Rib instance segmentation, counting and positioning method and system

Abstract

The invention provides a rib instance segmentation, counting and positioning method and system, and the method comprises the following steps: carrying out the semantic segmentation of ribs in a chest CT, and obtaining a rib semantic segmentation binary mask; collecting a manual label corresponding to the rib semantic segmentation binary mask to obtain a rib instance segmentation mask; processing the rib semantic segmentation binary mask and the rib instance segmentation mask, and making a sequence segmentation training sample set; establishing a deep convolutional neural network model; training the deep convolutional neural network model by using the training sample set to obtain a deep convolutional neural network capable of predicting the topmost ribs; inputting the rib semantic segmentation binary mask into the trained deep convolutional neural network, obtaining a prediction mask of the topmost layer of ribs from top to bottom in sequence, and further obtaining a predicted rib instance segmentation mask. According to the method, explicit modeling is carried out on the rib counting problem, the ribs are segmented one by one from the lung top to the lung bottom, and rib counting and positioning are achieved.

Description

technical field

[0001] The present invention relates to the field of computer technology, in particular, to a rib instance segmentation, counting and positioning method and system, especially a rib instance segmentation, counting and positioning method based on deep learning. Background technique

[0002] Diagnosis, description, and reporting of fractures (diseases) appearing in CT are one of the important contents for radiologists to read films. When a fracture (disease) is found, it is necessary to describe the lesion according to its anatomical location for follow-up analysis or reference for other departments. With the popularity of thin-section CT, doctors can find subtle fractures (diseases), but due to the increase in the number of layers, it has become a difficult problem to confirm the location of the lesion, especially the description of the ribs. People usually have 12 pairs of ribs, and each rib has an independent number, which can be divided into the first rib,...

Examples

Embodiment 1

[0039] This embodiment provides a rib instance segmentation, counting and positioning method, including the following steps:

[0040]Step 1: Perform semantic segmentation on ribs in chest CT to obtain a binary mask for rib semantic segmentation. Denoise the obtained rib semantic segmentation binary mask, and delete the small noise in the semantic segmentation mask whose volume is smaller than the preset value.

[0041] Step 2: Collect the manual annotations corresponding to the rib semantic segmentation binary mask to obtain the rib instance segmentation mask.

[0042] Step 3: Process the rib semantic segmentation binary mask and the rib instance segmentation mask to create a training sample set for hierarchical segmentation. According to the information provided by the rib instance segmentation mask, the rib semantic segmentation binary mask retains the first and subsequent ribs, the second and subsequent ribs, the third and subsequent ribs, and the fourth and subsequent rib...

Embodiment 2

[0047] This embodiment provides a rib instance segmentation, counting and positioning system, including the following modules:

[0048] Rib semantic segmentation binary mask module: perform semantic segmentation on ribs in chest CT to obtain rib semantic segmentation binary mask;

[0049] Rib instance segmentation mask module: collect the manual annotation corresponding to the rib semantic segmentation binary mask, and obtain the rib instance segmentation mask;

[0050] Training sample set module: process the rib semantic segmentation binary mask and the rib instance segmentation mask to make a hierarchical segmentation training sample set;

[0051] Neural network model module: establish a deep convolutional neural network model;

[0052] Training module: using the training sample set to train the neural network architectures at all levels in the deep convolutional neural network model to obtain a deep convolutional neural network capable of predicting top ribs;

[0053] Pre...

Embodiment 3

[0055] Those skilled in the art can understand this embodiment as a more specific description of Embodiment 1 and Embodiment 2.

[0056] Such as figure 1 and figure 2 As shown, this embodiment provides an effective chest CT rib instance segmentation, rib counting and rib positioning algorithm. With the positioning method, the method includes the following steps:

[0057] Step 1. Perform semantic segmentation on the ribs in the chest CT, that is, the rib area in the chest CT is marked as 1, and the other areas are marked as 0, and the rib semantic segmentation binary mask is obtained. This step can be realized by methods such as threshold-based segmentation and deep learning-based segmentation, which are not the main content of the present invention and will not be described further.

[0058] Step 2. Collect the rib semantic segmentation binary mask obtained in step 1, and manually mark the rib semantic segmentation binary mask. In particular, during the manual labeling pr...

technical field

[0001] The present invention relates to the field of computer technology, in particular, to a rib instance segmentation, counting and positioning method and system, especially a rib instance segmentation, counting and positioning method based on deep learning. Background technique

[0002] Diagnosis, description, and reporting of fractures (diseases) appearing in CT are one of the important contents for radiologists to read films. When a fracture (disease) is found, it is necessary to describe the lesion according to its anatomical location for follow-up analysis or reference for other departments. With the popularity of thin-section CT, doctors can find subtle fractures (diseases), but due to the increase in the number of layers, it has become a difficult problem to confirm the location of the lesion, especially the description of the ribs. People usually have 12 pairs of ribs, and each rib has an independent number, which can be divided into the first rib,...

Examples

Embodiment 1

[0039] This embodiment provides a rib instance segmentation, counting and positioning method, including the following steps:

[0040]Step 1: Perform semantic segmentation on ribs in chest CT to obtain a binary mask for rib semantic segmentation. Denoise the obtained rib semantic segmentation binary mask, and delete the small noise in the semantic segmentation mask whose volume is smaller than the preset value.

[0041] Step 2: Collect the manual annotations corresponding to the rib semantic segmentation binary mask to obtain the rib instance segmentation mask.

[0042] Step 3: Process the rib semantic segmentation binary mask and the rib instance segmentation mask to create a training sample set for hierarchical segmentation. According to the information provided by the rib instance segmentation mask, the rib semantic segmentation binary mask retains the first and subsequent ribs, the second and subsequent ribs, the third and subsequent ribs, and the fourth and subsequent rib...

Embodiment 2

[0047] This embodiment provides a rib instance segmentation, counting and positioning system, including the following modules:

[0048] Rib semantic segmentation binary mask module: perform semantic segmentation on ribs in chest CT to obtain rib semantic segmentation binary mask;

[0049] Rib instance segmentation mask module: collect the manual annotation corresponding to the rib semantic segmentation binary mask, and obtain the rib instance segmentation mask;

[0050] Training sample set module: process the rib semantic segmentation binary mask and the rib instance segmentation mask to make a hierarchical segmentation training sample set;

[0051] Neural network model module: establish a deep convolutional neural network model;

[0052] Training module: using the training sample set to train the neural network architectures at all levels in the deep convolutional neural network model to obtain a deep convolutional neural network capable of predicting top ribs;

[0053] Pre...

Embodiment 3

[0055] Those skilled in the art can understand this embodiment as a more specific description of Embodiment 1 and Embodiment 2.

[0056] Such as figure 1 and figure 2 As shown, this embodiment provides an effective chest CT rib instance segmentation, rib counting and rib positioning algorithm. With the positioning method, the method includes the following steps:

[0057] Step 1. Perform semantic segmentation on the ribs in the chest CT, that is, the rib area in the chest CT is marked as 1, and the other areas are marked as 0, and the rib semantic segmentation binary mask is obtained. This step can be realized by methods such as threshold-based segmentation and deep learning-based segmentation, which are not the main content of the present invention and will not be described further.

[0058] Step 2. Collect the rib semantic segmentation binary mask obtained in step 1, and manually mark the rib semantic segmentation binary mask. In particular, during the manual labeling pr...

Images