| 1. |
- Bengtsson, Johan, et al.
(författare)
-
A Robot Playing Scrabble Using Visual Feedback
- 2000
-
Ingår i: IFAC Proceedings Volumes. ; 33:27, s. 551-556
-
Tidskriftsartikel (refereegranskat)abstract
- Today most industrial robot systems use dedicated and rather limited sensors, and available control systems provide limited support for feedback control. Aiming towards more autonomous robot systems, we want to improve flexibility. The game Scrabble is used as a test problem capturing these aspects. Our approach is to incorporate visual servoing and a conventional powerful off-line prograrnrning (OLP) system into the real-time control system, providing task specification and visual debugging. We use the OLP tool Envision from Deneb and an ABB robot with reconfigured control system, where the control system has an Open Robot Control architecture (ORC). The vision system is connected to a host computer and the camera is attached to the robot gripper. By extending the control system, we have designed and implemented both the vision system and the application for the Scrabble game. Our system implementation shows that ORC constitutes a necessary support for incorporation of real-time visual feedback and that OLP may effectively be used with real-time feedback of sensor data.
|
|
| 2. |
- Haner, Sebastian, et al.
(författare)
-
Optimal View Path Planning for Visual SLAM
- 2011
-
Ingår i: Lecture Notes in Computer Science. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 0302-9743 .- 1611-3349. - 9783642212277 - 9783642212260 ; 6688, s. 370-380
-
Konferensbidrag (refereegranskat)abstract
- In experimental design and 3D reconstruction it is desirable to minimize the number of observations required to reach a prescribed estimation accuracy. Many approaches in the literature attempt to find the next best view from which to measure, and iterate this procedure. This paper discusses a continuous optimization method for finding a whole set of future imaging locations which minimize the reconstruction error of observed geometry along with the distance traveled by the camera between these locations. A computationally efficient iterative algorithm targeted toward application within real-time SLAM systems is presented and tested on simulated data.
|
|
| 3. |
- Arvidsson, Ida, et al.
(författare)
-
Artificial intelligence for detection of prostate cancer in biopsies during active surveillance
- 2024
-
Ingår i: BJU International. - : WILEY. - 1464-4096 .- 1464-410X.
-
Tidskriftsartikel (refereegranskat)abstract
- ObjectivesTo evaluate a cancer detecting artificial intelligence (AI) algorithm on serial biopsies in patients with prostate cancer on active surveillance (AS).Patients and methodsA total of 180 patients in the Prostate Cancer Research International Active Surveillance (PRIAS) cohort were prospectively monitored using pre-defined criteria. Diagnostic and re-biopsy slides from 2011 to 2020 (n = 4744) were scanned and analysed by an in-house AI-based cancer detection algorithm. The algorithm was analysed for sensitivity, specificity, and for accuracy to predict need for active treatment. Prognostic properties of cancer size, prostate-specific antigen (PSA) level and PSA density at diagnosis were evaluated.ResultsThe sensitivity and specificity of the AI algorithm was 0.96 and 0.73, respectively, for correct detection of cancer areas. Original pathology report diagnosis was used as the reference method. The area of cancer estimated by the pathologists correlated highly with the AI detected cancer size (r = 0.83). By using the AI algorithm, 63% of the slides would not need to be read by a pathologist as they were classed as benign, at the risk of missing 0.55% slides containing cancer. Biopsy cancer content and PSA density at diagnosis were found to be prognostic of whether the patient stayed on AS or was discontinued for active treatment.ConclusionThe AI-based biopsy cancer detection algorithm could be used to reduce the pathologists' workload in an AS cohort. The detected cancer amount correlated well with the cancer length measured by the pathologist and the algorithm performed well in finding even small areas of cancer. To our knowledge, this is the first report on an AI-based algorithm in digital pathology used to detect cancer in a cohort of patients on AS.
|
|
| 4. |
- Arvidsson, Ida, et al.
(författare)
-
Domain-adversarial neural network for improved generalization performance of gleason grade classification
- 2020
-
Ingår i: Medical Imaging 2020 : Digital Pathology - Digital Pathology. - : SPIE. - 1605-7422. - 9781510634077 ; 11320
-
Konferensbidrag (refereegranskat)abstract
- When training a deep learning model, the dataset used is of great importance to make sure that the model learns relevant features of the data and that it will be able to generalize to new data. However, it is typically difficult to produce a dataset without some bias toward any specific feature. Deep learning models used in histopathology have a tendency to overfit to the stain appearance of the training data - if the model is trained on data from one lab only, it will usually not be able to generalize to data from other labs. The standard technique to overcome this problem is to use color augmentation of the training data which, artificially, generates more variations for the network to learn. In this work we instead test the use of a so called domain-adversarial neural network, which is designed to prevent the model from being biased towards features that in reality are irrelevant such as the origin of an image. To test the technique, four datasets from different hospitals for Gleason grading of prostate cancer are used. We achieve state of the art results for these particular datasets, and furthermore for two of our three test datasets the approach outperforms the use of color augmentation.
|
|
| 5. |
- Arvidsson, Ida, et al.
(författare)
-
Generalization of prostate cancer classification for multiple sites using deep learning
- 2018
-
Ingår i: 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. - 9781538636367 ; 2018-April, s. 191-194
-
Konferensbidrag (refereegranskat)abstract
- Deep learning has the potential to drastically increase the accuracy and efficiency of prostate cancer diagnosis, which would be of uttermost use. Today the diagnosis is determined manually from H&E stained specimens using a light microscope. In this paper several different approaches based on convolutional neural networks for prostate cancer classification are presented and compared, using three different datasets with different origins. The issue that algorithms trained on a certain site might not generalize to other sites, due to for example inevitable stain variations, is highlighted. Two different techniques to overcome this complication are compared; by training the networks using color augmentation and by using digital stain separation. Furthermore, the potential of using an autoencoder to get a more efficient downsampling is investigated, which turned out to be the method giving the best generalization. We achieve accuracies of 95% for classification of benign versus malignant tissue and 81% for Gleason grading for data from the same site as the training data. The corresponding accuracies for images from other sites are in average 88% and 52% respectively.
|
|
| 6. |
- Gummeson, Anna, et al.
(författare)
-
Automatic Gleason grading of H&E stained microscopic prostate images using deep convolutional neural networks
- 2017
-
Ingår i: Medical Imaging 2017: Digital Pathology. - : SPIE. - 9781510607255 ; 10140
-
Konferensbidrag (refereegranskat)abstract
- Prostate cancer is the most diagnosed cancer in men. The diagnosis is confirmed by pathologists based on ocular inspection of prostate biopsies in order to classify them according to Gleason score. The main goal of this paper is to automate the classification using convolutional neural networks (CNNs). The introduction of CNNs has broadened the field of pattern recognition. It replaces the classical way of designing and extracting hand-made features used for classification with the substantially different strategy of letting the computer itself decide which features are of importance. For automated prostate cancer classification into the classes: Benign, Gleason grade 3, 4 and 5 we propose a CNN with small convolutional filters that has been trained from scratch using stochastic gradient descent with momentum. The input consists of microscopic images of haematoxylin and eosin stained tissue, the output is a coarse segmentation into regions of the four different classes. The dataset used consists of 213 images, each considered to be of one class only. Using four-fold cross-validation we obtained an error rate of 7.3%, which is significantly better than previous state of the art using the same dataset. Although the dataset was rather small, good results were obtained. From this we conclude that CNN is a promising method for this problem. Future work includes obtaining a larger dataset, which potentially could diminish the error margin.
|
|
| 7. |
|
|
| 8. |
- Marginean, Felicia, et al.
(författare)
-
An Artificial Intelligence-based Support Tool for Automation and Standardisation of Gleason Grading in Prostate Biopsies
- 2021
-
Ingår i: European Urology Focus. - : Elsevier BV. - 2405-4569. ; 7:5, s. 995-1001
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Gleason grading is the standard diagnostic method for prostate cancer and is essential for determining prognosis and treatment. The dearth of expert pathologists, the inter- and intraobserver variability, as well as the labour intensity of Gleason grading all necessitate the development of a user-friendly tool for robust standardisation.OBJECTIVE: To develop an artificial intelligence (AI) algorithm, based on machine learning and convolutional neural networks, as a tool for improved standardisation in Gleason grading in prostate cancer biopsies.DESIGN, SETTING, AND PARTICIPANTS: A total of 698 prostate biopsy sections from 174 patients were used for training. The training sections were annotated by two senior consultant pathologists. The final algorithm was tested on 37 biopsy sections from 21 patients, with digitised slide images from two different scanners.OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Correlation, sensitivity, and specificity parameters were calculated.RESULTS AND LIMITATIONS: The algorithm shows high accuracy in detecting cancer areas (sensitivity: 100%, specificity: 68%). Compared with the pathologists, the algorithm also performed well in detecting cancer areas (intraclass correlation coefficient [ICC]: 0.99) and assigning the Gleason patterns correctly: Gleason patterns 3 and 4 (ICC: 0.96 and 0.94, respectively), and to a lesser extent, Gleason pattern 5 (ICC: 0.82). Similar results were obtained using two different scanners.CONCLUSIONS: Our AI-based algorithm can reliably detect prostate cancer and quantify the Gleason patterns in core needle biopsies, with similar accuracy as pathologists. The results are reproducible on images from different scanners with a proven low level of intraobserver variability. We believe that this AI tool could be regarded as an efficient and interactive tool for pathologists.PATIENT SUMMARY: We developed a sensitive artificial intelligence tool for prostate biopsies, which detects and grades cancer with similar accuracy to pathologists. This tool holds promise to improve the diagnosis of prostate cancer.
|
|
| 9. |
- Olsson, Carl, et al.
(författare)
-
Triangulating a Plane
- 2011
-
Ingår i: Lecture Notes in Computer Science (Image Analysis : 17th Scandinavian Conference, SCIA 2011, Ystad, Sweden, May 2011. Proceedings). - Berlin, Heidelberg : Springer Berlin Heidelberg. - 0302-9743 .- 1611-3349. - 9783642212260 - 9783642212277 ; 6688, s. 13-23
-
Konferensbidrag (refereegranskat)abstract
- In this theoretical paper we consider the problem of accurately triangulating a scene plane. Rather than first triangulating a set of points and then fitting a plane to these points, we try to minimize the back-projection errors as functions of the plane parameters directly. As this is both geometrically and statistically meaningful our method performs better than the standard two step procedure. Furthermore, we show that the error residuals of this formulation are quasiconvex thereby making it very easy to solve using for example standard local optimization methods.
|
|
| 10. |
- Ryberg, Anders, 1973-
(författare)
-
Camera Modelling and Calibration with Machine Vision Applications
- 2010
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Camera modelling and calibration are important parts of machine vision. They can be used for calculating geometric information from images. A camera model is a mathematical projection between a 3D object space and a 2D image. The camera calibration is a mathematical procedure calculating parameters of the camera model, usually based on several images of reference points. These fundamental parts of machine vision are improved in this thesis. One large part is the development of a generic camera model, GCM, that is accurate, computationally efficient and can be used for both conventional, fisheye and even catadioptric cameras. Different models were used in the past for conventional and omnidirectional cameras and this is a well-known problem, the solution of which is described in this thesis. The accuracy of camera models is improved by introducing new ways of compensating for different distortions, such as radial istortion, varying entrance pupil point and decentring distortion. Calibration is mproved by introducing newmeans of calculating start estimates of camera parameters, from analysing shapes, sizes and positions of the reference points in the images. These start estimates are needed in order to make the calibration converge. Methods for calculating better reference centre points than the centres of gravity are developed in order to increase the accuracy further. Non-trivial null spaces that occur during calibration are identified. Awareness of these improve the calibration. Calibrations with different camera models are implemented and tested for real cameras in order to compare their accuracy. Certain models are better for certain situations, but the overall performance and properties are favourable for the GCM. A stereo vision welding robot system is developed, using the new model. It determines the geometry of a 3D weld joint, so that a robot can follow it. The same system is implemented in a virtual environment using a simulation software. Such simulation is important since it makes it possible to develop robot vision systems off-line.
|
|
