[Retrospective validation of a model to predict the outcome of pregnancies of unknown location]. / Évaluation rétrospective d'un algorithme d'aide à la décision concernant les grossesses de localisation indéterminée.

OBJECTIVE: The prediction model M6 classifies pregnancy of unknown location (PUL) into a low-risk or a high-risk group in developing ectopic pregnancy (EP). The aim of this study was to validate the two-step M6 model's ability to classify PUL in French women. MATERIAL AND METHODS: All women with a diagnosis of PUL over a year were included in this single center retrospective study. Patients with a diagnosis of EP at the first consultation of with incomplete data were excluded. For each patient, the M6 model calculator was used to classified them into "high risk of EP" and "low risk of EP" group. The reference standard was the final diagnostic: failed PUL (FPUL), intrauterine pregnancy (IUP) of EP. The statistical measures of the test's performance were calculated. RESULTS: Over the period, 255 women's consulted for a PUL, 197 has been included in the study. Final diagnosis were: 94 FPUL (94/197; 47.7%), 74 IUP (74/197; 37.6%) et 29 EP (29/197; 14.7%). The first step of the M6 model classified 16 women in the FPUL group of which 15 (15/16; 93.7%) correctly. The second step of the M6 model classified 181 women: 90 (90/181; 49.7%) in the "high risk of EP" group of which 63 (63/90; 70%) were FPUL/IUP and 27 (27/90; 30%) were EP. 91 (91/181; 50.3%) was classified in the "low risk of EP" group of which 90 (90/91; 98.9%) were FPUL/IUP and 1 (1/91; 1.1%) were EP. EP were correctly classified with sensitivity of 96.4%, negative predictive value of 98.9%, specificity of 58.8% and positive predictive value of 30.0%. CONCLUSIONS: The prediction model of PUL M6 classified EP in "high risk of EP group" with a sensitivity of 96.4%. It classified 50.3% of PUL in a "low risk of EP" group with a negative predictive value of 98.9%.

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.

Negative association of antibiotics on clinical activity of immune checkpoint inhibitors in patients with advanced renal cell and non-small-cell lung cancer.

Background: The composition of gut microbiota affects antitumor immune responses, preclinical and clinical outcome following immune checkpoint inhibitors (ICI) in cancer. Antibiotics (ATB) alter gut microbiota diversity and composition leading to dysbiosis, which may affect effectiveness of ICI. Patients and methods: We examined patients with advanced renal cell carcinoma (RCC) and non-small-cell lung cancer (NSCLC) treated with anti-programmed cell death ligand-1 mAb monotherapy or combination at two academic institutions. Those receiving ATB within 30 days of beginning ICI were compared with those who did not. Objective response, progression-free survival (PFS) determined by RECIST1.1 and overall survival (OS) were assessed. Results: Sixteen of 121 (13%) RCC patients and 48 of 239 (20%) NSCLC patients received ATB. The most common ATB were ß-lactam or quinolones for pneumonia or urinary tract infections. In RCC patients, ATB compared with no ATB was associated with increased risk of primary progressive disease (PD) (75% versus 22%, P < 0.01), shorter PFS [median 1.9 versus 7.4 months, hazard ratio (HR) 3.1, 95% confidence interval (CI) 1.4-6.9, P < 0.01], and shorter OS (median 17.3 versus 30.6 months, HR 3.5, 95% CI 1.1-10.8, P = 0.03). In NSCLC patients, ATB was associated with similar rates of primary PD (52% versus 43%, P = 0.26) but decreased PFS (median 1.9 versus 3.8 months, HR 1.5, 95% CI 1.0-2.2, P = 0.03) and OS (median 7.9 versus 24.6 months, HR 4.4, 95% CI 2.6-7.7, P < 0.01). In multivariate analyses, the impact of ATB remained significant for PFS in RCC and for OS in NSCLC. Conclusion: ATB were associated with reduced clinical benefit from ICI in RCC and NSCLC. Modulatation of ATB-related dysbiosis and gut microbiota composition may be a strategy to improve clinical outcomes with ICI.

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.