UTS site search

Associate Professor Allan Jones


Allan is the director of the surgical and anatomical skills laboratory at UTS. His primary area of research is the application of X-ray micro-tomography to the study of anatomical structure.

Image of Allan Jones
Associate Professor, School of Life Sciences
B. App. Sci, Grad Dip. Biomedical Engineering, Ph D

Journal articles

Eross, E., Turk, T., Elekdag-Turk, S., Cakmak, F., Jones, A.S., Vegh, A., Papadopoulou, A.K. & Darendelilerh, M.A. 2015, 'Physical properties of root cementum: Part 25. Extent of root resorption after the application of light and heavy buccopalatal jiggling forces for 12 weeks: A microcomputed tomography study', AMERICAN JOURNAL OF ORTHODONTICS AND DENTOFACIAL ORTHOPEDICS, vol. 147, no. 6, pp. 738-746.
View/Download from: Publisher's site
Zheng, Q., Milthorpe, B.K. & Jones, A.S. 2004, 'Direct Neural Network Application for Automated Cell Recognition', Cytometry, vol. 57A, no. 1, pp. 1-9.
View/Download from: UTS OPUS or Publisher's site
Background Automated cell recognition from histologic images is a very complex task. Traditionally, the image is segmented by some methods chosen to suit the image type, the objects are measured, and then a classifier is used to determine cell type from the object's measurements. Different classifiers have been used with reasonable success, including neural networks working with data from morphometric analysis. Methods Image data of cells were input directly into neural networks to determine the feasibility of direct classification by using pixel intensity information. Several types of neural network and their ability to work with cells in a complex patterned background were assessed for a variety of images and cell types and for the accuracy of classification. Results Inflammatory cells from animal biomaterial implants in rabbit paravertebral muscle were imaged in histologic sections. Simple, three-layer, fully connected, back-propagation neural networks and four-layer networks with two layers of a shared-weights neural network were most successful at classifying the cells from the images, with 97% and 98% correct recognition rates, respectively. Conclusions The high accuracy recognition rate shows the potential for direct classification of visual image pixel data by neural networks.
Jones, A.S., Milthorpe, B.K. & Howlett, C.R. 1994, 'Measurement of Microtomy Induced Section Distortion and Its Correction for 3-Dimensional Histological Reconstructions', Cytometry, vol. 15, no. 2, pp. 95-105.
View/Download from: UTS OPUS or Publisher's site
The presence of microtomy induced distortion in paraffin sections is a significant hindrance to the accurate alignment of sections for three-dimensional reconstructive techniques. Measurement of section distortion in various rat tissues demonstrated distortions to be present in all sections, with over 85% of such distortions being manifest as expansions when compared to the original distances between a series of eight drilled fiducial marks. Mean percentage dimensional changes in the direction of the cutting stroke and at right angles to this direction were -0.5 ± 1.5% and 3.7 ± 1.2% for liver, 7.6 ± 2.4% and 9.1 ± 1.2% for kidney, 6.6 ± 2.3% and 10.5 ± 1.4% for lung, and 20.3 ± 6.6% and 8.9 ± 5.9% for skeletal muscle. Individual sections invariably displayed measurable distortions, with only skeletal muscle showing any consistent pattern, in the form of barrel distortion at right angles to the cutting stroke. In addition a method of distortion correction and simultaneous image alignment is presented as a means of section alignment with full distortion correction capability. This method uses a quadratic polynomial transform in a non-linear unwarping algorithm, to correct for the rotational and translational misalignment as well as for microtomy and camera aspect ratio distortions. Application of this method to a sequence of 46 serial sections demonstrated an alignment accuracy to within 2.6 ± 0.8 pixels