Radiomics in cone-beam breast CT for the prediction of axillary lymph node metastasis in breast cancer: a multi-center multi-device study.

OBJECTIVES: To develop a radiomics model in contrast-enhanced cone-beam breast CT (CE-CBBCT) for preoperative prediction of axillary lymph node (ALN) status and metastatic burden of breast cancer. METHODS: Two hundred and seventy-four patients who underwent CE-CBBCT examination with two scanners between 2012 and 2021 from two institutions were enrolled. The primary tumor was annotated in each patient image, from which 1781 radiomics features were extracted with PyRadiomics. After feature selection, support vector machine models were developed to predict ALN status and metastatic burden. To avoid overfitting on a specific patient subset, 100 randomly stratified splits were made to assign the patients to either training/fine-tuning or test set. Area under the receiver operating characteristic curve (AUC) of these radiomics models was compared to those obtained when training the models only with clinical features and combined clinical-radiomics descriptors. Ground truth was established by histopathology. RESULTS: One hundred and eighteen patients had ALN metastasis (N + (≥ 1)). Of these, 74 had low burden (N + (1~2)) and 44 high burden (N + (≥ 3)). The remaining 156 patients had none (N0). AUC values across the 100 test repeats in predicting ALN status (N0/N + (≥ 1)) were 0.75 ± 0.05 (0.67~0.93, radiomics model), 0.68 ± 0.07 (0.53~0.85, clinical model), and 0.74 ± 0.05 (0.67~0.88, combined model). For metastatic burden prediction (N + (1~2)/N + (≥ 3)), AUC values were 0.65 ± 0.10 (0.50~0.88, radiomics model), 0.55 ± 0.10 (0.40~0.80, clinical model), and 0.64 ± 0.09 (0.50~0.90, combined model), with all the ranges spanning 0.5. In both cases, the radiomics model was significantly better than the clinical model (both p < 0.01) and comparable with the combined model (p = 0.56 and 0.64). CONCLUSIONS: Radiomics features of primary tumors could have potential in predicting ALN metastasis in CE-CBBCT imaging. CLINICAL RELEVANCE STATEMENT: The findings support potential clinical use of radiomics for predicting axillary lymph node metastasis in breast cancer patients and addressing the limited axilla coverage of cone-beam breast CT. KEY POINTS: • Contrast-enhanced cone-beam breast CT-based radiomics could have potential to predict N0 vs. N + (≥ 1) and, to a limited extent, N + (1~2) vs. N + (≥ 3) from primary tumor, and this could help address the limited axilla coverage, pending future verifications on larger cohorts. • The average AUC of radiomics and combined models was significantly higher than that of clinical models but showed no significant difference between themselves. • Radiomics features descriptive of tumor texture were found informative on axillary lymph node status, highlighting a higher heterogeneity for tumor with positive axillary lymph node.

Radiomics nomogram for predicting axillary lymph node metastasis-a potential method to address the limitation of axilla coverage in cone-beam breast CT: a bi-center retrospective study.

PURPOSE: Cone-beam breast CT (CBBCT) has an inherent limitation that the axilla cannot be imaged in its entirety. We aimed to develop and validate a nomogram based on clinical factors and contrast-enhanced (CE) CBBCT radiomics features to predict axillary lymph node (ALN) metastasis and complement limited axilla coverage. MATERIAL AND METHODS: This retrospective study included 312 patients with breast cancer from two hospitals who underwent CE-CBBCT examination in a clinical trial (NCT01792999) during 2012-2020. Patients from TCIH comprised training set (n = 176) and validation set (n = 43), and patients from SYSUCC comprised external test set (n = 93). 3D ROIs were delineated manually and radiomics features were extracted by 3D Slicer software. RadScore was calculated and radiomics model was constructed after feature selection. Clinical model was built on independent predictors. Nomogram was developed with independent clinical predictors and RadScore. Diagnostic performance was compared among three models by ROC curve, and decision curve analysis (DCA) was used to evaluate the clinical utility of nomogram. RESULTS: A total of 139 patients were ALN positive and 173 patients were negative. Twelve radiomics features remained after feature selection. Location and focality were selected as independent predictors for ALN status. The AUC of nomogram in external test set was higher than that of clinical model (0.80 vs. 0.66, p = 0.012). DCA demonstrated that the nomogram had higher overall net benefit than that of clinical model. CONCLUSION: The nomogram combined CE-CBBCT-based radiomics features and clinical factors could have potential in distinguishing ALN positive from negative and addressing the limitation of axilla coverage in CBBCT.

Quantitative breast density measurement based on three-dimensional images: a study on cone-beam breast computed tomography.

BACKGROUND: Breast density is an independent predictor of breast cancer risk. Quantitative volumetric breast density (QVBD) is expected to provide more information on the prediction of breast cancer risk. PURPOSE: To evaluate the reliability of QVBD measurements based on cone-beam breast computed tomography (CBBCT) images. MATERIAL AND METHODS: A total of 216 breasts were used to evaluate the stability of QVBD measurements based on CBBCT images and the correlations between this volumetric measurement and visual and area-based measurement methods. The intra- and inter-observer consistency of QVBD measurements were compared. Visual breast density (VBD) was evaluated with Breast Imaging Reporting and Data System (BI-RADS) standard on CBBCT images. The correlation between QVBD and VBD was evaluated by Spearman correlation coefficient. Receiver operating characteristic (ROC) curve was used to assess the sensitivity and specificity of the volumetric method in distinguishing dense and non-dense breasts. The correlation between QVBD and quantitative area-based breast density (QABD) was determined with Pearson correlation coefficient. Then, the breast volume measured with CBBCT images was compared with the breast specimen obtained during nipple-sparing mastectomy (NSM) by Pearson correlation coefficient and linear regression. RESULTS: Excellent intra- and inter-observer consistency was found from QVBD measurements. The volumetric method distinguished dense and non-dense breasts at a cutoff value of 9.5%, with 94.5% sensitivity and 77.1% specificity. Positive correlations were found between QVBD and QABD (r=0.890; P<0.001) and between the volume measured with CBBCT images and Archimedes method (r=0.969; P<0.001). CONCLUSION: CBBCT images can evaluate breast density reliably on a continuous scale.

Differentiating the lung lesions using Intravoxel incoherent motion diffusion-weighted imaging: a meta-analysis.

BACKGROUND AND OBJECTIVES: The diagnostic performance of intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) in the differential diagnosis of pulmonary tumors remained debatable among published studies. This study aimed to pool and summary the relevant results to provide more robust evidence in this issue using a meta-analysis method. MATERIALS AND METHODS: The researches regarding the differential diagnosis of lung lesions using IVIM-DWI were systemically searched in Pubmed, Embase, Web of science and Wangfang database without time limitation. Review Manager 5.3 was used to calculate the standardized mean difference (SMD) and 95% confidence intervals of apparent diffusion coefficient (ADC), tissue diffusivity (D), pseudo-diffusivity (D*), and perfusion fraction (f). Stata 12.0 was used to pool the sensitivity, specificity, and area under the curve (AUC), as well as publication bias and heterogeneity. Fagan's nomogram was used to predict the post-test probabilities. RESULTS: Eleven studies with 481 malignant and 258 benign lung lesions were included. Most include studies showed a low to unclear risk of bias and low concerns regarding applicability. Lung cancer demonstrated a significant lower ADC (SMD = -1.17, P < 0.001), D (SMD = -1.02, P < 0.001) and f values (SMD = -0.43, P = 0.005) than benign lesions, except D* value (SMD = 0.01, P = 0.96). D value demonstrated the best diagnostic performance (sensitivity = 89%, specificity = 71%, AUC = 0.90) and highest post-test probability (57, 57, 43 and 43% for D, ADC, f and D* values) in the differential diagnosis of lung tumors, followed by ADC (sensitivity = 85%, specificity = 72%, AUC = 0.86), f (sensitivity = 71%, specificity = 61%, AUC = 0.71) and D* values (sensitivity = 70%, specificity = 60%, AUC = 0.66). CONCLUSION: IVIM-DWI parameters show potentially strong diagnostic capabilities in the differential diagnosis of lung tumors based on the tumor cellularity and perfusion characteristics, and D value demonstrated better diagnostic performance compared to mono-exponential ADC.

CT Characterization of Duodenal Gastrointestinal Stromal Tumors.

OBJECTIVE: Diagnosis and staging of duodenal gastrointestinal stromal tumors (GISTs) by noninvasive imaging is critical for effective treatment, but the imaging features of duodenal GISTs remain largely undefined because of their rarity. The purpose of this article was to characterize duodenal GISTs using CT. MATERIALS AND METHODS: Thirty-four patients with duodenal GISTs were analyzed by clinical symptom evaluation, pathologic examination, and CT in this retrospective study. Unenhanced and contrast-enhanced examinations were performed in all patients. Imaging characteristics, including the lesion location, size, growth pattern, ulceration, internal components, arterial blood supply, intratumoral arterioportal shunting, intratumoral vessels, rim enhancement, and enhancement patterns were reviewed. RESULTS: The duodenal GISTs were solitary masses with well-defined margins. The average diameter was 7.1 cm. The second portion was the most common site (20/34). Ulceration was a common feature (15/34). Calcification was uncommon (3/34), and mixed growth pattern was more common (26/34). Rim enhancement (24/34) and mixed enhancement pattern (15/34) were common. Arterial blood supply, intratumoral vasculature, and draining veins were all detected and were obvious on the arterial phase. The portal venous trunk and superior mesenteric vein were the main veins into which early arterioportal shunting drained. CONCLUSION: Primary duodenal GISTs are generally large, well-defined, heterogeneously enhancing, and hypervascular masses with a prominent mixed growth pattern on CT images. Our findings suggest that CT can help depict the origin of the tumoral arteries and draining veins on the arterial phase and may be a key defining diagnostic feature for duodenal GISTs.

Nasopharyngeal carcinoma patients with retropharyngeal lymph node metastases: a minimum axial diameter of 6 mm is a more accurate prognostic predictor than 5 mm.

OBJECTIVE: The criteria for the diagnosis of metastatic retropharyngeal lymph nodes (RLNs) have not yet been resolved and are not included in the current edition of the American Joint Committee on Cancer (AJCC) staging system (seventh edition) for the staging of nasopharyngeal carcinoma (NPC). The aim of this study was to use MRI to identify an RLN size criterion that can accurately predict prognosis in patients with NPC. MATERIALS AND METHODS: Eight hundred seventeen patients with newly diagnosed localized NPC were identified. All of the patients underwent MRI before treatment with definitive radiation therapy. All the MRI studies and medical records were reviewed retrospectively. Overall survival (OS), distant metastasis-free survival (DMFS), and local relapse-free survival (LRFS) were assessed using SPSS software (version 17.0). RESULTS: RLN size cutoffs of ≥ 5 mm and of ≥ 6 mm were used. There was no significant difference in OS (p = 0.216), DMFS (p = 0.081), or LRFS (p = 0.067) in patients with RLNs ≥ 5 mm and in those with RLNs < 5 mm. When 6 mm was used as a size cutoff, significant differences in OS (p = 0.000) and DMFS (p = 0.001) were identified; there was no significant difference observed for LRFS (p = 0.380). CONCLUSION: A minimum axial RLN diameter of 6 mm was a more accurate prognostic predictor in NPC patients with RLN metastases than 5 mm.

Diagnostic assessment by dynamic contrast-enhanced and diffusion-weighted magnetic resonance in differentiation of breast lesions under different imaging protocols.

BACKGROUND: The apparent diffusion coefficient (ADC) is a highly diagnostic factor in discriminating malignant and benign breast masses in diffusion-weighted magnetic resonance imaging (DW-MRI). The combination of ADC and other pictorial characteristics has improved lesion type identification accuracy. The objective of this study was to reassess the findings on an independent patient group by changing the magnetic field from 1.5-Tesla to 3.0-Tesla. METHODS: This retrospective study consisted of a training group of 234 female patients, including 85 benign and 149 malignant lesions, imaged using 1.5-Tesla MRI, and a test group of 95 female patients, including 19 benign and 85 malignant lesions, imaged using 3.0-Tesla MRI. The lesion of interest was segmented from the raw image and four sets of measurements describing the morphology, kinetics, DW-MRI, and texture of the pictorial properties of each lesion were obtained. Each lesion was characterized by 28 features in total. Three classical machine-learning algorithms were used to build prediction models on the training group, which evaluated the prognostic performance of the multi-sided features in three scenarios. To reduce information redundancy, five highly diagnostic factors were selected to obtain a compact yet informative characterization of the lesion status. RESULTS: Three classification models were built on the training of 1.5-Tesla patients and were tested on the independent 3.0-Tesla test group. The following results were found. i) Characterization of breast masses in a multi-sided way dramatically increased prediction performance. The usage of all features gave a higher performance in both sensitivity and specificity than any individual feature groups or their combinations. ii) ADC was a highly effective factor in improving the sensitivity in discriminating malignant from benign masses. iii) Five features, namely ADC, Sum Average, Entropy, Elongation, and Sum Variance, were selected to achieve the highest performance in diagnosis of the 3.0-Tesla patient group. CONCLUSIONS: The combination of ADC and other multi-sided characteristics can increase the capability of discriminating malignant and benign breast lesions, even under different imaging protocols. The selected compact feature subsets achieved a high diagnostic performance and thus are promising in clinical applications for discriminating lesion type and for personalized treatment planning.

Effect of vascular haemoglobin concentrations on ultrasound-guided diffuse optical tomography in differentiating benign from malignant breast lesions.

OBJECTIVES: Ultrasound-guided diffuse optical tomography (US-DOT) can potentially detect breast carcinomas by measuring total tumour haemoglobin concentrations (TTHC). The purpose of this study was to evaluate whether vascular haemoglobin concentrations (VHC) affect the ability of US-DOT to distinguish breast carcinomas from benign. MATERIALS AND METHODS: In 85 women (97 palpable lesions) referred for core breast biopsy, we measured VHC with a complete blood count and calculated TTHCs for each lesion with US-DOT. Anaemia was defined as a VHC less than 120.0 g/L. RESULTS: Mean TTHCs were significantly higher in malignant lesions (n = 53) than in benign lesions (n = 44), regardless of whether the lesions were from women with anaemia (TTHC, 248.5 vs. 123.3 µmol/L; P = 0.001) or from those without (TTHC, 229.7 vs. 173.9 µmol/L; P = 0.016). A cut-off TTHC of 155.1 µmol/L provided 81.3 % sensitivity, 81.8 % specificity and 81.5 % accuracy for detecting malignant tumours in women with anaemia and 78.4 % sensitivity, 54.5 % specificity and 67.1 % accuracy for women without. There was no significant difference in sensitivity (P = 0.813), specificity (P = 0.108) and accuracy (P = 0.162) between the anaemic group and the non-anaemic group. CONCLUSIONS: Vascular haemoglobin concentrations did not affect the ability of US-DOT to differentiate breast carcinomas from benign lesions. KEY POINTS: • US-DOT can differentiate benign from malignant breast lesions by measuring TTHC. • No difference in TTHC between the anaemia and non-anaemia group. • Vascular haemoglobin concentrations do not affect the diagnostic ability of US-DOT.

Simple measurements on diffusion-weighted MR imaging for assessment of complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer.

PURPOSE: To determine diagnostic performance of simple measurements on diffusion-weighted MR imaging (DWI) for assessment of complete tumour response (CR) after neoadjuvant chemoradiotherapy (CRT) in patients with locally advanced rectal cancer (LARC) by signal intensity (SI) and apparent diffusion coefficient (ADC) measurements. MATERIALS AND METHODS: Sixty-five patients with LARC who underwent neoadjuvant CRT and subsequent surgery were included. Patients underwent pre-CRT and post-CRT 3.0 T MRI. Regions of interest of the highest brightness SI were included in the tumour volume on post-CRT DWI to calculate the SIlesion, rSI, ADClesion and rADC; diagnostic performance was compared by using the receiver operating characteristic (ROC) curves. In order to validate the accuracy and reproducibility of the current strategy, the same procedure was reproduced in 80 patients with LARC at 1.5 T MRI. RESULTS: Areas under the ROC curve for identification of a CR, based on SIlesion, rSI, ADClesion, and rADC, respectively, were 0.86, 0.94, 0.66, and 0.71 at 3.0 T MRI, and 0.92, 0.91, 0.64, and 0.61 at 1.5 T MRI. CONCLUSION: Post-CRT DWI SIlesion and rSI provided high diagnostic performance in assessing CR and were significantly more accurate than ADClesion, and rADC at 3.0 T MRI and 1.5 T MRI. KEY POINTS: • Signal intensity (SI lesion ) and rSI are accurate for assessment of complete response. • rSI seems to be superior to SI lesion at 3.0 T MRI. • ADC or rADC measurements are not accurate for assessment of complete response.

CT and MRI of radiation-induced sarcomas of the head and neck following radiotherapy for nasopharyngeal carcinoma.

AIM: To investigate the radiological findings of head and neck radiation-induced sarcomas (RISs) following radiotherapy for nasopharyngeal carcinoma (NPC). MATERIALS AND METHODS: Fifty-nine patients with RISs were identified. Imaging characteristics on computed tomography (CT) and magnetic resonance imaging (MRI), including lesion location, extent, size, margin, internal architecture, pattern, and degree of enhancement, together with patient characteristics at NPC diagnosis and latency periods, were reviewed. RESULTS: The study included 20 women and 39 men, with a median age of 49 years (range 30-71 years). The median latency was 9 years (range 3-37 years). The median radiation dose at the site of RIS was 66 Gy (range 44-78 Gy). The most common histological RIS types were fibrosarcoma (44.1%) and osteosarcoma (30.5%). The most common RIS sites were the paranasal sinuses and the nasal cavity (39%), the neck (16.9%), and the mandible (15.3%). The mean size was 5.1 cm (range 1.2-8.6 cm). Overall, 78% of lesions extended to adjacent spaces and 66.1% were accompanied by bone destruction. Heterogeneous density/signal intensity before and after enhancement was seen in all lesions on imaging. Marked lesion enhancement was noted in 49 cases (76.3%). CONCLUSIONS: The radiologist should be aware of the different sites at which RISs occur and the radiological appearance of the wide variety of RIS subtypes. Careful imaging follow-up is necessary for early detection of RISs in patients with NPC after radiotherapy.

Hepatic angiomyolipoma: CT and MR imaging findings with clinical-pathologic comparison.

OBJECTIVE: The objective of this study is to evaluate the clinical, pathologic, and computed tomography (CT) and/or magnetic resonance imaging (MRI) findings of hepatic angiomyolipoma (HAML) and to improve the diagnostic efficacy of the tumor. MATERIALS AND METHODS: Clinical, pathologic, and imaging findings were retrospectively evaluated in 18 patients with HAML. Two patients underwent both CT and MRI, ten underwent CT alone, and six underwent MRI alone. Unenhanced and contrast-enhanced examinations were performed in all patients. Imaging characteristics, such as the lesion location, lesion diameter, presence of early draining veins, attenuation/signal intensity of the lesions on imaging, and enhancement pattern were reviewed. RESULTS: There were 3 male and 15 female patients. HAML was seen as a well-defined, solitary mass on imaging with medium size (mean diameter, 5.9 cm). Fat was detected in ten patients. Calcification was noted in two patients and cystic degeneration was seen in one patient. Hepatic cirrhosis and capsule were not detected in all patients. The mean attenuation values exceeded 120 hounsfield units (HU) in 11 patients (91.7%). Peripherally decreasing enhancement rim as well as early draining vein was seen in 15 patients (83.3%). The early draining veins were all hepatic veins. Tumor vessels were noted in all patients. CONCLUSION: The presence of early draining vein, peripheral decreasing enhancement rim, and the absence of tumor capsule in the hypervascular hepatic tumor on CT and/or MRI together with normal alpha fetal protein may be helpful for the diagnosis of HAML in non-cirrhotic liver.

Abnormal baseline brain activity in patients with HBV-related cirrhosis without overt hepatic encephalopathy revealed by resting-state functional MRI.

Neurocognitive dysfunction of varying degrees is common in patients with hepatitis B virus-related cirrhosis (HBV-RC) without overt hepatic encephalopathy (OHE). However, the neurobiological mechanisms underlying these dysfunctions are not well understood. We sought to identify changes in the neural activity of patients with HBV-RC without OHE in the resting state by using the amplitude of low-frequency fluctuation (ALFF) method and to determine whether these changes were related to impaired cognition. Resting-state functional MRI data from 30 patients with HBV-RC and 30 healthy controls matched for age, sex, and years of education were compared to determine any differences in the ALFF between the two groups. Cognition was measured with the psychometric hepatic encephalopathy score (PHES), and the relationship between these scores and ALFF variation was assessed. Compared with controls, patients showed widespread lower standardized ALFF (mALFF) values in visual association areas (bilateral lingual gyrus, middle occipital gyrus, and left inferior temporal gyrus), motor-related areas (bilateral precentral gyrus, paracentral lobule, and right postcentral gyrus), and the default mode network (bilateral cuneus/precuneus and inferior parietal lobule). Higher mALFF values were found in the bilateral orbital gyrus/rectal gyrus. In patients, mALFF values were significantly positive correlated with the PHES in the right middle occipital gyrus and bilateral precentral gyrus. Our findings of resting-state abnormalities in patients with HBV-RC without OHE suggest that neurocognitive dysfunction in patients with HBV-RC without OHE may be caused by abnormal neural activity in multiple brain regions.

Cone-beam breast CT-guided surface location facilitates breast-conserving surgery in breast cancer patients with extensive calcifications: A pilot study.

Background: Extensive malignant-appearing calcifications have traditionally been considered a contraindication for breast-conserving surgery. The evaluation of calcifications largely depends on mammography, which is limited by tissue superimposition and is unable to reveal spatial information about extensive calcifications. Three-dimensional imaging modality is needed to reveal the architecture of extensive calcifications. In the present study, a novel cone-beam breast CT-guided surface location technique was investigated to facilitate breast-conserving surgery in breast cancer patients with extensive malignant breast calcifications. Methods: Biopsy-proved early breast cancer patients with extensive malignant-appearing breast calcifications were included. A patient will be considered suitable for breast-conserving surgery if the spatial segmental distribution of calcifications is found by 3D images of cone-beam breast CT. Then, the margins of the calcifications were located in contrast-enhanced cone-beam breast CT images. Next, skin markers were located using radiopaque materials, and cone-beam breast CT was reperformed to confirm the accuracy of surface location. During breast-conserving surgery, lumpectomy was performed according to the previous surface location, and an intraoperative specimen x-ray was applied to double-check that the entire lesion was removed. Margin assessment was made for both intraoperative frozen section and postoperative pathology examination. Results: From May 2019 to Jun 2022, 11 eligible breast cancer patients in our institution were included. Breast-conserving surgery was performed successfully in all patients using the surface location approach mentioned before. All patients achieved negative margins and satisfied cosmetic results. Conclusion: This study proved the feasibility of cone-beam breast CT-guided surface location for facilitating breast-conserving surgery in breast cancer patients with extensive malignant breast calcifications.

Is tamoxifen alone adequate therapy in very young Chinese women with operable breast cancer?

Breast cancer occurs earlier in Chinese women than in Caucasian women. We have compared the clinicopathologic characteristics and prognosis in very young and older premenopausal women with breast cancer in south China. We separated 905 consecutive premenopausal patients with first diagnosis of breast cancer, surgically treated at the Sun Yat-sen University Cancer Center from October 2003 to December 2006, into a very young group (189 [13.7%]; <35 years old) and an older group (716 [52.0%]; 35-57 years old). Approximately, 90% of patients received adjuvant chemotherapy and hormonal therapy with tamoxifen for hormone-receptor (HR)-positive breast cancer. We retrospectively compared the clinicopathologic factors and survival rates of these two groups. The 3-year disease-free survival rate (78.0% versus 89.1%, p < 0.001) was poorer in the very young group, and 3-year overall survival rate (94.3% versus. 96.8%, p = 0.10) was similar. Moreover, the 3-year overall survival rate (p = 0.020) and disease-free survival rate (p < 0.001) were significantly poorer in HR-positive patients in the very young group whereas there was no significant difference in outcomes between the HR-negative groups. In China, age younger than 35 years is an independent predictor of breast cancer recurrence. In very young women with HR-positive breast cancer, chemotherapy plus tamoxifen alone may not be adequate standard treatment.

Solid neuroendocrine breast carcinoma: mammographic and sonographic features in thirteen cases.

This study aimed to determine and quantitate the mammographic and sonographic characteristics in 13 cases of solid neuroendocrine breast carcinoma (NEBC) and to analyze the association of radiological findings with the clinical and histopathologic findings. The clinical data and imaging findings of 13 female patients with histologically confirmed solid NEBC were reviewed. Imaging data were evaluated by two radiologists for a consensual diagnosis. All patients presented with one palpable mass; only 1 experienced occasional breast pain, and 5 complained of fluid discharge. In 7 patients, the masses were firm and mobile. Regional lymph node metastasis was noted in only 1 patient. For the 10 patients who underwent mammography, 6 had a mass, 1 had clustered small nodules with clustered punctuate microcalcifications, 2 had asymmetric focal density, and 1 had solitary punctuate calcification. Most of the masses had irregular shape with indistinct or microlobulated margins. For the 9 patients who underwent ultrasonography (US), 9 masses were depicted, all of which were hypoechoic, mostly with irregular shape and without acoustic phenomena. Different types of acoustic phenomena were also identified. One patient had developed distant metastases during follow-up. NEBC has a variety of presentations, but it is mostly observed on mammograms as a dense, irregular mass with indistinct or microlobulated margins. Sonographically, it typically presents as an irregular, heterogeneously hypoechoic mass with normal sound transmission. Histories of nipple discharge and calcification observed using imaging are not rare.

Assessment of Cone-Beam Breast Computed Tomography for Predicting Pathologic Response to Neoadjuvant Chemotherapy in Breast Cancer: A Prospective Study.

Background: Response surveillance of neoadjuvant chemotherapy is needed to facilitate treatment decisions. We aimed to assess the imaging features of cone-beam breast computed tomography (CBBCT) for predicting the pathologic response of breast cancer after neoadjuvant chemotherapy. Methods: This prospective study included 81 women with locally advanced breast cancer who underwent neoadjuvant chemotherapy from August 2017 to January 2021. All patients underwent CBBCT before treatment, and 55 and 65 patients underwent CT examinations during the midtreatment (3 cycles) and late-treatment phases (7 cycles), respectively. Clinical information and quantitative parameters such as the diameter, volume, surface area, and CT density were compared between pathologic responders and nonresponders using the T-test and the Mann-Whitney U test. The performance of meaningful parameters was evaluated with the receiver operating characteristic curve, sensitivity, and specificity. Results: The quantitative results for the segmented volume, segmented surface area, segmented volume reduction, maximum enhancement ratio, wash-in rate and two-minute enhancement value in the mid- and late-treatment periods had predictive value for pathologic complete response. The area under the curve for the prediction model after multivariate regression analysis was 0.874. Conclusion: After comparing the outcomes of each timepoint, mid- and late-treatment parameters can be used to predict pathologic outcome. The late-treatment parameters showed significant value with a predictive model.

Correlation between contrast-enhanced cone-beam breast computed tomography features and prognostic staging in breast cancer.

OBJECTIVE: To evaluate whether contrast-enhanced cone-beam breast CT (CE-CBBCT) features can risk-stratify prognostic stage in breast cancer. METHODS: Overall, 168 biopsy-proven breast cancer patients were analysed: 115 patients in the training set underwent scanning using v. 1.5 CE-CBBCT between August 2019 and December 2019, whereas 53 patients in the test set underwent scanning using v. 1.0 CE-CBBCT between May 2012 and August 2014. All patients were restaged according to the American Joint Committee on Cancer eighth edition prognostic staging system. Following the combination of CE-CBBCT imaging parameters and clinicopathological factors, predictors that were correlated with stratification of prognostic stage via logistic regression were analysed. Predictive performance was assessed according to the area under the receiver operating characteristic curve (AUC). Goodness-of-fit of the models was assessed using the Hosmer-Lemeshow test. RESULTS: As regards differentiation between prognostic stage (PS) I and II/III, increased tumour-to-breast volume ratio (TBR), rim enhancement pattern, and the presence of penetrating vessels were significant predictors for PS II/III disease (p < 0.05). The AUCs in the training and test sets were 0.967 [95% confidence interval (CI) 0.938-0.996; p < 0.001] and 0.896 (95% CI, 0.809-0.983; p = 0.001), respectively. Two features were selected in the training set of PS II vs III, including tumour volume [odds ratio (OR)=1.817, p = 0.019] and calcification (OR = 4.600, p = 0.040), achieving an AUC of 0.790 (95% CI, 0.636-0.944, p = 0.001). However, there was no significant difference in the test set of PS II vs III (P＞0.05). CONCLUSION: CE-CBBCT imaging biomarkers may provide a large amount of anatomical and radiobiological information for the pre-operative distinction of prognostic stage. ADVANCES IN KNOWLEDGE: CE-CBBCT features have distinctive promise for stratification of prognostic stage in breast cancer.

Radiocolloid in combination with methylene dye localization, rather than wire localization, is a preferred procedure for excisional biopsy of nonpalpable breast lesions.

BACKGROUND: Wire localization (WL) is traditionally performed before excisional biopsy for patients with nonpalpable breast lesions, but it has several disadvantages. Our current study examines whether the method of radiocolloid combined with methylene dye localization (RCML) has an advantage over WL. MATERIALS AND METHODS: From August 2006 to May 2009, 157 patients with nonpalpable breast lesions classified as BI-RADS category 5 were enrolled in our study. Of the 157 patients, 78 were assigned to WL and 79 to RCML. The status of surgical margins, weight of specimens, length of incisions, and duration of operation were compared between these two groups. RESULTS: All patients were diagnosed after first excisional biopsy. The patients with malignancy accounted for 55.1% in WL group, and 53.2% in RCML group. For malignant lesions, fewer patients undergoing RCML had close or involved surgical margins than did those who had WL (19.0% vs. 39.5%, P = .038). The mean weight of specimen was 45.2 g in WL group and 39.0 g in RCML group (P < .001). The mean length of incision was 44.8 mm in WL group and 36.3 mm in RCML group (P < .001). The mean time of operation was 16.3 min for WL and 14.7 min for RCML (P = .001). CONCLUSIONS: RCML provides precise identification of the site of the nonpalpable lesion and a visible marker to the lesion for surgeons and allows rapid, easy, and accurate excision of nonpalpable breast lesions. Therefore, RCML is a promising alternative to WL.

Characterizing the clustered microcalcifications on mammograms to predict the pathological classification and grading: a mathematical modeling approach.

In this study, we explore a mathematical model to characterize the clustered microcalcifications on mammograms for predicting the pathological classification and grading. Our database consists of both retrospective cases (78 cases) and prospective cases (31 cases) with pathologically diagnosed clusters of microcalcifications on mammograms. The microcalcifications were divided into four grades: grade 0, benign breast disease including mastopathies (n = 12) and fibroadenomas (n = 20); grade 1, well-differentiated infiltrating ductal carcinoma (n = 12); grade 2, moderately differentiated infiltrating ductal carcinoma (n = 38); grade 3, poorly differentiated infiltrating ductal carcinoma (n = 27). A feature parameter, defined as the pattern form factor of microcalcification cluster θ by us, combines five computer-extracted image parameters of microcalcification clusters of those mammograms. In every case, only one imaging was selected for modeling analysis. A total of 109 imagings were adopted in current study. We find the existence of a positive relationship between the feature parameter θ and pathological grading G of microcalcifications in retrospective cases, which was expressed as G = 6.438 + 1.186 × Ln <θ>. The model above has been verified further by the prospective study with a comparative evaluation accuracy of approximately 77.42%. The binary predication simply for both benignancy and malignancy was also included using same but reshuffled data, and the receiver operating characteristic (ROC) analysis was performed with ROC value 0.74351∼0.79891. As one candidate for feature parameter in computer-aided diagnosis, the pattern form factor θ of clustered microcalcifications may be useful to predict the pathological grading and classification of microcalcification clusters on mammography in breast cancer.

Distinguishing benign and malignant lesions on contrast-enhanced breast cone-beam CT with deep learning neural architecture search.

PURPOSE: To utilize a neural architecture search (NAS) approach to develop a convolutional neural network (CNN) method for distinguishing benign and malignant lesions on breast cone-beam CT (BCBCT). METHOD: 165 patients with 114 malignant and 86 benign lesions were collected by two institutions from May 2012 to August 2014. The NAS method autonomously generated a CNN model using one institution's dataset for training (patients/lesions: 71/91) and validation (patients/lesions: 20/23). The model was externally tested on another institution's dataset (patients/lesions: 74/87), and its performance was compared with fine-tuned ResNet-50 models and two breast radiologists who independently read the lesions in the testing dataset without knowing lesion diagnosis. RESULTS: The lesion diameters (mean ± SD) were 18.8 ± 12.9 mm, 22.7 ± 10.5 mm, and 20.0 ± 11.8 mm in the training, validation, and external testing set, respectively. Compared to the best ResNet-50 model, the NAS-generated CNN model performed three times faster and, in the external testing set, achieved a higher (though not statistically different) AUC, with sensitivity (95% CI) and specificity (95% CI) of 0.727, 80% (66-90%), and 60% (42-75%), respectively. Meanwhile, the performances of the NAS-generated CNN and the two radiologists' visual ratings were not statistically different. CONCLUSIONS: Our preliminary results demonstrated that a CNN autonomously generated by NAS performed comparably to pre-trained ResNet models and radiologists in predicting malignant breast lesions on contrast-enhanced BCBCT. In comparison to ResNet, which must be designed by an expert, the NAS approach may be used to automatically generate a deep learning architecture for medical image analysis.