US guidance should be considered for biopsy of peripheral lung and pleural lesions larger than 10 mm, because it is safer, faster, and possibly more accurate than CT guidance.

No abstract

Optical coherence tomography (OCT) images of the retina are a powerful tool for diagnosing and monitoring eye disease. However, they are plagued by speckle noise, which reduces image quality and reliability of assessment. This paper introduces a novel speckle reduction method inspired by the recent successes of deep learning in medical imaging. We present two versions of the network to reflect the needs and preferences of different end-users. Specifically, we train a convolution neural network to denoise cross-sections from OCT volumes of healthy eyes using either (1) mean-squared error, or (2) a generative adversarial network (GAN) with Wasserstein distance and perceptual similarity. We then interrogate the success of both methods with extensive quantitative and qualitative metrics on cross-sections from both healthy and glaucomatous eyes. The results show that the former approach provides state-of-the-art improvement in quantitative metrics such as PSNR and SSIM, and aids layer segmentation. However, the latter approach, which puts more weight on visual perception, outperformed for qualitative comparisons based on accuracy, clarity, and personal preference. Overall, our results demonstrate the effectiveness and efficiency of a deep learning approach to denoising OCT images, while maintaining subtle details in the images.

OBJECTIVE Prior research indicates CT colonography (CTC) would be a cost-effective colorectal cancer (CRC) screening test if widespread availability were to increase overall CRC screening adherence rates. The primary aims of this multicenter study were to evaluate patient experience and satisfaction with CTC screening and compare preference against screening colonoscopy. MATERIALS AND METHODS A 12-question survey instrument measuring pretest choice, experience, and satisfaction was given to a consecutive cohort of adults undergoing CTC screening in three disparate screening settings: university academic center, military medical center, and community practice. The study cohort was composed of individuals voluntarily participating in clinical CTC screening programs. RESULTS A total of 1417 patients responded to the survey. The top reasons for choosing CTC for screening included “noninvasiveness” (68.0%), “avoidance of sedation/anesthesia” (63.1%), “ability to drive after the test” (49.2%), “avoidance of optical colonoscopy risks” (46.9%), and “identifying abnormalities outside the colon” (43.3%). Only 7.2% of patients reported pain during the CTC examination and only 2.5% reported greater than moderate discomfort. Of 441 patients who had experienced both CTC and optical colonoscopy, 77.1% preferred CTC and 13.8% preferred optical colonoscopy. Of all patients, 29.6% indicated that they may not have undergone optical colonoscopy screening if CTC were not available. Of all patients, 92.9% labeled their overall experience with CTC as “excellent” or “good,” and 93.0% indicated they would choose CTC for their next screening. CONCLUSION Respondents reported a very high satisfaction level with CTC, and those who had experienced both modalities indicated a preference for CTC over optical colonoscopy. These results suggest that CTC has the potential to increase adherence to CRC screening guidelines if widely available.