Comparing deep learning-based automatic segmentation of breast masses to expert interobserver variability in ultrasound imaging.

Deep learning is a powerful tool that became practical in 2008, harnessing the power of Graphic Processing Unites, and has developed rapidly in image, video, and natural language processing. There are ongoing developments in the application of deep learning to medical data for a variety of tasks across multiple imaging modalities. The reliability and repeatability of deep learning techniques are of utmost importance if deep learning can be considered a tool for assisting experts, including physicians, radiologists, and sonographers. Owing to the high costs of labeling data, deep learning models are often evaluated against one expert, and it is unknown if any errors fall within a clinically acceptable range. Ultrasound is a commonly used imaging modality for breast cancer screening processes and for visually estimating risk using the Breast Imaging Reporting and Data System score. This process is highly dependent on the skills and experience of the sonographers and radiologists, thereby leading to interobserver variability and interpretation. For these reasons, we propose an interobserver reliability study comparing the performance of a current top-performing deep learning segmentation model against three experts who manually segmented suspicious breast lesions in clinical ultrasound (US) images. We pretrained the model using a US thyroid segmentation dataset with 455 patients and 50,993 images, and trained the model using a US breast segmentation dataset with 733 patients and 29,884 images. We found a mean Fleiss kappa value of 0.78 for the performance of three experts in breast mass segmentation compared to a mean Fleiss kappa value of 0.79 for the performance of experts and the optimized deep learning model.

Correction to: Best MRI sequences for identifying axillary lymph node markers in patients with metastatic breast cancer: an inter-reader observational study.

An amendment to this paper has been published and can be accessed via the original article.

Best MRI sequences for identifying axillary lymph node markers in patients with metastatic breast cancer: an inter-reader observational study.

BACKGROUND: We assessed confidence in visualization of markers within metastatic axillary lymph nodes (LNs) on magnetic resonance imaging (MRI), which were placed post-ultrasound (US)-guided biopsy. METHODS: A retrospective review was performed on 55 MRI cases between May 2015 and October 2017. Twenty-two MRIs were performed before neoadjuvant therapy, and 33 MRIs were after its initiation. There were 34/55 HydroMARK®, 10/55 Tumark®, and 11/55 other marker types. Time interval between marker placement and MRI examination was 103 ± 81 days (mean ± standard deviation). Three readers with 1-30 years of experience independently assessed four axial sequences: unenhanced fat-suppressed three-dimensional T1-weighted spoiled gradient-recalled (SPGR), first contrast-enhanced fat-suppressed SPGR, T2-weighted water-only fast spin-echo (T2-WO), and T2-weighted fat-only fast-spin-echo (T2-FO). RESULTS: Markers were 5.2× more likely to be visualized on T2-WO than on unenhanced images (p = < 0.001), and 3.3× more likely to be visualized on contrast-enhanced than on unenhanced sequences (p = 0.009). HydroMARK markers demonstrated a 3× more likelihood of being visualized than Tumark (p = 0.003). Markers were 8.4× more likely to be visualized within morphologically abnormal LNs (p < 0.001). After 250 days post-placement, confidence in marker brightness of HydroMARK markers on T2-WO images was less than 50% (p < 0.001). Inter-rater agreement was excellent for T2-WO and contrast-enhanced SPGR, good for unenhanced SPGR, and poor for T2-FO images. CONCLUSION: T2-WO and contrast-enhanced images should be used for marker identification. HydroMARK was the best visualized marker. Markers were easier to identify when placed in abnormal LNs. The visibility of HydroMARK markers was reduced with time.

Imaging Features and Treatment Options for Breast Pseudoaneurysms After Biopsy: A Case-Based Pictorial Review.

Pseudoaneurysm (PSA) formation is a potential complication of breast biopsies. Ultrasound is the most common imaging modality used for evaluation and treatment of a PSA. Color Doppler images show a cystic structure with swirling flow inside in a "to-and-fro" pattern. Treatment options for PSA include observation, ultrasound-guided focused compression, thrombin injection, open surgical repair, and percutaneous embolization. The risks and benefits of these treatment options will be discussed in the following cases.

A Clinical Approach to Diffusion-Weighted Magnetic Resonance Imaging in Evaluating Chest Wall Invasion of Breast Tumors.

OBJECTIVE: The purpose of this study is to evaluate diffusion weighted magnetic rsonance imaging (MRI) acquisitions in delineating posterior extent of breast tumors and in predicting chest wall invasion prior to treatment. To our knowledge, there has not been any literature specifically evaluating the utility of diffusion-weighted acquisitions in chest wall invasion of breast tumors. MATERIALS AND METHODS: A retrospective review of our breast imaging database for keywords "chest wall invasion" and "breast MRI" was performed over the last 14 years. Diffusion sequences, T1 sequences (pre and post contrast), and T2 sequences were evaluated. Apparent diffusion coefficient (ADC) values in tumor and chest wall were assessed. Imaging findings were correlated with surgical pathology. RESULTS: 23 patients met inclusion criteria. All 23 had loss of fat plane on T2 sequences. 22/23 had loss of fat plane on postcontrast T1 sequences. Pectoralis muscle enhancement was present in 19/23 (83%) tumors and chest wall enhancement was present 9/23 (39%) tumors. Qualitative restricted diffusion within the pectoralis muscle was present in 18/23 (71%) tumors and in the chest wall was present in 8/23 (35%) tumors. Mean ADC values were 1.15 s/mm2 in the tumor and 1.29 s/mm2 in the chest wall. Sensitivity, specificity, positive predictive value and negative predictive value were 100%, 36%, 63%, and 100% for chest wall enhancement respectively and 69%, 36%, 61%, and 80% for chest wall diffusion-weighted imaging restriction respectively. CONCLUSION: Diffusion weighted sequences can be helpful in characterizing chest wall invasion of breast tumors.

Imaging findings of mammary and systemic silicone deposition secondary to breast implants.

In patients with silicone breast implants, implant rupture can occur, which can be intra- or extracapsular. Following implant rupture, silicone can travel through the lymphatic system into regional and distant lymph nodes. The purpose of this pictorial essay is to present findings of silicone implant rupture with intramammary and systemic silicone deposition as seen on dual energy CT, ultrasound, mammogram, PET/CT and MRI. We include imaging findings of silicone deposition in the breast in cases of intra- and extracapsular rupture. We also present silicone deposition in mediastinal, axillary, and internal mammary lymph nodes, as well as in the liver and spleen. To our knowledge, deposition of silicone in the liver and spleen has not been previously demonstrated on cross-sectional imaging. While all imaging modalities were able to detect silicone in the spleen, ultrasound appeared to be more sensitive than dual energy CT or MRI for detection of silicone deposition in the liver.

Extra-adrenal pheochromocytoma at the organ of Zuckerkandl: a case report and literature review.

Pheochromocytomas and paragangliomas are tumors that occur in characteristic locations and are commonly detected on imaging studies. A correct diagnosis is important because of differences in associated neoplasms, risk for malignancy, and need for genetic testing. In addition, associated complications, including death, can be avoided if appropriately recognized and treated. Here, we report a rare case of an extra-adrenal paraganglioma of the organ of Zuckerkandl.