Tumor Segmentation
Tumor segmentation, the automated identification and delineation of tumors in medical images, aims to improve diagnostic accuracy and treatment planning. Current research emphasizes robust segmentation across diverse imaging modalities (MRI, CT, PET) and scanners, often employing deep learning architectures like U-Net, Swin-UNet, and transformers, and addressing challenges such as missing modalities and domain shifts through techniques like knowledge distillation, multi-task learning, and data augmentation. These advancements hold significant promise for improving cancer diagnosis, treatment personalization, and ultimately, patient outcomes.
Papers
A Localization-to-Segmentation Framework for Automatic Tumor Segmentation in Whole-Body PET/CT Images
Linghan Cai, Jianhao Huang, Zihang Zhu, Jinpeng Lu, Yongbing Zhang
Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction
Qinghui Liu, Elies Fuster-Garcia, Ivar Thokle Hovden, Donatas Sederevicius, Karoline Skogen, Bradley J MacIntosh, Edvard Grødem, Till Schellhorn, Petter Brandal, Atle Bjørnerud, Kyrre Eeg Emblem
Two-Stage Hybrid Supervision Framework for Fast, Low-resource, and Accurate Organ and Pan-cancer Segmentation in Abdomen CT
Wentao Liu, Tong Tian, Weijin Xu, Lemeng Wang, Haoyuan Li, Huihua Yang
Tumor-Centered Patching for Enhanced Medical Image Segmentation
Mutyyba Asghar, Ahmad Raza Shahid, Akhtar Jamil, Kiran Aftab, Syed Ather Enam
Anisotropic Hybrid Networks for liver tumor segmentation with uncertainty quantification
Benjamin Lambert, Pauline Roca, Florence Forbes, Senan Doyle, Michel Dojat
A Hierarchical Transformer Encoder to Improve Entire Neoplasm Segmentation on Whole Slide Image of Hepatocellular Carcinoma
Zhuxian Guo, Qitong Wang, Henning Müller, Themis Palpanas, Nicolas Loménie, Camille Kurtz
3D Medical Image Segmentation based on multi-scale MPU-Net
Zeqiu. Yu, Shuo. Han, Ziheng. Song