| 1. |
- Arvidsson, Ida, et al.
(författare)
-
Comparison of different augmentation techniques for improved generalization performance for gleason grading
- 2019
-
Ingår i: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). - 9781538636411 ; , s. 923-927
-
Konferensbidrag (refereegranskat)abstract
- The fact that deep learning based algorithms used for digital pathology tend to overfit to the site of the training data is well-known. Since an algorithm that does not generalize is not very useful, we have in this work studied how different data augmentation techniques can reduce this problem but also how data from different sites can be normalized to each other. For both of these approaches we have used cycle generative adversarial networks (GAN); either to generate more examples to train on or to transform images from one site to another. Furthermore, we have investigated to what extent standard augmentation techniques improve the generalization performance. We performed experiments on four datasets with slides from prostate biopsies, stained with HE, detailed annotated with Gleason grades. We obtained results similar to previous studies, with accuracies of 77% for Gleason grading for images from the same site as the training data and 59% for images from other sites. However, we also found out that the use of traditional augmentation techniques gave better performance compared to when using cycle GANs, either to augment the training data or to normalize the test data.
|
|
| 2. |
- Arvidsson, Ida, et al.
(författare)
-
Deep learning prediction of quantitative coronary angiography values using myocardial perfusion images with a CZT camera
- 2023
-
Ingår i: Journal of Nuclear Cardiology. - : Springer Science and Business Media LLC. - 1071-3581 .- 1532-6551. ; 30:1, s. 116-126
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: Evaluate the prediction of quantitative coronary angiography (QCA) values from MPI, by means of deep learning. Methods: 546 patients (67% men) undergoing stress 99mTc-tetrofosmin MPI in a CZT camera in the upright and supine position were included (1092 MPIs). Patients were divided into two groups: ICA group included 271 patients who performed an ICA within 6 months of MPI and a control group with 275 patients with low pre-test probability for CAD and a normal MPI. QCA analyses were performed using radiologic software and verified by an expert reader. Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. A deep learning model was trained using a double cross-validation scheme such that all data could be used as test data as well. Results: Area under the receiver-operating characteristic curve for the prediction of QCA, with > 50% narrowing of the artery, by deep learning for the external test cohort: per patient 85% [95% confidence interval (CI) 84%-87%] and per vessel; LAD 74% (CI 72%-76%), RCA 85% (CI 83%-86%), LCx 81% (CI 78%-84%), and average 80% (CI 77%-83%). Conclusion: Deep learning can predict the presence of different QCA percentages of coronary artery stenosis from MPIs.
|
|
| 3. |
- Arvidsson, Ida, et al.
(författare)
-
Detection of left bundle branch block and obstructive coronary artery disease from myocardial perfusion scintigraphy using deep neural networks
- 2021
-
Ingår i: Medical Imaging 2021 : Computer-Aided Diagnosis - Computer-Aided Diagnosis. - : SPIE. - 1605-7422. - 9781510640238 ; 11597
-
Konferensbidrag (refereegranskat)abstract
- Myocardial perfusion scintigraphy, which is a non-invasive imaging technique, is one of the most common cardiological examinations performed today, and is used for diagnosis of coronary artery disease. Currently the analysis is performed visually by physicians, but this is both a very time consuming and a subjective approach. These are two of the motivations for why an automatic tool to support the decisions would be useful. We have developed a deep neural network which predicts the occurrence of obstructive coronary artery disease in each of the three major arteries as well as left bundle branch block. Since multiple, or none, of these could have a defect, this is treated as a multi-label classification problem. Due to the highly imbalanced labels, the training loss is weighted accordingly. The prediction is based on two polar maps, captured during stress in upright and supine position, together with additional information such as BMI and angina symptoms. The polar maps are constructed from myocardial perfusion scintigraphy examinations conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). The study includes data from 759 patients. Using 5-fold cross-validation we achieve an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level for the three major arteries, 0.94 on per-patient level and 0.82 for left bundle branch block.
|
|
| 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. |
- Arvidsson, Ida, et al.
(författare)
-
Prediction of Obstructive Coronary Artery Disease from Myocardial Perfusion Scintigraphy using Deep Neural Networks
- 2021
-
Ingår i: 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR). - : IEEE COMPUTER SOC. - 1051-4651. - 9781728188089 ; , s. 4442-4449
-
Konferensbidrag (refereegranskat)abstract
- For diagnosis and risk assessment in patients with stable ischemic heart disease, myocardial perfusion scintigraphy is one of the most common cardiological examinations performed today. There are however many motivations for why an artificial intelligence algorithm would provide useful input to this task. For example to reduce the subjectiveness and save time for the nuclear medicine physicians working with this time consuming task. In this work we have developed a deep learning algorithm for multi-label classification based on a convolutional neural network to estimate the probability of obstructive coronary artery disease in the left anterior artery, left circumflex artery and right coronary artery. The prediction is based on data from myocardial perfusion scintigraphy studies conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). Data from 588 patients was available, with stress images in both upright and supine position, as well as a number of auxiliary parameters such as angina symptoms and age. The data was used to train and evaluate the algorithm using 5-fold cross-validation. We achieve state-of-the-art results for this task with an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level and 0.95 on per-patient level.
|
|
| 7. |
- Karlsson, Jennie, et al.
(författare)
-
Classification of point-of-care ultrasound in breast imaging using deep learning
- 2023
-
Ingår i: Medical Imaging 2023 : Computer-Aided Diagnosis - Computer-Aided Diagnosis. - 1605-7422 .- 2410-9045. - 9781510660359 ; 12465
-
Konferensbidrag (refereegranskat)abstract
- Early detection of breast cancer is important to reduce morbidity and mortality. Access to breast imaging is limited in low- and middle-income countries compared to high-income countries. This contributes to advance-stage breast cancer presentation with poor survival. Pocket-sized portable ultrasound device, also known as point-of-care ultrasound (POCUS), aided by decision support using deep learning-based algorithms for lesion classification could be a cost-effective way to enable access to breast imaging in low-resource settings. A previous study, where using convolutional neural networks (CNN) to classify breast cancer in conventional ultrasound (US) images, showed promising results. The aim of the present study is to classify POCUS breast images. A POCUS data set containing 1100 breast images was collected. To increase the size of the data set, a Cycle-Consistent Adversarial Network (CycleGAN) was trained on US images to generate synthetic POCUS images. A CNN was implemented, trained, validated and tested on POCUS images. To improve performance, the CNN was trained with different combinations of data consisting of POCUS images, US images, CycleGAN-generated POCUS images and spatial augmentation. The best result was achieved by a CNN trained on a combination of POCUS images and CycleGAN-generated POCUS images and augmentation. This combination achieved a 95% confidence interval for AUC between 93.5% - 96.6%.
|
|
| 8. |
- Karlsson, Jennie, et al.
(författare)
-
Machine learning algorithm for classification of breast ultrasound images
- 2022
-
Ingår i: Medical Imaging 2022 : Computer-Aided Diagnosis - Computer-Aided Diagnosis. - : SPIE. - 9781510649422 ; 12033
-
Konferensbidrag (refereegranskat)abstract
- Breast cancer is the most common type of cancer globally. Early detection is important for reducing the morbidity and mortality of breast cancer. The aim of this study was to evaluate the performance of different machine learning models to classify malignant or benign lesions on breast ultrasound images. Three different convolutional neural network approaches were implemented: (a) Simple convolutional neural network, (b) transfer learning using pre-trained InceptionV3, ResNet50V2, VGG19 and Xception and (c) deep feature networks based on combinations of the four transfer networks in (b). The data consisted of two breast ultrasound image data sets: (1) an open, single-vendor, data set collected by Cairo University at Baheya Hospital, Egypt, consisting of 437 benign lesions and 210 malignant lesions, where 10% was set to be a test set and the rest was used for training and validation (development) and (2) An in-house, multi-vendor data set collected at Unilabs Mammography Unit, Skåne University Hospital, Sweden, consisting of 13 benign lesions and 265 malignant lesions, was used as an external test set. Both test sets were used for evaluating the networks. The performance measures used were area under the receiver operating characteristic curve (AUC), sensitivity, specificity and weighted accuracy. Holdout, i.e. the splitting of the development data into training and validation data sets just once, was used to find a model with as good performance as possible. 10-fold cross-validation was also performed to provide uncertainty estimates. For the transfer networks which were obtained with holdout, Gradient-weighted Class Activation Mapping was used to generate heat maps indicating which part of the image contributed to the network’s decision. For 10-fold cross-validation it was possible to achieve a mean AUC of 92% and mean sensitivity of 95% for the transfer network based on Xception when testing on the first data set. When testing on the second data set it was possible to obtain a mean AUC of 75% and mean sensitivity of 86% for the combination of ResNet50V2 and Xception.
|
|
| 9. |
- Landgren, Matilda, et al.
(författare)
-
A Measure of Septum Shape Using Shortest Path Segmentation in Echocardiographic Images of LVAD Patients
- 2014
-
Ingår i: Pattern Recognition (ICPR), 2014 22nd International Conference on. - 1051-4651. ; , s. 3398-3403
-
Konferensbidrag (refereegranskat)abstract
- Patients waiting for heart transplantation due to a failing heart can get a left ventricular assist device (LVAD) implanted through open chest surgery. The device consists of a pump that pumps blood from the left ventricle into the aorta. To get the correct rotation speed of the pump, the physicians consider a number of measurements as well as a sequence of echocardiographic images. The important information obtained from the images is the shape of the inter-ventricular septum. For instance, if the septum bulges towards the left ventricle the speed is too high and it might harm the right ventricular function. To get a measure of the shape of the septum, which can be incorporated in a decision support system, we perform a segmentation of the septum using a shortest path method. To reduce user interaction, the user only needs to annotate two anchor points in the first frame. They mark the endpoints of the septum and they are tracked through the sequence with our tracking algorithm. After the segmentation the septum is divided into two regions, the one closest to the right ventricle and the one closest to the left ventricle, and the desired measure is the difference between the areas of these regions divided by the total septum area. The performance of the segmentation algorithm is acceptable and the obtained septum measure corresponds in most cases to the assessments from a physician.
|
|
| 10. |
- Landgren, Matilda, et al.
(författare)
-
An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images
- 2011
-
Ingår i: Lecture Notes in Computer Science. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 0302-9743 .- 1611-3349. - 9783642212277 - 9783642212260 ; 6688, s. 489-500
-
Konferensbidrag (refereegranskat)abstract
- Designing a system for computer aided diagnosis is a complex procedure requiring an understanding of the biology of the disease, insight into hospital workflow and awareness of available technical solutions. This paper aims to show that a valuable system can be designed for diagnosing kidney lesions in children and adolescents from 99m Tc-DMSA scintigraphy images. We present the chain of analysis and provide a discussion of its performance. On a per-lesion basis, the classification reached an ROC-curve area of 0.96 (sensitivity/specificity e.g. 97%/85%) measured using an independent test group consisting of 56 patients with 730 candidate lesions. We conclude that the presented system for diagnostic support has the potential of increasing the quality of care regarding this type of examination.
|
|
