Radiologia Medica最新文献

{"title":"Machine learning and radiomics analysis by computed tomography in colorectal liver metastases patients for RAS mutational status prediction.","authors":"Vincenza Granata, Roberta Fusco, Sergio Venanzio Setola, Maria Chiara Brunese, Annabella Di Mauro, Antonio Avallone, Alessandro Ottaiano, Nicola Normanno, Antonella Petrillo, Francesco Izzo","doi":"10.1007/s11547-024-01828-5","DOIUrl":"10.1007/s11547-024-01828-5","url":null,"abstract":"<p><strong>Purpose: </strong>To assess the efficacy of machine learning and radiomics analysis by computed tomography (CT) in presurgical setting, to predict RAS mutational status in colorectal liver metastases.</p><p><strong>Methods: </strong>Patient selection in a retrospective study was carried out from January 2018 to May 2021 considering the following inclusion criteria: patients subjected to surgical resection for liver metastases; proven pathological liver metastases; patients subjected to enhanced CT examination in the presurgical setting with a good quality of images; and RAS assessment as standard reference. A total of 851 radiomics features were extracted using the PyRadiomics Python package from the Slicer 3D image computing platform after slice-by-slice segmentation on CT portal phase by two expert radiologists of each individual liver metastasis performed first independently by the individual reader and then in consensus. Balancing technique was performed, and inter- and intraclass correlation coefficients were calculated to assess the between-observer and within-observer reproducibility of features. Receiver operating characteristics (ROC) analysis with the calculation of area under the ROC curve (AUC), sensitivity (SENS), specificity (SPEC), positive predictive value (PPV), negative predictive value (NPV) and accuracy (ACC) were assessed for each parameter. Linear and non-logistic regression model (LRM and NLRM) and different machine learning-based classifiers were considered. Moreover, features selection was performed before and after a normalized procedure using two different methods (3-sigma and z-score).</p><p><strong>Results: </strong>Seventy-seven liver metastases in 28 patients with a mean age of 60 years (range 40-80 years) were analyzed. The best predictors, at univariate analysis for both normalized procedures, were original_shape_Maximum2DDiameter and wavelet_HLL_glcm_InverseVariance that reached an accuracy of 80%, an AUC ≥ 0.75, a sensitivity ≥ 80% and a specificity ≥ 70% (p value <  < 0.01). However, a multivariate analysis significantly increased the accuracy in RAS prediction when a linear regression model (LRM) was used. The best performance was obtained using a LRM combining linearly 12 robust features after a z-score normalization procedure: AUC of 0.953, accuracy 98%, sensitivity 96%, specificity of 100%, PPV 100% and NPV 96% (p value <  < 0.01). No statistically significant increase was obtained considering the tested machine learning both without normalization and with normalization methods.</p><p><strong>Conclusions: </strong>Normalized approach in CT radiomics analysis allows to predict RAS mutational status in colorectal liver metastases patients.</p>","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"957-966"},"PeriodicalIF":9.7,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140959249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Health technology assessment in musculoskeletal radiology: the case study of EOSedge™.","authors":"Rossella Tomaiuolo, Giuseppe Banfi, Carmelo Messina, Domenico Albano, Salvatore Gitto, Luca Maria Sconfienza","doi":"10.1007/s11547-024-01832-9","DOIUrl":"10.1007/s11547-024-01832-9","url":null,"abstract":"<p><strong>Objectives: </strong>Health technology assessment (HTA) is a systematic process used to evaluate the properties and effects of healthcare technologies within their intended use context. This paper describes the adoption of HTA process to assess the adoption of the EOSedge™ system in clinical practice.</p><p><strong>Methods: </strong>The EOSedge™ system is a digital radiography system that delivers whole-body, high-quality 2D/3D biplanar images covering the complete set of musculoskeletal and orthopedic exams. Full HTA model was chosen using the EUnetHTA Core Model^® version 3.0. The HTA Core Model organizes the information into nine domains. Information was researched and obtained by consulting the manufacturers' user manuals, scientific literature, and institutional sites for regulatory aspects.</p><p><strong>Results: </strong>All nine domains of the EUnetHTA Core Model^® helped conduct the HTA of the EOSedge, including (1) description and technical characteristics of the technology; (2) health problem and current clinical practice; (3) safety; (4) clinical effectiveness; (5) organizational aspects; (6) economic evaluation; (7) impact on the patient; (8) ethical aspects; and (9) legal aspects.</p><p><strong>Conclusions: </strong>EOS technologies may be a viable alternative to conventional radiographs. EOSedge has the same intended use and similar indications for use, technological characteristics, and operation principles as the EOS System and provides significant dose reduction factors for whole spine imaging compared to the EOS System without compromising image quality. Regarding the impact of EOS imaging on patient outcomes, most studies aim to establish technical ability without evaluating their ability to improve patient outcomes; thus, more studies on this aspect are warranted.</p>","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"1076-1085"},"PeriodicalIF":9.7,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11252187/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141296635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The performance of the node reporting and data system 1.0 (Node-RADS) and DWI-MRI in staging patients with cervical carcinoma according to the new FIGO classification (2018).","authors":"Roberta Valerieva Ninkova, Alessandro Calabrese, Federica Curti, Sandrine Riccardi, Marco Gennarini, Valentina Miceli, Angelica Cupertino, Violante Di Donato, Angelina Pernazza, Stefania Maria Rizzo, Valeria Panebianco, Carlo Catalano, Lucia Manganaro","doi":"10.1007/s11547-024-01824-9","DOIUrl":"10.1007/s11547-024-01824-9","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the diagnostic accuracy of the Node-RADS score and the utility of apparent diffusion coefficient (ADC) values in predicting metastatic lymph nodes (LNs) involvement in cervical cancer (CC) patients using magnetic resonance imaging (MRI). The applicability of the Node RADS score across three readers with different years of experience in pelvic imaging was also assessed.</p><p><strong>Material and methods: </strong>Among 140 patients, 68 underwent staging MRI, neoadjuvant chemotherapy and radical surgery, forming the study cohort. Node-RADS scores of the main pelvic stations were retrospectively determined to assess LN metastatic likelihood and compared with the histological findings. Mean ADC, relative ADC (rADC), and correct ADC (cADC) values of LNs classified as Node-RADS ≥ 3 were measured and compared with histological reports, considered as gold standard.</p><p><strong>Results: </strong>Sensitivity, specificity, positive and negative predictive values (PPVs and NPVs), and accuracy were calculated for different Node-RADS thresholds. Node RADS ≥ 3 showed a sensitivity of 92.8% and specificity of 72.5%. Node RADS ≥ 4 yielded a sensitivity of 71.4% and specificity of 100%, while Node RADS 5 yielded 42.9% and 100%, respectively. The diagnostic performance of mean ADC, cADC and rADC values from 78 LNs with Node-RADS score ≥ 3 was assessed, with ADC demonstrating the highest area under the curve (AUC 0.820), compared to cADC and rADC values.</p><p><strong>Conclusion: </strong>The Node-RADS score provides a standardized LNs assessment, enhancing diagnostic accuracy in CC patients. Its ease of use and high inter-observer concordance support its clinical utility. ADC measurement of LNs shows promise as an additional tool for optimizing patient diagnostic evaluation.</p>","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"1062-1075"},"PeriodicalIF":9.7,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11252186/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140904642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of window settings for coronary arteries assessment using spectral CT-derived virtual monoenergetic imaging.","authors":"Tommaso D'Angelo, Domenico Mastrodicasa, Ludovica R M Lanzafame, Ibrahim Yel, Vitali Koch, Leon D Gruenewald, Simran P Sharma, Velio Ascenti, Antonino Micari, Alfredo Blandino, Thomas J Vogl, Silvio Mazziotti, Ricardo P J Budde, Christian Booz","doi":"10.1007/s11547-024-01835-6","DOIUrl":"10.1007/s11547-024-01835-6","url":null,"abstract":"<p><strong>Purpose: </strong>To determine the optimal window setting for virtual monoenergetic images (VMI) reconstructed from dual-layer spectral coronary computed tomography angiography (DE-CCTA) datasets.</p><p><strong>Material and methods: </strong>50 patients (30 males; mean age 61.1 ± 12.4 years who underwent DE-CCTA from May 2021 to June 2022 for suspected coronary artery disease, were retrospectively included. Image quality assessment was performed on conventional images and VMI reconstructions at 70 and 40 keV. Objective image quality was assessed using contrast-to-noise ratio (CNR). Two independent observers manually identified the best window settings (B-W/L) for VMI 70 and VMI 40 visualization. B-W/L were then normalized with aortic attenuation using linear regression analysis to obtain the optimized W/L (O-W/L) settings. Additionally, subjective image quality was evaluated using a 5-point Likert scale, and vessel diameters were measured to examine any potential impact of different W/L settings.</p><p><strong>Results: </strong>VMI 40 demonstrated higher CNR values compared to conventional and VMI 70. B-W/L settings identified were 1180/280 HU for VMI 70 and 3290/900 HU for VMI 40. Subsequent linear regression analysis yielded O-W/L settings of 1155/270 HU for VMI 70 and 3230/880 HU for VMI 40. VMI 40 O-W/L received the highest scores for each parameter compared to conventional (all p < 0.0027). Using O-W/L settings for VMI 70 and VMI 40 did not result in significant differences in vessel measurements compared to conventional images.</p><p><strong>Conclusion: </strong>Optimization of VMI requires adjustments in W/L settings. Our results recommend W/L settings of 1155/270 HU for VMI 70 and 3230/880 HU for VMI 40.</p>","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"999-1007"},"PeriodicalIF":9.7,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11252218/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141458979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dual-energy CT in musculoskeletal imaging: technical considerations and clinical applications.","authors":"Domenico Albano, Filippo Di Luca, Tommaso D'Angelo, Christian Booz, Federico Midiri, Salvatore Gitto, Stefano Fusco, Francesca Serpi, Carmelo Messina, Luca Maria Sconfienza","doi":"10.1007/s11547-024-01827-6","DOIUrl":"10.1007/s11547-024-01827-6","url":null,"abstract":"<p><p>Dual-energy CT stands out as a robust and innovative imaging modality, which has shown impressive advancements and increasing applications in musculoskeletal imaging. It allows to obtain detailed images with novel insights that were once the exclusive prerogative of magnetic resonance imaging. Attenuation data obtained by using different energy spectra enable to provide unique information about tissue characterization in addition to the well-established strengths of CT in the evaluation of bony structures. To understand clearly the potential of this imaging modality, radiologists must be aware of the technical complexity of this imaging tool, the different ways to acquire images and the several algorithms that can be applied in daily clinical practice and for research. Concerning musculoskeletal imaging, dual-energy CT has gained more and more space for evaluating crystal arthropathy, bone marrow edema, and soft tissue structures, including tendons and ligaments. This article aims to analyze and discuss the role of dual-energy CT in musculoskeletal imaging, exploring technical aspects, applications and clinical implications and possible perspectives of this technique.</p>","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"1038-1047"},"PeriodicalIF":9.7,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11252181/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140923118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The influence of manual segmentation strategies and different phases selection on machine learning-based computed tomography in renal tumors: a systematic review and meta-analysis.","authors":"Honghao Song, Xiaoqing Wang, Rongde Wu, Wei Liu","doi":"10.1007/s11547-024-01825-8","DOIUrl":"10.1007/s11547-024-01825-8","url":null,"abstract":"<p><strong>Background: </strong>Delineating the region/volume of interest (ROI/VOI) and selecting the phases are of importance in developing machine learning (ML). The results will change when choosing different methods of drawing the ROI/VOI and selecting different phases. However, there is no related standard for delineating the ROI/VOI and selecting the phases in renal tumors to develop ML based on computed tomography (CT).</p><p><strong>Methods: </strong>The PubMed and Web of Science were searched for related studies published until March 1, 2023. Inclusion criteria were studies that developed ML models in renal tumors from CT images. And the binary diagnostic accuracy data were extracted to obtain the outcomes, such as sensitivity (SE), specificity (SP), accuracy (ACC), and area under the curve (AUC).</p><p><strong>Results: </strong>Twenty-three papers were included in the meta-analysis with a pooled SE of 87% (95% CI 85-88%), SP of 82% (95% CI 79-85%), and AUC of 91% (95% CI 89-93%) in phases; a pooled SE of 82% (95% CI 80-84%), SP of 85% (95% CI 83-86%), and AUC of 90% (95% CI 88-93%) in phases combined with delineating strategies, respectively. In all different combinations, the contour-focused and single phase produce the highest AUC of 93% (95% CI 90-95%). In subgroup analyses (sample size, year of publication, and geographical distribution), the performance was acceptable on phases and phases combined strategies.</p><p><strong>Conclusions: </strong>To explore the effect of manual segmentation strategies and different phases selection on ML-based CT, we find that the method of single phase (CMP or NP) combined with contour-focused was considered a better strategy compared to the other strategies.</p>","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"1025-1037"},"PeriodicalIF":9.7,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140916351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"What the urologist needs to know before radical prostatectomy: MRI effective support to pre-surgery planning.","authors":"Ludovica Laschena, Emanuele Messina, Rocco Simone Flammia, Antonella Borrelli, Simone Novelli, Daniela Messineo, Costantino Leonardo, Alessandro Sciarra, Antonio Ciardi, Carlo Catalano, Valeria Panebianco","doi":"10.1007/s11547-024-01831-w","DOIUrl":"10.1007/s11547-024-01831-w","url":null,"abstract":"<p><strong>Background: </strong>Radical prostatectomy (RP) is recommended in case of localized or locally advanced prostate cancer (PCa), but it can lead to side effects, including urinary incontinence (UI) and erectile dysfunction (ED). Magnetic resonance imaging (MRI) is recommended for PCa diagnosis and staging, but it can also improve preoperative risk-stratification.</p><p><strong>Purpose: </strong>This nonsystematic review aims to provide an overview on factors involved in RP side effects, highlighting anatomical and pathological aspects that could be included in a structured report.</p><p><strong>Evidence synthesis: </strong>Considering UI evaluation, MR can investigate membranous urethra length (MUL), prostate volume, the urethral sphincter complex, and the presence of prostate median lobe. Longer MUL measurement based on MRI is linked to a higher likelihood of achieving continence restoration. For ED assessment, MRI and diffusion tensor imaging identify the neurovascular bundle and they can aid in surgery planning. Finally, MRI can precisely describe extra-prostatic extension, prostate apex characteristics and lymph-node involvement, providing valuable preoperative information for PCa treatment.</p><p><strong>Conclusions: </strong>Anatomical principals structures involved in RP side effects can be assessed with MR. A standardized MR report detailing these structures could assist urologists in planning optimal and tailored surgical techniques, reducing complications, and improving patients' care.</p>","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"1048-1061"},"PeriodicalIF":9.7,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11252184/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141451371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PSMA-positive prostatic volume prediction with deep learning based on T2-weighted MRI.","authors":"Riccardo Laudicella, Albert Comelli, Moritz Schwyzer, Alessandro Stefano, Ender Konukoglu, Michael Messerli, Sergio Baldari, Daniel Eberli, Irene A Burger","doi":"10.1007/s11547-024-01820-z","DOIUrl":"10.1007/s11547-024-01820-z","url":null,"abstract":"<p><strong>Purpose: </strong>High PSMA expression might be correlated with structural characteristics such as growth patterns on histopathology, not recognized by the human eye on MRI images. Deep structural image analysis might be able to detect such differences and therefore predict if a lesion would be PSMA positive. Therefore, we aimed to train a neural network based on PSMA PET/MRI scans to predict increased prostatic PSMA uptake based on the axial T2-weighted sequence alone.</p><p><strong>Material and methods: </strong>All patients undergoing simultaneous PSMA PET/MRI for PCa staging or biopsy guidance between April 2016 and December 2020 at our institution were selected. To increase the specificity of our model, the prostatic beds on PSMA PET scans were dichotomized in positive and negative regions using an SUV threshold greater than 4 to generate a PSMA PET map. Then, a C-ENet was trained on the T2 images of the training cohort to generate a predictive prostatic PSMA PET map.</p><p><strong>Results: </strong>One hundred and fifty-four PSMA PET/MRI scans were available (133 [⁶⁸Ga]Ga-PSMA-11 and 21 [¹⁸F]PSMA-1007). Significant cancer was present in 127 of them. The whole dataset was divided into a training cohort (n = 124) and a test cohort (n = 30). The C-ENet was able to predict the PSMA PET map with a dice similarity coefficient of 69.5 ± 15.6%.</p><p><strong>Conclusion: </strong>Increased prostatic PSMA uptake on PET might be estimated based on T2 MRI alone. Further investigation with larger cohorts and external validation is needed to assess whether PSMA uptake can be predicted accurately enough to help in the interpretation of mpMRI.</p>","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"901-911"},"PeriodicalIF":9.7,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11168990/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140857738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Systemic chemotherapy plus transarterial chemoembolization versus systemic chemotherapy alone for unresectable intrahepatic cholangiocarcinoma: a multicenter retrospective cohort study.","authors":"Nan Jiang, Ze Zhang, Xiaoxv Yin, Huaiming Qiu, Weipeng Yan, Yonghong Hao, Wenhua Yang, Hualing Li, Anhui Xu, Ketao Mu","doi":"10.1007/s11547-024-01823-w","DOIUrl":"10.1007/s11547-024-01823-w","url":null,"abstract":"","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"955"},"PeriodicalIF":9.7,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140912584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer.","authors":"Antonella Petrillo, Roberta Fusco, Teresa Petrosino, Paolo Vallone, Vincenza Granata, Maria Rosaria Rubulotta, Paolo Pariante, Nicola Raiano, Giosuè Scognamiglio, Annarita Fanizzi, Raffaella Massafra, Miria Lafranceschina, Daniele La Forgia, Laura Greco, Francesca Romana Ferranti, Valeria De Soccio, Antonello Vidiri, Francesca Botta, Valeria Dominelli, Enrico Cassano, Eugenio Sorgente, Biagio Pecori, Vincenzo Cerciello, Luca Boldrini","doi":"10.1007/s11547-024-01817-8","DOIUrl":"10.1007/s11547-024-01817-8","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the performance of radiomic analysis on contrast-enhanced mammography images to identify different histotypes of breast cancer mainly in order to predict grading, to identify hormone receptors, to discriminate human epidermal growth factor receptor 2 (HER2) and to identify luminal histotype of the breast cancer.</p><p><strong>Methods: </strong>From four Italian centers were recruited 180 malignant lesions and 68 benign lesions. However, only the malignant lesions were considered for the analysis. All patients underwent contrast-enhanced mammography in cranium caudal (CC) and medium lateral oblique (MLO) view. Considering histological findings as the ground truth, four outcomes were considered: (1) G1 + G2 vs. G3; (2) HER2 + vs. HER2 - ; (3) HR + vs. HR - ; and (4) non-luminal vs. luminal A or HR + /HER2-  and luminal B or HR + /HER2 + . For multivariate analysis feature selection, balancing techniques and patter recognition approaches were considered.</p><p><strong>Results: </strong>The univariate findings showed that the diagnostic performance is low for each outcome, while the results of the multivariate analysis showed that better performances can be obtained. In the HER2 + detection, the best performance (73% of accuracy and AUC = 0.77) was obtained using a linear regression model (LRM) with 12 features extracted by MLO view. In the HR + detection, the best performance (77% of accuracy and AUC = 0.80) was obtained using a LRM with 14 features extracted by MLO view. In grading classification, the best performance was obtained by a decision tree trained with three predictors extracted by MLO view reaching an accuracy of 82% on validation set. In the luminal versus non-luminal histotype classification, the best performance was obtained by a bagged tree trained with 15 predictors extracted by CC view reaching an accuracy of 94% on validation set.</p><p><strong>Conclusions: </strong>The results suggest that radiomics analysis can be effectively applied to design a tool to support physician decision making in breast cancer classification. In particular, the classification of luminal versus non-luminal histotypes can be performed with high accuracy.</p>","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":"864-878"},"PeriodicalIF":9.7,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140959215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}