Direct identification of ALK and ROS1 fusions in non-small cell lung cancer from hematoxylin and eosin-stained slides using deep learning algorithms.

Anaplastic lymphoma kinase (ALK) and ROS oncogene 1 (ROS1) gene fusions are well-established key players in non-small cell lung cancer (NSCLC). Although their frequency is relatively low, their detection is important for patient care and guides therapeutic decisions. The accepted methods used for their detection are immunohistochemistry (IHC) and fluorescence in situ hybridization (FISH) assay, as well as DNA and RNA-based sequencing methodologies. These assays are expensive, time-consuming, and require technical expertise and specialized equipment as well as biological specimens that are not always available. Here we present an alternative detection method using a computer vision deep learning approach. An advanced convolutional neural network (CNN) was used to generate classifier models to detect ALK and ROS1-fusions directly from scanned hematoxylin and eosin (H&E) whole slide images prepared from NSCLC tumors of patients. A two-step training approach was applied, with an initial unsupervised training step performed on a pan-cancer sample cohort followed by a semi-supervised fine-tuning step, which supported the development of a classifier with performances equal to those accepted for diagnostic tests. Validation of the ALK/ROS1 classifier on a cohort of 72 lung cancer cases who underwent ALK and ROS1-fusion testing at the pathology department at Sheba Medical Center displayed sensitivities of 100% for both genes (six ALK-positive and two ROS1-positive cases) and specificities of 100% and 98.6% respectively for ALK and ROS1, with only one false-positive result for ROS1-alteration. These results demonstrate the potential advantages that machine learning solutions may have in the molecular pathology domain, by allowing fast, standardized, accurate, and robust biomarker detection overcoming many limitations encountered when using current techniques. The integration of such novel solutions into the routine pathology workflow can support and improve the current clinical pipeline.

Nurse-performed ultrasound assessment of gastric residual volume and enteral nasogastric tube placement in the general intensive care unit.

OBJECTIVE: Ultrasonography is an essential imaging modality in the critical care population and has been increasingly utilized to check gastric residual volume . Various studies have shown that intensive care unit nurses untrained in ultrasound can easily be trained in its accurate interpretation. We prospectively analyzed nurse-performed repeated measurements of gastric residual volume and nasogastric tube positioning via an ultrasound technique in the intensive care unit. DESIGN: This was a single-center, cross-sectional prospective study. Four intensive care unit nurses, evenly divided into two groups (teams A and B), underwent four hours of formal ultrasound training by three critical care staff physicians. The trained nurses provided bedside ultrasound assessments of gastric residual volume and nasogastric tube positioning which were compared to a standard protocol of syringe aspiration. RESULTS: Ninety patients were recruited to the study. Four measurements per patient were performed, for a total of 360 assessments. The ultrasound gastric residual volume assessments were correlated with the syringe aspiration protocol and demonstrated high Intraclass Correlation Coefficient rates of 0.814 (0.61-0.92) for team A and 0.85 (0.58-0.91) for team B. Nasogastric tube placement was successfully and independently verified by ultrasound in most of the critically ill patients (78% of team A and 70% of team B). The comparative ultrasound assessments of tube positioning demonstrated good correlation of 0.733 (0.51-0.88) between each team's two independent observers. CONCLUSION: Our study demonstrated a strong correlation between US utilization for assessment of gastric residual volume and nasogastric tube positioning and standard protocol methods, suggesting it is a safe, simple and effective practice for intensive care unit nurses.