Detection and characterization of MRI breast lesions using deep learning.

PURPOSE: The purpose of this study was to assess the potential of a deep learning model to discriminate between benign and malignant breast lesions using magnetic resonance imaging (MRI) and characterize different histological subtypes of breast lesions. MATERIALS AND METHODS: We developed a deep learning model that simultaneously learns to detect lesions and characterize them. We created a lesion-characterization model based on a single two-dimensional T1-weighted fat suppressed MR image obtained after intravenous administration of a gadolinium chelate selected by radiologists. The data included 335 MR images from 335 patients, representing 17 different histological subtypes of breast lesions grouped into four categories (mammary gland, benign lesions, invasive ductal carcinoma and other malignant lesions). Algorithm performance was evaluated on an independent test set of 168 MR images using weighted sums of the area under the curve (AUC) scores. RESULTS: We obtained a cross-validation score of 0.817 weighted average receiver operating characteristic (ROC)-AUC on the training set computed as the mean of three-shuffle three-fold cross-validation. Our model reached a weighted mean AUC of 0.816 on the independent challenge test set. CONCLUSION: This study shows good performance of a supervised-attention model with deep learning for breast MRI. This method should be validated on a larger and independent cohort.

An uncommon cause of dysuria solved by "boom-boom" radiotherapy.

BACKGROUND: Chronic lymphocytic leukaemia is a common disease affecting the hematopoietic organs. The disease remains classically indolent for years preceding a blast crisis. However, the disease can affect all parts of the body. We report here an unusual localization. CASE PRESENTATION: A 72-year-old man was followed for 2 years for an indolent chronic lymphocytic leukaemia while he presented a rapidly progressive dysuria. Prostate biopsies were performed concluding to a prostate involvement by the chronic lymphocytic leukaemia. In the absence of progression according to RAI staging system and Binet's classification, he was treated with local low-dose radiotherapy, twice 2 Gy, allowing for a rapid resolution of the symptoms. No systemic treatment was introduced, and 1 year after the completion of his treatment, he is still under watchful waiting strategy for his chronic lymphocytic leukaemia. CONCLUSION: Low-dose radiotherapy is an underused effective strategy in indolent lymphoma. In this case, urinary symptoms from a prostate involvement were relieved non-invasively at low cost.

Breast pain and imaging.

Breast pain is a common reason for consultation and a source of anxiety for patients. Cyclical breast pain can be distinguished from non-cyclical pain and breast pain with other symptoms. Many causes, usually benign are possible and the clinical enquiry and physical examination are essential to establish predisposing factors. Although imaging is not always needed for isolated breast pain, it is still useful for the diagnosis of specific causes such as tension cysts, giant adenofibromas or Mondor's thrombophlebitis. Ultrasound is the first line investigation before mammography, MRI or biopsy, which may be indicated for suspicious abnormalities. Some cancers may be associated with pain, which implies that radiologists and physicians should always take breast pain seriously.