index.html

<script src="http://www.google.com/jsapi" type="text/javascript"></script> 
<script type="text/javascript">google.load("jquery", "1.3.2");</script>

<style type="text/css">
	body {
		font-family: "HelveticaNeue-Light", "Helvetica Neue Light", "Helvetica Neue", Helvetica, Arial, "Lucida Grande", sans-serif; 
		font-weight:300;
		font-size:18px;
		margin-left: auto;
		margin-right: auto;
		width: 1100px;
		background-color : #EFEFEF;
	}
	.content{
    width : 1110px;
    padding : 25px 50px;
    margin : 25px auto;
    background-color : #fff;
    box-shadow: 0px 0px 10px #999;
    border-radius: 15px; 
	}
	h1 {
		font-weight:300;
	}

	.row {
		display: flex;
	  }
	  
	/* Create three equal columns that sits next to each other */
	.column {
	flex: 50%;
	padding: 5px;
	}

    .imageDiv img { 
        box-shadow: 1px 1px 10px rgb(255, 255, 255); 
        margin: 2px;
        max-height: 50px;
        cursor: pointer;
    display:inline-block;
    *display:inline;
    *zoom:1;
    vertical-align:top;
    }


	tr.spaceUnder>td {
		padding-bottom: 3em;
	}

	.paddingBetweenRows td
	{
		padding:0 15px;
		border-spacing: 100px;
	}





    /*
      Rollover Image
     */
	 .figure {
        position: relative;
        max-width: 100%;
    }
    .figure img.image-hover {
      position: absolute;
      top: 0;
      right: 0;
      left: 0;
      bottom: 0;
      object-fit: contain;
      opacity: 0;
      transition: opacity .2s;
    }
    .figure:hover img.image-hover {
      opacity: 1;
    }
	
	* {box-sizing:border-box}

	/* Slideshow container */
	.slideshow-container {
	max-width: 232;
	position: relative;
	margin: auto;
	}

	/* Hide the images by default */
	.mySlides {
	display: none;
	}

	/* Next & previous buttons */
	.prev, .next {
	cursor: pointer;
	position: absolute;
	top: 50%;
	width: auto;
	margin-top: -22px;
	padding: 16px;
	color: white;
	font-weight: bold;
	font-size: 18px;
	transition: 0.6s ease;
	border-radius: 0 3px 3px 0;
	user-select: none;
	}

	/* Position the "next button" to the right */
	.next {
	right: 0;
	border-radius: 3px 0 0 3px;
	}

	/* On hover, add a black background color with a little bit see-through */
	.prev:hover, .next:hover {
	background-color: rgba(0,0,0,0.8);
	}

	/* Caption text */
	.text {
	color: #f2f2f2;
	font-size: 15px;
	padding: 8px 12px;
	position: absolute;
	bottom: 8px;
	width: 100%;
	text-align: center;
	}

	/* Number text (1/3 etc) */
	.numbertext {
	color: #f2f2f2;
	font-size: 12px;
	padding: 8px 12px;
	position: absolute;
	top: 0;
	}

	/* The dots/bullets/indicators */
	.dot {
	cursor: pointer;
	height: 15px;
	width: 15px;
	margin: 0 2px;
	background-color: #bbb;
	border-radius: 50%;
	display: inline-block;
	transition: background-color 0.6s ease;
	}

	.active, .dot:hover {
	background-color: #717171;
	}

	/* Fading animation */
	.fade {
	}

	@keyframes fade {
	from {opacity: .4}
	to {opacity: 1}
	}




	.disclaimerbox {
		background-color: #eee;		
		border: 1px solid #eeeeee;
		border-radius: 10px ;
		-moz-border-radius: 10px ;
		-webkit-border-radius: 10px ;
		padding: 20px;
	}

	video.header-vid {
		height: 140px;
		border: 1px solid black;
		border-radius: 10px ;
		-moz-border-radius: 10px ;
		-webkit-border-radius: 10px ;
	}
	
	img.header-img {
		height: 140px;
		border: 1px solid black;
		border-radius: 10px ;
		-moz-border-radius: 10px ;
		-webkit-border-radius: 10px ;
	}
	
	img.rounded {
		border: 1px solid #eeeeee;
		border-radius: 10px ;
		-moz-border-radius: 10px ;
		-webkit-border-radius: 10px ;
	}
	
	a:link,a:visited
	{
		color: #1367a7;
		text-decoration: none;
	}
	a:hover {
		color: #208799;
	}
	
	td.dl-link {
		height: 160px;
		text-align: center;
		font-size: 22px;
	}
	
	.layered-paper-big { /* modified from: http://css-tricks.com/snippets/css/layered-paper/ */
		box-shadow:
		        0px 0px 1px 1px rgba(0,0,0,0.35), /* The top layer shadow */
		        5px 5px 0 0px #fff, /* The second layer */
		        5px 5px 1px 1px rgba(0,0,0,0.35), /* The second layer shadow */
		        10px 10px 0 0px #fff, /* The third layer */
		        10px 10px 1px 1px rgba(0,0,0,0.35), /* The third layer shadow */
		        15px 15px 0 0px #fff, /* The fourth layer */
		        15px 15px 1px 1px rgba(0,0,0,0.35), /* The fourth layer shadow */
		        20px 20px 0 0px #fff, /* The fifth layer */
		        20px 20px 1px 1px rgba(0,0,0,0.35), /* The fifth layer shadow */
		        25px 25px 0 0px #fff, /* The fifth layer */
		        25px 25px 1px 1px rgba(0,0,0,0.35); /* The fifth layer shadow */
		margin-left: 10px;
		margin-right: 45px;
	}

	.paper-big { /* modified from: http://css-tricks.com/snippets/css/layered-paper/ */
		box-shadow:
		        0px 0px 1px 1px rgba(0,0,0,0.35); /* The top layer shadow */

		margin-left: 10px;
		margin-right: 45px;
	}


	.layered-paper { /* modified from: http://css-tricks.com/snippets/css/layered-paper/ */
		box-shadow:
		        0px 0px 1px 1px rgba(0,0,0,0.35), /* The top layer shadow */
		        5px 5px 0 0px #fff, /* The second layer */
		        5px 5px 1px 1px rgba(0,0,0,0.35), /* The second layer shadow */
		        10px 10px 0 0px #fff, /* The third layer */
		        10px 10px 1px 1px rgba(0,0,0,0.35); /* The third layer shadow */
		margin-top: 5px;
		margin-left: 10px;
		margin-right: 30px;
		margin-bottom: 5px;
	}
	
	.vert-cent {
		position: relative;
	    top: 50%;
	    transform: translateY(-50%);
	}
	
	hr
	{
		border: 0;
		height: 1px;
		background-image: linear-gradient(to right, rgba(0, 0, 0, 0), rgba(0, 0, 0, 0.75), rgba(0, 0, 0, 0));
	}

	table {
		border-collapse: collapse;
	}
	.vtable {
		border-collapse:separate;
		border-spacing:10px 15px;
	}
	.rtable {
		margin-left: 2em;
		border-collapse:separate;
		border-spacing:10px 15px;
	}
</style>

<html>
  <head>
		<title>MORE</title>
		<meta property="og:title" content="MORE" />
  </head>

  <body>
	<div class="content">
		
		<br>
          <center>
          	<span style="font-size:28px">GBIR: A Novel Gaussian Iterative Method for Medical Image Reconstruction</span>
			<br>
			<br>
			  <a href='https://openreview.net/forum?id=AkCWbxntll'> ICLR 2025 Under Review</a></span>
			  <br>
			  <br>
				<table align=center width=850px id="vis">
					<center><h1>Visualization</h1></center>
				</table>
				<img name="vis" src = "./Assets/vis_comparison.png", width="100%"></img></center>
				<p style="font-size:16px;"> Visualization of reconstruction results obtained using different methods. The first row displays the reconstructed 3D volumes, while the second row shows the residual images, representing the differences between the reconstructed volume and the ground truth volume. </p>
			<br>
          </center>
		  <p><strong>Quick Jump:</strong></p>
			<ol>
				<!-- <li><a href="#news">News</a></li> -->
				<li><a href="#vis">Visualization</a></li>
				<li><a href="#overview">Overview</a></li>
				<li><a href="#gbir">GBIR Model</a></li>
				<li><a href="#more">MORE Dataset</a></li>
				<!-- <li><a href="#benchmark">Benchmarks</a></li> -->
			</ol>
	</div>

	  
	<div class="content" id="overview">

		<table align=center width=850px>
			<center><h1>Overview</h1></center>
		</table>
		<p>In this research, we introduce the GBIR model and the MORE dataset, both of which are designed to facilitate the development of medical image reconstruction algorithms.</p>
	
		
		<p>		The MORE dataset was developed to address the limitations of existing medical imaging datasets, which often focus on specific organs and lack diversity. The aim is to create a resource that supports the evaluation of methods across different anatomical regions, ensuring that AI models can generalize well across various clinical scenarios.</p>

		<p>
					Our GBIR (Gaussian-Based Iterative Reconstruction) framework introduces a novel approach to medical image reconstruction by modeling the 3D volume as a set of learnable Gaussians. Notably, GBIR is a different Gaussian representation and reconstruction method from the heated 3D Gaussian Splatting. Our GBIR directly reconstructs the 3D volume from the Gaussian representation without the need for intermediate steps, such as splatting and view synthesis. 
		</p>


	

		
	</div>  
	
	<div class="content" id="gbir">
		<table align=center width=850px>
			<center><h1>GBIR Framework</h1></center>
		</table>
		<br>Below shows the distinctive pipelines of GBIR from previous neural-network based methods</br>
		<br><img name="stone" src = "./Assets/Pipeline_00.png", width="100%"></img></br>
		<br></br>

		In the beginning of each iteration, the learnable Gaussians are constrained into 3-sigma range, and then discretized and aligned to the grid. During our high parallel efficient reconstruction, the total volume is reconstructed by the summation of the contribution of Gaussian volumes. The reconstruction process is differentiable and directly supervised by the measurement, thus GBIR can be trained end-to-end.
		<br>
		<br><img name="stone" src = "./Assets/gbir2.png", width="100%"></img>
		
	
	</div>
	<div class="content" id="more">
		<table align=center width=850px>
			<center><h1>MORE Dataset</h1></center>
		</table>
		<p>The MORE dataset has the following features:</p>
		(1) Large. There are 135 CT instances and 54 MRI instances in total, with 65,575 CT scans and 7,498 MRI scans.<br>
		(2) Multi-Organ. CT part contain 15 types of organs and MRI part contain 5 types of organs.<br>
		(3) Multi-disease.  CT part contain 25 types of diseases and MRI part contain 17 types of diseases.<br>
		<br>
		<br>

		  <div style="display: flex;">
			<img src="Assets/ct_00.png" alt="Image 1" style="width:50%;">
			<img src="Assets/MRI++_00.png" alt="Image 2" style="width:50%;">
		  </div>
		  <br>
		  <br>
		Below we show some samples of MORE dataset:</p>
		<img name="stone" src = "./Assets/sample.png", width="100%"></img>
	</div>


</body>
</html>