Liver segmentation from computed tomography images using cascade deep learning.

BACKGROUND: Liver segmentation is a fundamental step in the treatment planning and diagnosis of liver cancer. However, manual segmentation of liver is time-consuming because of the large slice quantity and subjectiveness associated with the specialist's experience, which can lead to segmentation errors. Thus, the segmentation process can be automated using computational methods for better time efficiency and accuracy. However, automatic liver segmentation is a challenging task, as the liver can vary in shape, ill-defined borders, and lesions, which affect its appearance. We aim to propose an automatic method for liver segmentation using computed tomography (CT) images. METHODS: The proposed method, based on deep convolutional neural network models and image processing techniques, comprise of four main steps: (1) image preprocessing, (2) initial segmentation, (3) reconstruction, and (4) final segmentation. RESULTS: We evaluated the proposed method using 131 CT images from the LiTS image base. An average sensitivity of 95.45%, an average specificity of 99.86%, an average Dice coefficient of 95.64%, an average volumetric overlap error (VOE) of 8.28%, an average relative volume difference (RVD) of -0.41%, and an average Hausdorff distance (HD) of 26.60 mm were achieved. CONCLUSIONS: This study demonstrates that liver segmentation, even when lesions are present in CT images, can be efficiently performed using a cascade approach and including a reconstruction step based on deep convolutional neural networks.

Kidney segmentation from computed tomography images using deep neural network.

BACKGROUND: The precise segmentation of kidneys and kidney tumors can help medical specialists to diagnose diseases and improve treatment planning, which is highly required in clinical practice. Manual segmentation of the kidneys is extremely time-consuming and prone to variability between different specialists due to their heterogeneity. Because of this hard work, computational techniques, such as deep convolutional neural networks, have become popular in kidney segmentation tasks to assist in the early diagnosis of kidney tumors. In this study, we propose an automatic method to delimit the kidneys in computed tomography (CT) images using image processing techniques and deep convolutional neural networks (CNNs) to minimize false positives. METHODS: The proposed method has four main steps: (1) acquisition of the KiTS19 dataset, (2) scope reduction using AlexNet, (3) initial segmentation using U-Net 2D, and (4) false positive reduction using image processing to maintain the largest elements (kidneys). RESULTS: The proposed method was evaluated in 210 CTs from the KiTS19 database and obtained the best result with an average Dice coefficient of 96.33%, an average Jaccard index of 93.02%, an average sensitivity of 97.42%, an average specificity of 99.94% and an average accuracy of 99.92%. In the KiTS19 challenge, it presented an average Dice coefficient of 93.03%. CONCLUSION: In our method, we demonstrated that the kidney segmentation problem in CT can be solved efficiently using deep neural networks to define the scope of the problem and segment the kidneys with high precision and with the use of image processing techniques to reduce false positives.

Pathophysiological mapping of tumor habitats in the breast in DCE-MRI using molecular texture descriptor.

BACKGROUND: We propose a computational methodology capable of detecting and analyzing breast tumor habitats in images acquired by magnetic resonance imaging with dynamic contrast enhancement (DCE-MRI), based on the pathophysiological behavior of the contrast agent (CA). METHODS: The proposed methodology comprises three steps. In summary, the first step is the acquisition of images from the Quantitative Imaging Network Breast. In the second step, the segmentation of the breasts is performed to remove the background, noise, and other unwanted objects from the image. In the third step, the generation of habitats is performed by applying two techniques: the molecular texture descriptor (MTD) that highlights the CA regions in the breast, and pathophysiological texture mapping (MPT), which generates tumor habitats based on the behavior of the CA. The combined use of these two techniques allows the automatic detection of tumors in the breast and analysis of each separate habitat with respect to their malignancy type. RESULTS: The results found in this study were promising, with 100% of breast tumors being identified. The segmentation results exhibited an accuracy of 99.95%, sensitivity of 71.07%, specificity of 99.98%, and volumetric similarity of 77.75%. Moreover, we were able to classify the malignancy of the tumors, with 6 classified as malignant type III (WashOut) and 14 as malignant type II (Plateau), for a total of 20 cases. CONCLUSION: We proposed a method for the automatic detection of tumors in the breast in DCE-MRI and performed the pathophysiological mapping of tumor habitats by analyzing the behavior of the CA, combining MTD and MPT, which allowed the mapping of internal tumor habitats.