Verte-Box: A Novel Convolutional Neural Network for Fully Automatic Segmentation of Vertebrae in CT Image

Automatic Skeleton Segmentation in CT Images Based on U-Net

Bone metastasis, emerging oncological therapies, and osteoporosis represent some of the distinct clinical contexts which can result in morphological alterations in bone structure. The visual assessment of these changes through anatomical images is considered suboptimal, emphasizing the importance of precise skeletal segmentation as a valuable aid for its evaluation. In the present study, a neural network model for automatic skeleton segmentation from bidimensional computerized tomography (CT) slices is proposed. A total of 77 CT images and their semimanual skeleton segmentation from two acquisition protocols (whole-body and femur-to-head) are used to form a training group and a testing group. Preprocessing of the images includes four main steps: stretcher removal, thresholding, image clipping, and normalization (with two different techniques: interpatient and intrapatient). Subsequently, five different sets are created and arranged in a randomized order for the training phase. A neural network model based on U-Net architecture is implemented with different values of the number of channels in each feature map and number of epochs. The model with the best performance obtains a Jaccard index (IoU) of 0.959 and a Dice index of 0.979. The resultant model demonstrates the potential of deep learning applied in medical images and proving its utility in bone segmentation.

NAMSTCD: A Novel Augmented Model for Spinal Cord Segmentation and Tumor Classification Using Deep Nets

Spinal cord segmentation is the process of identifying and delineating the boundaries of the spinal cord in medical images such as magnetic resonance imaging (MRI) or computed tomography (CT) scans. This process is important for many medical applications, including the diagnosis, treatment planning, and monitoring of spinal cord injuries and diseases. The segmentation process involves using image processing techniques to identify the spinal cord in the medical image and differentiate it from other structures, such as the vertebrae, cerebrospinal fluid, and tumors. There are several approaches to spinal cord segmentation, including manual segmentation by a trained expert, semi-automated segmentation using software tools that require some user input, and fully automated segmentation using deep learning algorithms. Researchers have proposed a wide range of system models for segmentation and tumor classification in spinal cord scans, but the majority of these models are designed for a specific segment of the spine. As a result, their performance is limited when applied to the entire lead, limiting their deployment scalability. This paper proposes a novel augmented model for spinal cord segmentation and tumor classification using deep nets to overcome this limitation. The model initially segments all five spinal cord regions and stores them as separate datasets. These datasets are manually tagged with cancer status and stage based on observations from multiple radiologist experts. Multiple Mask Regional Convolutional Neural Networks (MRCNNs) were trained on various datasets for region segmentation. The results of these segmentations were combined using a combination of VGGNet 19, YoLo V2, ResNet 101, and GoogLeNet models. These models were selected via performance validation on each segment. It was observed that VGGNet-19 was capable of classifying the thoracic and cervical regions, while YoLo V2 was able to efficiently classify the lumbar region, ResNet 101 exhibited better accuracy for sacral-region classification, and GoogLeNet was able to classify the coccygeal region with high performance accuracy. Due to use of specialized CNN models for different spinal cord segments, the proposed model was able to achieve a 14.5% better segmentation efficiency, 98.9% tumor classification accuracy, and a 15.6% higher speed performance when averaged over the entire dataset and compared with various state-of-the art models. This performance was observed to be better, due to which it can be used for various clinical deployments. Moreover, this performance was observed to be consistent across multiple tumor types and spinal cord regions, which makes the model highly scalable for a wide variety of spinal cord tumor classification scenarios.

MINet: Multi-scale input network for fundus microvascular segmentation

Vessel segmentation in fundus images is a key procedure in the diagnosis of ophthalmic diseases, which can play a role in assisting doctors in diagnosis. Although current deep learning-based methods can achieve high accuracy in segmenting fundus vessel images, the results are not satisfactory in segmenting microscopic vessels that are close to the background region. The reason for this problem is that thin blood vessels contain very little information, with the convolution operation of each layer in the deep network, this part of the information will be randomly lost. To improve the segmentation ability of the small blood vessel region, a multi-input network (MINet) was proposed to segment vascular regions more accurately. We designed a multi-input fusion module (MIF) in the encoder, which is proposed to acquire multi-scale features in the encoder stage while preserving the microvessel feature information. In addition, to further aggregate multi-scale information from adjacent regions, a multi-scale atrous spatial pyramid (MASP) module is proposed. This module can enhance the extraction of vascular information without reducing the resolution loss. In order to better recover segmentation results with details, we designed a refinement module, which acts on the last layer of the network output to refine the results of the last layer of the network to get more accurate segmentation results. We use the HRF, CHASE_DB1 public dataset to validate the fundus vessel segmentation performance of the MINet model. Also, we merged these two public datasets with our collected Ultra-widefield fundus image (UWF) data as one dataset to test the generalization ability of the model. Experimental results show that MINet achieves an F₁ score of 0.8324 on the microvessel segmentation task, achieving a high accuracy compared to the current mainstream models.

Automated detection and classification of acute vertebral body fractures using a convolutional neural network on computed tomography

BACKGROUND

Acute vertebral fracture is usually caused by low-energy injury with osteoporosis and high-energy trauma. The AOSpine thoracolumbar spine injury classification system (AO classification) plays an important role in the diagnosis and treatment of the disease. The diagnosis and description of vertebral fractures according to the classification scheme requires a great deal of time and energy for radiologists.

PURPOSE

To design and validate a multistage deep learning system (multistage AO system) for the automatic detection, localization and classification of acute thoracolumbar vertebral body fractures according to AO classification on computed tomography.

MATERIALS AND METHODS

The CT images of 1,217 patients who came to our hospital from January 2015 to December 2019 were collected retrospectively. The fractures were marked and classified by 2 junior radiology residents according to the type A standard in the AO classification. Marked fracture sites included the upper endplate, lower endplate and posterior wall. When there were inconsistent opinions on classification labels, the final result was determined by a director radiologist. We integrated different networks into different stages of the overall framework. U-net and a graph convolutional neural network (U-GCN) are used to realize the location and classification of the thoracolumbar spine. Next, a classification network is used to detect whether the thoracolumbar spine has a fracture. In the third stage, we detect fractures in different parts of the thoracolumbar spine by using a multibranch output network and finally obtain the AO types.

RESULTS

The mean age of the patients was 61.87 years with a standard deviation of 17.04 years, consisting of 760 female patients and 457 male patients. On vertebrae level, sensitivity for fracture detection was 95.23% in test dataset, with an accuracy of 97.93% and a specificity of 98.35%. For the classification of vertebral body fractures, the balanced accuracy was 79.56%, with an AUC of 0.904 for type A1, 0.945 for type A2, 0.878 for type A3 and 0.942 for type A4.

CONCLUSION

The multistage AO system can automatically detect and classify acute vertebral body fractures in the thoracolumbar spine on CT images according to AO classification with high accuracy.

A novel 3D lumbar vertebrae location and segmentation method based on the fusion envelope of 2D hybrid visual projection images

In recent years, fast and precise lumbar vertebrae segmentation technology have been one of the important topics in practical medical diagnosis and assisted medical surgery scenarios. However, most of the existing vertebral segmentation methods are based on the whole vertebral scanning space, which, up to some extent, is difficult to meet the clinical needs because of its large time complexity and space complexity. Different from the existing methods, for better exploiting the real time of lumbar segmentation, meanwhile ensuring its accuracy, a novel 3D lumbar vertebrae location and segmentation method based on the fusion envelope of 2D hybrid visual projection images (LVLS-HVPFE) is proposed in this paper. Firstly, a 2D projection location network of lumbar vertebrae based on fusion envelope of hybrid visual projection images is proposed to obtain the accurate location of each intact lumbar vertebra in the coronal and sagittal planes respectively. Among them, the envelope dataset of hybrid visual projection images (ED^HVPs) is established to enhance feature representation and suppress interference in the process of dimensionality reduction projection. An envelope deep neural network (EDNN) for ED^HVPs is established to effectively obtain depth envelope structure features with three different sizes, and a dimension reduction fusion mechanism is proposed to increase the sampling density of features and ensure the mutual independence of multi-scale features. Secondly, the concept of 3D localization criterion with spatial dimensionality reduction (SDRLC) is first proposed as a measure to verify the distribution consistency of vertebral targets in coronal and sagittal planes of a CT scan, and it can directionally guide for the subsequent 3D lumbar segmentation. Thirdly, under the condition of 3D positioning subspace of each intact lumbar vertebra, the 3D segmentation network based on spatial orientation guidance is used to realize an accurate segmentation of corresponding lumbar vertebra. The proposed method is evaluated with three representative datasets, and experimental results show that it is superior to the state-of-the-art methods.