F. Arámbula Cosío

Autonomous robot navigation using adaptive potential fields

In this paper is presented a new scheme for autonomous navigation of a mobile robot, based on improved artificial potential fields and a genetic algorithm. In conventional artificial potential field methods, the robot is attracted by the goal position only, and rejected by several obstacles. Use of a single attraction point can lead to trap situations where the method is unable to produce the resultant force needed to avoid large obstacles. In the scheme presented here, multiple auxiliary attraction points have been used to allow the robot to avoid large, or closely spaced, obstacles. The configuration of the optimum potential field is automatically determined by a genetic algorithm. Simulation experiments performed with three different obstacle configurations, and ten different routes, showed that the scheme reported has a good performance in environments with high obstacle densities, achieving a success rate of 93 per cent.

Automated prostate recognition: a key process for clinically effective robotic prostatectomy

Clinical trials of PROBOT, a robotic system for prostate surgery, have shown that robotic surgery of soft tissue can be successful. Monitoring of the progress of the resection has shown to be a necessary feature of an effective robotic system for prostate surgery. It should provide the surgeon with a reliable method of assessing the cavity during resection. An automatic system for intraoperative monitoring of the progress of the resection during robotic prostatectomy consists of two subsystems: real-time intraoperative imaging of the prostate and automatic identification of the contour of the gland on each image. The development of a fully automatic scheme for prostate recognition on transurethral ultrasound scans is reported. A genetic algorithm has been developed to automatically adjust a model of the prostate boundary until an optimum fit to the prostate in a given image is obtained. An analysis of its performance on 22 different ultrasound images showed an average error of 6.21 mm. Use of a genetic algorithm and a constrained prostate model have shown to be a robust way to automatically identify the prostate in ultrasound images. The scheme is able to produce approximate prostate boundaries, without any human intervention, on ultrasound scans of varying quality. In addition to soft tissue robotic surgery, the genetic algorithm technique is also applicable to a wide range of computer assisted surgical techniques.

Automatic counting of immunocytochemically stained cells

In this work is described the development of an automatic color image segmentation and cell counting system for immunocytochemical analysis of stained tissue samples. The system is designed to automatically count the total number of positive and negative cells in tissue samples treated with cytokines DNA probes of pigs naturally parasitized with Taenia solium metacestodes and using in situ hybridization. The objectives of automatic counting are to improve the reproducibility of the analysis and the processing time of large image batches. A Bayes classifier was used for color image segmentation. Improved watershed segmentation combined with edge detection was used to isolate individual cells which are automatically labeled from the color segmented images. Preliminary results of 174 digital images are reported. The correlation coefficient of the automatic system with manual counting is 0.8 approx. Processing of each digital image takes 20 s on a SUN BLADE 2000.

Automatic identification of metaphase spreads and nuclei using neural networks

The mitotic index (MI) is an important measure in cell proliferation studies. Determination of the MI is usually made by light-microscope analysis of slide preparations. The analyst identifies and counts thousands of cells and reports the percentage of mitotic shapes found, among the interphase nuclei. Full automation of this process is an ambitious task, because there can exist very few mitotic shapes among hundreds of nuclei and thousands of artifacts, resulting in a high probability of false positives, i.e. objects erroneously identified as mitosis or nuclei. A semiautomated approach for MI calculation is reported, based on the development of a neural network (NN) for automatic identification of metaphase spreads and stimulated nuclei in digital images of microscope preparations at 10X magnification. After segmentation of the objects on each image, ten different morphometrical, photometrical and textural features are measured on each segmented object. An NN is used to classify the feature vectors into three classes: metaphases, nuclei and artifacts. The system has been able to classify correctly approximately 91% of the objects in each class, in a test set of 191 mitosis, 331 nuclei and 387 artifacts, obtained from 30 different microscope slides. Manual editing of false positives from the metaphase classification results allows the calculation of the MI with an error of 6.5%.

Automatic analysis of immunocytochemically stained tissue samples

An automatic colour image segmentation and cell counting software system has been developed for immunocytochemical analysis of stained tissue samples. The system was designed to count the total number of positive and negative cells in tissue samples treated with cytokine DNA probes from pigs naturally parasitised with Taenia solium metacestodes, using in situ hybridisation. A reaction index was calculated as the ratio of the number of cells with a positive reaction to the total number of cells (positives plus negatives) for each of five different probes. The objectives of automatic counting were to improve the reproducibility of the analysis and reduce the processing time of large image batches. A fast KNN classifier was used for colour segmentation. Watershed segmentation combined with edge detection was used to isolate individual cells that were then automatically labelled, using the results of the corresponding colour segmented image. Validation was performed on 122 non-training digital images with a total of 1069 positive cells and 1459 negative cells, with the following results: a mean true positive rate of 90.2% for positive cells and a mean true positive rate of 85.4% for negative cells. The corresponding mean false positive rates were 9.6% and 6.6%. The mean reaction index error of the automatic analysis was 5.35%. The processing of each digital image took 10 s on a Pentium IV PC.

A neural network based workstation for automated cell proliferation analysis

In this paper is reported the development of a neural network (NN) based workstation for automated cell proliferation analysis, of cytological microscope images. The software of the system assists the expert biotechnologist during cell proliferation and chromosome aberration studies by automatically identifying metaphase spreads and stimulated nuclei on each digital image. After manual edition of metaphase false positives, the system automatically calculates the mitotic index (MI) i.e. the ratio of metaphases to stimulated nuclei of a given tissue sample. The system reported has been able to classify correctly approximately 91% of the metaphases and stimulated nuclei, in a test set of 191 mitosis, 331 nuclei, and 387 artefacts, obtained from 30 different microscope slides. Manual edition of false positives from the metaphase classification results allows the calculation of the MI with an error of 6.5%.

Signal processing for photoacoustic tomography

This study examines one of the open problems yet to solve in photoacoustic tomography: How to prepare photoacoustic signals to ensure interpretation as projection data? The main part of this difficulty is related to the setting of the linear photoacoustic transport model. Notably errors are due to the discrepancy between the mathematical reconstruction and the physical realization: Tomographic image reconstruction from projections require a linear acquisition system. However in practice, the physical reality presents different non-linear phenomena. In account of this incompatibility, it was our purpose to provide some advancement in signal processing for dealing the projection issue while considering different perspectives in the interpretation of the transport model to be applied in a broader manner. Numerical examples are analyzed in detail and unveil the foundations for photoacoustic signal processing methodologies focused on the task of tomographic image reconstruction from projections.

Electromagnetic compatibility aspects of active robotic systems for surgery : the robotic prostatectomy experience

The paper discusses the susceptibility to electromagnetic interference (EMI) of active robots for surgery, which are safety-critical systems. The high EMI environment of an operating room in the presence of an electrosurgical generator is considered. Experience of a surgeon assistant robot for prostatectomies in improving the immunity to EMI is described. It has been found that effective isolation of the robotic system hardware from grounded metal objects provides significant improvements to safety by its immunity to EMI, in minimising the flow of high-frequency current to ground through the system hardware.

COMPUTER ASSISTED PROSTATE SURGERY TRAINING

We report the current development of a new computer assisted system for local and remote training of transurethral resection of the prostate (TURP). The system is based on a 3D computer model of the prostate gland, which simulates deformations and resections of prostatic tissue. Simulated resections of the prostate can be repeatedly performed by the residents of urology to enhance their training. Automatic prostate recognition software was developed for the construction of a large library of prostate models. We report the software development of the system and show promising preliminary results of a new prostate recognition algorithm.

3D freehand ultrasound for medical assistance in diagnosis and treatment of breast cancer: preliminary results

Image-guided interventions allow the physician to have a better planning and visualization of a procedure. 3D freehand ultrasound is a non-invasive and low-cost imaging tool that can be used to assist medical procedures. This tool can be used in the diagnosis and treatment of breast cancer. There are common medical practices that involve large needles to obtain an accurate diagnosis and treatment of breast cancer. In this study we propose the use of 3D freehand ultrasound for planning and guiding such procedures as core needle biopsy and radiofrequency ablation. The proposed system will help the physician to identify the lesion area, using image-processing techniques in the 3D freehand ultrasound images, and guide the needle to this area using the information of position and orientation of the surgical tools. We think that this system can upgrade the accuracy and efficiency of these procedures.