Analysis of segmentation of lung parenchyma based on deep learning methods.

Precise segmentation of lung parenchyma is essential for effective analysis of the lung. Due to the obvious contrast and large regional area compared to other tissues in the chest, lung tissue is less difficult to segment. Special attention to details of lung segmentation is also needed. To improve the quality and speed of segmentation of lung parenchyma based on computed tomography (CT) or computed tomography angiography (CTA) images, the 4th International Symposium on Image Computing and Digital Medicine (ISICDM 2020) provides interesting and valuable research ideas and approaches. For the work of lung parenchyma segmentation, 9 of the 12 participating teams used the U-Net network or its modified forms, and others used the methods to improve the segmentation accuracy include attention mechanism, multi-scale feature information fusion. Among them, U-Net achieves the best results including that the final dice coefficient of CT segmentation is 0.991 and the final dice coefficient of CTA segmentation is 0.984. In addition, attention U-Net and nnU-Net network also performs well. In this paper, the methods chosen by 12 teams from different research groups are evaluated and their segmentation results are analyzed for the study and references to those involved.

[Segmentation and accuracy validation of mandibular molar and pulp cavity on cone-beam CT images by U-net neural network].

PURPOSE: To realize the automatic segmentation of mandibular molar and pulp cavity on cone-beam CT (CBCT) images by U-net convolutional neural network, and to use the 3D models reconstructed by Micro-CT data as the ground truth to validate its accuracy. METHODS： Twenty groups of small field of view(FOV) CBCT data containing complete mandibular molars were collected from the Department of Radiology, Affiliated Stomatology Hospital of Tongji University. After preprocessing, an endodontic specialist labeled teeth and pulp cavities by MITK Workbench software. These data were used as the training set for training U-net neural network. In addition, five mandibular molars and corresponding small FOV CBCT data were collected. These five CBCT were processed in the same way and used as the testing set. Then, teeth and pulp cavities on CBCT images of the testing set were segmented and reconstructed by U-net neural network and the same specialist. The isolated teeth were scanned by a Micro-CT machine after preprocessing and the results were reconstructed to 3D models, which were used as the ground truth. Then the 3D models reconstructed by the specialist's labeling, U-net network segmentation results, and the ground truth in the testing set were compared. Dice similarity coefficient(DSC), average symmetric surface distance (ASSD), Hausdorff distance (HD), and morphological analysis were used to evaluate the results. SPSS 20.0 software package was used for statistical analysis. RESULTS: Compared with the ground truth, the segmentation accuracy of the U-net neural network measured by DSC, ASSD, and AHD was (95.30±1.01)%, (0.11±0.02) mm, and (1.05±0.31) mm in teeth and (81.21±2.27)%, (0.15±0.05) mm, and (3.29±1.85) mm in the pulp cavity, respectively. Morphological analysis results showed that the U-net network segmentation results were similar to the ground truth in tooth and pulp chamber. As for the segmentation results of root canals, only thick root canals could be segmented rather than the thin root canals, such as the canals in the apical third and lateral root canals. CONCLUSIONS: Under the experimental conditions, the U-net neural network trained by the specialist's labeling realized the automatic and accurate segmentation of mandibular molar and their pulp chamber on CBCT images. For the segmentation of root canals, the results need to be further improved.

Micro-Computed Tomography-Guided Artificial Intelligence for Pulp Cavity and Tooth Segmentation on Cone-beam Computed Tomography.

INTRODUCTION: This study proposes a novel data pipeline based on micro-computed tomographic (micro-CT) data for training the U-Net network to realize the automatic and accurate segmentation of the pulp cavity and tooth on cone-beam computed tomographic (CBCT) images. METHODS: We collected CBCT data and micro-CT data of 30 teeth. CBCT data were processed and transformed into small field of view and high-resolution CBCT images of each tooth. Twenty-five sets were randomly assigned to the training set and the remaining 5 sets to the test set. We used 2 data pipelines for U-Net network training: one manually labeled by an endodontic specialist as the control group and one processed from the micro-CT data as the experimental group. The 3-dimensional models constructed using micro-CT data in the test set were taken as the ground truth. The Dice similarity coefficient, precision rate, recall rate, average symmetric surface distance, Hausdorff distance, and morphologic analysis were used for performance evaluation. RESULTS: The segmentation accuracy of the experimental group measured by the Dice similarity coefficient, precision rate, recall rate, average symmetric surface distance, and Hausdorff distance were 96.20% ± 0.58%, 97.31% ± 0.38%, 95.11% ± 0.97%, 0.09 ± 0.01 mm, and 1.54 ± 0.51 mm in the tooth and 86.75% ± 2.42%, 84.45% ± 7.77%, 89.94% ± 4.56%, 0.08 ± 0.02 mm, and 1.99 ± 0.67 mm in the pulp cavity, respectively, which were better than the control group. Morphologic analysis suggested the segmentation results of the experimental group were better than those of the control group. CONCLUSIONS: This study proposed an automatic and accurate approach for tooth and pulp cavity segmentation on CBCT images, which can be applied in research and clinical tasks.