Deep Learning for Breast Cancer Diagnosis via MRI

Deep Learning for Breast Cancer Diagnosis via MRI

Magnetic resonance imaging (MRI) is a sensitive modality for detection of breast cancer; yet, as its use in screening is expanded from high-risk patients to intermediate- and average-risk individuals, positive predictive value deteriorates, leading to unnecessary biopsies and follow-up. To improve the overall accuracy of breast cancer diagnosis and allow for personalization of patient management, Witowski et al., reporting in Science Translational Medicine(1), propose an artificial intelligence-based solution. A system of deep neural networks was trained to output the probability of malignancy given the MRI sequences of a patient’s breast. The deep learning system performed equivalently to board-certified breast radiologists, generalized well to different patient populations in three external test sets, and was unbiased with respect to patient race. Importantly, the model predictions could serve as an aid for downgrading certain breast lesions from BI-RADS 4 to BI-RADS 3, enabling patients with lower risk of malignancy to opt of unnecessary biopsies. The results of the study underscore the value of...
Read More
Hormonal Contraceptive Use and Risk of Sexually Transmitted Infection

Hormonal Contraceptive Use and Risk of Sexually Transmitted Infection

The global incidence of sexually transmitted infections (STIs) is high, which has adverse effects on sexual and reproductive health outcomes. Given the widespread use of hormonal contraceptives (HC), it is important to consider their potential etiological association with acquisition of STIs. In a systematic review and meta-analysis recently published in Scientific Reports(1), Akter et al. examined associations between HC use (progesterone-only, combined estrogen-progesterone, or unspecified) and prevalence, incidence, or recurrence of STIs, compared with a control group of non-users of HC. A positive association with HC use was observed for risk of chlamydia trachomatis and herpes simplex virus type 2, in contrast to a negative association for risk of trichomoniasis and bacterial vaginosis. Importantly, only around half of all associations included in the meta-analysis were adjusted for condom use. Furthermore, while a plausible biological explanation based on the interaction between pathogen, host immune response, and vaginal microbiome can be proposed for these findings, the effects of differential sexual behavior, testing,...
Read More
A New Mechanism of Non-Hormonal Contraception using Mucoadhesive Polymers

A New Mechanism of Non-Hormonal Contraception using Mucoadhesive Polymers

Effective family planning is critical for women’s empowerment and improvement in child and maternal health, yet nearly half of the world’s pregnancies are unintended(1), representing a clear unmet need for contraception. Hormonal contraceptive regimens offer high efficacy but may induce a systemic side effect profile that reduces compliance. New research into contraceptive development has stagnated since the 1980s, due to the exit of the U.S. pharmaceutical industry from the arena. Consequently, existing pericoital non-hormonal contraceptives, such as spermicides and gels, are unsatisfactory, suffering from high failure rates in typical use as well as high discontinuation rates, which partially stem from vaginal irritation and discomfort. To solve these issues, Schimpf and colleagues, reporting in Science Translational Medicine(2), proposed a novel mechanism that could represent the next generation in contraceptive design. They developed a formulation of chitosan mucoadhesive polymers that can be topically applied to physically reinforce the cervical mucus barrier against sperm penetration. Their vaginal gel formulation decreased average uterine sperm...
Read More