Digital Library[ Search Result ]
Improvement of Prostate Cancer Aggressiveness Prediction Based on the Deep Learning Model Using Size Normalization and Multiple Loss Functions on Multi-parametric MR Images
Yoon Jo Kim, Julip Jung, Sung Il Hwang, Helen Hong
http://doi.org/10.5626/JOK.2023.50.10.866
Prostate cancer is the second most common cancer in men worldwide, and it is essential to predict the aggressiveness of prostate cancer because the recurrence rate and the effectiveness of treatment vary depending on the aggressiveness. This study enhances the information on small tumors by applying size normalization to predict the aggressiveness of prostate cancer in multi-parametric MR imaging. Additionally, we propose the use of multiple loss functions to distinguish tumors with different aggressiveness while having a similar visual appearance. Experimental results show that the proposed model trained with size-normalized ADC maps achieves an accuracy of 76.28%, sensitivity of 76.81%, specificity of 75.86%, and an AUC of 0.77. Moreover, compared to the tumor-centered ADC maps, size-normalized ADC maps demonstrate improved performance in tumors smaller than 1.5 cm, with an accuracy of 76.47%, sensitivity of 90.91%, and specificity of 69.57%, corresponding to a significant improvement of 17.65%, 27.27%, and 13.05% respectively.
Automatic Classification of Pneumonia Based on Ensemble Deep Learning Model Using Intensity Normalization and Multiscale Lung-Focused Patches on Chest X-Ray Images
Yoon Jo Kim, Jinseo An, Helen Hong
http://doi.org/10.5626/JOK.2022.49.9.677
It is difficult to classify normal and pneumonia in pediatric chest X-ray (CXR) images due to irregular intensity values. In addition, deep learning model has a limitation in that it can misclassify CXR by incorrectly focusing on the outer part of the lung. This study proposed an automatic classification of pneumonia based on ensemble deep learning model using three intensity normalizations and multiscale lung-focused patches on CXR images. First, to correct for irregular intensity values in internal lungs, three intensity normalization methods were performed respectively. Second, to focus on internal lungs, regions of interest were extracted by segmenting lung regions. Third, multiscale lung-focused patches were extracted to train the characterization of pneumonia. Finally, ensemble modeling with attention module was performed to improve the classification performance. In the experiment, the method using large patches of CLAHE images showed an accuracy of 92%, which was 5% higher than that of original images. Furthermore, the proposed method using an ensemble of large and middle patches showed the best performance with an accuracy of 93%.
Automatic Segmentation of Lung Cancer in Chest CT Images through Capsule Network-based Dual-Window Ensemble Learning
Jumin Lee, Julip Jung, Helen Hong, Bong-Seog Kim
http://doi.org/10.5626/JOK.2021.48.8.905
It is difficult to accurately segment lung cancer in chest CT images when it has an irregular shape or nearby structures have a similar intensity as lung cancer. In this study, we proposed a dual window ensemble network that uses a capsule network to learn the relationship between lung cancer and nearby structures and additionally considers the mediastinal window image with the lung window image to distinguish lung cancer from the nearby structures. First, intensity and spacing normalization was performed on the input images of the lung window setting and mediastinal window setting. Second, two types of 2D capsule network were performed with the lung and mediastinal setting images. Third, the final segmentation mask was generated by ensemble the probability maps of the lung and mediastinal window images through average voting by reflecting the weight based on the characteristics of each image. The proposed method showed a Dice similarity coefficient(DSC) of 75.98% which was 0.53% higher than the method not considering the weight of each window setting. Furthermore, segmentation accuracy was improved even when lung cancer was surrounded by nearby structures.
Automatic Pancreas Segmentation Based on Cascaded Network Considering Pancreatic Uncertainty in Abdominal CT Images
Hyeon Dham Yoon, Hyeonjin Kim, Helen Hong
http://doi.org/10.5626/JOK.2021.48.5.548
Pancreas segmentation from abdominal CT images is a prerequisite step for understanding the shape of the pancreas in pancreatic cancer detection. In this paper, we propose an automatic pancreas segmentation method based on a deep convolutional neural network(DCNN) that considers information about the uncertain regions generated by the positional and morphological diversity of the pancreas in abdominal CT images. First, intensity and spacing normalizations are performed in the whole abdominal CT images. Second, the pancreas is localized using 2.5D segmentation networks based on U-Net on the axial, coronal, and sagittal planes and by combining through a majority voting. Third, pancreas segmentation is performed in the localized volume using a 3D U-Net-based segmentation network that takes into account the information about the uncertain areas of the pancreas. The average DSC of pancreas segmentation was 83.50%, which was 10.30%p, 10.44%p, 6.52%p, 1.14%p, and 3.95%p higher than the segmentation method using 2D U-Net at axial view, coronal view, sagittal view, majority voting of the three planes, and 3D U-Net at localized volume, respectively.
Automatic Teeth Separation through Searching Teeth Separation Lines and Planes based on Intensity Cost Function Optimization in Maxillofacial CBCT Images
Soyoung Lee, Min Jin Lee, Helen Hong
http://doi.org/10.5626/JOK.2019.46.1.65
In this paper, we propose an automatic teeth separation method based on the intensity cost function which finds optimal teeth separation line in 2D panorama image. It also finds the optimal teeth separation plane considering the spatial information of teeth in 3D maxillofacial CBCT images. First, to observe the overall structure of an individual tooth, the 2D panorama image of the teeth is reconstructed by extracting the teeth arch curve of the crown and root region. Second, the optimal teeth separation lines are searched through the intensity-based cost function in the reconstructed 2D panorama image. Third, to improve the accuracy of teeth separation, the optimal separation planes considering the spatial information are searched through the intensity-based cost function in 3D CBCT images. Experimental results show that the proposed method improves the separation accuracy compared to the comparative method. The average intensity value of the proposed method was reduced by 8.61% compared to the comparative method. The processing time of the proposed method was completed within 30 seconds.
Automatic Segmentation of Renal Parenchyma using Shape and Intensity Information based on Multi-atlas in Abdominal CT Images
Hyeonjin Kim, Helen Hong, Kidon Chang, Koon Ho Rha
http://doi.org/10.5626/JOK.2018.45.9.937
Renal parenchyma segmentation is necessary to predict contralateral hypertrophy after renal partial nephrectomy. In this paper, we propose an automatic segmentation method of renal parenchyma using shape and intensity information based on the multi-atlas in abdominal CT images. First, similar atlases are selected using volume-based similarity registration and intensity-similarity measure. Second, renal parenchyma is segmented using two-stage registration and constrained intensity-based locally-weighted voting. Finally, renal parenchyma is refined using a Gaussian mixture model-based multi-thresholds and shape-prediction map in under- and over-segmented data. The average dice similarity coefficient of renal parenchyma was 91.34%, which was 18.19%, 1.35% higher than the segmentation method using majority voting and locally-weighted voting in dice similarity coefficient, respectively.
Automatic Segmentation of Femoral Cartilage in Knee MR Images using Multi-atlas-based Locally-weighted Voting
Hyeun A Kim, Hyeonjin Kim, Han Sang Lee, Helen Hong
In this paper, we propose an automated segmentation method of femoral cartilage in knee MR images using multi-atlas-based locally-weighted voting. The proposed method involves two steps. First, to utilize the shape information to show that the femoral cartilage is attached to a femur, the femur is segmented via volume and object-based locally-weighted voting and narrow-band region growing. Second, the object-based affine transformation of the femur is applied to the registration of femoral cartilage, and the femoral cartilage is segmented via multi-atlas shape-based locally-weighted voting. To evaluate the performance of the proposed method, we compared the segmentation results of majority voting method, intensity-based locally-weighted voting method, and the proposed method with manual segmentation results defined by expert. In our experimental results, the newly proposed method avoids a leakage into the neighboring regions having similar intensity of femoral cartilage, and shows improved segmentation accuracy.
Tumor Motion Tracking during Radiation Treatment using Image Registration and Tumor Matching between Planning 4D MDCT and Treatment 4D CBCT
During image-guided radiation treatment of lung cancer patients, it is necessary to track the tumor motion because it can change during treatment as a consequence of respiratory motion and cardiac motion. In this paper, we propose a method for tracking the motion of the lung tumors based on the three-dimensional image information from planning 4D MDCT and treatment 4D CBCT images. First, to effectively track the tumor motion during treatment, the global motion of the tumor is estimated based on a tumor-specific motion model obtained from planning 4D MDCT images. Second, to increase the accuracy of the tumor motion tracking, the local motion of the tumor is estimated based on the structural information of the tumor from 4D CBCT images. To evaluate the performance of the proposed method, we estimated the tracking results of proposed method using digital phantom. The results show that the tumor localization error of local motion estimation is reduced by 45% as compared with that of global motion estimation.
Anterior Cruciate Ligament Segmentation in Knee MRI with Locally-aligned Probabilistic Atlas and Iterative Graph Cuts
Segmentation of the anterior cruciate ligament (ACL) in knee MRI remains a challenging task due to its inhomogeneous signal intensity and low contrast with surrounding soft tissues. In this paper, we propose a multi-atlas-based segmentation of the ACL in knee MRI with locally-aligned probabilistic atlas (PA) in an iterative graph cuts framework. First, a novel PA generation method is proposed with global and local multi-atlas alignment by means of rigid registration. Second, with the generated PA, segmentation of the ACL is performed by maximum-aposteriori (MAP) estimation and then by graph cuts. Third, refinement of ACL segmentation is performed by improving shape prior through mask-based PA generation and iterative graph cuts. Experiments were performed with a Dice similarity coefficients of 75.0%, an average surface distance of 1.7 pixels, and a root mean squared distance of 2.7 pixels, which increased accuracy by 12.8%, 22.7%, and 22.9%, respectively, from the graph cuts with patient-specific shape constraints.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr