医用画像
Deep Learning Toolbox™ を Medical Imaging Toolbox™ と共に使用して、医用画像アプリケーションに深層学習を適用します。
アプリ
| 医用画像ラベラー | Interactively explore, label, and publish animations of 2-D or 3-D medical image data (R2022b 以降) |
関数
medicalSegmentAnythingModel | Pretrained Medical Segment Anything Model (MedSAM) for medical image segmentation (R2024b 以降) |
extractEmbeddings | Extract image embeddings from Medical Segment Anything Model (MedSAM) encoder (R2024b 以降) |
segmentObjectsFromEmbeddings | Segment objects in medical image using Medical Segment Anything Model (MedSAM) image embeddings (R2024b 以降) |
cellpose | Configure Cellpose model for cell segmentation (R2023b 以降) |
segmentCells2D | Segment 2-D image using Cellpose (R2023b 以降) |
segmentCells3D | Segment 3-D image volume using Cellpose (R2023b 以降) |
トピック
- Get Started with Medical Image Labeler (Medical Imaging Toolbox)
Interactively explore, label, and publish animations of 2-D or 3-D medical image data.
- Get Started with MONAI Label in Medical Image Labeler (Medical Imaging Toolbox)
Apply AI models from the MONAI Label library for 3-D medical image segmentation.
- Get Started with Medical Segment Anything Model for Medical Image Segmentation (Medical Imaging Toolbox)
Perform interactive medical image segmentation using Medical Segment Anything Model (MedSAM) and deep learning. (R2024b 以降)
- Get Started with MedSAM in Medical Image Labeler (Medical Imaging Toolbox)
This example shows how to interactively segment objects in medical images and in cross-sections of medical volumes using the MedSAM algorithm in the Medical Image Labeler app. (R2025a 以降)
- Getting Started with Cellpose (Medical Imaging Toolbox)
Segment cells from microscopy images using a pretrained Cellpose model, or train a custom model.
- Create Datastores for Medical Image Semantic Segmentation (Medical Imaging Toolbox)
Create datastores that contain images and pixel label data from a
groundTruthMedicalobject for training semantic segmentation deep learning networks.- Convert Ultrasound Image Series into Training Data for 2-D Semantic Segmentation Network (Medical Imaging Toolbox)
- Create Training Data for 3-D Medical Image Semantic Segmentation (Medical Imaging Toolbox)
注目の例
Interactively Segment and Analyze ROI Using MedSAM and Radiomics
Perform interactive segmentation of an object in a region of interest (ROI) of an image using the Medical Segment Anything Model (MedSAM) and analyze the segmented object using radiomics.
Segment and Analyze Brain MRI Scan Using AI
Preprocess, label, postprocess, and analyze a brain MRI image using MONAI Label.
Cardiac Left Ventricle Segmentation from Cine-MRI Images Using U-Net Network
Segment 2-D cardiac MRI images using U-Net, and explore predictions using Grad-CAM explainability maps.
Segment Lungs from CT Scan Using Pretrained Neural Network
Import a pretrained ONNX™ (Open Neural Network Exchange) 3-D U-Net [1] and use it to perform semantic segmentation of the left and right lungs from a 3-D chest CT scan. Semantic segmentation associates each voxel in a 3-D image with a class label. In this example, you classify each voxel in a test data set as belonging to the left lung or right lung. For more information about semantic segmentation, see セマンティック セグメンテーション (Computer Vision Toolbox).
Brain MRI Segmentation Using Pretrained 3-D U-Net Network
Segment a brain MRI using a deep neural network.
Breast Tumor Segmentation from Ultrasound Using Deep Learning
Perform semantic segmentation of breast tumors from 2-D ultrasound images using a deep neural network.
Segment CT Scan Using MONAI Label
Apply deep learning models from the Medical Open Network for AI (MONAI) Label platform to segment a CT scan.
深層学習を使用した脳腫瘍の 3 次元セグメンテーション
この例では、3 次元医用画像から脳腫瘍のセマンティック セグメンテーションを実行する方法を説明します。
Unsupervised Medical Image Denoising Using CycleGAN
Generate high-quality high-dose computed tomography (CT) images from noisy low-dose CT images using a CycleGAN neural network.
Unsupervised Medical Image Denoising Using UNIT
Generate high-quality computed tomography (CT) images from noisy low-dose CT images using a UNIT neural network.
Choose Pretrained Cellpose Model for Cell Segmentation
Segment cells from microscopy images using a pretrained Cellpose model.
Refine Cellpose Segmentation by Tuning Model Parameters
Use options in the segmentCells2D (Medical Imaging Toolbox) function to improve the segmentation results from a Cellpose model. To learn how to select a suitable model, see Choose Pretrained Cellpose Model for Cell Segmentation (Medical Imaging Toolbox).
Detect Nuclei in Large Whole Slide Images Using Cellpose
Detect cell nuclei in whole slide images (WSIs) of tissue stained using hematoxylin and eosin (H&E) by using Cellpose.
Classify Tumors in Digital Pathology Images Using Cell Nucleus Morphology
Classify whole slide image (WSI) patches as normal or cancerous using pathomics.
Multilabel Diabetic Retinopathy Fundus Image Classification Using Deep Learning
Classify diabetic retinopathy (DR) fundus images using a ResNet-101 deep neural network with transfer learning.
