Weakly Supervised Deep Learning Approach to Breast MRI Assessment.

RATIONALE AND OBJECTIVES: To evaluate a weakly supervised deep learning approach to breast Magnetic Resonance Imaging (MRI) assessment without pixel level segmentation in order to improve the specificity of breast MRI lesion classification. MATERIALS AND METHODS: In this IRB approved study, the dataset consisted of 278,685 image slices from 438 patients. The weakly supervised network was based on the Resnet-101 architecture. Training was implemented using the Adam optimizer and a final SoftMax score threshold of 0.5 was used for two class classification (malignant or benign). 278,685 image slices were combined into 92,895 3-channel images. 79,871 (85%) images were used for training and validation while 13,024 (15%) images were separated for testing. Of the testing dataset, 11,498 (88%) were benign and 1531 (12%) were malignant. Model performance was assessed. RESULTS: The weakly supervised network achieved an AUC of 0.92 (SD ± 0.03) in distinguishing malignant from benign images. The model had an accuracy of 94.2% (SD ± 3.4) with a sensitivity and specificity of 74.4% (SD ± 8.5) and 95.3% (SD ± 3.3) respectively. CONCLUSION: It is feasible to use a weakly supervised deep learning approach to assess breast MRI images without the need for pixel-by-pixel segmentation yielding a high degree of specificity in lesion classification.

Successful cryoablation of breast cancer.

The current standard of care for screen-detected breast cancers is surgical excision. Cryotherapy is a promising non- surgical alternative treatment for these cancers and is performed under local anesthesia as an outpatient, circumventing the risks that come with an operation. New research also shows promising results for the treatment of breast cancer when cryotherapy is combined with immune modulation as it may help prevent tumor recurrence. We herein report a case of breast cancer treated successfully with cryoablation. A brief literature review of cryoablation as a treatment for breast cancer is added.

Rare Popliteal Venous Aneurysm: A Case Report and Review of the Literature.

Popliteal venous aneurysms (PVAs) are rare and may represent a cause of recurrent pulmonary embolism. We present a case of PVA identified on ultrasound for deep venous thrombosis in a 27-year-old female with popliteal fossa pain. We discuss our recommendations for treatment and present a review of the previously reported cases.

Phyllodes tumor: review of key imaging characteristics.

Phyllodes tumor of the breast is rare and often resembles the more commonly seen fibroadenoma at imaging and histologically. As core biopsy cannot always distinguish the two, assessing radiologic-pathologic concordance is essential to guide appropriate clinical management. We review the imaging characteristics of phyllodes tumor at mammography, ultrasound, and MRI to help the interpreting radiologist be aware of key imaging features that should alert him to the possibility of a phyllodes tumor even if not verified by initial core biopsy.