1<!DOCTYPE HTML> 2<html lang="en"> 3<head> 4 <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> 5 <title>Pak Hei (Hugo) Yeung</title> 6 <meta name="author" content="Pak Hei (Hugo) Yeung"> 7 <meta name="viewport" content="width=device-width, initial-scale=1"> 8 <link rel="stylesheet" type="text/css" href="stylesheet.css"> 9</head> 10<body> 11 <!-- Main content table --> 12 <table style="width:100%;max-width:800px;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> 13 <tbody> 14 <tr> 15 <td> 16 17 <!-- Profile information --> 18 <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> 19 <tbody> 20 <tr> 21 <td style="padding:2.5%;width:63%;vertical-align:middle"> 22 <p style="text-align:center"> 23 <name>Pak Hei (Hugo) YEUNG 楊栢熙</name> 24 </p> 25 26 <!-- Personal information --> 27 <p> 28 I am an Assistant Professor 29 in the <a href="https://qurai.amsterdam/researcher/pak-hei-yeung/">Quantitative Healthcare Analysis (qurAI)</a> group 30 at the University of Amsterdam. 31 </p> 32 33 <p> 34 I am also an associate researcher 35 in the <a href="https://omni.cs.ox.ac.uk/">Oxford Machine Learning in NeuroImaging Lab (OMNI)</a> 36 at the University of Oxford, 37 where I obtained my DPhil (<em>i.e.</em> PhD) under the supervision of 38 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Prof. Ana Namburete</a> 39 and <a href="https://weidixie.github.io/">Prof. Weidi Xie</a>, 40 generously supported by The R C Lee Centenary Scholarship. 41 </p> 42 43 <p> 44 I received my BEng in Medical Engineering from the University of Hong Kong, 45 where I was supervised by 46 <a href="https://www.eee.hku.hk/~wnlee/people.html">Prof. Wei<span>‐</span>Ning Lee</a> 47 for my final year project. 48 </p> 49 50 <!-- Contact links --> 51 <p style="text-align:center"> 52 <a href="mailto:[email protected]">Email</a> / 53 <a href="https://scholar.google.com/citations?view_op=list_works&hl=en&user=wJD2IMcAAAAJ">Google Scholar</a> / 54 <a href="https://twitter.com/PakHei_Yeung">Twitter</a> / 55 <a href="https://github.com/pakheiyeung/">Github</a> / 56 <!-- <a href="./data/Pak_Hei_Yeung-CV.pdf">CV</a> --> 57 </p> 58 </td> 59 <td style="padding:2.5%;width:40%;max-width:40%"> 60 <!-- Profile image --> 61 <a href="image/icon_suit_circle.JPG"> 62 <img style="width:100%;max-width:100%" alt="profile photo" src="image/icon_suit_circle.jpg" class="hoverZoomLink"> 63 </a> 64 </td> 65 </tr> 66 </tbody> 67 </table> 68 69 <!-- Research section --> 70 <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> 71 <tbody> 72 <tr> 73 <td style="padding:20px;width:100%;vertical-align:middle"> 74 <heading>Selected Works</heading> 75 <p> 76 I'm interested in medical image analysis, machine learning, ultrasound imaging, and computer vision. 77 Please check my <a href="https://scholar.google.com/citations?view_op=list_works&hl=en&user=wJD2IMcAAAAJ">Google Scholar</a> for the most updated and complete list of publications. 78 </p> 79 <p> 80 * stands for co-first or co-last authorship. 81 </p> 82 </td> 83 </tr> 84 </tbody> 85 </table> 86 87 <!-- Projects Section --> 88 <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> 89 <tbody> 90 <!-- ====== Project Blocks Start ====== --> 91 92 <!-- [Project 12] M&N --> 93 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 94 <td style="padding:20px;width:25%;vertical-align:middle"> 95 <div class="one"> 96 <div class="two" id='qaerts'> 97 <video width=100% height=100% muted autoplay loop> 98 <source src="image/m&n.jpg" type="video/mp4"> 99 Your browser does not support the video tag. 100 </video> 101 </div> 102 <img src='image/m&n.jpg' width="160"> 103 </div> 104
104<script type="text/javascript"> 105 function nerfbake_start() { 106 document.getElementById('qaerts').style.opacity = "1"; 107 } 108 function nerfbake_stop() { 109 document.getElementById('qaerts').style.opacity = "0"; 110 } 111 nerfbake_stop(); 112 </script>
112 113 </td> 114 <td style="padding:20px;width:75%;vertical-align:middle"> 115 <!-- Project details --> 116 <a href="https://pakheiyeung.github.io/M-N_wp/"> 117 <papertitle>Semi-Supervised 3D Medical Segmentation from 2D Natural Images Pretrained Model</papertitle> 118 </a> 119 <br> 120 <!-- Authors --> 121 <strong>Pak Hei Yeung</strong>, 122 <a href="https://reuben.ox.ac.uk/people/jayroop-ramesh">Jayroop Ramesh</a>, 123 <a href="https://ieeexplore.ieee.org/author/37089412766">Pengfei Lyu</a>, 124 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Ana I.L. Namburete</a>, 125 <a href="https://personal.ntu.edu.sg/asjagath/">Jagath Ragapakse</a>, 126 <br> 127 <em>Machine Learning in Medical Imaging (MLMI)</em>, 2025 <strong>(Oral)</strong> 128 <br> 129 <a href="https://pakheiyeung.github.io/M-N_wp/">project page</a> / 130 <a href="https://arxiv.org/abs/2509.15167">paper</a> / 131 <a href="https://github.com/pakheiyeung/M-N">code</a> / 132 <a href="https://www.youtube.com/watch?v=mCc9JTBRHNM">video</a> / 133 <a href="./data/m&n_bibtex.bib">bibtex</a> 134 <p></p> 135 <p>A model-agnostic approach for transferring knowledge from 2D natural images pretrained models for 3D medical image segmentation with only a few labeled data.</p> 136 </td> 137 </tr> 138 139 140 141 <!-- [Project 11] FedDEAP --> 142 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 143 <td style="padding:20px;width:25%;vertical-align:middle"> 144 <div class="one"> 145 <div class="two" id='feddeap'> 146 <video width=100% height=100% muted autoplay loop> 147 <source src="image/feddeap.jpg" type="video/mp4"> 148 Your browser does not support the video tag. 149 </video> 150 </div> 151 <img src='image/feddeap.jpg' width="160"> 152 </div> 153
153<script type="text/javascript"> 154 function nerfbake_start() { 155 document.getElementById('feddeap').style.opacity = "1"; 156 } 157 function nerfbake_stop() { 158 document.getElementById('feddeap').style.opacity = "0"; 159 } 160 nerfbake_stop(); 161 </script>
161 162 </td> 163 <td style="padding:20px;width:75%;vertical-align:middle"> 164 <!-- Project details --> 165 <a href=""> 166 <papertitle>FedDEAP: Adaptive Dual-Prompt Tuning for Multi-Domain Federated Learning</papertitle> 167 </a> 168 <br> 169 <!-- Authors --> 170 <a href="https://scholar.google.com/citations?user=WrhQejQAAAAJ&hl=zh-CN">Yubin Zheng</a>, 171 <strong>Pak Hei Yeung</strong>, 172 <a href="https://person.zju.edu.cn/xiajing">Jing Xia</a>, 173 <a href="https://scholar.google.com/citations?user=f8PPcnoAAAAJ&hl=zh-CN">Tianjie Ju</a>, 174 <a href="">Peng Tang</a>, 175 <a href="https://ieeexplore.ieee.org/author/37534637700">Weidong Qiu</a>, 176 <a href="https://personal.ntu.edu.sg/asjagath/">Jagath C Rajapakse</a> 177 <br> 178 <em>ACM Multimedia</em>, 2025 179 <br> 180 <a href="https://dl.acm.org/doi/10.1145/3746027.3754587">paper</a> / 181 <a href="./data/feddeap_bibtex.bib">bibtex</a> 182 <p></p> 183 <p>An adaptive federated prompt tuning framework to enhance CLIP's generalization in multi-domain scenarios by disentangling semantic and domain-specific features with dual-prompt design.</p> 184 </td> 185 </tr> 186 187 <!-- [Project 10] Subcortical Masks Generation --> 188 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 189 <td style="padding:20px;width:25%;vertical-align:middle"> 190 <div class="one"> 191 <div class="two" id='subcortical_masks'> 192 <video width=100% height=100% muted autoplay loop> 193 <source src="image/ct_subcortical.png" type="video/mp4"> 194 Your browser does not support the video tag. 195 </video> 196 </div> 197 <img src='image/ct_subcortical.png' width="160"> 198 </div> 199
199<script type="text/javascript"> 200 function nerfbake_start() { 201 document.getElementById('subcortical_masks').style.opacity = "1"; 202 } 203 function nerfbake_stop() { 204 document.getElementById('subcortical_masks').style.opacity = "0"; 205 } 206 nerfbake_stop(); 207 </script>
207 208 </td> 209 <td style="padding:20px;width:75%;vertical-align:middle"> 210 <!-- Project details --> 211 <a href="https://arxiv.org/abs/2508.11450"> 212 <papertitle>Subcortical Masks Generation in CT Images via Ensemble-Based Cross-Domain Label Transfer</papertitle> 213 </a> 214 <br> 215 <!-- Authors --> 216 <a href="https://www.researchgate.net/scientific-contributions/Augustine-X-W-Lee-2319140715">Augustine XW Lee*</a>, 217 <strong>Pak Hei Yeung*</strong>, 218 <a href="https://personal.ntu.edu.sg/asjagath/">Jagath C Rajapakse</a> 219 <br> 220 <em>Annual Conference on Medical Image Understanding and Analysis (MIUA)</em>, 2025 <strong>(Oral)</strong> 221 <br> 222 <a href="https://arxiv.org/abs/2508.11450">paper</a> / 223 <a href="https://github.com/SCSE-Biomedical-Computing-Group/CT-Subcortical-Segmentation">code</a> / 224 <a href="./data/augustine_miua_bibtex.bib">bibtex</a> 225 <p></p> 226 <p>An automatic ensemble framework to generate subcortical segmentation labels for CT scans by leveraging existing MRI-based models, providing the first publicly available annotated CT dataset in the field.</p> 227 </td> 228 </tr> 229 230 <!-- [Project 9] Test Time Adaptation --> 231 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 232 <td style="padding:20px;width:25%;vertical-align:middle"> 233 <div class="one"> 234 <div class="two" id='tta_subcortical'> 235 <video width=100% height=100% muted autoplay loop> 236 <source src="image/tta_segmentation.gif" type="video/mp4"> 237 Your browser does not support the video tag. 238 </video> 239 </div> 240 <img src='image/tta_segmentation.gif' width="160"> 241 </div> 242
242<script type="text/javascript"> 243 function nerfbake_start() { 244 document.getElementById('tta_subcortical').style.opacity = "1"; 245 } 246 function nerfbake_stop() { 247 document.getElementById('tta_subcortical').style.opacity = "0"; 248 } 249 nerfbake_stop(); 250 </script>
250 251 </td> 252 <td style="padding:20px;width:75%;vertical-align:middle"> 253 <!-- Project details --> 254 <a href="https://arxiv.org/pdf/2502.08774?"> 255 <papertitle>Exploring Test Time Adaptation for Subcortical Segmentation of the Fetal Brain in 3D Ultrasound</papertitle> 256 </a> 257 <br> 258 <!-- Authors --> 259 <a href="https://uk.linkedin.com/in/joshua-omolegan">Joshua Omolegan</a>, 260 <strong>Pak Hei Yeung</strong>, 261 <a href="https://mwyburd.github.io/">Madeleine K Wyburd</a>, 262 <a href="https://lindehesse.github.io/">Linde Hesse</a>, 263 <a href="https://www.lumc.nl/org/geboortehuis-leiden/medewerkers/MwDr.M.C.Haak">Monique Haak</a>, 264 <a href="https://intergrowth21.tghn.org/">The INTERGROWTH-21<sup>st</sup> Consortium</a> 265 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Ana I.L. Namburete</a>, 266 <a href="https://nkdinsdale.github.io/nkdinsdale/">Nicola K Dinsdale</a>, 267 <br> 268 <em>IEEE International Symposium on Biomedical Imaging (ISBI)</em>, 2025 <strong>(Oral)</strong> 269 <br> 270 <a href="https://arxiv.org/pdf/2502.08774?">paper</a> / 271 <a href="https://github.com/joshuaomolegan/TTA-for-3D-Fetal-Subcortical-Segmentation">code</a> / 272 <a href="./data/joshua_isbi_bibtex.bib">bibtex</a> 273 <p></p> 274 <p>A novel test time adaptation method for improving 3D subcortical segmentation of fetal brain in ultrasound images.</p> 275 </td> 276 </tr> 277 278 279 280 <!-- [Project 8] RapidVol --> 281 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 282 <td style="padding:20px;width:25%;vertical-align:middle"> 283 <div class="one"> 284 <div class="two" id='rapidvol'> 285 <video width=100% height=100% muted autoplay loop> 286 <source src="image/rapidvol.png" type="video/mp4"> 287 Your browser does not support the video tag. 288 </video> 289 </div> 290 <img src='image/rapidvol.png' width="160"> 291 </div> 292
292<script type="text/javascript"> 293 function nerfbake_start() { 294 document.getElementById('rapidvol').style.opacity = "1"; 295 } 296 function nerfbake_stop() { 297 document.getElementById('rapidvol').style.opacity = "0"; 298 } 299 nerfbake_stop(); 300 </script>
300 301 </td> 302 <td style="padding:20px;width:75%;vertical-align:middle"> 303 <!-- Project details --> 304 <a href="https://arxiv.org/pdf/2404.10766?"> 305 <papertitle>RapidVol: Rapid Reconstruction of 3D Ultrasound Volumes from Sensorless 2D Scans</papertitle> 306 </a> 307 <br> 308 <!-- Authors --> 309 <a href="https://ieeexplore.ieee.org/author/341665993759124">Mark C Eid</a>, 310 <strong>Pak Hei Yeung</strong>, 311 <a href="https://mwyburd.github.io/">Madeleine K Wyburd</a>, 312 <a href="https://www.robots.ox.ac.uk/~joao/">João F Henriques</a>, 313 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Ana I.L. Namburete</a> 314 <br> 315 <em>IEEE International Symposium on Biomedical Imaging (ISBI)</em>, 2025 316 <br> 317 <a href="https://arxiv.org/pdf/2404.10766?">paper</a> / 318 <a href="./data/rapidvol_bibtex.bib">bibtex</a> 319 <p></p> 320 <p>A neural representation framework using tensor-rank decomposition to enable rapid 3D volume reconstruction from 2D freehand scans.</p> 321 </td> 322 </tr> 323 324 <!-- [Project 7] QAERTS --> 325 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 326 <td style="padding:20px;width:25%;vertical-align:middle"> 327 <div class="one"> 328 <div class="two" id='qaerts'> 329 <video width=100% height=100% muted autoplay loop> 330 <source src="image/planeinvol.gif" type="video/mp4"> 331 Your browser does not support the video tag. 332 </video> 333 </div> 334 <img src='image/planeinvol.gif' width="160"> 335 </div> 336
336<script type="text/javascript"> 337 function nerfbake_start() { 338 document.getElementById('qaerts').style.opacity = "1"; 339 } 340 function nerfbake_stop() { 341 document.getElementById('qaerts').style.opacity = "0"; 342 } 343 nerfbake_stop(); 344 </script>
344 345 </td> 346 <td style="padding:20px;width:75%;vertical-align:middle"> 347 <!-- Project details --> 348 <a href="https://arxiv.org/pdf/2405.13235"> 349 <papertitle>Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videos</papertitle> 350 </a> 351 <br> 352 <!-- Authors --> 353 <a href="https://reuben.ox.ac.uk/people/jayroop-ramesh">Jayroop Ramesh</a>, 354 <a href="https://nkdinsdale.github.io/nkdinsdale/">Nicola K Dinsdale</a>, 355 <a href="https://intergrowth21.tghn.org/">The INTERGROWTH-21<sup>st</sup> Consortium</a>, 356 <strong>Pak Hei Yeung</strong><sup>*</sup>, 357 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Ana I.L. Namburete</a><sup>*</sup> 358 <br> 359 <em>International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)</em>, 2024 <strong>(Oral)</strong> 360 <br> 361 <a href="https://arxiv.org/pdf/2405.13235">paper</a> / 362 <a href="https://github.com/jayrmh/QAERTS.git">code</a> / 363 <a href="./data/qaerts_bibtex.bib">bibtex</a> 364 <p></p> 365 <p>An uncertainty-aware deep learning model for automated 3D plane localization in 2D fetal brain images.</p> 366 </td> 367 </tr> 368 369 <!-- [Project 6] Hoda MLCN 2024 --> 370 <!-- 371 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 372 <td style="padding:20px;width:25%;vertical-align:middle"> 373 <div class="one"> 374 <div class="two" id='hoda_mlcn'> 375 <video width=100% height=100% muted autoplay loop> 376 <source src="image/hoda_mlcn.png" type="video/mp4"> 377 Your browser does not support the video tag. 378 </video> 379 </div> 380 <img src='image/hoda_mlcn.png' width="130"> 381 </div> 382
382<script type="text/javascript"> 383 function nerfbake_start() { 384 document.getElementById('hoda_mlcn').style.opacity = "1"; 385 } 386 function nerfbake_stop() { 387 document.getElementById('hoda_mlcn').style.opacity = "0"; 388 } 389 nerfbake_stop(); 390 </script>
390 391 </td> 392 <td style="padding:20px;width:75%;vertical-align:middle"> 393 --> 394 <!-- Project details --> 395 <!-- 396 <a href="https://www.bdi.ox.ac.uk/publications/2024005"> 397 <papertitle>Is Your Style Transfer Doing Anything Useful? An Investigation Into Hippocampus Segmentation and the Role of Preprocessing</papertitle> 398 </a> 399 <br> 400 --> 401 <!-- Authors --> 402 <!-- 403 Hoda Kalabizadeh, 404 Ludovica Griffanti, 405 <strong>Pak Hei Yeung</strong>, 406 Natalie Voets, 407 Grace Gillis, 408 Clare Mackay, 409 Ana I.L. Namburete, 410 Nicola K Dinsdale, 411 Konstantinos Kamnitsas 412 <br> 413 <em>MICCAI Machine Learning in Clinical Neuroimaging Workshop (MLCN)</em>, 2024 414 <br> 415 <a href="https://www.bdi.ox.ac.uk/publications/2024005">paper</a> / 416 <a href="./data/hoda_mlcn_bibtex.bib">bibtex</a> 417 <p></p> 418 <p>Investigating the importance of intensity normalisation methods in MRI segmentation.</p> 419 </td> 420 </tr> 421 --> 422 423 424 425 <!-- [Project 5] ImplicitVol (MedIA) --> 426 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 427 <td style="padding:20px;width:25%;vertical-align:middle"> 428 <div class="one"> 429 <div class="two" id='implicitvol'> 430 <video width=100% height=100% muted autoplay loop> 431 <source src="image/implicitvol.gif" type="video/mp4"> 432 Your browser does not support the video tag. 433 </video> 434 </div> 435 <img src='image/implicitvol.gif' width="160"> 436 </div> 437
437<script type="text/javascript"> 438 // JavaScript functions for controlling opacity 439 function nerfbake_start() { 440 document.getElementById('implicitvol').style.opacity = "1"; 441 } 442 function nerfbake_stop() { 443 document.getElementById('implicitvol').style.opacity = "0"; 444 } 445 // Initial opacity setting 446 nerfbake_stop() 447 </script>
447 448 </td> 449 <td style="padding:20px;width:75%;vertical-align:middle"> 450 <!-- Project details --> 451 <a href="https://pakheiyeung.github.io/ImplicitVol_wp/"> 452 <papertitle>Sensorless volumetric reconstruction of fetal brain freehand ultrasound scans with deep implicit representation</papertitle> 453 </a> 454 <br> 455 <!-- Authors --> 456 <strong>Pak Hei Yeung</strong>, 457 <a href="https://lindehesse.github.io/">Linde Hesse</a>, 458 <a href="https://www.researchgate.net/profile/Moska-Aliasi">Moska Aliasi</a>, 459 <a href="https://www.lumc.nl/org/geboortehuis-leiden/medewerkers/MwDr.M.C.Haak">Monique Haak</a>, 460 <a href="https://intergrowth21.tghn.org/">The INTERGROWTH-21<sup>st</sup> Consortium</a>, 461 <a href="https://weidixie.github.io/">Weidi Xie</a><sup>*</sup>, 462 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Ana I.L. Namburete</a><sup>*</sup> 463 <br> 464 <em>Medical Image Analysis, Volume 94</em>, 2024 <strong>(Impact factor ∼ 12)</strong> 465 <br> 466 <a href="https://pakheiyeung.github.io/ImplicitVol_wp/">project page</a> 467 / 468 <a href="https://www.sciencedirect.com/science/article/pii/S1361841524000720">paper</a> 469 / 470 <a href="https://www.youtube.com/watch?v=D4ZCo14mqxs">video</a> 471 / 472 <a href="https://github.com/pakheiyeung/ImplicitVol">code</a> 473 / 474 <a href="./data/implicitvol_media_bibtex.bib">bibtex</a> 475 <p></p> 476 <p>Reconstructing a 3D volume from 2D freehand ultrasound images by training a deep network to implicitly represent the volume.</p> 477 </td> 478 </tr> 479 480 481 <!-- [Project 4] AdLocUI --> 482 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 483 <td style="padding:20px;width:25%;vertical-align:middle"> 484 <div class="one"> 485 <div class="two" id='adlocui'> 486 <video width=100% height=100% muted autoplay loop> 487 <source src="image/adlocui.gif" type="video/mp4"> 488 Your browser does not support the video tag. 489 </video> 490 </div> 491 <img src='image/adlocui.gif' width="160"> 492 </div> 493
493<script type="text/javascript"> 494 // JavaScript functions for controlling opacity 495 function nerfbake_start() { 496 document.getElementById('adlocui').style.opacity = "1"; 497 } 498 function nerfbake_stop() { 499 document.getElementById('adlocui').style.opacity = "0"; 500 } 501 // Initial opacity setting 502 nerfbake_stop() 503 </script>
503 504 </td> 505 <td style="padding:20px;width:75%;vertical-align:middle"> 506 <!-- Project details --> 507 <a href="https://pakheiyeung.github.io/AdLocUI_wp/"> 508 <papertitle>Adaptive 3D Localization of 2D Freehand Ultrasound Brain Images</papertitle> 509 </a> 510 <br> 511 <!-- Authors --> 512 <strong>Pak Hei Yeung</strong>, 513 <a href="https://www.researchgate.net/profile/Moska-Aliasi">Moska Aliasi</a>, 514 <a href="https://intergrowth21.tghn.org/">The INTERGROWTH-21<sup>st</sup> Consortium</a>, 515 <a href="https://weidixie.github.io/">Weidi Xie</a>, 516 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Ana I.L. Namburete</a> 517 <br> 518 <em>International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)</em>, 2022 519 <br> 520 <a href="https://pakheiyeung.github.io/AdLocUI_wp/">project page</a> 521 / 522 <a href="https://arxiv.org/abs/2209.05477">paper</a> 523 / 524 <a href="https://www.youtube.com/watch?v=2VGH_XxqGRw&ab_channel=PakHeiYeung">video</a> 525 / 526 <a href="./data/adlocui_bibtex.bib">bibtex</a> 527 <p></p> 528 <p>Sensorless 3D localization of 2D freehand scans. Trained with just 3D volumes, the model can be adapted to any domains (<em>e.g.</em> machines) in an unsupervised manner.</p> 529 </td> 530 </tr> 531 532 <!-- [Project 3] ImplicitVol --> 533 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 534 <td style="padding:20px;width:25%;vertical-align:middle"> 535 <div class="one"> 536 <div class="two" id='implicitvol'> 537 <video width=100% height=100% muted autoplay loop> 538 <source src="image/implicitvol.gif" type="video/mp4"> 539 Your browser does not support the video tag. 540 </video> 541 </div> 542 <img src='image/implicitvol.gif' width="160"> 543 </div> 544
544<script type="text/javascript"> 545 function nerfbake_start() { 546 document.getElementById('implicitvol').style.opacity = "1"; 547 } 548 function nerfbake_stop() { 549 document.getElementById('implicitvol').style.opacity = "0"; 550 } 551 nerfbake_stop(); 552 </script>
552 553 </td> 554 <td style="padding:20px;width:75%;vertical-align:middle"> 555 <!-- Project details --> 556 <a href="https://pakheiyeung.github.io/ImplicitVol_wp/"> 557 <papertitle>ImplicitVol: Sensorless 3D Ultrasound Reconstruction with Deep Implicit Representation</papertitle> 558 </a> 559 <br> 560 <!-- Authors --> 561 <strong>Pak Hei Yeung</strong>, 562 <a href="https://lindehesse.github.io/">Linde Hesse</a>, 563 <a href="https://www.researchgate.net/profile/Moska-Aliasi">Moska Aliasi</a>, 564 <a href="https://www.lumc.nl/org/geboortehuis-leiden/medewerkers/MwDr.M.C.Haak">Monique Haak</a>, 565 <a href="https://intergrowth21.tghn.org/">The INTERGROWTH-21<sup>st</sup> Consortium</a>, 566 <a href="https://weidixie.github.io/">Weidi Xie</a><sup>*</sup>, 567 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Ana I.L. Namburete</a><sup>*</sup> 568 <br> 569 <em>Arxiv preprint</em>, 2021 570 <br> 571 <a href="https://pakheiyeung.github.io/ImplicitVol_wp/">project page</a> / 572 <a href="https://arxiv.org/abs/2109.12108">paper</a> / 573 <a href="https://www.youtube.com/watch?v=D4ZCo14mqxs">video</a> / 574 <a href="https://github.com/pakheiyeung/ImplicitVol">code</a> / 575 <a href="./data/implicitvol_bibtex.bib">bibtex</a> 576 <p></p> 577 <p>Reconstructing a 3D volume from 2D freehand ultrasound images by training a deep network to implicitly represent the volume.</p> 578 </td> 579 </tr> 580 581 <!-- [Project 2] Sli2Vol --> 582 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 583 <td style="padding:20px;width:25%;vertical-align:middle"> 584 <div class="one"> 585 <div class="two" id='sli2vol'> 586 <video width=100% height=100% muted autoplay loop> 587 <source src="image/sli2vol.gif" type="video/mp4"> 588 Your browser does not support the video tag. 589 </video> 590 </div> 591 <img src='image/sli2vol.gif' width="160"> 592 </div> 593
593<script type="text/javascript"> 594 // JavaScript functions for controlling opacity 595 function nerfbake_start() { 596 document.getElementById('sli2vol').style.opacity = "1"; 597 } 598 function nerfbake_stop() { 599 document.getElementById('sli2vol').style.opacity = "0"; 600 } 601 // Initial opacity setting 602 nerfbake_stop() 603 </script>
603 604 </td> 605 <td style="padding:20px;width:75%;vertical-align:middle"> 606 <!-- Project details --> 607 <a href="https://pakheiyeung.github.io/Sli2Vol_wp/"> 608 <papertitle>Sli2Vol: Annotate a 3D Volume from a Single Slice with Self-Supervised Learning</papertitle> 609 </a> 610 <br> 611 <!-- Authors --> 612 <strong>Pak Hei Yeung</strong>, 613 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Ana I.L. Namburete</a><sup>*</sup>, 614 <a href="https://weidixie.github.io/">Weidi Xie</a><sup>*</sup> 615 <br> 616 <em>International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)</em>, 2021 617 <br> 618 <a href="https://pakheiyeung.github.io/Sli2Vol_wp/">project page</a> 619 / 620 <a href="https://arxiv.org/abs/2105.12722">paper</a> 621 / 622 <a href="https://www.youtube.com/watch?v=lbQQV-jOEuk">video</a> 623 / 624 <a href="https://github.com/pakheiyeung/Sli2Vol">code</a> 625 / 626 <a href="./data/sli2vol_bibtex.bib">bibtex</a> 627 <p></p> 628 <p>Trained with just raw 3D volumes, a single <em>Sli2Vol</em> model can be used to propagate a single-slice annotation to the whole 3D volume, for any structures across different modalities.</p> 629 </td> 630 </tr> 631 632 <!-- [Project 1] PlaneInVol --> 633 <tr onmouseout="nerfbake_stop()" onmouseover="nerfbake_start()"> 634 <td style="padding:20px;width:25%;vertical-align:middle"> 635 <div class="one"> 636 <div class="two" id='planeinvol'> 637 <video width=100% height=100% muted autoplay loop> 638 <source src="image/planeinvol.gif" type="video/mp4"> 639 Your browser does not support the video tag. 640 </video> 641 </div> 642 <img src='image/planeinvol.gif' width="160"> 643 </div> 644
644<script type="text/javascript"> 645 // JavaScript functions for controlling opacity 646 function nerfbake_start() { 647 document.getElementById('planeinvol').style.opacity = "1"; 648 } 649 function nerfbake_stop() { 650 document.getElementById('planeinvol').style.opacity = "0"; 651 } 652 // Initial opacity setting 653 nerfbake_stop() 654 </script>
654 655 </td> 656 <td style="padding:20px;width:75%;vertical-align:middle"> 657 <!-- Project details --> 658 <a href="https://pakheiyeung.github.io/PlaneInVol_wp/"> 659 <papertitle>Learning to Map 2D Ultrasound Images into 3D Space with Minimal Human Annotation</papertitle> 660 </a> 661 <br> 662 <!-- Authors --> 663 <strong>Pak Hei Yeung</strong>, 664 <a href="https://www.researchgate.net/profile/Moska-Aliasi">Moska Aliasi</a>, 665 <a href="https://www.wrh.ox.ac.uk/team/aris-papageorghiou">Aris T. Papageorghiou</a>, 666 <a href="https://www.lumc.nl/org/geboortehuis-leiden/medewerkers/MwDr.M.C.Haak">Monique Haak</a>, 667 <a href="https://weidixie.github.io/">Weidi Xie</a>, 668 <a href="https://www.pmb.ox.ac.uk/person/dr-ana-namburete">Ana I.L. Namburete</a> 669 <br> 670 <em>Medical Image Analysis, Volume 70</em>, 2021 <strong>(Impact factor ∼ 12)</strong> 671 <br> 672 <a href="https://pakheiyeung.github.io/PlaneInVol_wp/">project page</a> 673 / 674 <a href="https://www.sciencedirect.com/science/article/pii/S136184152100044X">paper</a> 675 / 676 <a href="https://www.youtube.com/watch?v=D4ZCo14mqxs">video</a> 677 / 678 <a href="https://github.com/pakheiyeung/PlaneInVol">code</a> 679 / 680 <a href="./data/planeinvol_bibtex.bib">bibtex</a> 681 <p></p> 682 <p>A network, trained with just registered volumes, to predict the 3D location of 2D freehand ultrasound fetal brain images and video.</p> 683 </td> 684 </tr> 685 686 <!-- ====== Project Blocks End ====== --> 687 </tbody> 688 </table> 689 690 <!-- Credits --> 691 <br> 692 <p style="text-align:right;font-size:small;"> 693 The template of this webpage is from <a href="https://github.com/jonbarron/jonbarron_website">source code</a>. 694 </p> 695 </td> 696 </tr> 697 </tbody> 698 </table> 699</body> 700</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.