Quantifying lung fissure integrity using a three-dimensional patch-based convolutional neural network on CT images for emphysema treatment planning.

Purpose: Evaluation of lung fissure integrity is required to determine whether emphysema patients have complete fissures and are candidates for endobronchial valve (EBV) therapy. We propose a deep learning (DL) approach to segment fissures using a three-dimensional patch-based convolutional neural network (CNN) and quantitatively assess fissure integrity on CT to evaluate it in subjects with severe emphysema. Approach: From an anonymized image database of patients with severe emphysema, 129 CT scans were used. Lung lobe segmentations were performed to identify lobar regions, and the boundaries among these regions were used to construct approximate interlobar regions of interest (ROIs). The interlobar ROIs were annotated by expert image analysts to identify voxels where the fissure was present and create a reference ROI that excluded non-fissure voxels (where the fissure is incomplete). A CNN configured by nnU-Net was trained using 86 CT scans and their corresponding reference ROIs to segment the ROIs of left oblique fissure (LOF), right oblique fissure (ROF), and right horizontal fissure (RHF). For an independent test set of 43 cases, fissure integrity was quantified by mapping the segmented fissure ROI along the interlobar ROI. A fissure integrity score (FIS) was then calculated as the percentage of labeled fissure voxels divided by total voxels in the interlobar ROI. Predicted FIS (p-FIS) was quantified from the CNN output, and statistical analyses were performed comparing p-FIS and reference FIS (r-FIS). Results: The absolute percent error mean (±SD) between r-FIS and p-FIS for the test set was 4.0% (±4.1%), 6.0% (±9.3%), and 12.2% (±12.5%) for the LOF, ROF, and RHF, respectively. Conclusions: A DL approach was developed to segment lung fissures on CT images and accurately quantify FIS. It has potential to assist in the identification of emphysema patients who would benefit from EBV treatment.

Automated Endotracheal Tube Placement Check Using Semantically Embedded Deep Neural Networks.

RATIONALE AND OBJECTIVES: To develop artificial intelligence (AI) system that assists in checking endotracheal tube (ETT) placement on chest X-rays (CXRs) and evaluate whether it can move into clinical validation as a quality improvement tool. MATERIALS AND METHODS: A retrospective data set including 2000 de-identified images from intensive care unit patients was split into 1488 for training and 512 for testing. AI was developed to automatically identify the ETT, trachea, and carina using semantically embedded neural networks that combine a declarative knowledge base with deep neural networks. To check the ETT tip placement, a "safe zone" was computed as the region inside the trachea and 3-7 cm above the carina. Two AI outputs were evaluated: (1) ETT overlay, (2) ETT misplacement alert messages. Clinically relevant performance metrics were compared against prespecified thresholds of >85% overlay accuracy and positive predictive value (PPV) > 30% and negative predictive value NPV > 95% for alerts to move into clinical validation. RESULTS: An ETT was present in 285 of 512 test cases. The AI detected 95% (271/285) of ETTs, 233 (86%) of these with accurate tip localization. The system (correctly) did not generate an ETT overlay in 221/227 CXRs where the tube was absent for an overall overlay accuracy of 89% (454/512). The alert messages indicating that either the ETT was misplaced or not detected had a PPV of 83% (265/320) and NPV of 98% (188/192). CONCLUSION: The chest X-ray AI met prespecified performance thresholds to move into clinical validation.

Playing-Side Analytics in Team Sports: Multiple Directions, Opportunities, and Challenges.

This paper describes developments in the player-side analytics in major team sports. We take a decision-making lens to the role of analytics in player decisions by general managers and coaches. We outline key accelerators and inhibitors to the wider adoption and acceptance of data analytics playing a greater role in the decisions of clubs.

Bespoke human hypertrophic chondrocytic cell lines provide the osteoinductive signals required for vascularized bone formation.

Hypertrophic cartilage provides the morphological and biochemical template for orchestrating bone growth. To produce a bone-inductive material such as hypertrophic cartilage for clinical use, we have conditionally immortalized hypertrophic chondrocytic cells from human femur and expanded them in vitro through more than 145 divisions. The clonal cell lines generated by this process consistently express signals that induce both rat and human marrow cells to differentiate in vitro into osteoblastic cells. Further, implantation of the cell-free extracellular matrix from the immortalized chondrocytic cells causes vascularized bone to form in vivo in bony defects, but not in ectopic sites such as skeletal muscle. This study shows that molecular techniques can be used to generate bespoke human cell lines for bone tissue engineering. It also demonstrates that matrix material generated from human immortalized hypertrophic chondrocytic cells may provide an abundant, efficacious, and safer alternative to bone autograft--the currently preferred material for fracture repair.

Serum from postmenopausal women directs differentiation of human clonal osteoprogenitor cells from an osteoblastic toward an adipocytic phenotype.

A consistent observation in osteoporosis is bone volume reduction accompanied by increased marrow adipose tissue. No single cause linking the two phenomena has yet been identified. In a human progenitor cell clone (hOP 7) derived from bone marrow, however, we have demonstrated that rabbit serum can direct differentiation away from an osteoblast lineage to one of adipocytes. We now report on whether human serum has a similar effect. Serum was collected from 10 pre- and 10 postmenopausal women and from the 10 postmenopausal women before and following 6-week hormone replacement therapy (HRT). hOP 7 cells were cultured with the various sera, and after 7-14 days adipocytogenesis was determined by oil red O staining and lipoprotein lipase (LPL) and glycerol 3-phosphate dehydrogenase (G3PDH) expression. Incubation with 10% premenopausal serum led to labeling of 10.9% of cells (P < 0.05) with oil red O, whereas application of 10% postmenopausal serum led to a much larger effect, 43.5% labeling (P < 0.001 with respect to premenopausal serum). Oil red O positivity was accompanied by loss of type I collagen expression and increased LPL and G3PDH expression. HRT did not reverse the adipocytogenic effect of postmenopausal serum. In conclusion, serum from postmenopausal women contains factors that steer hOP 7 bone progenitor cells toward an adipocytic phenotype, irrespective of HRT. The study suggests a role for serum factors in the development of fatty marrow in postmenopausal osteoporosis.

Appendiceal carcinoma masquerading as recurrent urinary tract infections: case report and review of literature.

We report on a female patient who presented with recurrent urinary tract infections. The investigations revealed an adenocarcinoma of the appendix fistulating into the bladder and causing irritative symptoms. After right hemicolectomy and partial cystectomy, she was well at 3 months without any need for adjuvant therapy. This unusual situation reminds us that the finding of bladder adenocarcinoma is rare, and it would be prudent to examine the lower gastrointestinal tract thoroughly to look for a bowel source, before recommending any ablative surgery.

Molecular adhesion development in a neural cell monolayer forming in an ultrasound trap.

A 2-dimensional aggregate of C6 neural cells was formed rapidly (within 30 s) in suspension in a recently developed 1.5 MHz ultrasound standing wave trap. A typical 1 mm diameter aggregate contained about 3,500 cells. Spreading of membrane occurred between the aggregated cells. The rate of spreading of the tangentially developing intercellular contact area was 0.19 microm/min. The form of the suspended aggregate changed from one of a hexagonal arrangement of cells to one of a cell-monolayer-like continuous sheet of mostly quadrilateral and pentagonal cells as in a cell monolayer on a solid substratum. A range of fluorescent indicators showed that the >99% viability of the cells did not change during 1 h exposures; therefore cell viability was not compromised during the monolayer development. The average integral intensities from stained actin filaments at the spreading cell-cell interfaces after 1, 8 and 30 min were 14, 25 and 46 microm(2) respectively. The cells in this work progressed from physical aggregation, through molecular adhesion, to displaying the intracellular consequences of receptor interactions. The ability to form mechanically strong confluent monolayer structures that can be monitored in situ or harvested from the trap provides a technique with general potential for monitoring the synchronous development of cell responses to receptor-triggered adhesion.

On the origin of humoral medicine in Latin America

It supports the hypothesis that humoral medicine is a simplified folk variant of classical Greek and Persian humoral pathology, by tracing the well-documented history of classical medicine from Greece and Persia to Latin America, where it was disseminated via formal medical education, hospitals and missionary orders, home medical guides and pharmacies.(AU)