Pancreas Tumor Segmentation and Medical Image Analysis
Explore the segmentation of pancreas tumors and medical image processing techniques for monitoring treatment responses. Learn about data harmonization, preprocessing steps, and multi-target segmentation based on fusion of attention mechanism. Results show a Mean Intersection over Union (MIoU) of 0.8279 in tumors segmentation. Dive into the example of tumor segmentation prediction for a deeper understanding.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Segmentation of pancreas tumor Nicola Ferrara
TASK07_PANCREAS Public Database: Medical Segmentation Decathlon 420 ct Thickness 2.5 mm 281 training TASK: transform medical images into clinically relevant, spatially structured information for treatment response monitoring Computer-aided diagnosis, biomarker extraction, surgical intervention planning, disease prognosis parenchima pancreatico neoplasia mucinosa intraduttale, tumore pancreatico neuroendocrino e adenocarcinoma pancreatico duttale (PDAC).
PREPROCESSING Data harmonization: in all studies, before training the model there is a pre-processing phase which may include the following steps: Contrast enhancement (windowing with WW and WL based on the values present in the literature and/or Histogram equalization); Resampling, to make the size of the voxels and pixels of the entire dataset uniform; Filtering (e.g. Butterworth low-pass, local binary pattern filtering); Reduction of the size of the dataset (e.g. from a scan of 512x512xN to 256x256xN by cutting the images starting from the center or from 512x512xN to 512x512xM, with M<N by removing the slices in which the target is not present); Data augmentation (scaling, translation, rotation, addition of noise, etc.); Normalization/standardization of intensity values.
Case of study Multi-target segmentation of pancreas and pancreatic tumor based on fusion of attention mechanism (paper)
Results Our results on TUMORS segmentation: MIoU = 0.8279
Example of prediction Image Label Tumor segmentation
