| 1. |
- Jansson, Samuel, et al.
(author)
-
Correlation of mosquito wing-beat harmonics to aid in species classification and flight heading assessment
- 2019
-
In: Novel Biophotonics Techniques and Applications V. - : SPIE. - 1605-7422 .- 2410-9045. - 9781510628434 ; 20:60
-
Conference paper (peer-reviewed)abstract
- Surveying disease vectors is currently excessively laborious for continuous and widespread monitoring. Wing beat modulation spectroscopy gives opportunity for species and sex recognition in electronic traps or mosquito target classification in lidar. We used a polarimetric dual-wavelength-band laboratory system to record kHz modulated backscattered light from insects. The system operates in the near and short-wave infrared at 808 nm and 1550 nm and retrieves both co- and depolarized light. Here we give clues on the harmonic content and covariance of four mosquito species and fruit flies. Further, we interpret the interdependence of harmonic strengths when insects transit the probe volume with random heading direction and provide correlation matrices for coherent and incoherent light. Using the obtained parameters, we demonstrate that species that are difficult to distinguish with microscope can be classified with high accuracy. The results are valuable for understanding wingbeat harmonics in relation to heading and valuable for optimal sensor design for disease vector surveillance.
|
|
| 2. |
- Kanziz, Mustafa, et al.
(author)
-
Review of life science applications using submicron O-PTIR and simultaneous Raman microscopy: a new paradigm in vibrational spectroscopy
- 2021
-
In: Advanced Chemical Microscopy for Life Science and Translational Medicine 2021. - : SPIE. - 2410-9045 .- 1605-7422. - 9781510641471 ; 11656
-
Conference paper (peer-reviewed)abstract
- The recent advent of Optical Photothermal IR (O-PTIR), has enabled for the first time, submicron infrared microscopy in far-field reflection mode with the combination of Raman for simultaneous, correlative IR+Raman microscopy. These unique and exciting synergistic capabilities are now spawning interest in life science application. A broad range of life science applications, otherwise impossible with traditional FTIR/QCL microscopy, will be presented, ranging from live cell imaging in water, to ultra-high resolution images of breast tissue calcifications, amyloid aggregates in neurons (neurites and dendritic spines), individual collagen fibrils with polarized IR and individual isotopically labelled bacterial cells and more.
|
|
| 3. |
- Karlsson, Jennie, et al.
(author)
-
Classification of point-of-care ultrasound in breast imaging using deep learning
- 2023
-
In: Medical Imaging 2023 : Computer-Aided Diagnosis - Computer-Aided Diagnosis. - 2410-9045 .- 1605-7422. - 9781510660359 ; 12465
-
Conference paper (peer-reviewed)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%.
|
|
| 4. |
- Arvidsson, Ida, et al.
(author)
-
Detection of left bundle branch block and obstructive coronary artery disease from myocardial perfusion scintigraphy using deep neural networks
- 2021
-
In: Medical Imaging 2021 : Computer-Aided Diagnosis - Computer-Aided Diagnosis. - : SPIE. - 1605-7422. - 9781510640238 ; 11597
-
Conference paper (peer-reviewed)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.
|
|
| 5. |
- Arvidsson, Ida, et al.
(author)
-
Domain-adversarial neural network for improved generalization performance of gleason grade classification
- 2020
-
In: Medical Imaging 2020 : Digital Pathology - Digital Pathology. - : SPIE. - 1605-7422. - 9781510634077 ; 11320
-
Conference paper (peer-reviewed)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.
|
|
| 6. |
- Asplund, Sara, 1976, et al.
(author)
-
Extended analysis of the effect of learning with feedback on the detectability of pulmonary nodules in chest tomosynthesis
- 2011
-
In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. - : SPIE. - 1605-7422. ; 7966
-
Journal article (other academic/artistic)abstract
- In chest tomosynthesis, low-dose projections collected over a limited angular range are used for reconstruction of section images of the chest, resulting in a reduction of disturbing anatomy at a moderate increase in radiation dose compared to chest radiography. In a previous study, we investigated the effects of learning with feedback on the detection of pulmonary nodules in chest tomosynthesis. Six observers with varying degrees of experience of chest tomosynthesis analyzed tomosynthesis cases for presence of pulmonary nodules. The cases were analyzed before and after learning with feedback. Multidetector computed tomography (MDCT) was used as reference. The differences in performance between the two readings were calculated using the jackknife alternative free-response receiver operating characteristics (JAFROC-2) as primary measure of detectability. Significant differences between the readings were found only for observers inexperienced in chest tomosynthesis. The purpose of the present study was to extend the statistical analysis of the results of the previous study, including JAFROC-1 analysis and FROC curves in the analysis. The results are consistent with the results of the previous study and, furthermore, JAFROC-1 gave lower p-values than JAFROC-2 for the observers who improved their performance after learning with feedback. © 2011 SPIE.
|
|
| 7. |
- Axelsson, Johan, et al.
(author)
-
Prior information in fluorescence molecular tomography based on multispectral fluorescence emission
- 2007
-
In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. - : SPIE. - 1042-4687 .- 1605-7422. - 9780819465474 ; 6434, s. 4340-4340
-
Conference paper (peer-reviewed)abstract
- Fluorescence molecular tomography (FMT) suffers from inherent ill-posedness due to the vast number of possible solutions to the reconstruction problem. To increase the robustness of such a problem one need prior information. We present here a method for rendering a priori information of the position of a fluorescent inclusion inside turbid media. The method utilizes solely two spectral bands within the fluorescence spectrum emitted from the fluorophore. The method is presented and verified using experimental data from a tissue phantom. The confinement is also used to impose weights onto the voxels before the inversion of the linear set of equations describing the FMT problem.
|
|
| 8. |
- Axelsson, Rebecca, et al.
(author)
-
Computer model of mechanical imaging acquisition for virtual clinical trials
- 2021
-
In: Medical Imaging 2021 : Physics of Medical Imaging - Physics of Medical Imaging. - : SPIE. - 1605-7422. - 9781510640191 ; 11595, s. 1-115950
-
Conference paper (peer-reviewed)abstract
- Malignant breast tumours can be distinguished from benign lesions and normal tissue based on their mechanical properties. Our pilot studies have demonstrated the potential of using Mechanical Imaging (MI) combined with mammography to reduce recalls and false positives in breast cancer screening by more accurately identifying benign lesions. To enable further optimization of MI we propose a computer simulation of the MI acquisition, for use in a Virtual Clinical Trial (VCT) framework. VCTs are computer simulated clinical trials used to efficiently evaluate clinical imaging systems. A linear elastic finite element (FE) model of the breast under dynamic compression was implemented using an open-source FE solver. A spherical tumour (15 mm in diameter) was inserted into the simulated predominantly adipose breast. The location and stiffness of the tumour was varied. The average stress on the compressed breast surface was calculated and compared with the local average stress at the tumour location and the Relative Mean Pressure over lesion Area (RMPA) was calculated. Preliminary results were within a realistic range with an average stress on the breast (tumour) of 5.9-16.6 kPa which is in agreement with published values between 1.0 - 22.5 kPa. This corresponds to RMPA values of 0.96-2.15 depending on stiffness and location of the tumour. This can lead to more detailed validation of various MI acquisition schemes through VCTs before their use in clinical studies.
|
|
| 9. |
- Bakic, Predrag R., et al.
(author)
-
Pre-processing for image quality improvement in simultaneous DBT and mechanical imaging
- 2020
-
In: Medical Imaging 2020 : Physics of Medical Imaging - Physics of Medical Imaging. - : SPIE. - 1605-7422. - 9781510633919 ; 11312
-
Conference paper (peer-reviewed)abstract
- Simultaneous digital breast tomosynthesis (DBT) and mechanical imaging (MI) offer the potential to combine anatomic information from DBT with functional information from MI. This makes it possible to associate tissue stiffness with specific anatomic structures in the breast, a combination that can reduce false-positive findings by using the MI data to discriminate between ambiguous lesions in DBT. This, in turn, will reduce the frequency of negative biopsies. Simultaneous imaging requires that the MI sensor array be present during DBT acquisition. This introduces artifacts, since the sensor is attenuating. Previously, we demonstrated that the DBT reconstruction could be modified to reduce sensor conspicuity in DBT images. In this paper, we characterize the relative attenuation of the breast and the sensor, to calculate the artifact reduction in DBT reconstruction. We concentrate on pre-processing DBT projections prior to reconstruction. Using commercially available a DBT system, we have confirmed that the sensor array does not completely attenuate the x-rays. This suggests that a pre-processing method based upon flat fielding can be used to reduce artifacts. In a proof-of-concept study, we performed flat fielding by combining DBT projections of the MI sensor with and without an anthropomorphic breast phantom. Visual evaluation confirmed substantially improved image quality. The artifacts were reduced throughout the image for all sensor elements. Few residual artifacts are noticeable where the phantom thickness decreases. The investigation of additional pre-processing, including beam hardening correction is ongoing. Future work includes quantitative validation, noise stabilization, and method optimization in virtual clinical trials and subsequent patient studies.
|
|
| 10. |
- Balbekin, N.S., et al.
(author)
-
Nondestructive monitoring of aircraft composites using terahertz radiation
- 2014
-
In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. - : SPIE. - 1605-7422. - 9781628415643 ; 9448, s. 94482D-
-
Conference paper (peer-reviewed)abstract
- In this paper we consider using the terahertz (THz) time domain spectroscopy (TDS) for non destructive testing and determining the chemical composition of the vanes and rotor-blade spars. A versatile terahertz spectrometer for reflection and transmission has been used for experiments. We consider the features of measured terahertz signal in temporal and spectral domains during propagation through and reflecting from various defects in investigated objects, such as voids and foliation. We discuss requirements are applicable to the setup and are necessary to produce an image of these defects, such as signal-to-noise ratio and a method for registration THz radiation. Obtained results indicated the prospects of the THz TDS method for the inspection of defects and determination of the particularities of chemical composition of aircraft parts.
|
|
