Generating retinal flow maps from structural optical coherence tomography with artificial intelligence.

Despite advances in artificial intelligence (AI), its application in medical imaging has been burdened and limited by expert-generated labels. We used images from optical coherence tomography angiography (OCTA), a relatively new imaging modality that measures retinal blood flow, to train an AI algorithm to generate flow maps from standard optical coherence tomography (OCT) images, exceeding the ability and bypassing the need for expert labeling. Deep learning was able to infer flow from single structural OCT images with similar fidelity to OCTA and significantly better than expert clinicians (P < 0.00001). Our model allows generating flow maps from large volumes of previously collected OCT data in existing clinical trials and clinical practice. This finding demonstrates a novel application of AI to medical imaging, whereby subtle regularities between different modalities are used to image the same body part and AI is used to generate detailed inferences of tissue function from structure imaging.

Understanding the influence of patient demographics on disease severity, treatment strategy, and survival outcomes in merkel cell carcinoma: a surveillance, epidemiology, and end-results study.

OBJECTIVE: To identify trends in patient presentation and outcomes data that may guide the development of clinical algorithms on Merkel Cell Carcinoma (MCC). METHODS: We performed a retrospective cohort study searching in the National Cancer Institute's SEER registry for documented MCC cases from 1986-2013. No exclusion criteria were applied. We hereby identified 7,831 original MCC entries. Demographics, staging, and socioeconomic characteristics were identified and treatment modality likelihoods and survival data were calculated via logistic regression and Kaplan-Meier statistical modeling. RESULTS: Concerning tumor localization, 44.5% (n= 3,485) were located on the head and neck, and 47.8% were located on the trunk and extremities (n= 3,742). Male and younger patients are more likely to receive radiation than surgery with no differences seen among patient race. Caucasians and "Other" races both showed higher overall survival than African American patients. States with higher median household income levels demonstrated survival advantage. Income quartiles yielded no differences in surgical or radiotherapy interventions. Moreover, patients who forego radiotherapy had a poorer overall survival. LIMITATIONS: Generalizability of SEER data, potential intrinsic coding inconsistencies, and limited information on patient comorbidities, sentinel lymph node and surgical margin status are major limitations. There is no information regarding medical intervention such as systemic chemotherapy or immunotherapy. Recoding efforts are inconclusive regarding variables such as tumor infiltrating lymphocytes, mutations, or immunosuppression status, which are well-documented for other cancers within the database. CONCLUSION: MCC lesions of the head and neck region, lower income quartiles, and African American race are associated with higher mortality. MCC patients have a median household income that is significantly higher than national values with no significant difference in subsequent treatment modalities (surgery or radiotherapy) based on socioeconomic markers. A lack of radiotherapy is associated with higher mortality.

Deep-learning based, automated segmentation of macular edema in optical coherence tomography.

Evaluation of clinical images is essential for diagnosis in many specialties. Therefore the development of computer vision algorithms to help analyze biomedical images will be important. In ophthalmology, optical coherence tomography (OCT) is critical for managing retinal conditions. We developed a convolutional neural network (CNN) that detects intraretinal fluid (IRF) on OCT in a manner indistinguishable from clinicians. Using 1,289 OCT images, the CNN segmented images with a 0.911 cross-validated Dice coefficient, compared with segmentations by experts. Additionally, the agreement between experts and between experts and CNN were similar. Our results reveal that CNN can be trained to perform automated segmentations of clinically relevant image features.

The impact of first responder turnout and curb-to-care intervals on survival from out-of-hospital cardiac arrest.

PURPOSE: Patients with out-of-hospital cardiac arrest (OHCA) more likely survive when emergency medical services (EMS) arrive quickly. We studied time response elements in OHCA with attention to EMS intervals before wheels roll and after wheels stop to understand their contribution to total time response and clinical outcome. METHODS: We analyzed EMS responses to OHCA from 2009-2014 in an urban, fire department based system. The Call-to-Care Interval, from call receipt to hands-on EMS care, was comprised of four time intervals: 1) call received to EMS notification (Activation), 2) EMS notification to vehicle wheels rolling (Turnout), 3) wheels rolling to arrival at scene (Travel), and 4) arrival at scene to hands-on EMS care (Curb-to-Care). We created a new time interval (On-Feet) comprised of the turnout and curb-to-care intervals. Using logistic regression, we evaluated whether the total EMS response interval and discrete time intervals were related to survival to discharge. RESULTS: Of 1,831 cases, 1,806 (98.6%) had complete information. The mean lengths for the intervals were 7.2±3.6min. (call-to-care), 58±39s (activation), 63±29s (turnout), 2.5±1.3min (travel), 2.4±1.6min (curb-to-care), and 3.5±1.7min (on-feet). After adjustment, "On Feet" interval was associated with OHCA survival (OR=0.91 [95% CI=0.83-1.00] for each additional minute). CONCLUSIONS: Turnout and curb-to-care intervals were half of the total response interval in our EMS system. Measurement should incorporate these two intervals to accurately characterize and possibly reduce the professional response interval.