Exploration of anatomical distribution of brain metastasis from breast cancer at first diagnosis assisted by artificial intelligence.

Objectives: This study aimed to explore the spatial distribution of brain metastases (BMs) from breast cancer (BC) and to identify the high-risk sub-structures in BMs that are involved at first diagnosis. Methods: Magnetic resonance imaging (MRI) scans were retrospectively reviewed at our centre. The brain was divided into eight regions according to its anatomy and function, and the volume of each region was calculated. The identification and volume calculation of metastatic brain lesions were accomplished using an automatically segmented 3D BUC-Net model. The observed and expected rates of BMs were compared using 2-tailed proportional hypothesis testing. Results: A total of 250 patients with BC who presented with 1694 BMs were retrospectively identified. The overall observed incidences of the substructures were as follows: cerebellum, 42.1 %; frontal lobe, 20.1 %; occipital lobe, 9.7 %; temporal lobe, 8.0 %; parietal lobe, 13.1 %; thalamus, 4.7 %; brainstem, 0.9 %; and hippocampus, 1.3 %. Compared with the expected rate based on the volume of different brain regions, the cerebellum, occipital lobe, and thalamus were identified as higher risk regions for BMs (P value ≤ 5.6*10-3). Sub-group analysis according to the type of BC indicated that patients with triple-negative BC had a high risk of involvement of the hippocampus and brainstem. Conclusions: Among patients with BC, the cerebellum, occipital lobe and thalamus were identified as higher-risk regions than expected for BMs. The brainstem and hippocampus were high-risk areas of the BMs in triple negative breast cancer. However, further validation of this conclusion requires a larger sample size.

Diffusion-Weighted MRI-Based Virtual Elastography and Shear-Wave Elastography for the Assessment of Breast Lesions.

BACKGROUND: Diffusion-weighted imaging (DWI)-based virtual MR elastography (DWI-vMRE) in the assessment of breast lesions is still in the research stage. PURPOSE: To investigate the usefulness of elasticity values on DWI-vMRE in the evaluation of breast lesions, and the correlation with the values calculated from shear-wave elastography (SWE). STUDY TYPE: Prospective. POPULATION/SUBJECTS: 153 patients (mean age ± standard deviation: 55 ± 12 years) with 153 pathological confirmed breast lesions (24 benign and 129 malignant lesions). FIELD STRENGTH/SEQUENCE: 1.5-T MRI, multi-b readout segmented echo planar imaging (b-values of 0, 200, 800, and 1000 sec/mm2 ). ASSESSMENT: For DWI-vMRE assessment, lesions were manually segmented using apparent diffusion coefficient (ADC0-1000 ) map, then the region of interests were copied to the map of shifted-ADC (sADC200-800 , sADC 200-1500 ). For SWE assessment, the shear modulus of the lesions was measured by US elastic modulus (µUSE ). Intraclass/interclass kappa coefficients were calculated to measure the consistency. STATISTICAL TESTS: Pearson's correlation was used to assess the relationship between sADC and µUSE . A receiver operating characteristic analysis with the area under the curve (AUC) was performed to compare the diagnostic accuracy between benign and malignant breast lesions of sADC and µUSE . A P value <0.05 was considered statistically significant. RESULTS: There were significant differences between benign and malignant breast lesions of µUSE (24.17 ± 10.64 vs. 37.20 ± 12.61), sADC200-800 (1.38 ± 0.31 vs. 0.97 ± 0.18 × 10-3 mm2 /sec), and sADC200-1500 (1.14 ± 0.30 vs. 0.78 ± 0.13 × 10-3 mm2 /sec). In all breast lesions, a moderate but significant correlation was observed between µUSE and sADC200-800 /sADC200-1500 (r = -0.49/-0.44). AUC values to differentiate benign from malignant lesions were as follows: µUSE , 0.78; sADC200-800 , 0.89; sADC200-1500 , 0.89. DATA CONCLUSIONS: Both SWE and DWI-vMRE could be used for the differentiation of benign versus malignant breast lesions. Furthermore, DWI-vMRE with the use of sADC show relatively higher AUC values than SWE. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 2.

Anti-HER2 therapy response assessment for guiding treatment (de-)escalation in early HER2-positive breast cancer using a novel deep learning radiomics model.

OBJECTIVES: Anti-HER2 targeted therapy significantly reduces risk of relapse in HER2 + breast cancer. New measures are needed for a precise risk stratification to guide (de-)escalation of anti-HER2 strategy. METHODS: A total of 726 HER2 + cases who received no/single/dual anti-HER2 targeted therapies were split into three respective cohorts. A deep learning model (DeepTEPP) based on preoperative breast magnetic resonance (MR) was developed. Patients were scored and categorized into low-, moderate-, and high-risk groups. Recurrence-free survival (RFS) was compared in patients with different risk groups according to the anti-HER2 treatment they received, to validate the value of DeepTEPP in predicting treatment efficacy and guiding anti-HER2 strategy. RESULTS: DeepTEPP was capable of risk stratification and guiding anti-HER2 treatment strategy: DeepTEPP-Low patients (60.5%) did not derive significant RFS benefit from trastuzumab (p = 0.144), proposing an anti-HER2 de-escalation. DeepTEPP-Moderate patients (19.8%) significantly benefited from trastuzumab (p = 0.048), but did not obtain additional improvements from pertuzumab (p = 0.125). DeepTEPP-High patients (19.7%) significantly benefited from dual HER2 blockade (p = 0.045), suggesting an anti-HER2 escalation. CONCLUSIONS: DeepTEPP represents a pioneering MR-based deep learning model that enables the non-invasive prediction of adjuvant anti-HER2 effectiveness, thereby providing valuable guidance for anti-HER2 (de-)escalation strategies. DeepTEPP provides an important reference for choosing the appropriate individualized treatment in HER2 + breast cancer patients, warranting prospective validation. CLINICAL RELEVANCE STATEMENT: We built an MR-based deep learning model DeepTEPP, which enables the non-invasive prediction of adjuvant anti-HER2 effectiveness, thus guiding anti-HER2 (de-)escalation strategies in early HER2-positive breast cancer patients. KEY POINTS: • DeepTEPP is able to predict anti-HER2 effectiveness and to guide treatment (de-)escalation. • DeepTEPP demonstrated an impressive prognostic efficacy for recurrence-free survival and overall survival. • To our knowledge, this is one of the very few, also the largest study to test the efficacy of a deep learning model extracted from breast MR images on HER2-positive breast cancer survival and anti-HER2 therapy effectiveness prediction.

Whole-tumor histogram analysis of multiparametric breast magnetic resonance imaging to differentiate pure mucinous breast carcinomas from fibroadenomas with high-signal intensity on T2WI.

PURPOSE: To investigate the utility of whole-tumor histogram analysis based on multiparametric MRI in distinguishing pure mucinous breast carcinomas (PMBCs) from fibroadenomas (FAs) with strong high-signal intensity on T2-weighted imaging (T2-SHi). MATERIAL AND METHODS: The study included 20 patients (mean age, 55.80 ± 15.54 years) with single PBMCs and 29 patients (mean age, 42.31 ± 13.91 years) with single FAs exhibiting T2-SHi. A radiologist performed whole-tumor histogram analysis between PBMC and FA groups with T2-SHi using multiparametric MRI, including T2-weighted imaging (T2WI), diffusion weighted imaging (DWI) with apparent diffusion coefficient (ADC) maps, and the first (DCE_T1) and last (DCE_T4) phases of T1-weighted dynamic contrast-enhanced imaging (DCE) images, to extract 11 whole-tumor histogram parameters. Histogram parameters were compared between the two groups to identify significant variables using univariate analyses, and their diagnostic performance was assessed by receiver operating characteristic (ROC) curve analysis and logistic regression analyses. In addition, 15 breast lesions were randomly selected and histogram analysis was repeated by another radiologist to assess the intraclass correlation coefficient for each histogram feature. Pearson's correlation coefficients were used to analyze the correlations between histogram parameters and Ki-67 expression of PMBCs. RESULTS: For T2WI images, mean, median, maximum, 90th percentile, variance, uniformity, and entropy significantly differed in PBMCs and FAs with T2-SHi (all P < 0.05), yielding a combined area under the curve (AUC) of 0.927. For ADC maps, entropy was significantly lower in FAs with T2-SHi than in PMBCs (P = 0.03). In both DCE_T1 and DCE_T4 sequences, FAs with T2-SHi showed significantly higher minimum values than PBMCs (P = 0.007 and 0.02, respectively). The highest AUC value of 0.956 (sensitivity, 0.862; specificity, 0.944; positive predictive value, 0.962; negative predictive value, 0.810) was obtained when all significant histogram parameters were combined. CONCLUSIONS: Whole-tumor histogram analysis using multiparametric MRI is valuable for differentiating PBMCs from FAs with T2-SHi.

Pancreatic index: A prognostic factor of upfront surgery for body or tail pancreatic ductal adenocarcinoma with vascular involvement-A retrospective study.

BACKGROUND: The pancreatic index (PI) is a useful preoperative imaging predictor for pancreatic ductal adenocarcinoma (PDAC). In this retrospective study, we determined the predictive effect of PI to distinguish patients of pancreatic body/tail cancer (PBTC) with vascular involvement who can benefit from upfront surgery. METHOD: All patients who received distal pancreatectomy for PDAC from 2016 to 2020 at the Pancreatic Disease Center, Ruijin Hospital, Shanghai Jiaotong University School of Medicine were considered for the study. A total of 429 patients with PBTC were assessed in relation to the value of PI. Fifty-five patients were eventually included and divided into low PI group and 29 patients in the normal PI group. RESULTS: The median overall survival (mOS) was significantly shorter in the low PI group (13.1 vs. 30.0 months, p = 0.002) in this study, and PI ≥ 0.78 (OR = 0.552, 95% CI: 0.301-0.904, p = 0.020) was an independent influencing factor confirmed by multivariate analysis. Subgroup analysis showed that PI was an independent prognostic factor for LA-PBTC (OR = 0.272, 95% CI: 0.077-0.969, p = 0.045). As for BR PBTC, PI (OR = 0.519, 95% CI: 0.285-0.947, p = 0.033) combined with carbohydrate antigen 125 (CA125) (OR = 2.806, 95% CI: 1.206-6.526, p = 0.017) and chemotherapy (OR = 0.327, 95% CI: 0.140-0.763, p = 0.010) were independent factors. CONCLUSION: This study suggests that the PI can be used as a predictive factor to optimize the surgical indication for PBTC with vascular involvement. Preoperative patients with normal PI and CA125 can achieve a long-term prognosis comparable to that of resectable PBTC patients.

A deep-learning radiomics-based lymph node metastasis predictive model for pancreatic cancer: a diagnostic study.

OBJECTIVES: Preoperative lymph node (LN) status is essential in formulating the treatment strategy among pancreatic cancer patients. However, it is still challenging to evaluate the preoperative LN status precisely now. METHODS: A multivariate model was established based on the multiview-guided two-stream convolution network (MTCN) radiomics algorithms, which focused on primary tumor and peri-tumor features. Regarding discriminative ability, survival fitting, and model accuracy, different models were compared. RESULTS: Three hundred and sixty-three pancreatic cancer patients were divided in to train and test cohorts by 7:3. The modified MTCN (MTCN+) model was established based on age, CA125, MTCN scores, and radiologist judgement. The MTCN+ model outperformed the MTCN model and the artificial model in discriminative ability and model accuracy. [Train cohort area under curve (AUC): 0.823 vs. 0.793 vs. 0.592; train cohort accuracy (ACC): 76.1 vs. 74.4 vs. 56.7%; test cohort AUC: 0.815 vs. 0.749 vs. 0.640; test cohort ACC: 76.1 vs. 70.6 vs. 63.3%; external validation AUC: 0.854 vs. 0.792 vs. 0.542; external validation ACC: 71.4 vs. 67.9 vs. 53.5%]. The survivorship curves fitted well between actual LN status and predicted LN status regarding disease free survival and overall survival. Nevertheless, the MTCN+ model performed poorly in assessing the LN metastatic burden among the LN positive population. Notably, among the patients with small primary tumors, the MTCN+ model performed steadily as well (AUC: 0.823, ACC: 79.5%). CONCLUSIONS: A novel MTCN+ preoperative LN status predictive model was established and outperformed the artificial judgement and deep-learning radiomics judgement. Around 40% misdiagnosed patients judged by radiologists could be corrected. And the model could help precisely predict the survival prognosis.

Multimodality MRI radiomics analysis of TP53 mutations in triple negative breast cancer.

Objectives: To explore the value of T1-weighted imaging (T1WI), T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) radiomics features reflecting TP53 mutations in patients with triple negative breast cancer (TNBC). Study design: This retrospective study enrolled 91 patients with TNBC with TP53 testing (64 patients in the training cohort and 27 patients in the validation cohort). A total of 2832 radiomics features were extracted from the first phase of dynamic contrast-enhanced T1WI, T2WI and ADC maps. Analysis of variance (ANOVA) and the Kruskal-Wallis-test were used for feature selection. Then, linear discriminant analysis (LDA), multilayer perceptron (MLP), logistic regression (LR), LR with LASSO, decision tree (DT), naïve Bayes (NB), random forest (RF), and support vector machine (SVM) models were used for classification. Results: The validation AUCs of the eight classifiers ranged from 0.74 (NB) to 0.85 (SVM). SVM attained the highest AUC (0.85) and diagnostic accuracy (0.82) of all tested models. The top 3 ranking features in the SVM model were T1-square-first order-skewness (coefficient: 1.735), T2-wavelet-LHH-GLCM-joint energy, and T2-wavelet-LHH-GLCM-inverse difference moment (coefficient: -0.654, -0.634). Conclusions: Radiomics-based analysis with the SVM model is recommended for the detection of TP53 mutations in TNBC. Furthermore, T1WI- and T2WI-related features could be used as noninvasive biomarkers for predicting TP53 mutations.

TP53 Mutation Estimation Based on MRI Radiomics Analysis for Breast Cancer.

BACKGROUND: Noninvasive detection of TP53 mutations is useful for the molecular stratification of breast cancer. PURPOSE: To explore MRI radiomics features reflecting TP53 mutations in breast cancer and propose a classifier for detecting such mutations. STUDY TYPE: Retrospective. POPULATION/SUBJECTS: A total of 139 breast cancer patients with TP53 expression profiling (98 with TP53 mutations and 41 without TP53 mutations). FIELD STRENGTH/SEQUENCE: 1.5 T, T1-weighted (T1W) DCE-MRI. ASSESSMENT: Lesions were manually segmented using subtracted T1WI. A total of 944 radiomics features (including 744 wavelet-related features) and 7 clinicopathological features were extracted from each lesion. Principal component analysis and Pearson's correlation analysis were used to preprocess the features. Linear discriminant analysis, logistic regression (LR), support vector machine (SVM), and random forest (RF) were used as the classifiers. STATISTICAL TESTS: Analysis of variance, Kruskal-Wallis and recursive features elimination were used to select features. Receiver operating characteristic (ROC) analysis was performed to compare the diagnostic accuracy. RESULTS: For the radiomics model, the validation cohorts AUCs of the four classifiers ranged from 0.69 (RF) to 0.74 (LR), and LR (0.74) attained the highest AUCs. For the clinicopathological-radiomics combined model, the validation AUCs of the four classifiers ranged from 0.68 (RF) to 0.86 (SVM), and SVM (0.86) attained highest AUCs. In the subgroup analysis of triple-negative (TN) and luminal type breast cancer, RF achieved the highest AUCs (0.83 and 0.94). DATA CONCLUSION: Clinicopathological-radiomics combined model with SVM could be used as noninvasive biomarkers for predicting TP53 mutations. RF was recommended for the detection of TP53 mutations in TN and luminal type breast cancer. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Impact of the transection plan on postoperative pancreatic fistulas occurring after robot-assisted distal pancreatectomy for nonmalignant pancreatic neoplasms.

OBJECTIVES: Postoperative pancreatic fistula (POPF) is the main complication of distal pancreatectomy (DP) and affects the prognosis of patients. The impact of several clinical factors mentioned in recent studies on POPF remains controversial. This study aimed to investigate the impact of a remnant pancreas and other perioperative factors on POPFs occurring after robot-assisted distal pancreatectomy (RDP) for nonmalignant pancreatic neoplasms. METHODS: A total of 197 patients who received robot-assisted distal pancreatectomy (RDP) for nonmalignant pancreatic neoplasms at the Pancreatic Disease Center, Ruijin Hospital Shanghai Jiaotong University School of Medicine from January 2018 to December 2020 were included in this retrospective study. According to the intraoperative transection plan, patients were divided into an RDP body group and an RDP tail group. Clinical and pathological features and perioperative factors affecting POPF were analyzed and compared between the two groups. RESULTS: The results showed that a transection plan involving the tail of the pancreas (OR = 2.133, 95% CI 1.109-4.103, p = 0.023) and spleen preservation (OR = 2.588, 95% CI 1.435-4.665, p = 0.001) independently increased the incidence of POPF in patients with nonmalignant pancreatic neoplasms treated by RDP. A transection plan involving the tail of the pancreas was also an independent risk factor (OR = 3.464, 95% CI 1.270-9.450, p = 0.015) for grade B/C POPF. Length of remnant pancreas > 6.23 cm was an independent risk factor for POPF (OR = 3.116, 95% CI 1.364-7.121, p = 0.007). Length of remnant pancreas > 9.82 cm was an independent risk factor for grade B/C POPF (OR = 3.340, 95% CI 1.386-8.051, p = 0.007). CONCLUSION: This retrospective study suggests that a transection plan involving the tail of the pancreas is an independent risk factor for POPF in patients with nonmalignant neoplasms treated by RDP. We also propose that the postoperative length of the remnant pancreas evaluated by computed tomography scans can be used to identify patients with a high risk of POPF in order to optimize the individualized strategy.

Whole-tumor apparent diffusion coefficient (ADC) analyses of breast lesions based on simultaneous multi-slice readout-segmented echo-planar diffusion-weighted imaging.

OBJECTIVE: We aimed to evaluate the effectiveness of simultaneous multi-slice readout-segmented echo-planar diffusion-weighted imaging (SMS rs-EPI DWI), compared with readout-segmented echo-planar diffusion-weighted imaging (NOSMS rs-EPI DWI), in discriminating between benign and malignant breast lesions. MATERIALS AND METHODS: This retrospective study evaluated breast lesions from 185 consecutive patients who had undergone preoperative breast MRI. The NOSMS rs-EPI DWI and the prototype SMS rs-EPI DWI sequences were performed on a 1.5-T MR scanner. Two independent radiologists evaluated the image quality of the two sequences using a 5-point scale (1 = poor, 5 = excellent) and then assessed the scores through visual grading characteristics analysis (VGC). The values of signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and whole-tumor-based histogram parameter (ADCmedian) were compared between the two sequences using the Wilcoxon test. Then ROC curves were used for statistical analysis. RESULTS: The visual assessment showed that the SMS rs-EPI yielded superior overall image quality and lesion delineation than the NOSMS rs-EPI (AUCVGC = 0.980 and 0.984, respectively; all P < 0.001). There were no significant differences in relevant artifacts between the two sequences (AUCVGC = 0.531, P = 0.462). The SNR values for SMS rs-EPI DWI were significantly lower than for NOSMS rs-EPI DWI (P = 0.019) while there was no significant difference in CNR values between the two sequences (P = 0.955). In addition, evaluation of the diagnostic performance demonstrated that the difference in ADCmedian values for both DWI sequences between the malignant and benign lesions was statistically significant (P < 0.001). In contrast, the AUC for ADCmedian was higher with SMS rs-EPI than NOSMS rs-EPI (0.879 for SMS vs. 0.839 for NOSMS, P = 0.025). CONCLUSION: The SMS technique could further improve the image quality and the diagnostic performance of rs-EPI DWI in a comparable time.

A Novel Nomogram for Predicting Prognosis and Tailoring Local Therapy Decision for Ductal Carcinoma In Situ after Breast Conserving Surgery.

Purpose: We sought to explore the role of nomogram-combined biomarkers, mammographic microcalcification and inflammatory hematologic markers in guiding local therapy decisions in ductal carcinoma in situ (DCIS) subgroups with different ipsilateral breast tumour recurrence (IBTR) risk. Methods: Between January 2009 and December 2018, consecutive patients with DCIS and breast conserving surgery (BCS) were enrolled and randomly assigned to a training cohort (n = 181) and internally validation cohort (n = 78). Multivariate analyses were performed to identify predictors of IBTR. Model performance was evaluated by the concordance index (C-index) and calibration plot. The time-to-event curves were calculated by the Kaplan−Meier methods and compared by the log-rank test. Results: In total, 259 patients were enrolled and 182 of them received whole breast irradiation (WBI). After a median follow-up of 51.02 months, 23 IBTR events occurred in the whole cohort. By multivariate analyses of training cohort, presence of microinvasion, Ki67 index >14%, mammographic-clustered fine linear microcalcifications and neutrophil/lymphocyte ratio before BCS (preop-NLR), >1.1 remained independent risk factors of IBTR to develop a nomogram. The C-indexes of the nomogram were 0.87 and 0.86 in the training and internal validation set, respectively. Calibration plots illustrated good agreement between the predictions and actual observations for 5-year IBTR. Cut-off values of nomogram point were identified as 53 and 115 points, which divided all patients into low-, intermediate- and high-risk groups. Significant differences in IBTR existed between low-, intermediate- and high-risk subgroups (p < 0.01). For the whole cohort and ER-positive tumours, the benefit of WBI was found only in the intermediate-risk subgroup, but not in those with low or high risk. Fourteen out of 23 IBTRs occurred outside the original quadrant and all occurred in the high-risk group. Conclusions: The novel nomogram demonstrated potential to separate the risk of IBTR and locations of IBTR. For the whole cohort and ER-positive tumours, the benefit of WBI was restricted to an intermediate-risk subgroup.

Image quality and whole-lesion histogram and texture analysis of diffusion-weighted imaging of breast MRI based on advanced ZOOMit and simultaneous multislice readout-segmented echo-planar imaging.

Objectives: To investigate the image quality and diagnostic capability a of whole-lesion histogram and texture analysis of advanced ZOOMit (A-ZOOMit) and simultaneous multislice readout-segmented echo-planar imaging (SMS-RS-EPI) to differentiate benign from malignant breast lesions. Study design: From February 2020 to October 2020, diffusion-weighted imaging (DWI) using SMS-RS-EPI and A-ZOOMit were performed on 167 patients. Three breast radiologists independently ranked the image datasets. The inter-/intracorrelation coefficients (ICCs) of mean image quality scores and lesion conspicuity scores were calculated between these three readers. Histogram and texture features were extracted from the apparent diffusion coefficient (ADC) maps, respectively, based on a WL analysis. Student's t-tests, one-way ANOVAs, Mann-Whitney U tests, and receiver operating characteristic curves were used for statistical analysis. Results: The overall image quality scores and lesion conspicuity scores for A-ZOOMit and SMS-RS-EPI showed statistically significant differences (4.92 ± 0.27 vs. 3.92 ± 0.42 and 4.93 ± 0.29 vs. 3.87 ± 0.47, p < 0.0001). The ICCs for the image quality and lesion conspicuity scores had good agreements among the three readers (all ICCs >0.75). To differentiate benign and malignant breast lesions, the entropy of ADCA-Zoomit had the highest area (0.78) under the ROC curve. Conclusions: A-ZOOMit achieved higher image quality and lesion conspicuity than SMS-RS-EPI. Entropy based on A-ZOOMit is recommended for differentiating benign from malignant breast lesions.

The value of whole-tumor histogram and texture analysis based on apparent diffusion coefficient (ADC) maps for the discrimination of breast fibroepithelial lesions: corresponds to clinical management decisions.

PURPOSE: This study aims to comprehensively evaluate the diagnostic value of quantitative parameters extracted from apparent diffusion coefficient (ADC) maps in distinguishing fibroepithelial tumors using whole-tumor histogram and texture analysis. MATERIALS AND METHODS: This retrospective study included 66 female patients with single phyllodes tumor (PT) and 29 female patients with single fibroadenoma (FA) who underwent preoperative magnetic resonance imaging. By independently performing whole-tumor histogram and texture analysis based on ADC maps, two radiologists extracted seven histogram parameters and four texture parameters. The extracted parameters were compared using univariate analysis to determine their ability to distinguish FAs from PTs, benign PTs from FAs, as well as benign PTs from borderline and malignant PTs. RESULTS: When FAs and PTs were compared, ADC_skewness values of PTs were significantly lower than those of FAs (p < 0.05), whereas other significant extracted parameter values of PTs were significantly higher than those of FAs (p ≤ 0.001); the area under the curve of significant parameters combined was 0.936. Regarding the differences between FAs and benign PTs, ADC_SD, ADC_95th percentile and ADC_kurtosis of FAs were significantly lower than those of benign PT group, and ADC_skewness was higher than that of benign PT group (all p < 0.05). Furthermore, ADC_SD, ADC_95th percentile and all texture parameters are significantly higher in the borderline and malignant PT group than in FA and benign PT group (p < 0.05). In addition, ADC_kurtosis of malignant PT group was significantly lower than that of borderline PT group (p = 0.045). CONCLUSION: The extracted whole-tumor histogram and texture features of ADC maps can improve differential diagnosis of breast fibroepithelial tumors and contribute to optimal selection for clinical management of patients with fibroepithelial tumors.

Clinical significance of pancreatic calcifications: a 15-year single-center observational study.

OBJECTIVES: Pancreatic calcifications (PC) are considered specific for chronic pancreatitis (CP), but PC may also be present in non-CP diseases. The aims are to understand the pattern of calcifications in different diseases and to determine they were related to malignant diseases. METHODS: A retrospective study was performed including patients with PC or CP undergoing surgery in the Department of General Surgery of Ruijin Hospital from January 2003 to June 2018. RESULTS: PC were observed in 168 (4.5%) of the 3755 patients with pancreatic lesions treated during the study period. The majority of patients with PC had three kinds of CP (73.2%) while 26.8% had other five kinds of non-CP diseases. In patients with non-CP diseases, the incidence of PC in malignant intraductal papillary mucinous neoplasm (IPMN) was significantly higher than benign IPMN (8.3% vs. 0.7%, p = 0.004). In patients of CP with pancreatic mass (n = 81), PC (Odds ratio = 28.6, p = 0.000), advanced age (> 55 years) and parenchymal atrophy were independent predictors for malignancy. In patients of CP without pancreatic mass (n = 110), there were 82 cases (74.5%) with PC and 5 cases (4.5%) with pancreatic ductal adenocarcinoma. The regression model of risk factors was not successful. CONCLUSIONS: The disease spectrum with PC was very diverse. PC may be related to malignant IPMN in non-CP diseases and is related to malignancy in the patients of CP with pancreatic mass and indications for resection.

Is simultaneous multi-slice readout-segmented echo-planar imaging valuable for predicting molecular subtypes of breast cancer?

PURPOSE: To investigate the feasibility of simultaneous multi-slice readout-segmented diffusion-weighted echo-planar imaging (SMS rs-EPI DWI) in predicting invasive breast cancer molecular subtypes using whole-tumor histogram and texture analyses. METHODS: In our retrospective study, 125 patients (mean age, 52.81 ± 12.01 years; range, 24-84 years) with single invasive breast cancer who underwent preoperative MRI with SMS rs-EPI DWI and surgery at our institution were included. Two radiologists independently performed whole-tumor histogram and texture analyses on the apparentdiffusioncoefficient (ADC) map of SMS rs-EPI DWI (TR, 3800.0 ms; TE 90.0 ms; field of view, 340 mm × 206 mm; in-plane matrix, 244 × 148; section thickness, 5 mm; readout segments, 5, b = 0, 800 s/mm2; scan time, 3 mins; slice acceleration factor, 2). The Mann-Whitney U test or Kruskal-Wallis test were used to compare histogram and texture parameters to assess their potential in differentiating molecular subtypes of breast cancer and predicting axillary lymph node status. Receiver operating characteristic (ROC) curves were generated for parameters with significant differences, and the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. RESULTS: Compared to luminal A breast cancer, the HER2-positive breast cancer subtype showed higher ADC_95th percentile values (p = 0.016). In addition, HER2-positive breast cancer yielded significantly higher ADC_mean (p = 0.025), ADC_median (p = 0.025), and ADC_5th percentile (p = 0.041) values than luminal B breast cancer. The ADC_skewness value was higher for triple-negative breast cancer (TNBC) than Luminal A breast cancer (p = 0.021). The difference in ADC_mean, ADC_median, ADC_5th percentile and ADC_95th percentile values between the HER2-positive breast cancer and luminal types was statistically significant, with a combined AUC for these parameters of 0.762 (sensitivity 72.41%, specificity 75.00%, PPV 27.27 %, and NPV 95.45 %). The ADC_skewness value for TNBC was higher than for luminal types (p = 0.012) and yielded an AUC value of 0.688 (sensitivity 96.15%, specificity 36.78%, PPV 31.25%, and NPV 96.97 %). Additionally, significantly higher ADC_skewness and ADC_95th percentile values (p = 0.003, 0.002, respectively) were reported for non-luminal types than luminal types yielding a combined AUC value of 0.712 (sensitivity 92.11%, and specificity 50.23%, PPV 41.18%, and NPV 92.50%). The AUC value for ADC_5th percentile for axillary lymph node status prediction was 0.659 (sensitivity 65.38%, specificity of 64.86%). CONCLUSIONS: The whole-tumor histogram and texture analyses parameters based on SMS rs-EPI DWI may provide biological information on aggressive molecular subtypes of breast cancer. In addition, ADC_5th percentile values were significantly different between lymph node-positive and lymph node-negative breast cancer.

Downgrade BI-RADS 4A Patients Using Nomogram Based on Breast Magnetic Resonance Imaging, Ultrasound, and Mammography.

OBJECTIVES: To downgrade BI-RADS 4A patients by constructing a nomogram using R software. MATERIALS AND METHODS: A total of 1,717 patients were retrospectively analyzed who underwent preoperative ultrasound, mammography, and magnetic resonance examinations in our hospital from August 2019 to September 2020, and a total of 458 patients of category BI-RADS 4A (mean age, 47 years; range 18-84 years; all women) were included. Multivariable logistic regression was used to screen out the independent influencing parameters that affect the benign and malignant tumors, and the nomogram was constructed by R language to downgrade BI-RADS 4A patients to eligible category. RESULTS: Of 458 BI-RADS 4A patients, 273 (59.6%) were degraded to category 3. The malignancy rate of these 273 lesions is 1.5% (4/273) (<2%), and the sensitivity reduced to 99.6%, the specificity increased from 4.41% to 45.3%, and the accuracy increased from 63.4% to 78.8%. CONCLUSION: By constructing a nomogram, some patients can be downgraded to avoid unnecessary biopsy.

A Combined Nomogram Model to Predict Disease-free Survival in Triple-Negative Breast Cancer Patients With Neoadjuvant Chemotherapy.

Background: To investigate whether the radiomics signature (Rad-score) of DCE-MRI images obtained in triple-negative breast cancer (TNBC) patients before neoadjuvant chemotherapy (NAC) is associated with disease-free survival (DFS). Develop and validate an intuitive nomogram based on radiomics signatures, MRI findings, and clinicopathological variables to predict DFS. Methods: Patients (n = 150) from two hospitals who received NAC from August 2011 to May 2017 were diagnosed with TNBC by pathological biopsy, and follow-up through May 2020 was retrospectively analysed. Patients from one hospital (n = 109) were used as the training group, and patients from the other hospital (n = 41) were used as the validation group. ROIs were drawn on 1.5 T MRI T1W enhancement images of the whole volume of the tumour obtained with a 3D slicer. Radiomics signatures predicting DFS were identified, optimal cut-off value for Rad-score was determined, and the associations between DFS and radiomics signatures, MRI findings, and clinicopathological variables were analysed. A nomogram was developed and validated for individualized DFS estimation. Results: The median follow-up time was 53.5 months, and 45 of 150 (30.0%) patients experienced recurrence and metastasis. The optimum cut-off value of the Rad-score was 0.2528, which stratified patients into high- and low-risk groups for DFS in the training group (p<0.001) and was validated in the external validation group. Multivariate analysis identified three independent indicators: multifocal/centric disease status, pCR status, and Rad-score. A nomogram based on these factors showed discriminatory ability, the C-index of the model was 0.834 (95% CI, 0.761-0.907) and 0.868 (95% CI, 0.787-949) in the training and the validation groups, respectively, which is better than clinicoradiological nomogram(training group: C-index = 0.726, 95% CI = 0.709-0.743; validation group: C-index = 0.774,95% CI = 0.743-0.805). Conclusion: The Rad-score derived from preoperative MRI features is an independent biomarker for DFS prediction in patients with TNBC to NAC, and the combined radiomics nomogram improved individualized DFS estimation.

Radiomics-based machine learning analysis and characterization of breast lesions with multiparametric diffusion-weighted MR.

BACKGROUND: This study aimed to evaluate the utility of radiomics-based machine learning analysis with multiparametric DWI and to compare the diagnostic performance of radiomics features and mean diffusion metrics in the characterization of breast lesions. METHODS: This retrospective study included 542 lesions from February 2018 to November 2018. One hundred radiomics features were computed from mono-exponential (ME), biexponential (BE), stretched exponential (SE), and diffusion-kurtosis imaging (DKI). Radiomics-based analysis was performed by comparing four classifiers, including random forest (RF), principal component analysis (PCA), L1 regularization (L1R), and support vector machine (SVM). These four classifiers were trained on a training set with 271 patients via ten-fold cross-validation and tested on an independent testing set with 271 patients. The diagnostic performance of the mean diffusion metrics of ME (mADCall b, mADC0-1000), BE (mD, mD*, mf), SE (mDDC, mα), and DKI (mK, mD) were also calculated for comparison. The area under the receiver operating characteristic curve (AUC) was used to compare the diagnostic performance. RESULTS: RF attained higher AUCs than L1R, PCA and SVM. The AUCs of radiomics features for the differential diagnosis of breast lesions ranged from 0.80 (BE_D*) to 0.85 (BE_D). The AUCs of the mean diffusion metrics ranged from 0.54 (BE_mf) to 0.79 (ME_mADC0-1000). There were significant differences in the AUCs between the mean values of all diffusion metrics and radiomics features of AUCs (all P < 0.001) for the differentiation of benign and malignant breast lesions. Of the radiomics features computed, the most important sequence was BE_D (AUC: 0.85), and the most important feature was FO-10 percentile (Feature Importance: 0.04). CONCLUSIONS: The radiomics-based analysis of multiparametric DWI by RF enables better differentiation of benign and malignant breast lesions than the mean diffusion metrics.

Role of breast MRI in predicting histologic upgrade risks in high-risk breast lesions: A review.

PURPOSE: This article reviews the frequency, upgrade rate and valuable imaging characteristics for predicting the histologic upgrade risks of high-risk lesions on MRI, so as to provide a reference for the management of the lesions. METHODS: A comprehensive search for relevant publications from January 2011 to January 2021 was conducted in the PubMed database. The frequency, upgrade rate and valuable imaging characteristics for predicting the upgrade risks of high-risk lesions on MRI included in the articles were reviewed, and the management of high-risk lesions was provided with a reference according to the review results. RESULTS AND CONCLUSIONS: In terms of management options, Atypical ductal hyperplasia (ADH) and Lobular neoplasia (LN) (the top two high-risk lesions with the highest upgrade rate and frequency) were treated with surgical resection. However, the final treatment decision for other high-risk lesions should be made by a multidisciplinary committee. In terms of the value of breast MRI in predicting the upgrade risks of high-risk lesions, the lesions that were confirmed to upgrade after surgery showed some enhancement characteristics, especially for ADH and LN. At the same time, Dynamic contrast-enhanced MRI (DCE-MRI) has a high negative predictive value (NPV) in predicting the upgrade risks of the high-risk lesions, hence misdiagnosis and overtreatment can be reduced. Diffusion-weighted imaging (DWI) and relative apparent diffusion coefficient (rADC) can be used to predict the upgrade risks of the lesions, and the ADC of upgraded lesions is lower than that of non-upgraded lesions. However, these conclusions should be confirmed by further studies.

Differentiation of Hepatocellular Carcinoma from Hepatic Hemangioma and Focal Nodular Hyperplasia using Computed Tomographic Spectral Imaging.

BACKGROUND AND AIMS: Hepatocellular carcinoma (HCC) is the most common primary hepatic malignancy. This study was designed to investigate the value of computed tomography (CT) spectral imaging in differentiating HCC from hepatic hemangioma (HH) and focal nodular hyperplasia (FNH). METHODS: This was a retrospective study of 51 patients who underwent spectral multiple-phase CT at 40-140 keV during the arterial phase (AP) and portal venous phase (PP). Slopes of the spectral curves, iodine density, water density derived from iodine- and water-based material decomposition images, iodine uptake ratio (IUR), normalized iodine concentration, and the ratio of iodine concentration in liver lesions between AP and PP were measured or calculated. RESULTS: As energy level decreased, the CT values of HCC (n=31), HH (n=17), and FNH (n=7) increased in both AP and PP. There were significant differences in IUR in the AP, IUR in the PP, normalized iodine concentration in the AP, slope in the AP, and slope in the PP among HCC, HH, and FNH. The CT values in AP, IUR in the AP and PP, normalized iodine concentration in the AP, slope in the AP and PP had high sensitivity and specificity in differentiating HH and HCC from FNH. Quantitative CT spectral data had higher sensitivity and specificity than conventional qualitative CT image analysis during the combined phases. CONCLUSIONS: Mean CT values at low energy (40-90 keV) and quantitative analysis of CT spectral data (IUR in the AP) could be helpful in the differentiation of HCC, HH, and FNH.