Search Results (256)

Background: Breast imaging ends in a management decision, from routine return to biopsy, yet most models are evaluated by accuracy alone and say nothing about when they may be wrong. We present a trust-aware multimodal model that reads paired mammography and ultrasound, recommends one of three BI-RADS-derived management actions, and returns to the radiologist the cases it cannot call. Methods: Two foundation encoders are adapted with low-rank adapters and combined by a mask-aware fusion head. A trustworthiness layer adds calibration, conformal prediction sets, selective deferral, and an atypicality flag. We evaluated our method on the Breast Cancer Multimodal Imaging Dataset (BCMID), comprising 332 cases from 323 patients at a single centre. The reference standard is a three-class management grouping we derive from the reporting radiologist’s BI-RADS assessment, so performance is in concordance with that derived label rather than with pathology, observed patient management or longitudinal clinical outcome. Results: Macro AUROC was 0.759 and balanced accuracy was 0.556. Isotonic calibration reduced calibration error from 0.088 to 0.052, and prediction sets reached an empirical coverage of 0.934 at a mean set size of 2.32. Deferring the least confident 30% by a retrospective ranking of the pooled cohort raised balanced accuracy to 0.631. Two of 63 positive-management cases were under-triaged and 15 routed to additional imaging, with a recall of 0.730; freezing the encoders left macro AUROC at 0.756 but raised the under-triage count to twelve. Conclusions: Error rate and error direction are separable properties, and neither accuracy nor macro AUROC records the direction. The system therefore pairs each recommendation with calibrated probabilities, a conformal set of plausible actions and an explicit defer option, so uncertain cases return to the radiologist. These results establish an internally validated operating profile for radiologist-facing support; clinical safety, deployment readiness and benefit to patients still require external and prospective evaluation. Full article

This study evaluated unconditional synthetic mammography generation with Deep Convolutional Generative Adversarial Networks (DCGANs). The dataset comprised 690 anonymized mammograms, equally distributed across BI-RADS 1–6 (115 images/category). All images were standardized to 512 × 512 pixels, reoriented to a common right-breast view, and prepared in two input domains: grayscale and color-mapped intensity encoding. Two models were compared: a standard DCGAN trained directly at 512 × 512, and a progressive DCGAN trained through discrete stages from 8 × 8 to 512 × 512. Training used PyTorch (Python 3.10), latent dimension = 100, Adam, learning rate = 2 × 10⁻⁴, β1 = 0.5, binary cross-entropy loss, and batch size = 1. Both models learned the low-frequency mammographic manifold, generating breast-like silhouettes and heterogeneous internal intensity distributions. However, the progressive DCGAN produced smoother contours, more coherent internal organization, and fewer grid/line artifacts than the standard model. Grayscale-only training showed weak learning, whereas the color-mapped domain improved structural recovery, although this advantage should be interpreted as computational rather than clinical. Late-epoch checkpoint analysis showed a structurally invariant generator with 43 tensors and 19,531,127 parameters; from epochs 89–100, relative checkpoint drift remained within 0.294–0.317%, with epochs 93–96 showing the most stable regime. Despite these advances, generated images still exhibited background speckle, coarse mottled texture, extra-anatomical bright structures, and limited diversity. Thus, the results support feasibility of synthetic mammography generation, but not yet clinically reliable synthetic data for direct AI training. The generated images should presently be regarded as exploratory complementary data pending expert, metric-based, and downstream validation. Full article

Breast cancer continues to represent a major global health burden, highlighting the need for effective approaches to risk stratification and clinical decision support. Conventional methods, including the Breast Imaging Reporting and Data System (BI-RADS) and histopathological classifications, primarily rely on clinical assessments and may not fully account for relevant demographic and behavioral characteristics. To overcome these limitations, we present an integrated framework combining K-Means clustering, Random Forest classification, and Explainable Artificial Intelligence (XAI) to support breast cancer risk stratification and patient prioritization. The proposed methodology uses clustering to stratify patients into low-, medium-, and high-risk groups, followed by supervised machine learning to reproduce the cluster-derived risk categories, achieving an accuracy of 98%. To enhance interpretability, Local Interpretable Model-Agnostic Explanations (LIME) are incorporated to identify the variables that most strongly influence individual classifications, including body mass index (BMI), breastfeeding practices, and maternal age. By integrating multiple dimensions of patient information, the framework provides a more comprehensive characterization of risk while increasing the transparency of the decision-making process. Its relatively simple and scalable architecture also facilitates potential implementation in healthcare environments with limited resources. Simulation experiments further provide a proof-of-concept evaluation of the proposed prioritization approach. Compared with random patient selection, the strategy achieved a substantially higher average severity score (1.66 vs. 0.92) and prioritized 4.3 times more high-risk patients. These findings suggest that the proposed framework can serve as an intelligent decision-support tool for prioritizing breast cancer patients and improving resource allocation when healthcare capacity is constrained. Full article

Background/Objectives: Pretreatment imaging may help estimate axillary response after neoadjuvant chemotherapy (NAC) in clinically node-positive (cN+) breast cancer. This study compared routinely available magnetic resonance imaging (MRI) and ultrasound (US) descriptors from the primary tumor and axillary nodes for predicting axillary nodal response, defined as postneoadjuvant pathologic node-negative status (ypN0). Methods: This retrospective multicenter study included 243 patients from three centers: 146 in the training cohort, 59 in the internal validation cohort, and 38 in the external validation cohort. The index breast tumor and axillary node were identified by a senior radiologist, and two radiologists independently assessed structured descriptors based on BI-RADS 2025. Least absolute shrinkage and selection operator regression and logistic regression were used to develop imaging-only, clinical-only, and clinicoradiologic models. Performance was evaluated using area under the curve (AUC), calibration, decision curve analysis, net reclassification improvement, and integrated discrimination improvement. Results: In the internal and external validation cohorts, the trimodal imaging model achieved AUCs of 0.761 and 0.806, and the clinicoradiologic model achieved the highest AUCs of 0.858 and 0.931, respectively. In pooled validation subgroup analyses, AUCs were 0.928, 0.804, and 0.700 for HR-positive/HER2-negative, HER2-positive, and triple-negative tumors, and 0.898 and 0.880 for cN1 and cN2–3 disease, respectively. Conclusions: MRI tumor descriptors provided the strongest imaging signal for ypN0 prediction, while US descriptors offered modest complementary information. The clinicoradiologic model may support pretreatment risk stratification and multidisciplinary planning for post-NAC axillary reassessment, but should not independently determine sentinel lymph node biopsy, axillary lymph node dissection, or omission of axillary staging. Full article

Background/Objectives: Accurate preoperative detection of locally advanced breast cancer is essential for neoadjuvant therapy planning. We developed and validated gradient-boosting models using structured BI-RADS mammographic features to simultaneously predict locally advanced breast cancer (LABC), DCIS component, and multifocality in a multi-center cohort. Methods: This retrospective study enrolled 2295 patients from three university-affiliated hospitals; features were coded according to BI-RADS. CatBoost and logistic regression models were built using stratified 60/20/20 splits, with performance assessed via bootstrap resampling, nested cross-validation, and sensitivity analyses. AUROC, AUPRC, Brier score, and calibration metrics assessed discrimination and clinical utility; a leakage audit and SHAP analysis supported interpretation. Results: CatBoost achieved an AUROC of 0.906 (95% CI: 0.876–0.932) for LABC. Because several top predictors overlap with the anatomical criteria defining this outcome, we repeated the analysis excluding them; the reduced model retained a mean AUROC of 0.739, indicating genuine predictive signal beyond the staging overlap. Net benefit was positive across all relevant thresholds, with calibration error of 0.053. DCIS prediction was highly accurate (AUROC 0.979; nested AUROC 0.9707), with no evidence of leakage. Multifocality prediction was more modest (AUROC 0.810), reflecting known limits of two-dimensional mammography. Sensitivity analyses confirmed stable performance across splits, training sizes, and class-weighting schemes. Conclusions: Structured mammographic features combined with gradient-boosting support clinically meaningful, though partly overlapping, risk stratification for LABC; once accounted for, the model still retains independent value. The DCIS model performed very well; multifocality prediction remains more limited, and external validation is needed before clinical use. Full article

Objectives: Women with a history of breast cancer are at increased risk of developing subsequent breast cancer, including ipsilateral recurrence and contralateral new primary breast cancer. This study evaluated the discriminatory performance of a mammogram-based artificial intelligence (AI) risk model for predicting subsequent breast cancer within one year after a negative screening mammogram. Methods: This enriched retrospective case–control study included women with a prior history of breast cancer who underwent screening digital breast tomosynthesis between January 2018 and December 2023 at three affiliated academic breast imaging centers. Digital breast tomosynthesis examinations classified as BI-RADS 1 or 2 were retrospectively analyzed using the ProFound AI^® Risk model version 1.0 to estimate 1-year breast cancer risk. Patients were classified according to whether they developed subsequent breast cancer within one year of the index screening examination. Model discrimination was evaluated using receiver operating characteristic analysis. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated at an exploratory cutoff selected by maximizing the Youden index. Results: The study included 96 women (mean age, 65.3 ± 8.7 years), of whom 32 developed subsequent breast cancer within one year, and 64 did not. The mean AI risk score was significantly higher in the subsequent breast cancer group than in the control group (1.18 ± 0.59 vs. 0.49 ± 0.41; p < 0.001). The AI model demonstrated an AUC of 0.824 (95% CI: 0.728–0.921). At an exploratory cutoff of 0.39, sensitivity was 81.3%, specificity was 76.6%, PPV was 63.4%, and NPV was 89.1%. In separate exploratory analyses, the AUC was 0.790 (95% CI: 0.641–0.939) for ipsilateral recurrence and 0.860 (95% CI: 0.752–0.974) for contralateral new primary breast cancer. AI risk scores were not significantly correlated with tumor size or age at subsequent breast cancer diagnosis. Conclusions: In this enriched retrospective case–control study, higher mammogram-based AI risk scores were associated with subsequent breast cancer within one year after a negative screening examination. The model demonstrated discriminatory performance for both ipsilateral recurrence and contralateral new primary breast cancer; however, these analyses were exploratory. Because the cohort was enriched for subsequent breast cancer events, the reported predictive values are specific to the study sample and should not be extrapolated to routine surveillance populations. Larger prospective cohorts are needed to validate discrimination, calibration, and clinical utility. Full article

Background/Objectives: Contralateral prophylactic mastectomy (CPM) is increasingly performed despite negative preoperative imaging. We evaluated the prevalence and MRI detectability of occult pathology in the contralateral breast. Methods: In this single-center retrospective cohort, 82 patients with unilateral invasive breast cancer underwent simultaneous CPM after preoperative contralateral MRI. Occult findings were classified as occult malignancy, atypical/high-risk lesions, or other lesions of uncertain malignant potential (B3 lesions); the primary outcome was clinically significant occult pathology (malignancy or an atypical/high-risk lesion). Proportions are reported with exact 95% confidence intervals and associations with exact odds ratios and Benjamini–Hochberg correction. Results: Occult malignancy occurred in 1/82 (1.2%; a single DCIS), clinically significant occult pathology in 14/82 (17.1%) and any occult pathology in 21/82 (25.6%). Among 59 patients with a negative MRI (BI-RADS 1–2), clinically significant occult pathology occurred in 18.6% and atypical/high-risk lesions in 16.9% (whole cohort, 15.9%). The single occult malignancy arose in an MRI-negative breast. No factor remained significant after correction for multiple comparisons. Conclusions: After preoperative MRI, occult malignancy is rare, whereas atypical and high-risk lesions frequently remain occult; a negative contralateral MRI excluded neither. These findings support individualized, shared decision-making rather than the yield of occult pathology as the basis for CPM. Full article

Background: Breast cancer continues to be a major contributor to illness among women in Jordan, particularly in underserved regions. Despite the establishment of mammography services in southern Jordan, no formal quality assurance audit has evaluated diagnostic performance or geographic equity of access. This study aimed to evaluate the diagnostic performance of mammography services using established quality assurance indicators and to investigate geographic variation in mammographic findings and diagnostic pathways among women attending a regional referral center in southern Jordan. Methods: This study employed a retrospective hospital-based clinical audit that was conducted using mammography records from Ma’an Hospital between 2016 and 2024. A total of 592 women aged 20 years and older who underwent mammography were included. Data extracted from electronic and paper-based medical records included demographic characteristics, mammography indication, BI-RADS^® classifications, follow-up procedures, reporting timelines, and histopathological outcomes. Histopathological confirmation served as the reference standard for diagnostic accuracy analyses. Diagnostic performance was evaluated using Cancer Detection Rate (CDR), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Geographic variation was evaluated according to place of residence, while multivariable logistic regression was used to determine whether associations remained independent of age and mammography indication. Results: Of the 592 mammography examinations, 354 (59.8%) were performed for screening purposes and 238 (40.2%) for diagnostic evaluation. BI-RADS^® 1 and BI-RADS^® 2 were the most frequently assigned categories, accounting for 38.3% and 28.7% of examinations, respectively, whereas BI-RADS^® 4 and 5 findings accounted for 6.3% and 1.0%. The overall CDR was 52.4 per 1000 examinations with sensitivity (93.9% (95% CI 80.4–98.3%)) and specificity (97.4% (95% CI 95.3–98.5%)), positive predictive value (PPV) (73.8% (95% CI 58.0–86.1%)), and negative predictive value (NPV) (99.5% (95% CI 98.2–99.9%)). Suspicious findings (BI-RADS^® 4–5) were significantly more frequent among urban than rural women (9.4% vs. 3.7%; adjusted OR 3.05, 95% CI 1.37–6.78), whereas reporting delay, ultrasound use, biopsy rate, and further follow-up did not differ significantly by residence. Conclusions: Mammography services at Ma’an Hospital exhibit high diagnostic accuracy and strong clinical performance in breast cancer detection over the nine-year study period. Women in rural areas were less likely to have suspicious mammographic findings detected than those in urban areas, regardless of age and mammography type. No significant differences were observed in reporting timelines or follow-up procedures by place of residence. These findings underscore the value of regional quality assurance audits in identifying service disparities and guiding improvements in breast cancer screening and diagnostic services, especially in underserved communities. Full article

Background/Objectives: Erdheim–Chester disease (ECD) is a rare non-Langerhans cell histiocytosis characterized by multisystem infiltration of foamy histiocytes, leading to chronic inflammation, fibrosis, and organ dysfunction. Breast involvement in ECD is extremely uncommon, and the sonographic features of ECD involving the breast remain poorly described. Case Presentation: We report the case of a 59-year-old woman with chronic bone pain and multisystem disease who experienced an extended diagnostic course despite undergoing renal biopsy, biopsy of a right elbow lesion, bone marrow examination, and multidisciplinary evaluation. Breast ultrasound revealed bilateral infiltrative hypoechoic lesions involving the breasts and axillae. These were classified as BI-RADS 4C and were highly suspicious for breast malignancy. Subsequently, an ultrasound-guided core needle biopsy was performed on the breast and axillary lesions. Results: Histopathology showed fibroadipose tissue infiltrated by numerous foamy histiocytes, scattered epithelioid cells, and occasional Touton giant cells. Immunohistochemistry showed positivity for CD68, CD163, CD4, and Cyclin D1, partial positivity for OCT2 and CD30, and negativity for S100, CD1a, Langerin, ALK, CK (Pan), and GATA3. The Ki-67 index was approximately 3%. Molecular testing detected the BRAF V600E mutation, supporting the diagnosis of ECD. A review of reported cases showed that breast involvement in ECD lacks specific ultrasound findings and may closely mimic primary breast malignancy. Conclusions: Breast involvement in ECD is rare and may present as bilateral infiltrative hypoechoic lesions with axillary involvement on ultrasound. In patients with chronic bone pain, symmetric osteosclerosis, or multisystem disease, ECD should be considered in the differential diagnosis. Ultrasound-detected superficial lesions may provide accessible biopsy targets, helping to establish a timely diagnosis and reduce diagnostic delay. Full article

Background: Sclerosing adenosis (SA) is a benign, proliferative breast lesion that frequently mimics malignancy on multimodality imaging. The appropriate clinical management of SA diagnosed via core needle biopsy (CNB) remains a highly debated topic in breast oncology. This study aimed to evaluate the clinical, imaging, and histopathological characteristics of CNB-diagnosed SA-spectrum lesions and to determine the rate of, and factors associated with, pathological upgrade at the time of surgical excision in a symptomatic cohort. Methods: This retrospective, single-center study evaluated 34 symptomatic female patients who received a CNB diagnosis of SA. Patients were assessed using targeted ultrasound (US, n = 34), digital mammography (n = 19), and/or dynamic contrast-enhanced breast MRI (n = 17). Based on CNB findings, lesions were classified as isolated SA, complex/accompanied SA, or atypical SA. Patients subsequently underwent either definitive surgical excision or long-term imaging surveillance. Upgrades were defined as the presence of a high-risk B3 lesion not identified on CNB (Level 1) or overt malignancy, such as ductal carcinoma in situ or invasive carcinoma (Level 2), at final surgical pathology. Results: Twenty-one patients (61.8%) underwent surgical excision, while thirteen (38.2%) were managed with radiological follow-up (median surveillance 16 months, range 7–84). Within the surgical cohort, 9 of 21 patients (42.9%; 95% CI: 24.5–63.5%) demonstrated an upgrade: 6 (28.6%; 95% CI: 13.8–50.0%) to a B3-level lesion and 3 (14.3%; 95% CI: 5.0–34.6%) to malignancy. Notably, two of the three malignant upgrades originated from lesions initially classified as isolated SA without atypia on CNB. Due to the limited sample size, no single clinical or imaging variable (BI-RADS category, lesion size, or age) reached statistical significance as an independent predictor of upgrade (all p > 0.10). All patients managed with imaging surveillance remained radiologically stable. Conclusions: In stark contrast to the 1–2% upgrade rates traditionally reported in asymptomatic screening populations, symptomatic SA-spectrum lesions selected for surgical excision following CNB exhibited a substantially higher overall upgrade rate (42.9%) and malignant upgrade rate (14.3%) in our cohort, albeit with wide confidence intervals reflecting the modest surgical subgroup size. The occurrence of malignant upgrades from presumed isolated SA underscores the limitations of CNB sampling and highlights the necessity of multimodality imaging–pathology concordance. Because this estimate derives exclusively from patients already selected for surgery on the basis of clinical and imaging suspicion, it reflects the upgrade risk of this pre-selected, imaging-discordant subgroup and should not be extrapolated to the baseline risk of all CNB-diagnosed SA. Accordingly, these findings caution against extending non-operative management without further scrutiny to symptomatic SA cases showing a similar degree of imaging–pathology discordance: in such cohorts, surgical excision or large-volume vacuum-assisted excision may still merit consideration despite the absence of atypia on CNB, although this observation is drawn from a small, non-randomly selected surgical subgroup and should be interpreted with corresponding caution. Full article

Objectives: We evaluated the performance of mammography-based radiomics in prediction of clinical nodal status, clinical tumor stage, clinical disease stage, status of the PIK3CA mutation and concordance with the radiologist-assessed BI-RADS category. Mammography is often the first imaging modality performed in the screening or diagnostic workup of breast cancer. Materials and Methods: In this single-center retrospective study, we included 102 histopathologically confirmed cases of breast cancer from 100 patients. The tumor region and whole-breast parenchyma were contoured on 368 craniocaudal and mediolateral-oblique mammograms. Cases were temporally split into training and test sets by histopathological diagnosis date (training: 70%, held-out test: 30%). Six linear models were tuned by 5-fold x 3-repeat stratified cross-validation. The winning model per endpoint was applied once to the test set. We report AUCs with 95% confidence intervals, permutation p-values and Benjamini–Hochberg false discovery rate (BH-FDR) correction across five endpoints. Results: Three of the studied endpoints reached significance after BH-FDR correction: clinical nodal status (cN0 vs. cN-positive; AUC: 0.726 (95% CI: 0.501–0.886)), clinical tumor stage (cT1-2 vs. cT3-4; AUC: 0.792 (95% CI: 0.575–0.929)) and overall disease stage (I–II vs. III–IV; AUC: 0.778 (95% CI: 0.572–0.917)). Mammography-based radiomics failed to predict the presence of PIK3CA mutation and concordance with radiologist-assessed BI-RADS category. Conclusions: Mammography-based radiomics has shown a hypothesis-generating discriminative value for differentiation between cN-negative and cN-positive disease, early from advanced clinical tumor stage, and early from advanced overall disease stage in breast cancer. Mammography-based radiomics did not predict PIK3CA status and did not discriminate between radiologist-assessed BI-RADS 4 and 5 groups. Full article

Background/Objectives: Breast imaging reports contain Breast Imaging Reporting and Data System (BI-RADS) assessments and management recommendations that may be difficult for patients to understand across languages. Large language models (LLMs) may support patient-facing communication, but clinically important details must be preserved. This study compared radiologists’ opinions regarding the quality, clinical fidelity, safety of wording, and communication usefulness of patient-friendly Arabic translations of BI-RADS breast imaging reports generated by three LLMs. Methods: Five de-identified reports representing BI-RADS categories 0, 2, 3, 4, and 6 were translated from English into Arabic by DeepSeek, ChatGPT, and Gemini using an identical structured prompt. Fifty radiologists rated the blinded outputs across eight 5-point domains. Model ratings were compared using Friedman tests, Kendall’s W, and multiplicity-adjusted Wilcoxon signed-rank tests. Laterality was also verified against the source reports. Results: Gemini achieved the highest overall mean score (3.73 ± 0.78), followed by DeepSeek (3.54 ± 0.73) and ChatGPT (3.03 ± 0.70). The overall model effect was significant (χ² = 34.11, df = 2, p < 0.001; Kendall’s W = 0.341). Gemini and DeepSeek each outperformed ChatGPT across all eight domains (adjusted p < 0.001), and Gemini outperformed DeepSeek overall (adjusted p = 0.009). No laterality errors were identified among the 15 translations. Conclusions: Performance remained model-dependent despite the shared prompt. Among the participating radiologists, Gemini received the highest expert ratings, while DeepSeek remained competitive. Because errors involving BI-RADS categories, laterality, measurements, lesion location, or recommendations could change diagnostic understanding, LLM-generated Arabic translations should serve as radiologist-reviewed communication aids rather than autonomous substitutes for clinical explanation. Full article

Breast cancer is the most commonly diagnosed cancer among women worldwide and remains a leading cause of cancer-related mortality. The most frequent histological subtypes are invasive ductal carcinoma (IDC) and invasive lobular carcinoma (ILC), which demonstrate different biological behaviours and heterogeneous imaging features. ILC is more likely to produce subtle radiological findings such as architectural distortion or asymmetry, whereas IDC commonly presents as a well-defined mass with spiculated margins and associated calcifications. This retrospective cohort study was conducted at Sur Hospital, Oman, and included Omani female patients diagnosed with histologically confirmed IDC or ILC between 2017 and 2025. Mammographic and ultrasound features were reviewed in relation to age, breast density, tumour size, and BI-RADS classification. A total of 46 cases were included, of which 91.3% were IDC and 8.7% were ILC. The median age at diagnosis was 50 years, and the median tumour diameter was 3.0 cm. On mammography, masses with calcifications and architectural distortion were the most common findings. Ultrasound demonstrated predominantly irregular lesions with hypoechoic or heterogeneous echotexture. Most lesions were classified as BI-RADS IV or V. This study documents the mammographic and ultrasound patterns encountered in routine clinical practice. Because only four ILC cases were included, the ILC observations should be interpreted descriptively and should not be regarded as evidence of definitive subtype-specific differences. Full article

Background/Objectives: Deciding between active surveillance and treatment for prostate cancer patients often requires accurate risk assessment of prostate tumors detected with multi-parametric MRI. Conventionally, radiologists visually inspect MRI and use scoring procedures such as PI-RADS to help assess the scans. More recently, artificial intelligence (AI) applied to MRI has allowed for supplementation and is complementary to clinical assessment. However, AI is computationally expensive and severely saps scarce energy and water resources and requires special processing components, requiring alternate approaches that require less computation and fewer resources. The novel, simpler spectral/statistics approach that mimics color vision was previously successfully applied in a number of retrospective pilot studies of bi-parametric MRI of prostate cancer. The novel approach needs far fewer resources, is less computationally intensive, and is simpler than artificial intelligence to evaluate prostate tumors. However, these earlier spectral/statistics pilot studies required intervention by an analyst and too much time for implementation in future large patient studies that are needed to validate the novel approach. This retrospective pilot study further developed, applied, and tested new automation tools to expedite simpler spectral statistical techniques that need fewer resources to evaluate prostate tumors on multi-parametric MRI. Methods: Automated spatial registration, automated prostate organ segmentation, automated blob generation and selection for spectral signatures derived from the apparent diffusion coefficient, high-B-value DWI, and T2 MRI were performed on 76 consecutive patients in the PI-CAI cohort in this retrospective pilot study. The signal-to-clutter ratio (SCR) was computed using target signatures and the processed statistical metrics of the registered prostate bi-parametric MRI. The processed SCR, spectral/spatial features of blobs and clinical metrics predict clinically significant prostate cancer using multivariate logistic regression. The proposed method was assessed using the area under the curve (AUC) from the receiver operating characteristic curve. Results: AUC values of >0.90 were achieved by combining the SCR with blob and clinical metrics. Increasing the number of non-congruent, independent variables resulted in higher AUC scores. Restricting analysis to blob volumes > 0.1 cm³ achieved higher AUC values. The additional total savings in time by applying the new automation tools reduced the processing time by 80 to 170 min for 10 patients. Implementing the new automation tools resulted in an overall processing time of 40 to 80 min per 10 patients. Conclusions: Automating the spectral/statistics approach resulted in AUCs not inferior to those obtained from AI. The automation achieved sufficiently high AUCs and also reduced processing times, warranting future assessments in large patient cohorts. Full article

Background/Objectives: Mammography remains central to breast cancer diagnosis, yet clinically meaningful uncertainty persists in women with dense breasts and in patients with very small lesions or indeterminate imaging findings. We evaluated whether circulating thioredoxin 1 (Trx1) could provide biological information that complements imaging-based assessment. Methods: This multicenter clinical validation study evaluated circulating Trx1 in 1901 serum samples across four predefined cohorts. Diagnostic performance was assessed using receiver operating characteristic (ROC) and precision–recall analyses, together with evaluation of integration with mammographic assessment and decision curve analysis (DCA). A predefined Trx1 cutoff established in prior clinical investigations was applied. Results: Circulating Trx1 concentrations were significantly elevated in breast cancer compared with controls (p < 0.001). Trx1 showed excellent diagnostic discrimination (AUC 0.985; 95% CI, 0.974–0.996), with sensitivity and specificity of 96.4% and 97.3%, respectively. Diagnostic performance was consistent across disease stages, tumor-size categories, molecular subtypes, mammographic categories, and breast-density groups. Trx1 sensitivity remained high in dense breasts (98.9% in BI-RADS density grades C/D), whereas mammographic sensitivity was substantially lower (67.0%). Integration of Trx1 with mammographic assessment improved diagnostic discrimination (AUC 0.980) and provided greater net benefit in decision curve analysis, particularly among women with low-suspicion or indeterminate imaging findings. Conclusions: Circulating Trx1 demonstrated robust diagnostic performance across disease stages, tumor-size categories, and clinically relevant patient subgroups while providing biologically independent information that complements mammographic assessment. Although this retrospective multicenter study requires prospective validation in independent diagnostic populations, Trx1 may serve as a clinically useful adjunct to imaging-based breast cancer evaluation, particularly in diagnostically uncertain settings. Full article