98:. The output for the network was an artifact free heat map of the targets axial and lateral position. The network had a mean error rate of less than 30 microns when localizing target below 40 mm and had a mean error rate of 1.06 mm for localizing targets between 40 mm and 60 mm. With a slight modification to the network, the model was able to accommodate multi target localization. A validation experiment was performed in which pencil lead was submerged into an intralipid solution at a depth of 32 mm. The network was able to localize the lead's position when the solution had a reduced scattering coefficient of 0, 5, 10, and 15 cm. The results of the network show improvements over standard delay-and-sum or frequency-domain beamforming algorithms and Johnstonbaugh proposes that this technology could be used for
169:
The typical network architectures used to remove these sparse sampling artifacts are U-net and Fully Dense (FD) U-net. Both of these architectures contain a compression and decompression phase. The compression phase learns to compress the image to a latent representation that lacks the imaging artifacts and other details. The decompression phase then combines with information passed by the residual connections in order to add back image details without adding in the details associated with the artifacts. FD U-net modifies the original U-net architecture by including dense blocks that allow layers to utilize information learned by previous layers within the dense block. Another technique was proposed using a simple CNN based architecture for removal of artifacts and improving the k-wave image reconstruction.
350:
can be up to two orders of magnitude lower than the conventional time-domain systems. To overcome the inherent SNR limitation of frequency-domain PAM, a U-Net neural network has been utilized to augment the generated images without the need for excessive averaging or the application of high optical power on the sample. In this context, the accessibility of PAM is improved as the system’s cost is dramatically reduced while retaining sufficiently high image quality standards for demanding biological observations.
35:. Photoacoustic imaging is based on the photoacoustic effect, in which optical absorption causes a rise in temperature, which causes a subsequent rise in pressure via thermo-elastic expansion. This pressure rise propagates through the tissue and is sensed via ultrasonic transducers. Due to the proportionality between the optical absorption, the rise in temperature, and the rise in pressure, the ultrasound pressure wave signal can be used to quantify the original optical energy deposition within the tissue.
237:
can cause artifacts and limit the axial resolution of the imaging system. The primary deep neural network architectures used to remove limited-bandwidth artifacts have been WGAN-GP and modified U-net. The typical method to remove artifacts and denoise limited-bandwidth reconstructions before deep learning was Wiener filtering, which helps to expand the PA signal's frequency spectrum. The primary advantage of the deep learning method over Wiener filtering is that Wiener filtering requires a high initial
64:
implementation, the applications of deep learning in PACT have branched out primarily into removing artifacts from acoustic reflections, sparse sampling, limited-view, and limited-bandwidth. There has also been some recent work in PACT toward using deep learning for wavefront localization. There have been networks based on fusion of information from two different reconstructions to improve the reconstruction using deep learning fusion based networks.
17:
51:
tissue. PAM on the other hand uses focused ultrasound detection combined with weakly-focused optical excitation (acoustic resolution PAM or AR-PAM) or tightly-focused optical excitation (optical resolution PAM or OR-PAM). PAM typically captures images point-by-point via a mechanical raster scanning pattern. At each scanned point, the acoustic time-of-flight provides axial resolution while the acoustic focusing yields lateral resolution.
216:
pixel-wise interpolation, the time-of-flight for each pixel was calculated using the wave propagation equation. Next, a reconstruction grid was created from pressure measurements calculated from the pixels' time-of-flight. Using the reconstruction grid as an input, the FD U-net was able to create artifact free reconstructed images. This pixel-wise interpolation method was faster and achieved better
295:
338:
220:(PSNR) and structural similarity index measures (SSIM) than artifact free images created when the time-reversal images served as the input to the FD U-net. This pixel-wise interpolation method was significantly faster and had comparable PSNR and SSIM than the images reconstructed from the computationally intensive
250:
is used. A novel fusion based architecture was proposed to combine the output of two different reconstructions and give a better image quality as compared to any of those reconstructions. It includes weight sharing, and fusion of characteristics to achieve the desired improvement in the output image quality.
349:
Frequency-domain PAM constitutes a powerful cost-efficient imaging method integrating intensity-modulated laser beams emitted by continuous wave sources for the excitation of single-frequency PA signals. Nevertheless, this imaging approach generally provides smaller signal-to-noise ratios (SNR) which
324:
used a simple three layer convolutional neural network, with each layer represented by a weight matrix and a bias vector, in order to remove the PAM motion artifacts. Two of the convolutional layers contain RELU activation functions, while the last has no activation function. Using this architecture,
249:
The complementary information is utilized using fusion based architectures for improving the photoacoustic image reconstruction. Since different reconstructions promote different characteristics in the output and hence the image quality and characteristics vary if a different reconstruction technique
168:
When the density of uniform tomographic view angles is under what is prescribed by the
Nyquist-Shannon's sampling theorem, it is said that the imaging system is performing sparse sampling. Sparse sampling typically occurs as a way of keeping production costs low and improving image acquisition speed.
151:
knowledge from network training to remove artifacts. In the deep learning methods that seek to remove these sparse sampling, limited-bandwidth, and limited-view artifacts, the typical workflow involves first performing the ill-posed reconstruction technique to transform the pre-beamformed data into a
258:
High energy lasers allow for light to reach deep into tissue and they allow for deep structures to be visible in PA images. High energy lasers provide a greater penetration depth than low energy lasers. Around an 8 mm greater penetration depth for lasers with a wavelength between 690 to 900 nm. The
236:
The limited-bandwidth problem occurs as a result of the ultrasound transducer array's limited detection frequency bandwidth. This transducer array acts like a band-pass filter in the frequency domain, attenuating both high and low frequencies within the photoacoustic signal. This limited-bandwidth
206:
was able to apply a FD U-net to remove artifacts from simulated limited-view reconstructed PA images. PA images reconstructed with the time-reversal process and PA data collected with either 16, 32, or 64 sensors served as the input to the network and the ground truth images served as the desired
185:
of the reconstructed image. Limited-view, similar to sparse sampling, makes the initial reconstruction algorithm ill-posed. Prior to deep learning, the limited-view problem was addressed with complex hardware such as acoustic deflectors and full ring-shaped transducer arrays, as well as solutions
50:
methods, the sample is imaged at multiple view angles, which are then used to perform an inverse reconstruction algorithm based on the detection geometry (typically through universal backprojection, modified delay-and-sum, or time reversal ) to elicit the initial pressure distribution within the
72:
Traditional photoacoustic beamforming techniques modeled photoacoustic wave propagation by using detector array geometry and the time-of-flight to account for differences in the PA signal arrival time. However, this technique failed to account for reverberant acoustic signals caused by acoustic
215:
proposed to use a pixel-wise interpolation as an input to the network instead of a reconstructed image. Using a pixel-wise interpolation would remove the need to produce an initial image that may remove small details or make details unrecoverable by obscuring them with artifacts. To create the
90:
convolution layer and differentiable spatial-to-numerical transform layer were also used within the architecture. Simulated PA wavefronts served as the input for training the model. To create the wavefronts, the forward simulation of light propagation was done with the NIRFast toolbox and the
63:
in which a deep neural network was trained to learn spatial impulse responses and locate photoacoustic point sources. The resulting mean axial and lateral point location errors on 2,412 of their randomly selected test images were 0.28 mm and 0.37 mm respectively. After this initial
89:
was able to localize the source of photoacoustic wavefronts with a deep neural network. The network used was an encoder-decoder style convolutional neural network. The encoder-decoder network was made of residual convolution, upsampling, and high field-of-view convolution modules. A Nyquist
272:
sheep brain created by a low energy laser of 20 mJ as the input to the network and images of the same sheep brain created by a high energy laser of 100 mJ, 20 mJ above the MPE, as the desired output. A perceptually sensitive loss function was used to train the network to increase the low
186:
like compressed sensing, weighted factor, and iterative filtered backprojection. The result of this ill-posed reconstruction is imaging artifacts that can be removed by CNNs. The deep learning algorithms used to remove limited-view artifacts include U-net and FD U-net, as well as
207:
output. The network was able to remove artifacts created in the time-reversal process from synthetic, mouse brain, fundus, and lung vasculature phantoms. This process was similar to the work done for clearing artifacts from sparse and limited view images done by
Davoudi
138:
In PACT, tomographic reconstruction is performed, in which the projections from multiple solid angles are combined to form an image. When reconstruction methods like filtered backprojection or time reversal, are ill-posed inverse problems due to sampling under the
302:
Photoacoustic microscopy differs from other forms of photoacoustic tomography in that it uses focused ultrasound detection to acquire images pixel-by-pixel. PAM images are acquired as time-resolved volumetric data that is typically mapped to a 2-D projection via a
122:
utilized a full VGG-16 architecture to locate point sources and remove reflection artifacts within raw photoacoustic channel data (in the presence of multiple sources and channel noise). This utilization of deep learning trained on simulated data produced in the
1243:
Waibel, Dominik; Gröhl, Janek; Isensee, Fabian; Kirchner, Thomas; Maier-Hein, Klaus; Maier-Hein, Lena (2018-02-19). "Reconstruction of initial pressure from limited view photoacoustic images using deep learning". In Wang, Lihong V; Oraevsky, Alexander A (eds.).
325:
kernel sizes of 3 × 3, 4 × 4, and 5 × 5 were tested, with the largest kernel size of 5 × 5 yielding the best results. After training, the performance of the motion correction model was tested and performed well on both simulation and
1354:
Awasthi, Navchetan; Pardasani, Rohit; Sandeep Kumar Kalva; Pramanik, Manojit; Yalavarthy, Phaneendra K. (2020). "Sinogram super-resolution and denoising convolutional neural network (SRCN) for limited data photoacoustic tomography".
2013:
Haltmeier, Markus; Sandbichler, Michael; Berer, Thomas; Bauer-Marschallinger, Johannes; Burgholzer, Peter; Nguyen, Linh (June 2018). "A sparsification and reconstruction strategy for compressed sensing photoacoustic tomography".
77:, a convolutional neural network (similar to a simple VGG-16 style architecture) was used that took pre-beamformed photoacoustic data as input and outputted a classification result specifying the 2-D point source location.
2274:
Liu, Xueyan; Peng, Dong; Ma, Xibo; Guo, Wei; Liu, Zhenyu; Han, Dong; Yang, Xin; Tian, Jie (2013-05-14). "Limited-view photoacoustic imaging based on an iterative adaptive weighted filtered backprojection approach".
267:
was able to increase the penetration of depth of low energy lasers that meet the MPE standard by applying a U-net architecture to the images created by a low energy laser. The network was trained with images of an
277:
in PA images created by the low energy laser. The trained network was able to increase the peak-to-background ratio by 4.19 dB and penetration depth by 5.88% for photos created by the low energy laser of an
307:
and maximum amplitude projection (MAP). The first application of deep learning to PAM, took the form of a motion-correction algorithm. This procedure was posed to correct the PAM artifacts that occur when an
263:
has set a maximal permissible exposure (MPE) for different biological tissues. Lasers with specifications above the MPE can cause mechanical or thermal damage to the tissue they are imaging. Manwar
177:
When a region of partial solid angles are not captured, generally due to geometric limitations, the image acquisition is said to have limited-view. As illustrated by the experiments of
Davoudi
809:
Reiter, Austin; Bell, Muyinatu A Lediju (2017-03-03). Oraevsky, Alexander A; Wang, Lihong V (eds.). "A machine learning approach to identifying point source locations in photoacoustic data".
143:'s sampling requirement or with limited-bandwidth/view, the resulting reconstruction contains image artifacts. Traditionally these artifacts were removed with slow iterative methods like
2148:
Duarte, Marco F.; Davenport, Mark A.; Takhar, Dharmpal; Laska, Jason N.; Sun, Ting; Kelly, Kevin F.; Baraniuk, Richard G. (March 2008). "Single-pixel imaging via compressive sampling".
1591:
Agranovsky, Mark; Kuchment, Peter (2007-08-28). "Uniqueness of reconstruction and an inversion procedure for thermoacoustic and photoacoustic tomography with variable sound speed".
2326:
Ma, Songbo; Yang, Sihua; Guo, Hua (2009-12-15). "Limited-view photoacoustic imaging based on linear-array detection and filtered mean-backprojection-iterative reconstruction".
2703:
Tserevelakis, George J.; Barmparis, Georgios D.; Kokosalis, Nikolaos; Giosa, Eirini Smaro; Pavlopoulos, Anastasios; Tsironis, Giorgos P.; Zacharakis, Giannis (2023-05-15).
1454:
Johnstonbaugh, Kerrick; Agrawal, Sumit; Durairaj, Deepit
Abhishek; Fadden, Christopher; Dangi, Ajay; Karri, Sri Phani Krishna; Kothapalli, Sri-Rajasekhar (December 2020).
1298:
Awasthi, Navchetan (28 February 2020). "Deep Neural
Network Based Sinogram Super-resolution and Bandwidth Enhancement for Limited-data Photoacoustic Tomography".
94:, while the forward simulation of sound propagation was done with the K-Wave toolbox. The simulated wavefronts were subjected to different scattering mediums and
979:
Guan, Steven; Khan, Amir A.; Sikdar, Siddhartha; Chitnis, Parag V. (February 2020). "Fully Dense UNet for 2-D Sparse
Photoacoustic Tomography Artifact Removal".
190:(GANs) and volumetric versions of U-net. One GAN implementation of note improved upon U-net by using U-net as a generator and VGG as a discriminator, with the
1901:
Sandbichler, M.; Krahmer, F.; Berer, T.; Burgholzer, P.; Haltmeier, M. (January 2015). "A Novel
Compressed Sensing Scheme for Photoacoustic Tomography".
1376:
Gutta, Sreedevi; Kadimesetty, Venkata
Suryanarayana; Kalva, Sandeep Kumar; Pramanik, Manojit; Ganapathy, Sriram; Yalavarthy, Phaneendra K. (2017-11-02).
639:
1097:
Hauptmann, Andreas; Lucka, Felix; Betcke, Marta; Huynh, Nam; Adler, Jonas; Cox, Ben; Beard, Paul; Ourselin, Sebastien; Arridge, Simon (June 2018).
573:"Experimental validation of tangential resolution improvement in photoacoustic tomography using modified delay-and-sum reconstruction algorithm"
638:
Bossy, Emmanuel; Daoudi, Khalid; Boccara, Albert-Claude; Tanter, Mickael; Aubry, Jean-François; Montaldo, Gabriel; Fink, Mathias (2006-10-30).
2792:
1690:
260:
1181:"Feature article: A generative adversarial network for artifact removal in photoacoustic computed tomography with a linear-array transducer"
140:
73:
reflection, resulting in acoustic reflection artifacts that corrupt the true photoacoustic point source location information. In Reiter
696:
Treeby, Bradley E; Zhang, Edward Z; Cox, B T (2010-09-24). "Photoacoustic tomography in absorbing acoustic media using time reversal".
320:
The two primary motion artifact types addressed by deep learning in PAM are displacements in the vertical and tilted directions. Chen
1269:
238:
1655:
Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas (2015), "U-Net: Convolutional
Networks for Biomedical Image Segmentation",
1051:
Davoudi, Neda; Deán-Ben, Xosé Luís; Razansky, Daniel (2019-09-16). "Deep learning optoacoustic tomography with sparse data".
187:
341:
Noisy input, denoised output through U-Net and averaged ground truth frequency-domain PA amplitude images of two label-free
2083:
Liang, Jinyang; Zhou, Yong; Winkler, Amy W.; Wang, Lidai; Maslov, Konstantin I.; Li, Chiye; Wang, Lihong V. (2013-07-22).
518:
Xu, Minghua; Wang, Lihong V. (2005-01-19). "Universal back-projection algorithm for photoacoustic computed tomography".
228:
experiments with homogenous medium, but Guan posits that the pixel-wise method can be used for real time PAT rendering.
153:
1570:
Simonyan, Karen; Zisserman, Andrew (2015-04-10). "Very Deep
Convolutional Networks for Large-Scale Image Recognition".
1520:"PA-Fuse: deep supervised approach for the fusion of photoacoustic images with distinct reconstruction characteristics"
1836:
Xia, Jun; Chatni, Muhammad R.; Maslov, Konstantin; Guo, Zijian; Wang, Kun; Anastasio, Mark; Wang, Lihong V. (2012).
217:
211:
To improve the speed of reconstruction and to allow for the FD U-net to use more information from the sensor, Guan
144:
91:
46:(PAM). PACT utilizes wide-field optical excitation and an array of unfocused ultrasound transducers. Similar to
2802:
2773:
2593:"Full image reconstruction in frequency-domain photoacoustic microscopy by means of a low-cost I/Q demodulator"
364:
221:
43:
1962:
Provost, J.; Lesage, F. (April 2009). "The Application of Compressed Sensing for Photo-Acoustic Tomography".
2797:
1659:, Lecture Notes in Computer Science, vol. 9351, Springer International Publishing, pp. 234–241,
2378:
Manwar, Rayyan; Li, Xin; Mahmoodkalayeh, Sadreddin; Asano, Eishi; Zhu, Dongxiao; Avanaki, Kamran (2020).
2768:
359:
274:
39:
28:
2778:
2716:
2604:
2479:
2335:
2284:
2222:
2157:
2096:
2033:
1920:
1849:
1784:
1729:
1670:
1610:
1389:
1249:
818:
705:
654:
584:
527:
409:
369:
156:(CNN) is trained to remove the artifacts, in order to produce an artifact-free representation of the
282:
sheep brain. Manwar claims that this technology could be beneficial in neonatal brain imaging where
2591:
Tserevelakis, George J.; Mavrakis, Kostas G.; Kakakios, Nikitas; Zacharakis, Giannis (2021-10-01).
2748:
2646:
Langer, Gregor; Buchegger, Bianca; Jacak, Jaroslaw; Klar, Thomas A.; Berer, Thomas (2016-07-01).
2469:
2425:
2191:
2065:
2023:
1995:
1944:
1910:
1696:
1660:
1634:
1600:
1571:
1356:
1333:
1275:
1146:
1076:
1022:
988:
834:
729:
678:
283:
191:
2534:"Deep-learning-based motion-correction algorithm in optical resolution photoacoustic microscopy"
1714:
16:
2740:
2732:
2685:
2667:
2628:
2620:
2573:
2555:
2505:
2417:
2399:
2351:
2308:
2300:
2256:
2238:
2183:
2130:
2112:
2085:"Random-access optical-resolution photoacoustic microscopy using a digital micromirror device"
2057:
2049:
1987:
1979:
1936:
1883:
1865:
1818:
1800:
1753:
1745:
1686:
1626:
1549:
1493:
1475:
1425:
1417:
1325:
1265:
1218:
1200:
1138:
1120:
1068:
1014:
1006:
956:
938:
894:
876:
786:
768:
721:
670:
620:
612:
553:
500:
482:
443:
425:
304:
110:
Removing acoustic reflection artifacts (in the presence of multiple sources and channel noise)
312:
model moves during scanning. This movement creates the appearance of vessel discontinuities.
2724:
2675:
2659:
2612:
2563:
2545:
2495:
2487:
2407:
2391:
2343:
2292:
2246:
2230:
2173:
2165:
2120:
2104:
2041:
1971:
1928:
1873:
1857:
1838:"Whole-body ring-shaped confocal photoacoustic computed tomography of small animals in vivo"
1808:
1792:
1737:
1678:
1618:
1539:
1531:
1483:
1467:
1407:
1397:
1315:
1307:
1257:
1208:
1192:
1128:
1110:
1060:
998:
946:
930:
884:
868:
826:
776:
760:
713:
662:
602:
592:
543:
535:
490:
474:
433:
417:
241:(SNR), which is not always possible, while the deep learning model has no such restriction.
198:
Pixel-wise interpolation and deep learning for faster reconstruction of limited-view signals
182:
2704:
99:
857:"Photoacoustic Source Detection and Reflection Artifact Removal Enabled by Deep Learning"
717:
152:
2-D representation of the initial pressure distribution that contains artifacts. Then, a
2720:
2608:
2592:
2483:
2412:
2379:
2339:
2288:
2226:
2161:
2100:
2037:
1924:
1853:
1788:
1733:
1674:
1614:
1456:"A Deep Learning approach to Photoacoustic Wavefront Localization in Deep-Tissue Medium"
1393:
1253:
822:
709:
658:
588:
531:
413:
2680:
2647:
2568:
2533:
2500:
2457:
2251:
2210:
2125:
2084:
1878:
1837:
1813:
1772:
1544:
1519:
1488:
1455:
1213:
1180:
1133:
951:
918:
889:
856:
781:
748:
495:
462:
438:
397:
95:
2458:"Limited View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learning"
2234:
2786:
2752:
2429:
1622:
1337:
1300:
Published in: IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
1248:. Vol. 10494. International Society for Optics and Photonics. pp. 104942S.
1080:
682:
32:
2195:
2069:
1999:
1948:
1638:
1279:
1026:
838:
733:
1700:
1150:
157:
147:, but the advent of deep learning approaches has opened a new avenue that utilizes
934:
345:
embryos. Yellow arrows indicate the cell membranes. Scalebars are equal to 100 μm.
245:
Fusion of information for improving photoacoustic Images with deep neural networks
181:, limited-view corruptions can be directly observed as missing information in the
1682:
1099:"Model-Based Learning for Accelerated, Limited-View 3-D Photoacoustic Tomography"
2491:
1796:
1471:
1402:
1377:
1311:
539:
2550:
1861:
1713:
Xu, Yuan; Wang, Lihong V.; Ambartsoumian, Gaik; Kuchment, Peter (2004-03-11).
1064:
1002:
597:
572:
2736:
2671:
2624:
2559:
2403:
2355:
2304:
2242:
2187:
2116:
2053:
1983:
1975:
1940:
1869:
1804:
1749:
1630:
1479:
1421:
1204:
1196:
1124:
1115:
1072:
1010:
942:
880:
872:
772:
725:
674:
616:
486:
429:
421:
2169:
1773:"Improving limited-view photoacoustic tomography with an acoustic reflector"
1179:
Vu, Tri; Li, Mucong; Humayun, Hannah; Zhou, Yuan; Yao, Junjie (2020-03-25).
2744:
2689:
2632:
2577:
2509:
2456:
Guan, Steven; Khan, Amir A.; Sikdar, Siddhartha; Chitnis, Parag V. (2020).
2421:
2395:
2312:
2260:
2134:
2061:
1991:
1887:
1822:
1757:
1553:
1497:
1429:
1329:
1222:
1142:
1018:
960:
898:
790:
624:
557:
504:
478:
447:
1535:
2663:
2296:
2108:
548:
103:
1771:
Huang, Bin; Xia, Jun; Maslov, Konstantin; Wang, Lihong V. (2013-11-27).
1657:
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015
1320:
294:
1460:
IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
1412:
1378:"Deep neural network-based bandwidth enhancement of photoacoustic data"
1261:
830:
764:
607:
47:
2728:
2616:
2347:
2178:
2045:
1932:
1741:
917:
Antholzer, Stephan; Haltmeier, Markus; Schwab, Johannes (2019-07-03).
666:
337:
855:
Allman, Derek; Reiter, Austin; Bell, Muyinatu A. Lediju (June 2018).
124:
749:"A Practical Guide to Photoacoustic Tomography in the Life Sciences"
2474:
2028:
1915:
1665:
1361:
993:
224:. The pixel-wise method proposed in this study was only proven for
2705:"Deep learning-assisted frequency-domain photoacoustic microscopy"
1605:
1576:
2380:"Deep learning protocol for improved photoacoustic brain imaging"
130:, and then later reaffirmed their results on experimental data.
38:
Photoacoustic imaging has applications of deep learning in both
1098:
919:"Deep learning for photoacoustic tomography from sparse data"
398:"Multiscale photoacoustic microscopy and computed tomography"
59:
The first application of deep learning in PACT was by Reiter
2648:"Frequency domain photoacoustic and fluorescence microscopy"
232:
Limited-bandwidth artifact removal with deep neural networks
2211:"Weight factors for limited angle photoacoustic tomography"
1715:"Reconstructions in limited-view thermoacoustic tomography"
817:. International Society for Optics and Photonics: 100643J.
127:
68:
Using deep learning to locate photoacoustic point sources
571:
Kalva, Sandeep Kumar; Pramanik, Manojit (August 2016).
254:
Deep learning to improve penetration depth of PA images
164:
Using deep learning to remove sparse sampling artifacts
194:
and gradient penalty to stabilize training (WGAN-GP).
2538:
Visual Computing for Industry, Biomedicine, and Art
2209:Paltauf, G; Nuster, R; Burgholzer, P (2009-05-08).
2532:Chen, Xingxing; Qi, Weizhi; Xi, Lei (2019-10-29).
173:Removing limited-view artifacts with deep learning
106:cell detection, and real-time vascular surgeries.
1246:Photons Plus Ultrasound: Imaging and Sensing 2018
981:IEEE Journal of Biomedical and Health Informatics
811:Photons Plus Ultrasound: Imaging and Sensing 2017
2016:The Journal of the Acoustical Society of America
286:is possible to look for any lessions or injury.
316:Deep learning to remove motion artifacts in PAM
298:Depiction of mechanical raster scanning method
8:
923:Inverse Problems in Science and Engineering
747:Wang, Lihong V.; Yao, Junjie (2016-07-28).
333:Deep learning-assisted frequency-domain PAM
81:Deep learning for PA wavefront localization
2679:
2567:
2549:
2499:
2473:
2411:
2250:
2177:
2124:
2027:
1914:
1877:
1812:
1664:
1604:
1575:
1543:
1487:
1411:
1401:
1360:
1319:
1212:
1132:
1114:
992:
950:
888:
780:
606:
596:
547:
494:
437:
336:
293:
31:(PA) with the rapidly evolving field of
27:combines the hybrid imaging modality of
15:
1524:Published in: Biomedical Optics Express
381:
2527:
2525:
2523:
2521:
2519:
2451:
2449:
2447:
2445:
2443:
2441:
2439:
2373:
2371:
2369:
2367:
2365:
1650:
1648:
1513:
1511:
1509:
1507:
1449:
1447:
1445:
1443:
1441:
1439:
1349:
1347:
1293:
1291:
1289:
640:"Time reversal of photoacoustic waves"
25:Deep learning in photoacoustic imaging
1565:
1563:
1238:
1236:
1234:
1232:
1174:
1172:
1170:
1168:
1166:
1164:
1162:
1160:
1092:
1090:
1046:
1044:
1042:
1040:
1038:
1036:
974:
972:
970:
912:
910:
908:
261:American National Standards Institute
55:Applications of deep learning in PACT
20:Depiction of photoacoustic tomography
7:
1964:IEEE Transactions on Medical Imaging
1103:IEEE Transactions on Medical Imaging
861:IEEE Transactions on Medical Imaging
850:
848:
804:
802:
800:
391:
389:
387:
385:
290:Applications of deep learning in PAM
1903:SIAM Journal on Applied Mathematics
1518:Awasthi, Navchetan (3 April 2019).
463:"Biomedical photoacoustic imaging"
14:
1185:Experimental Biology and Medicine
40:photoacoustic computed tomography
2215:Physics in Medicine and Biology
2150:IEEE Signal Processing Magazine
188:generative adversarial networks
160:initial pressure distribution.
114:Building on the work of Reiter
718:10.1088/0266-5611/26/11/115003
396:Wang, Lihong V. (2009-08-29).
1:
935:10.1080/17415977.2018.1518444
134:Ill-posed PACT reconstruction
92:light-diffusion approximation
2793:Computing in medical imaging
1842:Journal of Biomedical Optics
1777:Journal of Biomedical Optics
1683:10.1007/978-3-319-24574-4_28
1382:Journal of Biomedical Optics
577:Journal of Biomedical Optics
154:convolutional neural network
145:total variation minimization
2235:10.1088/0031-9155/54/11/002
1053:Nature Machine Intelligence
218:peak signal to noise ratios
2819:
2492:10.1038/s41598-020-65235-2
2328:Journal of Applied Physics
1797:10.1117/1.jbo.18.11.110505
1623:10.1088/0266-5611/23/5/016
1472:10.1109/tuffc.2020.2964698
1403:10.1117/1.jbo.22.11.116001
1312:10.1109/TUFFC.2020.2977210
540:10.1103/PhysRevE.71.016706
461:Beard, Paul (2011-08-06).
2652:Biomedical Optics Express
2551:10.1186/s42492-019-0022-9
1862:10.1117/1.jbo.17.5.050506
1065:10.1038/s42256-019-0095-3
1003:10.1109/jbhi.2019.2912935
598:10.1117/1.JBO.21.8.086011
100:optical wavefront shaping
48:other computed tomography
2774:Photoacoustic microscopy
1976:10.1109/tmi.2008.2007825
1197:10.1177/1535370220914285
1116:10.1109/TMI.2018.2820382
873:10.1109/TMI.2018.2829662
422:10.1038/nphoton.2009.157
365:Photoacoustic microscopy
44:photoacoustic microscopy
2384:Journal of Biophotonics
2334:(12): 123104–123104–6.
2170:10.1109/msp.2007.914730
647:Applied Physics Letters
284:transfontanelle imaging
2396:10.1002/jbio.202000212
479:10.1098/rsfs.2011.0028
346:
299:
21:
2769:Photoacoustic imaging
1536:10.1364/BOE.10.002227
360:Photoacoustic imaging
340:
297:
275:signal-to-noise ratio
239:signal-to-noise ratio
29:photoacoustic imaging
19:
2779:Photoacoustic effect
2664:10.1364/BOE.7.002692
2297:10.1364/ao.52.003477
2109:10.1364/ol.38.002683
370:Photoacoustic effect
2721:2023OptL...48.2720T
2609:2021OptL...46.4718T
2484:2020NatSR..10.8510G
2340:2009JAP...106l3104M
2289:2013ApOpt..52.3477L
2227:2009PMB....54.3303P
2162:2008ISPM...25...83D
2101:2013OptL...38.2683L
2038:2018ASAJ..143.3838H
1925:2015arXiv150104305S
1854:2012JBO....17e0506X
1789:2013JBO....18k0505H
1734:2004MedPh..31..724X
1675:2015arXiv150504597R
1615:2007InvPr..23.2089A
1394:2017JBO....22k6001G
1254:2018SPIE10494E..2SW
823:2017SPIE10064E..3JR
710:2010InvPr..26k5003T
659:2006ApPhL..89r4108B
589:2016JBO....21h6011K
532:2005PhRvE..71a6706X
414:2009NaPho...3..503W
343:Parhyale hawaiensis
2462:Scientific Reports
2390:(10): e202000212.
1262:10.1117/12.2288353
831:10.1117/12.2255098
765:10.1038/nmeth.3925
347:
300:
222:iterative approach
192:Wasserstein metric
22:
2729:10.1364/OL.486624
2715:(10): 2720–2723.
2617:10.1364/OL.435146
2603:(19): 4718–4721.
2348:10.1063/1.3273322
2221:(11): 3303–3314.
2046:10.1121/1.5042230
1933:10.1137/141001408
1742:10.1118/1.1644531
1692:978-3-319-24573-7
1466:(12): 2649–2659.
1306:(12): 2660–2673.
667:10.1063/1.2382732
520:Physical Review E
305:Hilbert transform
2810:
2757:
2756:
2700:
2694:
2693:
2683:
2658:(7): 2692–3302.
2643:
2637:
2636:
2588:
2582:
2581:
2571:
2553:
2529:
2514:
2513:
2503:
2477:
2453:
2434:
2433:
2415:
2375:
2360:
2359:
2323:
2317:
2316:
2271:
2265:
2264:
2254:
2206:
2200:
2199:
2181:
2145:
2139:
2138:
2128:
2080:
2074:
2073:
2031:
2022:(6): 3838–3848.
2010:
2004:
2003:
1959:
1953:
1952:
1918:
1909:(6): 2475–2494.
1898:
1892:
1891:
1881:
1833:
1827:
1826:
1816:
1768:
1762:
1761:
1719:
1710:
1704:
1703:
1668:
1652:
1643:
1642:
1608:
1599:(5): 2089–2102.
1593:Inverse Problems
1588:
1582:
1581:
1579:
1567:
1558:
1557:
1547:
1530:(5): 2227–2243.
1515:
1502:
1501:
1491:
1451:
1434:
1433:
1415:
1405:
1373:
1367:
1366:
1364:
1351:
1342:
1341:
1323:
1295:
1284:
1283:
1240:
1227:
1226:
1216:
1176:
1155:
1154:
1136:
1118:
1109:(6): 1382–1393.
1094:
1085:
1084:
1048:
1031:
1030:
996:
976:
965:
964:
954:
914:
903:
902:
892:
867:(6): 1464–1477.
852:
843:
842:
806:
795:
794:
784:
744:
738:
737:
698:Inverse Problems
693:
687:
686:
644:
635:
629:
628:
610:
600:
568:
562:
561:
551:
515:
509:
508:
498:
458:
452:
451:
441:
402:Nature Photonics
393:
183:frequency domain
2818:
2817:
2813:
2812:
2811:
2809:
2808:
2807:
2803:Medical imaging
2783:
2782:
2766:
2761:
2760:
2702:
2701:
2697:
2645:
2644:
2640:
2590:
2589:
2585:
2531:
2530:
2517:
2455:
2454:
2437:
2377:
2376:
2363:
2325:
2324:
2320:
2283:(15): 3477–83.
2273:
2272:
2268:
2208:
2207:
2203:
2147:
2146:
2142:
2082:
2081:
2077:
2012:
2011:
2007:
1961:
1960:
1956:
1900:
1899:
1895:
1835:
1834:
1830:
1770:
1769:
1765:
1722:Medical Physics
1717:
1712:
1711:
1707:
1693:
1654:
1653:
1646:
1590:
1589:
1585:
1569:
1568:
1561:
1517:
1516:
1505:
1453:
1452:
1437:
1375:
1374:
1370:
1353:
1352:
1345:
1297:
1296:
1287:
1272:
1242:
1241:
1230:
1178:
1177:
1158:
1096:
1095:
1088:
1059:(10): 453–460.
1050:
1049:
1034:
978:
977:
968:
929:(7): 987–1005.
916:
915:
906:
854:
853:
846:
808:
807:
798:
746:
745:
741:
695:
694:
690:
642:
637:
636:
632:
570:
569:
565:
517:
516:
512:
467:Interface Focus
460:
459:
455:
395:
394:
383:
378:
356:
335:
318:
292:
256:
234:
200:
175:
166:
141:Nyquist-Shannon
136:
112:
83:
70:
57:
12:
11:
5:
2816:
2814:
2806:
2805:
2800:
2795:
2785:
2784:
2765:
2764:External links
2762:
2759:
2758:
2709:Optics Letters
2695:
2638:
2597:Optics Letters
2583:
2515:
2435:
2361:
2318:
2277:Applied Optics
2266:
2201:
2140:
2095:(15): 2683–6.
2089:Optics Letters
2075:
2005:
1970:(4): 585–594.
1954:
1893:
1828:
1783:(11): 110505.
1763:
1728:(4): 724–733.
1705:
1691:
1644:
1583:
1559:
1503:
1435:
1388:(11): 116001.
1368:
1343:
1285:
1270:
1228:
1191:(7): 597–605.
1156:
1086:
1032:
987:(2): 568–576.
966:
904:
844:
796:
759:(8): 627–638.
753:Nature Methods
739:
704:(11): 115003.
688:
653:(18): 184108.
630:
563:
510:
473:(4): 602–631.
453:
408:(9): 503–509.
380:
379:
377:
374:
373:
372:
367:
362:
355:
352:
334:
331:
317:
314:
291:
288:
255:
252:
233:
230:
199:
196:
174:
171:
165:
162:
135:
132:
128:k-wave library
111:
108:
102:, circulating
96:Gaussian noise
85:Johnstonbaugh
82:
79:
69:
66:
56:
53:
13:
10:
9:
6:
4:
3:
2:
2815:
2804:
2801:
2799:
2798:Deep learning
2796:
2794:
2791:
2790:
2788:
2781:
2780:
2776:
2775:
2771:
2770:
2763:
2754:
2750:
2746:
2742:
2738:
2734:
2730:
2726:
2722:
2718:
2714:
2710:
2706:
2699:
2696:
2691:
2687:
2682:
2677:
2673:
2669:
2665:
2661:
2657:
2653:
2649:
2642:
2639:
2634:
2630:
2626:
2622:
2618:
2614:
2610:
2606:
2602:
2598:
2594:
2587:
2584:
2579:
2575:
2570:
2565:
2561:
2557:
2552:
2547:
2543:
2539:
2535:
2528:
2526:
2524:
2522:
2520:
2516:
2511:
2507:
2502:
2497:
2493:
2489:
2485:
2481:
2476:
2471:
2467:
2463:
2459:
2452:
2450:
2448:
2446:
2444:
2442:
2440:
2436:
2431:
2427:
2423:
2419:
2414:
2409:
2405:
2401:
2397:
2393:
2389:
2385:
2381:
2374:
2372:
2370:
2368:
2366:
2362:
2357:
2353:
2349:
2345:
2341:
2337:
2333:
2329:
2322:
2319:
2314:
2310:
2306:
2302:
2298:
2294:
2290:
2286:
2282:
2278:
2270:
2267:
2262:
2258:
2253:
2248:
2244:
2240:
2236:
2232:
2228:
2224:
2220:
2216:
2212:
2205:
2202:
2197:
2193:
2189:
2185:
2180:
2175:
2171:
2167:
2163:
2159:
2155:
2151:
2144:
2141:
2136:
2132:
2127:
2122:
2118:
2114:
2110:
2106:
2102:
2098:
2094:
2090:
2086:
2079:
2076:
2071:
2067:
2063:
2059:
2055:
2051:
2047:
2043:
2039:
2035:
2030:
2025:
2021:
2017:
2009:
2006:
2001:
1997:
1993:
1989:
1985:
1981:
1977:
1973:
1969:
1965:
1958:
1955:
1950:
1946:
1942:
1938:
1934:
1930:
1926:
1922:
1917:
1912:
1908:
1904:
1897:
1894:
1889:
1885:
1880:
1875:
1871:
1867:
1863:
1859:
1855:
1851:
1848:(5): 050506.
1847:
1843:
1839:
1832:
1829:
1824:
1820:
1815:
1810:
1806:
1802:
1798:
1794:
1790:
1786:
1782:
1778:
1774:
1767:
1764:
1759:
1755:
1751:
1747:
1743:
1739:
1735:
1731:
1727:
1723:
1716:
1709:
1706:
1702:
1698:
1694:
1688:
1684:
1680:
1676:
1672:
1667:
1662:
1658:
1651:
1649:
1645:
1640:
1636:
1632:
1628:
1624:
1620:
1616:
1612:
1607:
1602:
1598:
1594:
1587:
1584:
1578:
1573:
1566:
1564:
1560:
1555:
1551:
1546:
1541:
1537:
1533:
1529:
1525:
1521:
1514:
1512:
1510:
1508:
1504:
1499:
1495:
1490:
1485:
1481:
1477:
1473:
1469:
1465:
1461:
1457:
1450:
1448:
1446:
1444:
1442:
1440:
1436:
1431:
1427:
1423:
1419:
1414:
1409:
1404:
1399:
1395:
1391:
1387:
1383:
1379:
1372:
1369:
1363:
1358:
1350:
1348:
1344:
1339:
1335:
1331:
1327:
1322:
1317:
1313:
1309:
1305:
1301:
1294:
1292:
1290:
1286:
1281:
1277:
1273:
1271:9781510614734
1267:
1263:
1259:
1255:
1251:
1247:
1239:
1237:
1235:
1233:
1229:
1224:
1220:
1215:
1210:
1206:
1202:
1198:
1194:
1190:
1186:
1182:
1175:
1173:
1171:
1169:
1167:
1165:
1163:
1161:
1157:
1152:
1148:
1144:
1140:
1135:
1130:
1126:
1122:
1117:
1112:
1108:
1104:
1100:
1093:
1091:
1087:
1082:
1078:
1074:
1070:
1066:
1062:
1058:
1054:
1047:
1045:
1043:
1041:
1039:
1037:
1033:
1028:
1024:
1020:
1016:
1012:
1008:
1004:
1000:
995:
990:
986:
982:
975:
973:
971:
967:
962:
958:
953:
948:
944:
940:
936:
932:
928:
924:
920:
913:
911:
909:
905:
900:
896:
891:
886:
882:
878:
874:
870:
866:
862:
858:
851:
849:
845:
840:
836:
832:
828:
824:
820:
816:
812:
805:
803:
801:
797:
792:
788:
783:
778:
774:
770:
766:
762:
758:
754:
750:
743:
740:
735:
731:
727:
723:
719:
715:
711:
707:
703:
699:
692:
689:
684:
680:
676:
672:
668:
664:
660:
656:
652:
648:
641:
634:
631:
626:
622:
618:
614:
609:
604:
599:
594:
590:
586:
583:(8): 086011.
582:
578:
574:
567:
564:
559:
555:
550:
549:1969.1/180492
545:
541:
537:
533:
529:
526:(1): 016706.
525:
521:
514:
511:
506:
502:
497:
492:
488:
484:
480:
476:
472:
468:
464:
457:
454:
449:
445:
440:
435:
431:
427:
423:
419:
415:
411:
407:
403:
399:
392:
390:
388:
386:
382:
375:
371:
368:
366:
363:
361:
358:
357:
353:
351:
344:
339:
332:
330:
328:
323:
315:
313:
311:
306:
296:
289:
287:
285:
281:
276:
271:
266:
262:
253:
251:
247:
246:
242:
240:
231:
229:
227:
223:
219:
214:
210:
205:
197:
195:
193:
189:
184:
180:
172:
170:
163:
161:
159:
155:
150:
146:
142:
133:
131:
129:
126:
121:
117:
109:
107:
105:
101:
97:
93:
88:
80:
78:
76:
67:
65:
62:
54:
52:
49:
45:
41:
36:
34:
33:deep learning
30:
26:
18:
2777:
2772:
2767:
2712:
2708:
2698:
2655:
2651:
2641:
2600:
2596:
2586:
2541:
2537:
2465:
2461:
2387:
2383:
2331:
2327:
2321:
2280:
2276:
2269:
2218:
2214:
2204:
2156:(2): 83–91.
2153:
2149:
2143:
2092:
2088:
2078:
2019:
2015:
2008:
1967:
1963:
1957:
1906:
1902:
1896:
1845:
1841:
1831:
1780:
1776:
1766:
1725:
1721:
1708:
1656:
1596:
1592:
1586:
1527:
1523:
1463:
1459:
1385:
1381:
1371:
1321:10356/146551
1303:
1299:
1245:
1188:
1184:
1106:
1102:
1056:
1052:
984:
980:
926:
922:
864:
860:
814:
810:
756:
752:
742:
701:
697:
691:
650:
646:
633:
580:
576:
566:
523:
519:
513:
470:
466:
456:
405:
401:
348:
342:
326:
321:
319:
309:
301:
279:
269:
264:
257:
248:
244:
243:
235:
225:
212:
208:
203:
201:
178:
176:
167:
158:ground truth
148:
137:
119:
115:
113:
86:
84:
74:
71:
60:
58:
37:
24:
23:
2468:(1): 8510.
1413:10356/86305
608:10356/82178
42:(PACT) and
2787:Categories
2475:1911.04357
2179:1911/21682
2029:1801.00117
1916:1501.04305
1666:1505.04597
1362:2001.06434
994:1808.10848
376:References
2753:258229033
2737:1539-4794
2672:2156-7085
2625:0146-9592
2560:2524-4442
2544:(1): 12.
2430:224845812
2404:1864-0648
2356:0021-8979
2305:1559-128X
2243:0031-9155
2188:1053-5888
2117:0146-9592
2054:0001-4966
1984:0278-0062
1941:0036-1399
1870:1083-3668
1805:1083-3668
1750:0094-2405
1631:0266-5611
1606:0706.0598
1577:1409.1556
1480:0885-3010
1422:1083-3668
1338:212621872
1205:1535-3702
1125:1558-254X
1081:202640890
1073:2522-5839
1011:2168-2194
943:1741-5977
881:1558-254X
773:1548-7091
726:0266-5611
683:121195599
675:0003-6951
617:1083-3668
487:2042-8898
430:1749-4885
226:in silico
118:, Allman
2745:37186749
2690:27446698
2633:34598182
2578:32240397
2510:32444649
2422:33405275
2413:10906453
2313:23736232
2261:19430108
2196:11454318
2135:23903111
2070:49643233
2062:29960458
2000:11398335
1992:19272991
1949:15701831
1888:22612121
1823:24285421
1758:15124989
1639:17810059
1554:31149371
1498:31944951
1430:29098811
1330:32142429
1280:57745829
1223:32208974
1143:29870367
1027:52143594
1019:31021809
961:31057659
899:29870374
839:35030143
791:27467726
734:14745088
625:27548773
558:15697763
505:22866233
448:20161535
354:See also
149:a priori
104:melanoma
2717:Bibcode
2681:4948622
2605:Bibcode
2569:7099543
2501:7244747
2480:Bibcode
2336:Bibcode
2285:Bibcode
2252:3166844
2223:Bibcode
2158:Bibcode
2126:3784350
2097:Bibcode
2034:Bibcode
1921:Bibcode
1879:3382342
1850:Bibcode
1814:3818029
1785:Bibcode
1730:Bibcode
1701:3719281
1671:Bibcode
1611:Bibcode
1545:6524595
1489:7769001
1390:Bibcode
1250:Bibcode
1214:7153213
1151:4321879
1134:7613684
952:6474723
890:6075868
819:Bibcode
782:4980387
706:Bibcode
655:Bibcode
585:Bibcode
528:Bibcode
496:3262268
439:2802217
410:Bibcode
327:in vivo
310:in vivo
280:in vivo
270:ex vivo
2751:
2743:
2735:
2688:
2678:
2670:
2631:
2623:
2576:
2566:
2558:
2508:
2498:
2428:
2420:
2410:
2402:
2354:
2311:
2303:
2259:
2249:
2241:
2194:
2186:
2133:
2123:
2115:
2068:
2060:
2052:
1998:
1990:
1982:
1947:
1939:
1886:
1876:
1868:
1821:
1811:
1803:
1756:
1748:
1699:
1689:
1637:
1629:
1552:
1542:
1496:
1486:
1478:
1428:
1420:
1336:
1328:
1278:
1268:
1221:
1211:
1203:
1149:
1141:
1131:
1123:
1079:
1071:
1025:
1017:
1009:
959:
949:
941:
897:
887:
879:
837:
789:
779:
771:
732:
724:
681:
673:
623:
615:
556:
503:
493:
485:
446:
436:
428:
329:data.
322:et al.
265:et al.
213:et al.
209:et al.
204:et al.
179:et al.
125:MATLAB
120:et al.
116:et al.
87:et al.
75:et al.
61:et al.
2749:S2CID
2470:arXiv
2426:S2CID
2192:S2CID
2066:S2CID
2024:arXiv
1996:S2CID
1945:S2CID
1911:arXiv
1718:(PDF)
1697:S2CID
1661:arXiv
1635:S2CID
1601:arXiv
1572:arXiv
1357:arXiv
1334:S2CID
1276:S2CID
1147:S2CID
1077:S2CID
1023:S2CID
989:arXiv
835:S2CID
815:10064
730:S2CID
679:S2CID
643:(PDF)
202:Guan
2741:PMID
2733:ISSN
2686:PMID
2668:ISSN
2629:PMID
2621:ISSN
2574:PMID
2556:ISSN
2506:PMID
2418:PMID
2400:ISSN
2352:ISSN
2309:PMID
2301:ISSN
2257:PMID
2239:ISSN
2184:ISSN
2131:PMID
2113:ISSN
2058:PMID
2050:ISSN
1988:PMID
1980:ISSN
1937:ISSN
1884:PMID
1866:ISSN
1819:PMID
1801:ISSN
1754:PMID
1746:ISSN
1687:ISBN
1627:ISSN
1550:PMID
1494:PMID
1476:ISSN
1426:PMID
1418:ISSN
1326:PMID
1266:ISBN
1219:PMID
1201:ISSN
1139:PMID
1121:ISSN
1069:ISSN
1015:PMID
1007:ISSN
957:PMID
939:ISSN
895:PMID
877:ISSN
787:PMID
769:ISSN
722:ISSN
671:ISSN
621:PMID
613:ISSN
554:PMID
501:PMID
483:ISSN
444:PMID
426:ISSN
2725:doi
2676:PMC
2660:doi
2613:doi
2564:PMC
2546:doi
2496:PMC
2488:doi
2408:PMC
2392:doi
2344:doi
2332:106
2293:doi
2247:PMC
2231:doi
2174:hdl
2166:doi
2121:PMC
2105:doi
2042:doi
2020:143
1972:doi
1929:doi
1874:PMC
1858:doi
1809:PMC
1793:doi
1738:doi
1679:doi
1619:doi
1540:PMC
1532:doi
1484:PMC
1468:doi
1408:hdl
1398:doi
1316:hdl
1308:doi
1258:doi
1209:PMC
1193:doi
1189:245
1129:PMC
1111:doi
1061:doi
999:doi
947:PMC
931:doi
885:PMC
869:doi
827:doi
777:PMC
761:doi
714:doi
663:doi
603:hdl
593:doi
544:hdl
536:doi
491:PMC
475:doi
434:PMC
418:doi
2789::
2747:.
2739:.
2731:.
2723:.
2713:48
2711:.
2707:.
2684:.
2674:.
2666:.
2654:.
2650:.
2627:.
2619:.
2611:.
2601:46
2599:.
2595:.
2572:.
2562:.
2554:.
2540:.
2536:.
2518:^
2504:.
2494:.
2486:.
2478:.
2466:10
2464:.
2460:.
2438:^
2424:.
2416:.
2406:.
2398:.
2388:13
2386:.
2382:.
2364:^
2350:.
2342:.
2330:.
2307:.
2299:.
2291:.
2281:52
2279:.
2255:.
2245:.
2237:.
2229:.
2219:54
2217:.
2213:.
2190:.
2182:.
2172:.
2164:.
2154:25
2152:.
2129:.
2119:.
2111:.
2103:.
2093:38
2091:.
2087:.
2064:.
2056:.
2048:.
2040:.
2032:.
2018:.
1994:.
1986:.
1978:.
1968:28
1966:.
1943:.
1935:.
1927:.
1919:.
1907:75
1905:.
1882:.
1872:.
1864:.
1856:.
1846:17
1844:.
1840:.
1817:.
1807:.
1799:.
1791:.
1781:18
1779:.
1775:.
1752:.
1744:.
1736:.
1726:31
1724:.
1720:.
1695:,
1685:,
1677:,
1669:,
1647:^
1633:.
1625:.
1617:.
1609:.
1597:23
1595:.
1562:^
1548:.
1538:.
1528:10
1526:.
1522:.
1506:^
1492:.
1482:.
1474:.
1464:67
1462:.
1458:.
1438:^
1424:.
1416:.
1406:.
1396:.
1386:22
1384:.
1380:.
1346:^
1332:.
1324:.
1314:.
1304:67
1302:.
1288:^
1274:.
1264:.
1256:.
1231:^
1217:.
1207:.
1199:.
1187:.
1183:.
1159:^
1145:.
1137:.
1127:.
1119:.
1107:37
1105:.
1101:.
1089:^
1075:.
1067:.
1055:.
1035:^
1021:.
1013:.
1005:.
997:.
985:24
983:.
969:^
955:.
945:.
937:.
927:27
925:.
921:.
907:^
893:.
883:.
875:.
865:37
863:.
859:.
847:^
833:.
825:.
813:.
799:^
785:.
775:.
767:.
757:13
755:.
751:.
728:.
720:.
712:.
702:26
700:.
677:.
669:.
661:.
651:89
649:.
645:.
619:.
611:.
601:.
591:.
581:21
579:.
575:.
552:.
542:.
534:.
524:71
522:.
499:.
489:.
481:.
469:.
465:.
442:.
432:.
424:.
416:.
404:.
400:.
384:^
2755:.
2727::
2719::
2692:.
2662::
2656:7
2635:.
2615::
2607::
2580:.
2548::
2542:2
2512:.
2490::
2482::
2472::
2432:.
2394::
2358:.
2346::
2338::
2315:.
2295::
2287::
2263:.
2233::
2225::
2198:.
2176::
2168::
2160::
2137:.
2107::
2099::
2072:.
2044::
2036::
2026::
2002:.
1974::
1951:.
1931::
1923::
1913::
1890:.
1860::
1852::
1825:.
1795::
1787::
1760:.
1740::
1732::
1681::
1673::
1663::
1641:.
1621::
1613::
1603::
1580:.
1574::
1556:.
1534::
1500:.
1470::
1432:.
1410::
1400::
1392::
1365:.
1359::
1340:.
1318::
1310::
1282:.
1260::
1252::
1225:.
1195::
1153:.
1113::
1083:.
1063::
1057:1
1029:.
1001::
991::
963:.
933::
901:.
871::
841:.
829::
821::
793:.
763::
736:.
716::
708::
685:.
665::
657::
627:.
605::
595::
587::
560:.
546::
538::
530::
507:.
477::
471:1
450:.
420::
412::
406:3
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.