Deep Convolutional Neural Networks (CNNs) i.e. Residual Networks (ResNets) have been used successfully for many computer vision tasks, but are difficult to scale to 3D volumetric medical data. Memory is increasingly often the bottleneck when training 3D Convolutional Neural Networks (CNNs). Recently, invertible neural networks have been applied to significantly reduce activation memory footprint when training neural networks with backpropagation thanks to the invertible functions that allow retrieving input from its output without storing intermediate activations in memory to perform the backpropagation. Among many successful network architectures, 3D Unet1 has been established as a standard architecture for volumetric medical segmentation. Thus, we choose 3D Unet as a baseline for a non-invertible network and we then extend it with the invertible residual network. In this paper, we proposed two versions of invertible Residual Network, namely Partially Invertible Residual Network (Partially-InvRes) and Fully Invertible Residual Network (Fully-InvRes). In Partially-InvRes, the invertible residual layer is defined by a technique called additive coupling2 whereas in Fully-InvRes, both invertible upsampling and downsampling operations are learned based on squeezing (known as pixel shuffle).3 Furthermore, to avoid the overfitting problem because of less training data, a variational auto-encoder (VAE) branch is added to reconstruct the input volumetric data itself. Our results indicate that by using partially/fully invertible networks as the central workhorse in volumetric segmentation, we not only reduce memory overhead but also achieve compatible segmentation performance compared against the non-invertible 3D Unet. We have demonstrated the proposed networks on various volumetric datasets such as iSeg 20194 and BraTS 2020.5
Currently, photodynamic therapy (PDT) of primary tumors in peritoneal organs is limited by the lack of specificity of photosensitizers (PSs) and availability of appropriate laparoscopy for accurate and dexterous PDT optical fiber deployment. Invasive procedures are often required in the conventional approach, leads to significant side effects such as bleeding and extended recovery time. The purpose of this study is to design and evaluate a soft robot system for targeted and minimally invasive PDT of intraperitoneal tumors. Our soft robot system is fabricated with silicone materials to enable safe interaction with the abdominal organs. Compared to the conventional laparoscopic device, this soft robot system can be translated, bent, and rotated to reach the desired target by using three high-resolution DC motors. A miniature camera (ENA-10005-AS, Enable Inc.) is integrated with the soft robot to enable the intraoperative image guidance while reaching the target. A hollow channel was created within the soft robot so as to deploy the optical fiber towards the tumor. We conducted interstitial PDT using a peritoneal ovarian tumor mouse model and targeted near infrared photosensitizer. After the PS was injected, the optical fiber was inserted into the tumors through the soft robot. We found that PDT treatment greatly inhibited tumor growth. Our preliminary results suggest that our soft robot system may have great potential in the PDT treatment of intraperitoneal tumors.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.