Întotdeauna devotat.

patrocinadores1-300x72 1

In the initial stage of drug induced hepatic lesions, classic histological exams fail to reveal changes, while blood work already shows significant functional and enzyme level changes. This study examines the ability of fractal analysis to reflect drug induced minor changes in the liver.

Fractal dimension (FD) was computed on complete histology images (CHI) and on chromatin regions (CR) extracted by image segmentation. Images were available from a previous study on rats with induced tumours, investigating the hepatic effects of mitoxantrone, farmarubicine, and holoxan, as well as of phenol extracts from three plants. The statistical analysis carefully complied with the features of the input data and included ANOVA, t-test, power, size effect, and confidence intervals.

We found the impact of the toxic drugs on the FD of the histology images to be major and reliable, with variations among the drugs and the types of images (CHI and CR). The effect of the protective drugs on the FD of the images is less impressive.

This study provides additional evidence that FD of histology images can be used as an complementary diagnostic tool in the pathology lab. Introduction of FD as a regular image-processing step can lead in a short time to confirming its added value in identifying small and diffuse lesions.

Journal of Comparative Pathology, Volume 148, Issue 1, January 2013, Page 92

Full poster presentation can be viewed here.                                                  High resolution pdf here.

Authors: dr. Liviu Gaita, Prof. dr. Manuella Militaru

titulonuevo

Note of Liviu Gaita:

This study is made on primary data collected in an old research project - designed, performed, and concluded before any of my involvement. I am steadily committed to promoting a total ban on experiments on healthy animals, be they human or non-human animals. Liviu Gaita

Published in Oncologie

patrocinadores1-300x72 1

One of the oldest - and yet actual - medical challenges is the prediction of the most probable outcome of a disease in a given patient, based on the clinical and pathology information and a therapy scenario.

A model based on Artificial Neural Networks (ANN) was designed and programmed. The input data (over 120 parameters) include histology type and grade of tumours, morphometry and fractal dimension of microscopic images of lesions, clinical and para-clinical data, quality of life, and treatment. The key output is life expectation for dogs and cats with cancer, but many input parameters can be turned into unknowns and the network asked to provide an estimate.

The ANN was tested on a smaller set of 27 criteria and 39 cases of cancer in dogs to develop appropriate architecture and learning strategies. Robustness and predictive performance were confirmed. As previously reported, we also found overfitting/overtraining to be the most serious pitfall that needs to be addressed. The complete model is growing and learning.

ANN are one very promising way to respond to the growing interest for Evidence Based Medicine methods applied in veterinary practice. ANN provide a lean approach for integrating in the current diagnostic and prognostic procedures some new or still ‘exotic’ pathology information, like fractal dimensions of histology images.

Journal of Comparative Pathology, Volume 148, Issue 1, January 2013, Page 69

Full poster presentation can be viewed here.                                            High resolution pdf here.

Authors: dr. Liviu Gaita, Prof. dr. Manuella Militaru

titulonuevo

Published in Oncologie

Descoperiți Cronicile ORTOVET Excelsior. Scrise, fotografiate și filmate zi de zi...

hiero1