minor

index.html

@@ -236,21 +236,22 @@ <h2 class="title is-3">Proposed method</h2>
         <ol type="a">
           <li>Initial deep learning techniques applied to post-processing tasks on FBP reconstructed images show
             promise in artifact removal and structure preservation but face limitations due to constrained receptive
-            fields,leading to suboptimal results.</li>
+            fields, leading to suboptimal results. However, these methods are computationally efficient.
+          </li>
           <li>Deep unrolling algorithms, such as the learned primal-dual (LPD) algorithm, have been introduced to
-            optimize the reconstruction process. However, they face issues such
-            as slow convergence and high computational costs. Consequently, there is a need to explore more efficient
+            optimize the reconstruction process. However, they face issues such as slow convergence and high
+            computational costs. Consequently, there is a need to explore more efficient
             alternatives due to the difficulties in capturing long-range dependencies and the growing computational
-            demands of modern neural networks.</li>
-          <li>The paper introduces a second-order unrolling network <br>called QN-Mixer<br>, which employs a latent
+            demands of modern neural networks.
+          </li>
+          <li>The paper introduces a second-order unrolling network called QN-Mixer, which employs a latent
             BFGS algorithm to approximate the Hessian matrix with a deep-net learned regularization term.
             It outperforms state-of-the-art methods in terms of quantitative metrics while requiring fewer
-            iterations than first-order unrolling networks.</li>
+            iterations than first-order unrolling networks.
+          </li>
         </ol>
         </p>
 
-
-
       </div>
     </div>
     </div>