Background:Breast cancer is a heterogeneous disease, and accurate subtype characterization is essential for guiding personalized treatment. In particular, HER2-low tumors have recently emerged as a distinct clinical entity with potential responsiveness to novel HER2-targeted therapies. However, reliable noninvasive imaging methods to identify these subgroups remain lacking. Purpose:To evaluate the potential of time-dependent diffusion MRI (Td-dMRI) in differentiating breast cancer molecular subtypes and to investigate its correlation with immunohistochemical biomarkers, particularly the newly established three-tier HER2 classification. Materials and methods:In this retrospective study, female patients with untreated invasive ductal carcinoma underwent 3T breast MRI including Td-dMRI between June 2023 and October 2024. A custom protocol combining oscillating gradient spin-echo (OGSE) and pulsed gradient spin-echo (PGSE) sequences enabled diffusion sampling at multiple diffusion times and frequencies. Microstructural parameters-cellularity, extracellular and intracellular diffusivity (Dex, Din), cell diameter, intracellular volume fraction (fin), and intracellular water residence time (τin)-were estimated using a Bayesian model based on a joint multicompartmental framework. Molecular subtypes (Luminal A/B, HER2-enriched, triple-negative [TN]) and HER2 expression levels (HER2-zero, HER2-low, HER2-positive) were determined via IHC and fluorescence in situ hybridization (FISH). Quantitative Td-dMRI metrics were compared across subtypes and correlated with ER, PR, HER2, and Ki-67 status using ANOVA, Kruskal-Wallis, and ROC curve analysis. Results:This study included 71 female participants (mean age, 51.3 ± 10.2 years). Multiple Td-dMRI parameters varied significantly across molecular and HER2 subtypes. ADC50Hz was significantly higher in Luminal A compared to Luminal B (P = 0.003). HER2-enriched tumors showed higher ADC values and cell diameters but lower cellularity compared to Luminal B (P< 0.05). ER- and PR- tumors had higher ADCs, cell diameters, and Din, with lower cellularity than positive counterparts. Din effectively distinguished TN from non-TN cancers (AUC = 0.710). For HER2 stratification, ADC30ms distinguished HER2-zero from HER2-low tumors with high accuracy (AUC = 0.898), and cell diameter and cellularity were most effective for differentiating HER2-low from HER2-positive tumors (AUC = 0.770). No significant Td-dMRI differences were observed for Ki-67. Conclusion:ADC30ms most effectively distinguished HER2-zero from HER2-low tumors, while microstructural parameters such as cellularity and cell diameter moderately differentiated HER2-low from HER2-positive cancers. These results support the potential of Td-dMRI as a complementary imaging biomarker for subtype characterization, although findings were limited by small subgroup sizes and the single-center design.

Background: Accurate noninvasive prediction of pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) in invasive breast cancer (BC) remains challenging. This study aimed to develop and validate a multivariable prediction model integrating clinicopathological variables, immunoinflammatory markers, and multiparametric magnetic resonance imaging (MRI) features for predicting pCR after NAC. Methods: In this retrospective multicenter study, 345 women with invasive BC who underwent pretreatment breast MRI and NAC were included. pCR was defined as the absence of residual invasive cancer in the breast and axillary lymph nodes at surgery. Patients were divided into training and internal validation cohorts, with an independent external cohort used for validation. Clinicopathological variables, immunoinflammatory markers, and MRI features, including mean apparent diffusion coefficient (ADCmean), were collected. Predictor selection was performed using the least absolute shrinkage and selection operator and multivariable logistic regression. Model performance was assessed using receiver operating characteristic analysis. Results: Among the 345 patients, 116 (33.62%) achieved pCR. Clinical T stage, lymphocyte-to-monocyte ratio (LMR), systemic immune-inflammation index (SII), enhancement pattern, and ADCmean were independent predictors. The combined model showed the best performance, with area under the curves of 0.820, 0.810, and 0.799 in the training, internal validation, and external validation cohorts, outperforming the clinical and MRI models. Conclusions: The combined model integrating clinicopathological variables, immunoinflammatory markers, and multiparametric MRI features may help predict pCR after NAC and support individualized treatment planning and potential surgical de-escalation.

[This corrects the article DOI: 10.3389/fonc.2025.1739008.].

Accurately predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) early during treatment could enable therapy adaptation. Total choline (tCho) measured by Proton MR spectroscopy (1H-MRS) reflects tumor metabolism and may serve as an early biomarker, but its predictive performance requires further validation. To investigate the performance of tCho in singlevoxel 1H-MRS to early predict pCR to NAC in breast cancer patients. Patients with primary invasive breast cancer scheduled for NAC were prospectively enrolled from August 2021 to October 2023. The concentration of tCho was measured with 1H-MRS at four time points: T0 (pretreatment), T1, T2, and T3 (after 2, 4, and 6 NAC cycles respectively). The tCho were compared among the four time points and between pCR and non-pCR groups. The diagnostic performance was evaluated using the area under the receiver operating characteristic curves (AUC). 191 patients were enrolled, including 136 patients with non-pCR and 55 patients with pCR. The dynamic changes of tCho showed a downward trend during NAC in the pCR group, non-pCR group, and all molecular subtypes. Among the total patients, tCho at four time points were higher in the non-pCR group than those in the pCR group (all P < 0.05), and with an AUC of 0.72 at T0. In the Luminal B, HER2-enriched and triple-negative subgroups, tCho at T0 were higher in the non-pCR group than that in the pCR group (all P < 0.05). In all patients, tCho combined with the PR and HER2 at T0 showed good predicting performance, with an AUC of 0.85. tCho could be used as an early predictor of pCR during NAC in breast cancer patients. This may assist in guiding the clinical selection of individualized and effective treatment programs.

Early prediction of pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer remains challenging. Traditional imaging lacks molecular sensitivity, while single-modality radiomics may miss tumor microenvironment dynamics. Integrating amide proton transfer-weighted imaging (APTWI)—quantifying protein levels linked to chemo-response—into multimodal radiomics may enable precise early pCR prediction, guiding personalized therapy. This study aims to develop and validate a multimodal radiomics model, integrating amide proton transfer-weighted imaging (APTWI), diffusion-weighted imaging (DWI), and early-phase contrast-enhanced T1WI, for preoperative prediction of pathological complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). This retrospective study included 109 women (mean age 50 ± 10 years) with untreated breast cancer between May 2023 and August 2024, underwent NAC and pretreatment MRI scanning, including APTWI, DWI, and dynamic contrast-enhanced T1WI. Three-dimensional tumor segmentation was performed using ITK-SNAP. Radiomics features were extracted from APT, ADC maps, and enhanced subtraction images (30s/90s) using PyRadiomics, adhering to IBSI guidelines. LASSO regression selected predictive features, followed by Support Vector Machine and Logistic Regression classifiers with five-fold cross-validation. Performance was evaluated via ROC analysis, calibration curves, decision curve analysis (DCA), and SHAP interpretability. Patients were randomly divided into training (n = 77) and testing (n = 32) cohorts. The integrated model combining clinical (e.g. HER2, Ki-67) and radiomics features achieved superior predictive performance (AUC = 0.888, 95

BACKGROUND:Preoperative immuno-chemotherapy improves outcomes in triple-negative breast cancer, but associated imaging response patterns remain poorly characterized. This study aimed to describe a novel MRI phenomenon, tumor flare-like response (TFLR), and evaluate its association with pathological complete response (pCR). METHODS:Ad hoc imaging analysis of a prospective phase II trial (NCT04213898; n = 39). Breast MRI was performed at baseline and after every two cycles. TFLR was defined a priori as new enhancing nodules (≥5 mm) separate from the index tumor on DCE-MRI, appearing during neoadjuvant therapy with subsequent regression. Inter-reader agreement was assessed with Cohen's kappa and intraclass correlation coefficient. Univariate logistic regression and ROC analysis (Youden index) with 1000-bootstrap resampling identified the optimal largest-nodule size cut-off for pCR prediction. Two multivariable logistic regression models (continuous-size and binary-size) evaluated independence after adjustment for PD-L1 status, FGT category, baseline tumor size, and clinical stage; multicollinearity was assessed by variance inflation factor. RESULTS:TFLR occurred in 74.4% (29/39) of patients and was significantly associated with higher FGT density (P = .03). Among the 29 patients with TFLR, nodules were predominantly oval (93.1%) with circumscribed margins, homogeneous enhancement. Distribution was bilateral (72.5%), ipsilateral (17.2%), or contralateral (10.3%) relative to the primary tumor, with consistently asymmetric counts between breasts. Kinetic curves were persistent (31.0%), plateau (27.6%), or washout (41.4%). TFLR first appeared after cycle 2 in all cases and completely resolved in 75.9% (22/29) by treatment completion; median persistence was 152 days (95% CI 145-159). Presence of TFLR alone did not predict pCR (P = .72). Patients with largest nodule ≥9 mm had significantly higher pCR rate (77.8% vs. 36.4%, P = .048). ROC analysis identified 9 mm as the optimal cut-off. In multivariable analysis, largest nodule diameter remained independently predictive whether analyzed continuously (OR = 2.965, 95% CI 1.298-6.772, P = .01) or dichotomized at ≥9 mm (OR = 7.833, 95% CI 1.260-48.701, P = .027). Model AUCs were 0.904 (95% CI 0.797-1.00) and 0.727 (95% CI 0.519-0.936), respectively. CONCLUSIONS:TFLR is a frequent, reversible MRI finding in TNBC treated with camrelizumab-based neoadjuvant immuno-chemotherapy. Largest nodule diameter ≥9 mm is a strong, independent predictor of pathological complete response and represents a promising early, non-invasive imaging biomarker of immunotherapeutic efficacy.

Background:The hepatobiliary phase (HBP) of gadoxetic acid-enhanced liver magnetic resonance imaging (MRI) is important for detecting colorectal liver metastasis (CRLM), but image quality may be limited. This study evaluated whether deep learning-based reconstruction united compressed sensing (DR-uCS) and deep learning-based reconstruction high-resolution united compressed sensing (DR-HR-uCS) improve image quality and lesion detection in CRLM. Methods:This retrospective study included 86 patients with 116 CRLM lesions (71 lesions ≥1 cm and 45 lesions <1 cm) who underwent 3.0-T gadoxetic acid-enhanced liver MRI. A standard-resolution HBP acquisition was reconstructed into conventional united compressed sensing (uCS) and DR-uCS from the same raw k-space data, while a separate high-resolution acquisition generated DR-HR-uCS images. Two radiologists independently assessed subjective image quality, artifact severity, liver edge/vessel clarity, and lesion conspicuity. Quantitative metrics [liver signal-to-noise ratio (SNR), lesion SNR, and contrast-to-noise ratio (CNR)] were measured by standardized region-of-interest analysis. Diagnostic performance for lesions ≥1 and <1 cm was evaluated using pathology or multidisciplinary consensus. Diagnostic time was recorded across three reader experience levels. Results:Both DR-uCS and DR-HR-uCS significantly improved overall image quality compared with uCS (median score: 5 vs. 4, both P<0.001) and significantly reduced image artifacts (both P<0.001). DR-uCS achieved the highest liver SNR and CNR, while the lesion SNR was comparable across methods (P=0.03 and P=0.001, respectively). For lesions ≥1 cm, conspicuity and diagnostic performance were similar (all P>0.05). For lesions <1 cm, DR-HR-uCS demonstrated higher conspicuity and sensitivity (87.1%) than uCS (72.4%) and DR-uCS (78.6%) (adjusted P<0.05), with comparable specificity. Diagnostic time for sub-centimeter lesions was significantly shorter with DR-HR-uCS (P<0.001), and differences among readers were reduced. Conclusions:DR-uCS improves HBP image quality, while DR-HR-uCS further enhances the detection efficiency and conspicuity of sub-centimeter CRLMs. Its advantage likely reflects the combined effects of high-resolution acquisition and deep learning-based reconstruction.

A novel risk stratification model based on Lung-RADS® v2022 and CT features was constructed and validated for predicting invasive pure ground-glass nodules (pGGNs) in China. Five hundred and twenty-six patients with 572 pulmonary GGNs were prospectively enrolled and divided into training (n = 169) and validation (n = 403) sets. Utilising the Lung-RADS® v2022 framework and the types of GGN-vessel relationships (GVR), a complementary Lung-RADS® v2022 was established, and the pGGNs were reclassified from categories 2, 3 and 4x of Lung-RADS® v2022 into 2, 3, 4a, 4b, and 4x of cLung-RADS® v2022. The cutoff value of invasive pGGNs was defined as the cLung-RADS® v2022 4a-4x. Evaluation metrics like recall rate, precision, F1 score, accuracy, Matthews correlation coefficient (MCC), and the area under the receiver operating characteristic curve (AUC) were employed to assess the utility of the cLung-RADS® v2022. In the training set, compared with the Lung-RADS 1.0, the AUC of Lung-RADS® v2022 were decreased from 0.543 to 0.511 (p-value = 0.002), and compared to Lung-RADS 1.0 and Lung-RADS® v2022, the cLung-RADS® v2022 model exhibited the highest recall rate (94.9 https://www.medicalresearch.org.cn/search/research/researchView?id=a97e67d8-1ee6-40fb-aab1-e6238dbd8f29 .

Background:Accurate identification of brain metastases is critical for radiotherapy planning. The aim of this study was to evaluate the effectiveness of contrast-enhanced T1-weighted fluid-attenuated inversion recovery (CE-T1FLAIR) sequences combined with the three-dimensional modulated flip-angle technique to enhance the visualization of metastatic tumors. Methods:A retrospective study of 326 patients who were pathologically diagnosed with malignant tumors and clinically suspected of brain metastases from October 2023 to February 2024 was conducted. Magnetic resonance images from the modulated flip-angle technique in refocused imaging with extended echo trains (MATRIX) CE-T1FLAIR, three-dimensional magnetization-prepared rapid gradient echo (3D GRE) fast-spin echo (FSE) with modulated flip-angle flow-sensitive preparation (fsp) CE-T1FLAIR, and 2D FSE CE-T1FLAIR sequences were analyzed by three independent radiologists in a double-blind manner. Detection rates were compared with the χ2 test or Fisher exact test, with multiple comparisons conducted via the Bonferroni method. Interrater reliability was assessed with the Kappa consistency test. Results:A total of 176 patients with 887 brain metastases were included based on the linked intelligence brain metastasis artificial intelligence-assisted detection system and clinical follow-up. The MATRIX CE-T1FLAIR sequence had an overall lesion detection rate of 98.9%, significantly higher than the 93.5% for 3D GRE fsp CE-T1FLAIR and 80.6% for 2D FSE CE-T1FLAIR. For lesions <5 mm, the detection rate was 98.8%, with significant differences between the sequences. Lesion distribution analysis indicated that MATRIX CE-T1FLAIR had a higher detection rate in the superficial area of the brain's convexity, gray-white matter junction, and basal ganglia. Conclusions:The MATRIX CE-T1FLAIR sequence demonstrates superior overall and subgroup detection rates, particularly for small brain metastases (<5 mm) in the superficial areas of the brain's convexity as compared to 3D GRE fsp CE-T1FLAIR and 2D FSE CE-T1FLAIR.

To investigate the diagnostic value of CE-MATRIX-T1FLAIR and 3D CE-T2FLAIR sequences based on Contrast Enhancement Modulated flip Angle Technique in Refocused Imaging with eXtended echo train (CE-MATRIX) technology for detecting Leptomeningeal Metastasis (LM) using Fluid Attenuated Inversion Recovery (FLAIR) imaging. This prospective study included 563 hospitalized patients with clinically suspected LM, diagnosed with malignant tumors between January 2022 and October 2023 at Henan Cancer Hospital. Both CE-MATRIX-T1FLAIR and 3D CE-T2FLAIR sequences were used for imaging. Two radiologists independently evaluated image quality, diagnostic confidence, and objective measurements, diagnosing LM as positive or negative, with disagreements resolved by consultation. Subjective and objective scores were compared using the Wilcoxon signed-rank test. The diagnostic performance of the sequences was compared using ROC curve analysis, with cerebrospinal fluid (CSF) cytology as the gold standard. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and area under the curve (AUC) values were calculated and compared using Z-tests. LM was confirmed in 321 patients. CE-MATRIX-T1FLAIR showed superior subjective scores in image quality and diagnostic confidence (p < 0.001). Though CE-MATRIX-T1FLAIR had a lower SNR (p = 0.013), it demonstrated higher sensitivity, specificity, PPV, NPV, accuracy, and AUC than 3D CE-T2FLAIR (p < 0.001). Both sequences provided effective diagnosis and differentiation of LM. CE-MATRIX-T1FLAIR offers superior diagnostic performance compared to 3D CE-T2FLAIR for LM, with slightly better subjective ratings despite a lower SNR. Both sequences are effective for diagnosing LM.

To determine the threshold size for predicting metastasis of supraclavicular lymph nodes (SCLNs) < 10 mm on axial and multiplanar reconstruction CT in esophageal squamous cell carcinoma (ESCC). This retrospective, multicenter study received approval from three institutional review boards, which waived informed consent. Patients with ESCC had ultrasound-guided fine-needle aspiration biopsy (US-FNAB) for SCLNs, with contrast-enhanced CT performed within 2 weeks prior to US-FNAB. A CT and ultrasound radiologist jointly analyzed images to identify and mark biopsied SCLNs < 10 mm on CT, followed by two blinded radiologists who independently measured short-axis diameter (SAD), long-axis diameter (LAD), short diameter of multiplanar reconstruction (SD-MPR), long diameter of multiplanar reconstruction (LD-MPR) and the intra-class correlation coefficient (ICC) was analyzed. Center 1 included 220 SCLNs as the training set, and Centers 2 + 3 included 75 SCLNs as the validation set. The optimal cutoff value was determined using receiver operating characteristic (ROC) curves. In the training and validation sets, 31.8% (70/220) and 32.0% (24/75) of SCLNs were positive. ICC for SAD was excellent (ICC = 0.847). The area under the receiver operating characteristic curve of SAD was 0.832 in the training set, higher than others, with a cutoff value of > 6 mm, resulting in sensitivity, specificity, positive predictive value, negative predictive value, accuracy of 77.1%, 80.7%, 65.0%, 88.3%, 79.1%, respectively. In the validation set, these metrics were 87.5%, 74.5%, 61.8%, 92.7%, 81.0%, respectively. SAD on CT can suspect metastasis of SCLN < 10 mm in ESCC patients, with a threshold size of > 6 mm. Determining the threshold size criterion on CT images may enhance the prediction of supraclavicular lymph node metastasis in esophageal squamous cell carcinoma patients, thereby benefiting diagnostic and therapeutic strategies. Supraclavicular lymph nodes < 10 mm in esophageal carcinoma are indeterminate for malignancy. Supraclavicular lymph nodes > 6 mm are highly suspicious for malignancy. The metastasis status of supraclavicular lymph nodes is critical for staging esophageal carcinoma.

OBJECTIVES:Prostate cancer significantly impacts men's health, highlighting the necessity for precise diagnosis. This study evaluates combining Magnetic Resonance Image Compilation (MAGiC) parameters with Prostate Imaging Reporting and Data System (PI-RADS) scores to enhance diagnostic accuracy among radiologists with varied experience. METHODS:In this retrospective study, 174 patients with suspected prostate cancer were recruited from February 2023 to May 2024. Synthetic MRI-derived T1, T2, and proton density (PD) maps were generated, and synthetic T2-weighted imaging (T2WI) was reconstructed. Two radiologists of varying experience independently assessed lesions using PI-RADS based on both synthetic and conventional T2WI. Image quality was evaluated using the prostate imaging quality (PI-QUAL) scoring v2 system, and diagnostic performance was analyzed using receiver operating characteristic (ROC) curve analysis. RESULTS:Synthetic T2WI exhibited comparable image quality to conventional T2WI (P = 0.065). After excluding low-quality images, 99 lesions were analyzed. In the peripheral zone, higher T1 values were significantly linked to non-cancerous lesions (R1: OR = 0.989, P = 0.009; R2: OR = 0.990, P = 0.004). The integration of T1 values with PI-RADS scores improved diagnostic performance, achieving area under the curve (AUC) values of 0.960 for R1 and 0.944 for R2. CONCLUSION:The integration of MAGiC parameters, particularly T1 values, with PI-RADS scores significantly enhances diagnostic accuracy for clinically significant prostate cancer, especially benefitting less experienced radiologists. Additionally, synthetic T2WI demonstrates comparable image quality to conventional T2WI, supporting the clinical implementation of MAGiC parameters in prostate MRI assessments.

ABSTRACT Purpose To evaluate the predictive value of pre‐treatment histogram analysis using APTWI, diffusion‐weighted imaging (DWI), and early contrast‐enhanced silhouette imaging in determining pathological complete response (pCR) post‐NAC in breast cancer, and to investigate whether combining immunohistochemical indicators enhances predictive accuracy. Materials and Methods A retrospective continuous collection of 108 females with breast cancer who underwent NAC and pre‐treatment APTWI, DWI, and dynamic contrast‐enhanced imaging at our hospital. Clinical, MRI imaging, and pathological characteristics were analyzed for patients. NAC response was divided into pCR and non‐pCR. Tumor segmentation and histogram feature extraction were performed on APT, ADC, and early contrast‐enhanced silhouette images, and combined them with clinical features to construct an NAC efficacy prediction model. Diagnostic performance was assessed using receiver operating characteristic curves, with DeLong's test employed to compare areas under the curve (AUC). Results In pCR group, mean, root‐mean‐square deviation, and 5th, 10th, 15th, 25th, 50th, 75th, 85th percentile of MTRasym, along with 1st percentiles of ADC were significantly higher in the pCR group than in the non‐pCR group (p < 0.05). Conversely, the interquartile range of MTRasym and 10th percentiles of ADC were significantly lower in the pCR group (p < 0.05). ER‐negative, HER2‐positive expression, and 5th percentile MTRasym value were identified as independent predictors of pCR post‐NAC (odds ratios, 0.16, 7.25, and 1.35, respectively). The combined diagnostic model demonstrated an AUC of 0.844, significantly outperforming individual parameters (p < 0.05). Conclusion Pre‐treatment histogram analysis of MTRasym values derived from APTWI provides significant predictive value for pCR post‐NAC in breast cancer. The combined diagnostic model incorporating APTWI with ER and HER2 expression status further enhances diagnostic performance.

Background:Differentiating molecular subtypes and identifying biological markers in breast cancer (BC) are essential for prognostic stratification and treatment selection. This study aimed to compare the effectiveness of amide proton transfer-weighted imaging (APTWI) and diffusion-weighted imaging (DWI) in differentiating molecular subtypes and predicting the biological status of BC. Methods:This retrospective study included 109 women (aged 50.8±10.8 years) with BC who underwent 3T APTWI and DWI between May 2023 and January 2024. Patients were categorized by molecular subtypes and expression levels of estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and Ki-67. Magnetization transfer ratio asymmetry (MTRasym) and apparent diffusion coefficient (ADC) values were measured. The area under the receiver operating characteristic (ROC) curve (AUC) was used to assess the performance of MTRasym and ADC values in distinguishing subtypes. Pearson's correlation analysis was used to examine the relationship between MTRasym, ADC values, and the Ki-67 proliferation index. Results:Triple-negative (TN) cancers (3.03%±0.56%) had significantly higher MTRasym values than luminal A (2.25%±1.00%) and luminal B (2.39%±0.81%) cancers (P=0.006, 0.012). HER2-enriched cancers (2.93%±0.71%) also had significantly higher MTRasym than luminal A cancers (P=0.039). MTRasym and ADC values were significantly higher in ER-negative (ER-) than they were in ER-positive (ER+) cancers (P<0.001, P=0.040), and MTRasym values were higher in PR-negative (PR-) and high-Ki-67 cancers (P<0.001, P=0.013). AUC values for MTRasym ranged from 0.699 to 0.799, depending on the subtype and biological marker comparison. MTRasym and ADC values showed a weak positive correlation with the Ki-67 index (r=0.37, P<0.001, and r=0.31, P=0.003). Conclusions:APTWI is more effective than DWI for differentiating BC subtypes and predicting biological markers, providing valuable insights for clinical management.

BackgroundAlveolar Soft Part Sarcoma (ASPS) is a rare, aggressive cancer whose diagnosis and treatment depend on histological grading. However, tumor variability can lead to underestimation, affecting treatment, and patient survival.ObjectiveTo evaluate MRI features associated with Grade III ASPS and to determine the relationship between MRI features and patient prognosis.Study TypeRetrospective analysis.SubjectsSixty‐seven patients with ASPS were included with 37 males and 30 females (M/F = 1.23) follow‐up and survival analysis on 50 patients.Field Strength/SequenceA 3.0 T, T1WI‐FSE, T2WI‐FSE, DWI‐EPI, DCE‐MRI (gradient echo).AssessmentMRI features (margin, peritumoral oedema, peritumoral enhancement, necrosis, vascular flow void signal, heterogeneous signal intensity [SI] at T1WI and T2WI, ADCmean, time‐intensity curve [TIC] type, distant metastasis, and bone invasion) and histological grading were independently evaluated by three radiologists and two pathologists, with Grade III considered high‐grade.Statistical TestsThe chi‐square or Fisher's exact test was used to assess the correlation between MRI features and histological grading. Multivariable binary logistic regression identified independent factors associated with high‐grade tumors. The Kaplan–Meier method and Cox proportional hazards model were used to calculate hazard ratios for MRI features.ResultsTumor necrosis, heterogeneous SI at T2WI ≥50%, and ADCmean were associated with high‐grade ASPS. Tumor necrosis was an independent factors associated with local relapse‐free survival (odds ratio [OR], 3.88). TIC type was associated with 5‐year survival rate (OR, 2.80) and local relapse‐free survival (OR, 2.69). Heterogeneous SI at T2WI ≥50% was associated with 5‐year survival (OR, 4.00), local relapse‐free survival (OR, 5.58), and local relapse‐free survival (OR, 4.84).Data ConclusionMRI features including tumor necrosis, heterogeneity of SI at T2WI, ADCmean, and TIC type aid in assessing ASPS grading and prognosis.Evidence Level4Technical EfficacyStage 5

Background: Efforts to establish survival prediction model with a single platform have not met precision medicine goals. Here we explored multi-omics fusion integrated models with artificial intelligence for predicting survival in HER2 negative metastatic breast cancer (MBC) patients. Methods: HER2- MBC patients recruited in the multicentre perspective CAMELLIA study ((ClinicalTrials. NCT01917279) were treated with standard docetaxel plus capecitabine regimen. Multi-omics fusion prediction models by machine learning were constructed on the basis of three feature sets associated with survival prognosis： radiomics, clinicopathologic phenotypes and circulating tumour DNA (ctDNA)/circulating tumour cells (CTCs) features prospectively collected. Model performances were evaluated using area under the curve (AUC).The C-index comparison was performed using the time-to-event endpoints and risk scores of the models. Patients were divided into groups with high or low signatures based on Youden index cut-off values. Findings: Seventy patients treated with the first-line TX regimen were enrolled in this study. The median PFS in the cohort was 8.8 months (range 1.3‒72.8 months) and the median OS was 36.15 months (range 9.2‒83.8 months). For predicting PFS, the C-index of the multi-omics fusion model was 0.725 (HR 3.812, 95% CI 2.245-6.472, P<0.0001), superior to the clinical and clinical+ctDNA/CTC models, achieving areas under the curve (AUCs) of 0.866-0.918. For predicting OS, the multi-omics fusion model also performed significantly better than the other two models, with a C-index of 0.811 (HR 5.992, 95% CI 3.145-11.419, P<0.0001) and AUCs of 0.815-0.989. Interpretation: Our pretreatment multi-omics fusion models with machine learning could effectively predict survival of HER2- MBC patients with good discrimination power and outperformed conventional singlescale models. This framework highlights the multi-omics data integration in machine learning models and will be used to generate predictors for other cancers. Trial Registration Details: The study was registered with ClinicalTrials.gov (NCT01917279). Funding Information: Chinese Academy of Medical Sciences (CAMS) Initiative for Innovative Medicine, National Natural Science Foundation of China, Natural Science Foundation of Beijing City, Youth Innovation Promotion Association CAS and Key Project of Beijing Hope Marathon Special Fund from China Cancer Foundation. Declaration of Interests: No potential conflicts of interest were disclosed. Ethics Approval Statement: The study was approved by the Independent Ethics Committee of the National Cancer Centre/Cancer Hospital (CH-BC-023), and written informed consent to participate in the biomarker analysis study was obtained from all patients before their enrolment in this study. All interventions were performed in accordance with the Declaration of Helsinki guidelines of the International Conference for Harmonization/Good Clinical Practice.

Objectives The probability of Breast Imaging Reporting and Data Systems (BI-RADS) 4 lesions being malignant is 2%–95%, which shows the difficulty to make a diagnosis. Radiomics models based on magnetic resonance imaging (MRI) can replace clinicopathological diagnosis with high performance. In the present study, we developed and tested a radiomics model based on MRI images that can predict the malignancy of BI-RADS 4 breast lesions. Methods We retrospective enrolled a total of 216 BI-RADS 4 patients MRI and clinical information. We extracted 3,474 radiomics features from dynamic contrast-enhanced (DCE), T2-weighted images (T2WI), and diffusion-weighted imaging (DWI) MRI images. Least absolute shrinkage and selection operator (LASSO) and logistic regression were used to select features and build radiomics models based on different sequence combinations. We built eight radiomics models which were based on DCE, DWI, T2WI, DCE+DWI, DCE+T2WI, DWI+T2WI, and DCE+DWI+T2WI and a clinical predictive model built based on the visual assessment of radiologists. A nomogram was constructed with the best radiomics signature combined with patient characteristics. The calibration curves for the radiomics signature and nomogram were conducted, combined with the Hosmer-Lemeshow test. Results Pearson’s correlation was used to eliminate 3,329 irrelevant features, and then LASSO and logistic regression were used to screen the remaining feature coefficients for each model we built. Finally, 12 related features were obtained in the model which had the best performance. These 12 features were used to build a radiomics model in combination with the actual clinical diagnosis of benign or malignant lesion labels we have obtained. The best model built by 12 features from the 3 sequences has an AUC value of 0.939 (95% CI, 0.884-0.994) and an accuracy of 0.931 in the testing cohort. The sensitivity, specificity, precision and Matthews correlation coefficient (MCC) of testing cohort are 0.932, 0.923, 0.982, and 0.791, respectively. The nomogram has also been verified to have calibration curves with good overlap. Conclusions Radiomics is beneficial in the malignancy prediction of BI-RADS 4 breast lesions. The radiomics predictive model built by the combination of DCE, DWI, and T2WI sequences has great application potential.

规范的影像学评估贯穿乳腺癌新辅助治疗实施的全过程，包括治疗前基线影像明确病变范围、治疗中疗效评估及治疗后残存病灶评估等。目前新辅助治疗最常用的影像评估方法包括超声、乳腺X线摄影及乳腺MRI。本文主要对乳腺X线摄影及其延伸技术在乳腺癌新辅助治疗疗效评估中的应用进行介绍。

目的:探索新辅助化疗(neoadjuvant chemotherapy,NAC)1个周期后动态增强磁共振成像(dynamic contrast-enhanced magnetic resonance imaging,DCE-MRI)定量分析在预测局部进展期乳腺癌(locally advanced breast cancer,LABC)化疗效果中的价值.方法:收集NAC的LABC患者28例,NAC前及化疗1个周期后均进行多期DCE-MRI扫描,采用38期,每期10 s.测量DCE-MRI的定量参数:容量转移常数(Ktrans)、速率常数(Kep)和血管外细胞外间隙容积比(Ve).患者根据治疗后手术病理学检查结果分为组织学显著反应组和组织学非显著反应组两组,利用t检验或非参数检验的方法,比较NAC前和化疗1个周期后两组间DCE-MRI定量参数的差异.通过绘制受试者工作特征(receiver operating characteristic curve,ROC)曲线分析NAC前及化疗1个周期后DCE-MRI定量参数预测NAC疗效的诊断效能.结果:28例患者中,9例(32.1％)为组织学显著反应,19例(67.9％)为组织学非显著反应.化疗前定量DCE-MRI的Ktrans、Kep、Ve值在两组间差异并无统计学意义(P＞0.05);NAC 1个周期后Ktrans、Kep值较化疗前明显减低,化疗前后差异有统计学意义(P＜0.05);Ve值化疗前后变化不显著(P＞0.05).化疗1个周期后的Ktrans值能够区分组织学显著反应组和组织学非显著反应组,ROC曲线分析显示Ktrans值的曲线下面积(area under curve,AUC)为0.749,阈值为0.202/min,灵敏度为100.00％,特异度为63.16％.而Kep及Ve值的预测效能降低,AUC分别为0.667、0.632.结论:NAC前所有DCE-MRI的Ktrans、Kep、Ve值均不能够预测疗效;化疗1个周期后Ktrans是预测组织学显著反应的最佳指标,Kep、Ve值可作为辅助预测指标.

目的:探讨乳腺X线摄影检出的恶性微钙化病变在MR上的影像表现.方法:回顾性分析乳腺X线摄影上表现为微钙化且手术病理证实为乳腺癌的80例患者资料,均行乳腺MR检查及X线引导下金属丝定位.分析其X线、MR表现及两者的关系.统计学采用卡方检验或Fisher's精确检验.结果:共83个病灶,导管内癌45个,浸润性癌38个.X线表现:67个为单纯钙化,16个钙化伴局部密度增高;细小多形性(49个)及簇状分布(35个)是最常见的钙化形态及分布方式.MR表现:非肿块样强化57个,肿块样强化16个,未见异常强化10个.92.9％ (26/28)的段样分布钙化MR上表现为段样分布强化.段样分布钙化灶在MR上以段样分布强化更常见(P=0.000).81.3％(13/16)的肿块样强化见于簇状分布钙化.肿块样强化更多见于簇状分布的钙化灶(P=0.000).MR上假阴性钙化灶多见于簇状分布钙化灶,但没有显著差异(P=0.061).结论:恶性微钙化在MR上的强化类型以非肿块样强化常见,少部分表现为肿块样强化.其强化表现与钙化在X线上的分布方式有关.