canimorsus may cause a severe illness resembling thrombotic thrombocytopenic purpura (TTP). The pathogenesis and optimal therapy of this secondary thrombotic microangiopathy (TMA) remain uncertain. CASE REPORT: A 63-year-old Caucasian man was admitted with suspicion for TTP, but blood cultures grew C. canimorsus. Initial investigations revealed severe thrombocytopenia, a disintegrin and metalloproteinase with a thrombospondin type 1 motif, member 13 (ADAMTS13) activity level of less than 1%, and strongly elevated D-dimer and lactate dehydrogenase levels. He made a full recovery with antibiotics and plasma infusion for 3 days. Plasmapheresis was not performed. Retrospective determination of serial ADAMTS13 activity levels revealed that ADAMTS13 activity had already increased to 25% at the start of plasma infusion. CONCLUSION: This case highlights that a C. canimorsus sepsis may cause a secondary TMA with a severe ADAMTS13 deficiency. It also illustrates that the adjunctive role of plasma exchange or plasma infusion is doubtful as ADAMTS13 activity levels increased with antibiotics alone.

Treatment of invasive male breast cancer: a 40-year single-institution experience.

PURPOSE: We conducted a retrospective analysis to evaluate the management and outcome of invasive male breast cancer treated in a single-institution over a period of 40 years. MATERIALS AND METHODS: We reviewed the clinical and pathological features of 60 male patients affected by breast carcinoma treated at our Radiotherapy Unit between 1971 and 2011. Tumours were classified according to histological type and the updated 2010 TNM classification of malignant tumours. RESULTS: At a median follow-up of 8.9 [range, 0.6-20; standard deviation (SD), 4.98] years, 32 patients (53.3%) were alive and 16 patients died (26.7%) due to disease progression and 12 (20%) due to other causes. At univariate analysis for overall survival, pathological tumour size (p=0.031), histological subtype (p=0.013) and nodal status (p=0.006) emerged as significant predictors of death. At multivariate analysis, independent death predictors were advanced pathological tumour size (p=0.016), positive nodal status (p=0.003) and invasive cribriform histological type (p=0.0003). CONCLUSIONS: In consideration of the rarity of the disease, many issues are still being debated, and future collaborative studies are required. However, our experience confirms the prognostic role of greater pathological tumour size and positive nodal status as unfavourable features for survival in male breast cancer.

Associations of periconceptional oral contraceptive use with pregnancy complications and adverse birth outcomes.

BACKGROUND: Periconceptional use of oral contraceptives (OCs) has been reported to increase risks of pregnancy complications and adverse birth outcomes, but risks are suggested to differ depending on the timing of discontinuation, amount of oestrogen and progestin content. METHODS: Prospective cohort study among 6470 pregnancies included in the PRegnancy and Infant DEvelopment (PRIDE) Study in 2012-19. Exposure was defined as any reported use of OCs within 12 months pre-pregnancy or after conception. Outcomes of interest were gestational diabetes, gestational hypertension, pre-eclampsia, pre-term birth, low birthweight and small for gestational age (SGA). Multivariable Poisson regression using stabilized inverse probability weighting estimated relative risks (RRs) with 95% CIs. RESULTS: Any periconceptional OC use was associated with increased risks of pre-eclampsia (RR 1.38, 95% CI 0.99-1.93), pre-term birth (RR 1.38, 95% CI 1.09-1.75) and low birthweight (RR 1.45, 95% CI 1.10-1.92), but not with gestational hypertension (RR 1.09, 95% CI 0.91-1.31), gestational diabetes (RR 1.02, 95% CI 0.77-1.36) and SGA (RR 0.96, 95% CI 0.75-1.21). Associations with pre-eclampsia were strongest for discontinuation 0-3 months pre-pregnancy, for OCs containing ≥30 µg oestrogen and for first- or second-generation OCs. Pre-term birth and low birthweight were more likely to occur when OCs were discontinued 0-3 months pre-pregnancy, when using OCs containing <30 µg oestrogen and when using third-generation OCs. Associations with SGA were observed for OCs containing <30 µg oestrogen and for third- or fourth-generation OCs. CONCLUSIONS: Periconceptional OC use, particularly those containing oestrogen, was associated with increased risks of pre-eclampsia, pre-term birth, low birthweight and SGA.

Quality of Active versus Spontaneous Reporting of Adverse Drug Reactions in Pediatric Patients: Relevance for Pharmacovigilance and Knowledge in Pediatric Medical Care.

For drug safety in pediatric patients, knowledge about adverse drug reactions (ADRs) is essential to balance benefits and risks, especially because of the high incidence of off-label drug use. However, underreporting of ADRs is a serious problem, leading to a deficit in knowledge affecting clinical practice. The aim of this study is to find a method by which we can improve the quantity of ADR reporting while maintaining or improving the quality of the ADR reports. This was done in several steps. First, health care providers were educated to increase awareness of ADRs. Thereafter, a novel active supporting system was introduced, where reporting ADRs was simplified; if clinical physicians suspected an ADR, they only had to send the name or hospital number of the patient, the observed ADR, and the suspected drug to a supportive team. This team collects all information needed about the possible ADR from the patient's medical records and hospital charts. With this information, the supportive team fills in the forms necessary for reporting ADRs to the nationwide pharmacovigilance centre Lareb. With this system, the quantity of ADR reports from both inpatients and outpatients rose dramatically. Subsequently, the quality of the obtained ADR reports was measured using the ClinDoc and vigiGrade systems. This study shows there is no loss of quality of the ADR reports in the active reporting system compared to spontaneous reporting systems. Based on the data of the present study, we suggest that an active reporting system has the potential to increase our knowledge about ADRs in pediatric patients.

Off-Label, but on-Evidence? A Review of the Level of Evidence for Pediatric Pharmacotherapy.

Many drugs are still prescribed off-label to the pediatric population. Although off-label drug use not supported by high level of evidence is potentially harmful, a comprehensive overview of the quality of the evidence pertaining off-label drug use in children is lacking. The Dutch Pediatric Formulary (DPF) provides best evidence-based dosing guidelines for drugs used in children. For each drug-indication-age group combination-together compiling one record-we scored the highest available level of evidence: labeled use, systematic review or meta-analysis, randomized controlled trial (RCT), comparative research, noncomparative research, or consensus-based expert opinions. For records based on selected guidelines, the original sources were not reviewed. These records were scored as guideline. A total of 774 drugs were analyzed comprising a total of 6,426 records. Of all off-label records (n = 2,718), 14% were supported by high quality evidence (4% meta-analysis or systematic reviews, 10% RCTs of high quality), 20% by comparative research, 14% by noncomparative research, 37% by consensus-based expert opinions, and 15% by selected guidelines. Fifty-eight percent of all records were authorized, increasing with age from 30% in preterm neonates (n = 110) up to 64% in adolescents (n = 1,630). Many have advocated that off-label use is only justified when supported by a high level of evidence. We show that this prerequisite would seriously limit available drug treatment for children as the underlying evidence is low across ages and drug classes. Our data identify the drugs and therapeutic areas for which evidence is clearly missing and could drive the global research agenda.

Concomitant adjuvant chemo-radiation therapy with anthracycline-based regimens in breast cancer: a single centre experience.

PURPOSE: This study was done to evaluate the toxicity related to concurrent radiotherapy and anthracycline (AC)-based chemotherapy in the adjuvant treatment of early breast cancer and to investigate the impact of treatment interruptions and the feasibility of this uncommon therapeutic approach. MATERIALS AND METHODS: From September 2002 to December 2007, 60 patients were treated at our Centre. The mean age at presentation was 48.5 (range 38-64) years. All patients underwent conservative surgery, and radiotherapy to the entire breast (mean dose 50 Gy; range 46-52 Gy). AC-based regimens consisted of four cycles of AC (doxorubicin plus cyclophosphamide) or four cycles of epirubicin (EPI) followed by four courses of cyclophosphamide, methotrexate and 5-fluorouracil (CMF). RESULTS: Concomitant treatment caused acute skin G3 toxicity in 8.9% of patients and one case of G4 toxicity (1.7%). Concerning cardiac assessment, six of the 56 evaluable patients (10.7%) developed an asymptomatic decline of left ventricular ejection fraction >10% and <20% of the baseline value. Radiotherapy was temporarily stopped in 21.3% and chemotherapy in 57.1% of patients. CONCLUSIONS: In our experience, concomitant chemotherapy did not emerge as a significant factor in radiotherapy interruption. Moreover, no severe cardiac events were recorded.

Postmastectomy radiotherapy in breast cancer adjuvant treatment.

Radiotherapy (RT) plays an important role in the management of locally advanced breast cancer (BC). Postmastectomy RT has been shown to significantly reduce the risk of loco-regional failure and to improve disease free survival in high-risk women with BC. Many trials have shown a significant benefit in local control, disease-free and overall survival with the addition of RT for patients with stage II and III breast cancer. New perspectives are evaluating multiple biological variables that nowadays should be considered in clinical oncology for the prescription of postmastectomy radiation therapy. Tailored randomized trials are now ongoing to clarify the "grey zone" represented by the intermediate-risk group of patients (1-3 lymph nodes involved). We reviewed the major studies offered by literature with emphasis on the principal debated issues.

Completing the Enalaprilat Excretion Pathway-Renal Handling by the Proximal Tubule.

BACKGROUND: Enalapril is often used in the treatment of cardiovascular diseases. Clinical data suggest that the urinary excretion of enalaprilat, the active metabolite of enalapril, is mediated by renal transporters. We aimed to identify enalaprilat specificity for renal proximal tubular transporters. METHODS: Baculovirus-transduced HEK293 cells overexpressing proximal tubular transporters were used to study enalaprilat cellular uptake. Uptake into cells overexpressing the basolateral transporters OCT2, OAT1, OAT2, or OAT3 and apical transporters OAT4, PEPT1, PEPT2, OCTN1, OCTN2, MATE1, MATE2k, and URAT1 was compared with mock-transduced control cells. Transport by renal efflux transporters MRP2, MPR4, P-gp, and BCRP was tested using a vesicular assay. Enalaprilat concentrations were measured using LC-MS/MS. RESULTS: Uptake of enalaprilat into cells expressing OAT3 as well as OAT4 was significantly higher compared to control cells. The enalaprilat affinity for OAT3 was 640 (95% CI: 520-770) µM. For OAT4, no reliable affinity constant could be determined using concentrations up to 3 mM. No transport was observed for other transporters. CONCLUSION: The affinity of enalaprilat for OAT3 and OAT4 was notably low compared to other substrates. Taking this affinity and clinically relevant plasma concentrations of enalaprilat and other OAT3 substrates into account, we believe that drug-drug interactions on a transporter level do not have a therapeutic consequence and will not require dose adjustments of enalaprilat itself or other OAT3 substrates.

Pharmacology of enalapril in children: a review.

Enalapril is an angiotensin-converting enzyme (ACE) inhibitor that is used for the treatment of (paediatric) hypertension, heart failure and chronic kidney diseases. Because its disposition, efficacy and safety differs across the paediatric continuum, data from adults cannot be automatically extrapolated to children. This review highlights paediatric enalapril pharmacokinetic data and demonstrates that these are inadequate to support with certainty an age-related effect on enalapril/enalaprilat pharmacokinetics. In addition, our review shows that evidence to support effective and safe prescribing of enalapril in children is limited, especially in young children and heart failure patients; studies in these groups are either absent or show conflicting results. We provide explanations for observed differences between age groups and indications, and describe areas for future research.

Adjuvant hypofractionated radiation therapy for breast cancer after conserving surgery.

AIMS: To evaluate the incidence of locoregional recurrence (LRR) and the cosmetic results in a group of patients with breast cancer treated with a hypofractionated schedule of adjuvant radiotherapy after conservative surgery. MATERIALS AND METHODS: In total, 539 patients with pTis-pT1-pT2 breast cancer underwent radiotherapy treatment after conservative surgery at the University of Florence and at the Pistoia Hospital. The dose delivered was 44 Gy (2.75 Gy daily fraction). The tumour bed boost (10 Gy) was given by electrons. RESULTS: At the time of the analysis, 1.8% of patients (10/539) had breast relapse. No patients developed nodal recurrence (supraclavicular, axillary and internal mammary nodes). The 3- and 5-year actuarial rates for LRR were 1.2% (+/- 0.5% standard error) and 2.1% (+/- 0.6% standard error), respectively. Considering the late toxicity, we found that 412 (76.4%) patients had grade 0 or grade 1 late toxicity, 113 patients (20.9%) had grade 2 late toxicity and 14 patients (2.5%) had grade 3 late toxicity. No patients developed grade 4 toxicity. CONCLUSION: This type of approach resulted in an effective treatment in terms of local control in patients with negative or one to three positive axillary nodes and negative surgical margins. Patients treated with a hypofractionated schedule showed very good cosmesis.

Shape analysis of microcalcifications using Radon transform.

Microcalcifications are one of the early signs of breast cancer, and they are of great importance for an early diagnosis. Moreover, the spatial distribution and the shape of the microcalcifications have a significant impact in medical practice to evaluate the probability of malignancy of the tumor. In this work a method, performing computer-aided classification of the shape of calcifications accordingly to the classification scheme proposed by Le Gal, is presented. In the first stage, in order to remove mammographic background, the image is preprocessed with a matched filter, designed by modeling the microcalcifications as Gaussian spots and the image as a Fractional Brownian Motion. Afterwards, morphology of spots has been evaluated using two different sets of parameters. The first set utilizes the moments of inertia of the second and third order to compute a set of features, which are invariant to rotations and translations of the image. The second set of parameters is derived from the evaluation of the Radon transform, as computed along eight axes. The results of the Radon transform are used to associate to each lesion a set of features, which are invariant to rotation and scaling of the image. In the final stage, a multilayer neural network has been used to assign each microcalcification to the classes introduced by Le Gal. The topology of the neural network is the same for both sets of descriptors, in order to allow comparison of the discriminative power of the two feature sets. Experimental results obtained with the proposed method from a set of digitized mammograms are reported and discussed.