No abstract

We assessed the feasibility of a data-driven imaging biomarker based on weakly supervised learning (DIB; an imaging biomarker derived from large-scale medical image data with deep learning technology) in mammography (DIB-MG). A total of 29,107 digital mammograms from five institutions (4,339 cancer cases and 24,768 normal cases) were included. After matching patients’ age, breast density, and equipment, 1,238 and 1,238 cases were chosen as validation and test sets, respectively, and the remainder were used for training. The core algorithm of DIB-MG is a deep convolutional neural network; a deep learning algorithm specialized for images. Each sample (case) is an exam composed of 4-view images (RCC, RMLO, LCC, and LMLO). For each case in a training set, the cancer probability inferred from DIB-MG is compared with the per-case ground-truth label. Then the model parameters in DIB-MG are updated based on the error between the prediction and the ground-truth. At the operating point (threshold) of 0.5, sensitivity was 75.6% and 76.1% when specificity was 90.2% and 88.5%, and AUC was 0.903 and 0.906 for the validation and test sets, respectively. This research showed the potential of DIB-MG as a screening tool for breast cancer.

PurposeAlthough the incidence of thyroid cancer in Korea has rapidly increased over the past decade, few studies have investigated its risk factors. This study examined the risk factors for thyroid cancer in Korean adults.Materials and MethodsThe study design was a hospital-based case-control study. Between August 2002 and December 2011, a total of 802 thyroid cancer cases out of 34,211 patients screened from the Cancer Screenee. Cohort of the National Cancer Center in South Korea were included in the analysis. A total of 802 control cases were selected from the same cohort, and matched individually (1:1) by age (±2 years) and area of residence for control group 1 and additionally by sex for control group 2.ResultsMultivariate conditional logistic regression analysis using the control group 1 showed that females and those with a family history of thyroid cancer had an increased risk of thyroid cancer, whereas ever-smokers and those with a higher monthly household income had a decreased risk of thyroid cancer. On the other hand, the analysis using control group 2 showed that a family history of cancer and alcohol consumption were associated with a decreased risk of thyroid cancer, whereas higher body mass index (BMI) and family history of thyroid cancer were associated with an increased risk of thyroid cancer.ConclusionThese findings suggest that females, those with a family history of thyroid cancer, those with a higher BMI, non-smokers, non-drinkers, and those with a lower monthly household income have an increased risk of developing thyroid cancer.

Helicobacter pylori infection is an independent risk factor for colonic adenomas, especially in cases of advanced or multiple adenomas, but not for rectal adenomas.

This study demonstrated that breast cancer patients with higher skeletal muscle volume showed more favorable prognosis.