Proportion Of Tissue Types Research Articles

Predicting Time-to-Healing from a Digital Wound Image: A Hybrid Neural Network and Decision Tree Approach Improves Performance

Despite the societal burden of chronic wounds and despite advances in image processing, automated image-based prediction of wound prognosis is not yet in routine clinical practice. While specific tissue types are known to be positive or negative prognostic indicators, image-based wound healing prediction systems that have been demonstrated to date do not (1) use information about the proportions of tissue types within the wound and (2) predict time-to-healing (most predict categorical clinical labels). In this work, we analyzed a unique dataset of time-series images of healing wounds from a controlled study in dogs, as well as human wound images that are annotated for the tissue type composition. In the context of a hybrid-learning approach (neural network segmentation and decision tree regression) for the image-based prediction of time-to-healing, we tested whether explicitly incorporating tissue type-derived features into the model would improve the accuracy for time-to-healing prediction versus not including such features. We tested four deep convolutional encoder–decoder neural network models for wound image segmentation and identified, in the context of both original wound images and an augmented wound image-set, that a SegNet-type network trained on an augmented image set has best segmentation performance. Furthermore, using three different regression algorithms, we evaluated models for predicting wound time-to-healing using features extracted from the four best-performing segmentation models. We found that XGBoost regression using features that are (i) extracted from a SegNet-type network and (ii) reduced using principal components analysis performed the best for time-to-healing prediction. We demonstrated that a neural network model can classify the regions of a wound image as one of four tissue types, and demonstrated that adding features derived from the superpixel classifier improves the performance for healing-time prediction.

Spatial variations in prostate tissue histology as measured by a tactile resonance sensor

In recent years, tactile sensors based on piezoelectric resonance sensor technology have been used for medical diagnosis where the sensor's stiffness-measuring properties can reflect tissue pathology. The change in the frequency of the resonating system and the change in force when contact is made with tissue are used as a stiffness parameter. Earlier stiffness measurements of prostate tissue in vitro demonstrate variations related to tissue composition. In this study, measured stiffness from two human prostate specimens was compared to histological composition of prostate tissue below and around the measurement points. Tissue stiffness was measured with the resonance sensor system. Tissue composition was measured at four different depths in the tissue specimen using a microscopic-image-based morphometrical method. With this method, the proportion of tissue types was determined at the points of intersections in a circular grid on the images representing each measurement point. Numerical values were used for weighting the tissue proportions at different depths in the tissue specimen. For an impression depth of 1.0 mm, the sensing depth in this study was estimated to be 3.5–5.5 mm. Stiffness variations due to horizontal tissue variations were investigated by studying the dependence of the size of the circular grid area relative to the contact area of the sensor tip. The sensing area (grid radius) was estimated to be larger than the contact area (contact radius) between the sensor tip and the tissue. Thus, the sensor tip registers spatial variations in prostate tissue histology, both directly below and lateral to the tip itself. These findings indicate that tumours around the sensor tip could be detected, which in turn supports the idea of a future resonance-sensor-based clinical device for detecting tumours and for guiding biopsies.

A quantitative study of the equine soft palate using histomorphometry

Dorsal displacement of the soft palate is a common cause of upper airway obstruction in racehorses and is of unknown aetiology. To determine whether the palate may displace for structural reasons, knowledge of the normal soft palate is required. The present study aimed to describe, qualitatively and quantitatively, the structure of the normal equine soft palate using histomorphometry. In soft palates from 12 Thoroughbreds, glandular tissue predominated (ca. 40% of total area), located mainly in the rostral and ventral regions. Rostrally, muscles attached to a tendinous aponeurosis located dorsal to the glandular tissue. Muscle was most abundant in the dorsal mid region and decreased caudally. The oral mucosa consisted of a non-keratinised stratified squamous epithelium whereas the nasopharyngeal mucosa was pseudostratified, columnar and ciliated. Elastin fibres were observed in the nasopharyngeal submucosa, becoming more prevalent caudally. The palates were bilaterally symmetrical although the proportion of tissue types varied considerably between individuals.

A histopathological comparison of the uvula between snorers and non-snorers

Snoring is a very common problem but there are few publications on the histological findings of the soft palate/uvula and these lack consistency. The relative proportions of tissue types in the base of the uvula removed from 17 adults who underwent uvulopalatopharyngoplasty for heavy snoring were therefore compared with 14 cadaveric specimens. The mean percentage of muscle from the snoring group was 12.1% compared with 7.2% in the control group (P < 0.05). The percentage of fibrous tissue was greater in the cadavers (52.8% vs 45.5% in the snorers, P < 0.05). The percentage of muscle was inversely related to the percentage of fibrous tissue in the snoring group (P < 0.02). We hypothesize that these changes are a consequence of the repetitive forces on the soft palate during snoring rather than being related to the pathogenesis of snoring.

Quantitative morphology and water distribution of bronchial biopsy samples.

An approach to the study of the pharmacokinetics of drugs in the lung is to measure their concentrations in bronchial biopsy specimens. The main criticism of this technique is that bronchial biopsy specimens consist of more than one tissue type and that drugs are often not distributed evenly. The morphology of bronchial biopsy specimens and the distribution of water between the extracellular and the intracellular compartments is therefore important. Fifteen subjects undergoing fibreoptic bronchoscopy each had four bronchial biopsy samples taken. Thirty sections from 10 patients were examined and the proportion of tissue types noted, a morphometric analysis computer being used. The water distribution was investigated in the other biopsy specimens with radiolabelled markers. There was pronounced variation in the relative proportions of tissue types. Ciliated epithelium occupied a mean of 22.3% of the biopsy sample, submucosa 53.4%, muscle 17.6%, and glandular tissue 7.0%. There were no differences between second and the fourth generation subcarinae and macroscopic normality of the mucosa was a good predictor of histological normality. The extracellular water content was 40% of the total weight of the specimen and the total water content was 70%. These data provide the basis for pharmacokinetic study of drugs in bronchial mucosa. They show for pharmacokinetic study that macroscopically normal mucosa may be assumed to be histologically normal; that multiple biopsy specimens should be taken for any study, as there is considerable variation in the proportion of tissue types; that specimens from second and fourth generation subcarinae are the same; and that extracellular water contributes 40% to the total weight of the biopsy specimen.

Comparative digestibility and anatomy of some sympatric C3 and C4 arid zone grasses

The importance of C4 (panicoid) and C3 (festucoid) leaf anatomy to differences in in vitro dry matter digestibility (DMD) of grasses was assessed using two Australian summer-growing arid zone C4 grasses, Cymbopogon obtectus and Digitaria brownii, and two C3 grasses, Thyridolepis mitcheiliana and Monochather paradoxa. Seed of these sympatric species was collected from a 400 m2 area near Charleville, Qld. Thus the usual problem of confounding C4 and C3 type with species of different environmental adaptation was avoided in this study. Proportions of tissue types in leaf cross sections and DMD were measured for plants grown in a glasshouse under summer (� water stress) or winter ( - stress) conditions. Differences in tissue proportions due to C4 and C3 leaf anatomy were greater than those induced by growth conditions. C4 leaves consistently had less mesophyll and more of the less-digestible epidermis, bundle sheath, sclerenchyma and vascular tissues. Water-stress resulted in leaves with an increased proportion of mesophyll, but differences in tissue proportions between summer- and winter-grown leaves were small. Species were divided into fast (D. brownii and 7, mitchelliana) and slow (C. obtectus and M. paradoxa) leaf development groups for comparison of DMD. Within each group the C3 species consistently had the highest leaf DMD, but across groups the difference of 18-27 days in time to develop a new leaf sometimes overrode the advantage to DMD of the C3 anatomy. Stem DMD did not differ consistently between C4 and C3 species. The DMD was highest for water-stressed material, and higher in winter- than summer-grown plants. The anatomy associated with either C4 tropical or C3 temperate grass genera clearly contributes to difference in DMD between leaves, but variation in DMD associated with leaf age or environment was only in part attributable to differences in tissue proporxions.