Search

Quantitative measurement of hepatocellular carcinoma (HCC) on multi-phase contrast-enhanced magnetic resonance imaging (CEMRI) is one of the key processes for HCC treatment and prognosis. However, direct automated quantitative measurement using the CNN-based network a still challenging task due to: (1) The lack of ability for capturing long-range dependencies of multi-anatomy in the whole medical image; (2) The lack of mechanism for fusing and selecting multi-phase CEMRI information. In this study, we propose a multi-function Transformer regression network (mfTrans-Net) for HCC quantitative measurement. Specifically, we first design three parallel CNN-based encoders for multi-phase CEMRI feature extraction and dimension reducing. Next, the non-local Transformer makes our mfTrans-Net self-attention for capturing the long-range dependencies of multi-anatomy. At the same time, a phase-aware Transformer captures the relevance between multi-phase CEMRI for multi-phase CEMRI information fusion and selection. Lastly, we proposed a multi-level training strategy, which enables an enhanced loss function to improve the quantification task. The mfTrans-Net is validated on multi-phase CEMRI of 138 HCC subjects. Our mfTrans-Net achieves high performance of multi-index quantification that the mean absolute error of center point, max-diameter, circumference, and area is down to 2.35 mm, 2.38 mm, 8.28 mm, and 116.15 mm\(^2\), respectively. The results show that mfTrans-Net has great potential for small lesions quantification in medical images and clinical application value.

Feature extraction of lung nodules is very important in the diagnosis of lung cancer and is the premise of feature description, target matching, recognition and benign and malignant diagnosis. The main contribution of this work is the development of a new end-to-end feature extraction method that learns effective feature representation from images to effectively establish the direct relationship between multiple features and tissue features (that is, benign or malignant). The architecture consists of three seamlessly connected functional layers. RGB multichannel can automatically extract ROI sequence images involving lung parenchyma from the lung imaging sequence. The feature extraction layers, using Principal Component Analysis Network - random binary hash (PCANet-RBH), a) extract high-level semantic features of the R/G/B channel by cascading PCA and fuse the extracted normal color patterns, and b) generate multiple binary patterns via RBH to produce richer features with color information. The connected spatial pyramid pooling (SPP) layer can extract the location features of the lung nodules and map the feature matrix to the low-dimensional space and then establish a correspondence between the image features and the organizational identity. We validate the performance of the proposed method using the public dataset LIDC. The experimental results show that the fusion features extracted by our method have high and stable classification accuracy (accuracy:93.25 ± 0.53, sensitivity:93.12 ± 0.62 specificity:91.37 ± 0.62), which is significantly better than the traditional algorithm for lung nodule feature extraction. Moreover, RGB-PCANet has a short training time, which can meet the requirements of real-time diagnosis of lung cancer. In general, the advantage of our framework is that it provides a better and more comprehensive method to establish a direct relationship between image high-level semantic features, color features, location features and tissue features, making it an attractive clinical diagnostic tool for lung cancer.

Simultaneous segmentation and detection of liver tumors (hemangioma and hepatocellular carcinoma (HCC)) by using multi-modality non-contrast magnetic resonance imaging (NCMRI) are crucial for the clinical diagnosis. However, it is still a challenging task due to: (1) the HCC information on NCMRI is insufficient makes extraction of liver tumors feature difficult; (2) diverse imaging characteristics in multi-modality NCMRI causes feature fusion and selection difficult; (3) no specific information between hemangioma and HCC on NCMRI cause liver tumors detection difficult. In this study, we propose a united adversarial learning framework (UAL) for simultaneous liver tumors segmentation and detection using multi-modality NCMRI. The UAL first utilizes a multi-view aware encoder to extract multi-modality NCMRI information for liver tumor segmentation and detection. In this encoder, a novel edge dissimilarity feature pyramid module is designed to facilitate the complementary multi-modality feature extraction. Secondly, the newly designed fusion and selection channel is used to fuse the multi-modality feature and make the decision of the feature selection. Then, the proposed mechanism of coordinate sharing with padding integrates the multi-task of segmentation and detection so that it enables multi-task to perform united adversarial learning in one discriminator. Lastly, an innovative multi-phase radiomics guided discriminator exploits the clear and specific tumor information to improve the multi-task performance via the adversarial learning strategy. The UAL is validated in corresponding multi-modality NCMRI (i.e. T1FS pre-contrast MRI, T2FS MRI, and DWI) and three phases contrast-enhanced MRI of 255 clinical subjects. The experiments show that UAL gains high performance with the dice similarity coefficient of 83.63%, the pixel accuracy of 97.75%, the intersection-over-union of 81.30%, the sensitivity of 92.13%, the specificity of 93.75%, and the detection accuracy of 92.94%, which demonstrate that UAL has great potential in the clinical diagnosis of liver tumors.

Segmentation of the liver tumor is critical for preoperative planning, surgical protocol guidance, and post-operative treatment. Because of using contrast agents (CA), current liver tumor imaging still suffers from high-risk, time-consumption and expensive issues. In this study, a new Radiomics-guided generative adversarial network (Radiomics-guided GAN) is proposed as a safe, short time-consumption and inexpensive clinical tool to segment liver tumor without CA. The innovative Radiomics-guided adversarial mechanism learns the mapping relationship between the contrast images and the non-contrast images, which leads to completing the segmentation. Radiomics-guided GAN contains a segmentor and a discriminator module: the discriminator innovatively uses the Radiomics-feature from the contrast images as prior knowledge to guide the segmentor’s adversarial learning; the segmentor innovatively uses dense connection and skip connection to receive and share the guidance information, extracting the representing feature – Implicit Contract Radiomics (ICR) feature – in the non-contrast images. Our method yielded a pixel segmentation accuracy of 95.85%, and a Dice coefficient of 92.17 ± 0.79%, from 200 clinical subjects. The results illustrate that our method achieves the segmentation of liver tumor without CA and become the most potential useful tool for clinicians.

Statistically solitary pulmonary nodules are about 6% to 17% of juxtapleural nodules. The accurate segmentation of lung parenchyma sequences of juxtapleural nodules is the basis of subsequent pulmonary nodule segmentation and detection. In order to solve the problem of incomplete segmentation of the juxtapleural nodules and segmentation inefficiency, this paper proposes an automated framework to combine the threshold iteration method to segment the lung parenchyma images and the fractal geometry method to detect the depression boundary. The framework includes an improved convex hull repair to complete the accurate segmentation of the lung parenchyma. The evaluation results confirm that the proposed method can segment juxtapleural lung parenchymal images accurately and efficiently.