Search

PurposeTo develop and evaluate the diagnostic performance of an algorithm for multi-marker radiomic-based classification of breast masses in dedicated breast computed tomography (bCT) images.MethodsOver 1000 radiomic descriptors aimed at quantifying mass and border heterogeneity, morphology, and margin sharpness were developed and implemented. These included well-established texture and shape feature descriptors, which were supplemented with additional approaches for contour irregularity quantification, spicule and lobe detection, characterization of degree of infiltration, and differences in peritumoral compartments. All descriptors were extracted from a training set of 202 bCT masses (133 benign and 69 malignant), and their individual diagnostic performance was investigated in terms of area under the receiver operating characteristics (ROC) curve (AUC) of single-feature-based linear discriminant analysis (LDA) classifiers. Subsequently, the most relevant descriptors were selected through a multiple-step feature selection process (including stability analysis, statistical significance, evaluation of feature interaction, and dimensionality reduction), and used to develop a final LDA radiomic model for classification of benign and malignant masses, which was then tested on an independent test set of 82 cases (45 benign and 37 malignant).ResultsThe majority of the individual radiomic descriptors showed, on the training set, an AUC value deriving from a linear decision boundary higher than 0.65, with the lower limit of the associated 95% confidence interval (C.I.) not overlapping with random chance (AUC = 0.5). The final LDA radiomic model resulted in a test set AUC of 0.90 (95% C.I. 0.80-0.96).ConclusionsThe proposed multi-marker radiomic approach achieved high diagnostic accuracy in bCT mass classification, using a radiomic signature based on different feature types. While future studies with larger datasets are needed to further validate these results, quantitative radiomics applied to bCT shows potential to improve the breast cancer diagnosis pipeline.

Histological staining plays a crucial role in anatomic pathology for the analysis of biological tissues and the formulation of diagnostic reports. Traditional methods like hematoxylin and eosin (H&E) primarily offer morphological information but lack insight into functional details, such as the expression of biomarkers indicative of cellular activity. To overcome this limitation, we propose a computational approach to synthesize virtual immunohistochemical (IHC) stains from H&E input, transferring imaging features across staining domains. Our approach comprises two stages: (i) a multi‐stage registration framework ensuring precise alignment of cellular and subcellular structures between the source H&E and target IHC stains, and (ii) a deep learning‐based generative model which incorporates functional attributes from the target IHC stain by learning cell‐to‐cell mappings from paired training data. We evaluated our approach of virtual restaining H&E slides to simulate IHC staining for phospho‐histone H3, on inguinal lymph node and bladder tissues. Blind pathologist assessments and quantitative metrics validated the diagnostic quality of the synthetic slides. Notably, mitotic counts derived from synthetic images exhibited a strong correlation with physical staining. Moreover, global and stain‐specific metrics confirmed the high quality of the synthetic IHC images generated by our approach. This methodology represents an important advance in automated functional restaining, achieved through robust registration and a model trained on precisely paired H&E and IHC data to transfer functions cell‐by‐cell. Our approach forms the basis for multiparameter histology analysis and comprehensive cohort staining using only digitized H&E slides. [ABSTRACT FROM AUTHOR]

Objective: To assess the ultrasonographic, epidemiological, clinical and evolutive characteristics of enhanced myometrial vascularity (EMV) following a first‐trimester termination of pregnancy (TOP) or management of non‐viable pregnancy. Methods: This prospective study included women who underwent follow‐up ultrasound examination 5–6 weeks after a first‐trimester TOP or after management of a first‐trimester non‐viable pregnancy at the University Hospital Polyclinic San Martino of Genoa between March 2021 and March 2022. EMV was characterized using two‐ and three‐dimensional ultrasound and Virtual Organ Computer‐aided Analysis. Ultrasonographic diagnosis of EMV was made when an unusual, tortuous myometrial vessel structure, with high‐velocity blood flow, protruding towards the endometrium was observed, while an abnormal junctional zone, absent endometrial midline and heterogeneous endometrium supported the diagnosis. Patients with EMV underwent expectant management with planned ultrasonographic follow‐up every 2 weeks until resolution. Results: During the study period, 305 women underwent TOP, of whom 132 attended the initial follow‐up 5–6 weeks later, at which 52 were diagnosed with EMV. Ninety‐six women were managed for a non‐viable pregnancy, of whom 32 presented for follow‐up, at which six had a diagnosis of EMV. Thus, overall, 164 of 401 women were included in the study and EMV was identified in 58 (35%) of these. The prevalence of EMV 5–6 weeks after a TOP was therefore between 52/305 (17%) and 52/132 (39%), and that after management of a non‐viable pregnancy was between 6/96 (6%) and 6/32 (19%). Bleeding/pelvic pain was present in half (29/58) of the women with EMV, and serum human chorionic gonadotropin was detectable in 29% (17/58) at the first follow‐up examination. At ultrasound assessment, all cases with EMV presented abundant tortuous myometrial vessels with high‐velocity flow projecting from the myometrium towards the endometrium, along with non‐uniform heterogeneous endometrium in 97% of cases, which often (67% of these) contained cystic areas, absence of the endometrial midline in 98% of cases and an abnormal junctional zone in 97% of cases (64% interrupted, 33% irregular). Most (67%) women with EMV were parous and 90% of them had undergone TOP rather than management for a non‐viable pregnancy. Medical management of the TOP or non‐viable pregnancy was more frequent in women with than those without EMV (93% vs 77%, P = 0.023). Multiple regression analysis showed the risk of EMV to be increased following TOP vs non‐viable pregnancy (odds ratio (OR), 3.67 (95% CI, 1.16–11.56), P = 0.026) and in parous compared with nulliparous women (OR, 2.95 (95% CI, 1.45–6.01), P = 0.002). All women with EMV underwent expectant management. Eleven women did not return for subsequent follow‐up examinations and did not present to our outpatient or emergency facilities, so were lost to further follow‐up. Spontaneous resolution of the lesion was observed within 7–16 weeks after the procedure in 96% (45/47) of the remaining cases. Two women chose to undergo surgery for pelvic discomfort, and histology showed the presence of neovessels mixed with retained chorionic villi. Conclusions: EMV is a transient and common finding 5–6 weeks following first‐trimester TOP or management of non‐viable pregnancy. TOP and being parous are risk factors for EMV. Expectant management of EMV is appropriate, because, in almost all cases, this resolves spontaneously, without complications, within 2–4 months. © 2023 International Society of Ultrasound in Obstetrics and Gynecology. [ABSTRACT FROM AUTHOR]