Forget Me Not: Incidental Findings on Breast MRI.

With the growing utilization and expanding role of breast MRI, breast imaging radiologists may encounter an increasing number of incidental findings beyond the breast and axilla. Breast MRI encompasses a large area of anatomic coverage extending from the lower neck to the upper abdomen. While most incidental findings on breast MRI are benign, identifying metastatic disease can have a substantial impact on staging, prognosis, and treatment. Breast imaging radiologists should be familiar with common sites, MRI features, and breast cancer subtypes associated with metastatic disease to assist in differentiating malignant from benign findings. Furthermore, detection of malignancies of nonbreast origin as well as nonmalignant, but clinically relevant, incidental findings can significantly impact clinical management and patient outcomes. Breast imaging radiologists should consistently follow a comprehensive search pattern and employ techniques to improve the detection of these important incidental findings.

MRI of the Lactating Breast.

The breasts undergo marked physiologic changes during lactation that can make conventional imaging evaluation with mammography and US challenging. MRI can be a valuable diagnostic aid to differentiate physiologic and benign processes from malignancy in patients who are lactating. In addition, MRI may allow more accurate delineation of disease involvement than does conventional imaging and assists in locoregional staging, screening of the contralateral breast, assessment of response to neoadjuvant chemotherapy, and surgical planning. Although the American College of Radiology recommends against patients undergoing contrast-enhanced MRI during pregnancy because of fetal safety concerns, contrast-enhanced MRI is safe during lactation. As more women delay childbearing, the incidence of pregnancy-associated breast cancer (PABC) and breast cancer in lactating women beyond the 1st year after pregnancy is increasing. Thus, MRI is increasingly being performed in lactating women for diagnostic evaluation and screening of patients at high risk. PABC is associated with a worse prognosis than that of non-PABCs, with delays in diagnosis contributing to an increased likelihood of advanced-stage disease at diagnosis. Familiarity with the MRI features of the lactating breast and the appearance of various pathologic conditions is essential to avoid diagnostic pitfalls and prevent delays in cancer diagnosis and treatment. The authors review clinical indications for breast MRI during lactation, describe characteristic features of the lactating breast at MRI, and compare MRI features of a spectrum of benign and malignant breast abnormalities. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material. See the invited commentary by Chikarmane in this issue.

The role of digital mammographic surveillance for detection of asymptomatic recurrence in autologous flap reconstructions.

OBJECTIVE: To evaluate the utility of digital mammography in detecting asymptomatic malignancy in autologous flap reconstructions after mastectomy. METHODS: A retrospective database review identified all mammograms performed on asymptomatic patients with flap reconstructions over a 9-year period (1/1/2009 to 12/31/2017). A negative examination was defined as BI-RADS 1 or 2 and a positive examination was defined as BI-RADS 0, 4, or 5 assigned to the mastectomy side. Malignant outcomes were determined by pathology results. Interval cancers, or false negatives, were defined as locoregional malignant diagnosis within one year of a negative mammogram. Sensitivity, specificity, predictive values, abnormal interpretation rate, and cancer detection rate were calculated. RESULTS: 626 mammograms of asymptomatic flap reconstructions were performed in 183 patients. The most common flap type was TRAM (83.5 %, 523/626) and DIEP (13.4 %, 84/626). Most exams (98.2 %, 615/626) were negative, assessed as BI-RADS 1 or 2, with no interval cancers at follow-up. Eleven exams (1.8 %, 11/626) were positive, assessed as BI-RADS 0, 4, or 5. After diagnostic work-up of all BI-RADS 0 exams, 9 cases had a final recommendation for biopsy of which 3 were malignant. Mammography yielded a cancer detection rate of 0.5 % (3/626), abnormal interpretation rate of 1.8 % (11/626), NPV of 100 % (615/615), overall PPV of 27.3 % (3/11), PPV2 (positive predictive value of a biopsy recommendation) of 33.3 % (3/9), sensitivity of 100 % (3/3), and specificity of 98.7 % (615/623). CONCLUSION: Digital mammography of asymptomatic autologous flap reconstructions after mastectomy demonstrated high sensitivity and low abnormal interpretation rate. Cancer detection rate was comparable to current national benchmarks for mammographic screening in the general U.S. population without mastectomy.

Whole-body tumor segmentation from PET/CT images using a two-stage cascaded neural network with camouflaged object detection mechanisms.

BACKGROUND: Whole-body Metabolic Tumor Volume (MTVwb) is an independent prognostic factor for overall survival in lung cancer patients. Automatic segmentation methods have been proposed for MTV calculation. Nevertheless, most of existing methods for patients with lung cancer only segment tumors in the thoracic region. PURPOSE: In this paper, we present a Two-Stage cascaded neural network integrated with Camouflaged Object Detection mEchanisms (TS-Code-Net) for automatic segmenting tumors from whole-body PET/CT images. METHODS: Firstly, tumors are detected from the Maximum Intensity Projection (MIP) images of PET/CT scans, and tumors' approximate localizations along z-axis are identified. Secondly, the segmentations are performed on PET/CT slices that contain tumors identified by the first step. Camouflaged object detection mechanisms are utilized to distinguish the tumors from their surrounding regions that have similar Standard Uptake Values (SUV) and texture appearance. Finally, the TS-Code-Net is trained by minimizing the total loss that incorporates the segmentation accuracy loss and the class imbalance loss. RESULTS: The performance of the TS-Code-Net is tested on a whole-body PET/CT image data-set including 480 Non-Small Cell Lung Cancer (NSCLC) patients with five-fold cross-validation using image segmentation metrics. Our method achieves 0.70, 0.76, and 0.70, for Dice, Sensitivity and Precision, respectively, which demonstrates the superiority of the TS-Code-Net over several existing methods related to metastatic lung cancer segmentation from whole-body PET/CT images. CONCLUSIONS: The proposed TS-Code-Net is effective for whole-body tumor segmentation of PET/CT images. Codes for TS-Code-Net are available at: https://github.com/zyj19/TS-Code-Net.

Deep Learning to Simulate Contrast-enhanced Breast MRI of Invasive Breast Cancer.

Background There is increasing interest in noncontrast breast MRI alternatives for tumor visualization to increase the accessibility of breast MRI. Purpose To evaluate the feasibility and accuracy of generating simulated contrast-enhanced T1-weighted breast MRI scans from precontrast MRI sequences in biopsy-proven invasive breast cancer with use of deep learning. Materials and Methods Women with invasive breast cancer and a contrast-enhanced breast MRI examination that was performed for initial evaluation of the extent of disease between January 2015 and December 2019 at a single academic institution were retrospectively identified. A three-dimensional, fully convolutional deep neural network simulated contrast-enhanced T1-weighted breast MRI scans from five precontrast sequences (T1-weighted non-fat-suppressed [FS], T1-weighted FS, T2-weighted FS, apparent diffusion coefficient, and diffusion-weighted imaging). For qualitative assessment, four breast radiologists (with 3-15 years of experience) blinded to whether the method of contrast was real or simulated assessed image quality (excellent, acceptable, good, poor, or unacceptable), presence of tumor enhancement, and maximum index mass size by using 22 pairs of real and simulated contrast-enhanced MRI scans. Quantitative comparison was performed using whole-breast similarity and error metrics and Dice coefficient analysis of enhancing tumor overlap. Results Ninety-six MRI examinations in 96 women (mean age, 52 years ± 12 [SD]) were evaluated. The readers assessed all simulated MRI scans as having the appearance of a real MRI scan with tumor enhancement. Index mass sizes on real and simulated MRI scans demonstrated good to excellent agreement (intraclass correlation coefficient, 0.73-0.86; P < .001) without significant differences (mean differences, -0.8 to 0.8 mm; P = .36-.80). Almost all simulated MRI scans (84 of 88 [95%]) were considered of diagnostic quality (ratings of excellent, acceptable, or good). Quantitative analysis demonstrated strong similarity (structural similarity index, 0.88 ± 0.05), low voxel-wise error (symmetric mean absolute percent error, 3.26%), and Dice coefficient of enhancing tumor overlap of 0.75 ± 0.25. Conclusion It is feasible to generate simulated contrast-enhanced breast MRI scans with use of deep learning. Simulated and real contrast-enhanced MRI scans demonstrated comparable tumor sizes, areas of tumor enhancement, and image quality without significant qualitative or quantitative differences. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Slanetz in this issue. An earlier incorrect version appeared online. This article was corrected on January 17, 2023.

US as the Primary Imaging Modality in the Evaluation of Palpable Breast Masses in Breastfeeding Women, Including Those of Advanced Maternal Age.

Background Women are increasingly delaying childbearing, and thus lactation, into their 30s and 40s, when mammography would typically be the initial imaging modality to evaluate palpable masses in the general population. Current guidelines recommend US as the first-line imaging modality for palpable masses in pregnant and lactating women, but data regarding breastfeeding women age 30 years and older are near nonexistent. Purpose To evaluate the diagnostic performance of targeted US as the primary imaging modality for the evaluation of palpable masses in lactating women, including those of advanced maternal age. Materials and Methods Lactating women with palpable breast masses evaluated at targeted US over a 17-year period (January 2000 to July 2017) were retrospectively identified. All US evaluations were performed at diagnostic evaluation, and mammography was performed at the discretion of the interpreting radiologist. Breast Imaging Reporting and Data System assessments, imaging, and pathology results were collected. Descriptive statistics and 2 × 2 contingency tables were assessed at the patient level. Results There were 167 women (mean age, 35 years ± 5 [standard deviation]), 101 of whom (60%) were of advanced maternal age (≥35 years). All women underwent targeted US, and 98 (59%) underwent mammography in addition to US. The frequency of malignancy was five of 167 (3.0%). Targeted US demonstrated a sensitivity and specificity of five of five (100%; 95% confidence interval [CI]: 48%, 100%) and 114 of 162 (70%; 95% CI: 63%, 77%), respectively. Negative predictive value, positive predictive value of an abnormal examination, and positive predictive value of biopsy were 114 of 114 (100%; 95% CI: 97%, 100%), five of 53 (9.4%; 95% CI: 3%, 21%), and five of 50 (10%; 95% CI: 3%, 22%), respectively. In the subset of 98 women who underwent mammography in addition to US, mammography depicted seven incidental suspicious findings, which lowered the specificity from 62 of 93 (67%; 95% CI: 56%, 76%) to 57 of 93 (61%; 95% CI: 51%, 71%) (P = .02). Conclusion Targeted US depicted all malignancies in lactating women with palpable masses. Adding mammography increased false-positive findings without any additional cancer diagnoses. © RSNA, 2020 See also the editorial by Newell in this issue.

2D shear wave elastography: measurement acquisition and reliability criteria in noninvasive assessment of liver fibrosis.

PURPOSE: The objective was to evaluate the accuracy of 2D shear wave elastography (SWE) in predicting stages of liver fibrosis using five individual versus grouped measurements and different reliability criteria. MATERIALS AND METHODS: This is a prospective study of 109 patients who underwent hepatic 2D SWE (Canon Aplio 500) prior to liver biopsy for varied indications. Liver fibrosis was staged using the METAVIR scoring system (F = 0-4). Propagation mapping was used to guide ten SWE measurements from the liver parenchyma: five individual measurements and five grouped measurements. IQR/median, SD/median, and SD/mean were examined as quality criteria for patient inclusion at various thresholds (IQR/median ≤ 0.15, 0.2, 0.3, 0.4, 0.5; SD/median ≤ 0.15, 0.2, 0.3; SD/mean ≤ 0.2, 0.3, 0.5). Threshold for clinically significant fibrosis (F ≥ 2) was determined with receiver operating characteristic (ROC) analysis. RESULTS: There was high agreement between individual and grouped measurements without statistically significant differences (intraclass correlation coefficient = 0.82; p = 0.26-0.96). When no quality criterion was used (n = 103), the optimal threshold was 11.3 kPa [AUROC 0.78, 95% CI (0.69, 0.88)] with sensitivity and specificity of 80% and 66%, respectively. All quality criteria were associated with equal or higher AUROC ranging from 0.78 to 0.87. IQR/median ≤ 0.5 (n = 88) achieved the highest sensitivity of 85% and only excluded a small subset of patients. The AUROC and specificity were 0.83 [95% CI (0.74, 0.92)] and 72%, respectively. SIGNIFICANCE: Quality criterion IQR/median ≤ 0.5 increases sensitivity and specificity in prediction of clinically significant liver fibrosis while excluding only a small subset of patients. Grouped measurements are comparable to individual measurements and may help increase procedural efficiency.

Region-specific effects of isoflurane anesthesia on Fos immunoreactivity in response to intravenous cocaine challenge in rats with a history of repeated cocaine administration.

We have previously shown that acute intravenous (i.v.) administration of cocaine increases Fos immunoreactivity in rats under isoflurane anesthesia. Given that Fos expression is a marker of neural activation, the results suggested that isoflurane is appropriate for imaging cocaine effects under anesthesia. However, most imaging research in this area utilizes subjects with a history of repeated cocaine exposure and this drug history may interact with anesthetic use differently from acute cocaine exposure. Thus, this study further examined Fos expression under isoflurane in rats with a history of repeated i.v. cocaine administration. Rats received daily injections of either saline or cocaine (2mg/kg, i.v.) across 7 consecutive days, followed by 5 days of no drug exposure. On the test day, rats were either nonanesthetized or anesthetized under isoflurane and were given an acute challenge of cocaine (2mg/kg, i.v.). Additional saline-exposed controls received a saline challenge. Ninety min after the drug challenge, the rats were perfused under isoflurane anesthesia and their brains were processed for Fos protein immunohistochemistry. We found that challenge injections of cocaine following a regimen of repeated cocaine exposure resulted in Fos expression in the prefrontal cortex and striatum roughly equivalent to that found in rats who had received the cocaine challenge after a history of vehicle injections. Additionally, isoflurane anesthesia resulted in a heterogeneous attenuation of cocaine-induced Fos expression, with the most robust effect in the orbital cortex but no effect in the nucleus accumbens core (NAcC). These results indicate that cocaine-induced Fos is preserved in the NAcC under isoflurane, suggesting that isoflurane can be used in imaging studies involving cocaine effects in this region.