Following injurious stimuli, quiescent hepatic stellate cells (qHSCs) transdifferentiate into activated HSCs (aHSCs). aHSCs play pivotal roles in the onset and progression of liver fibrosis. Therefore, molecular imaging of aHSCs in liver fibrosis will facilitate early diagnosis, prognosis prediction, and instruction and evaluation of aHSC-targeted treatment. To date, several receptors, such as integrin αvβ3, mannose 6-phosphate/insulin-like growth factor II receptor (M6P/IGF-IIR), collagen type VI receptor (CVIR), platelet-derived growth factor receptor-β (PDGFR-β), vimentin, and desmin, have been identified as biomarkers of aHSCs. Corresponding ligands to these receptors have also been developed. This review will discuss strategies for developing aHSC-targeted imaging in liver fibrosis.

Antivascular therapy is a promising approach to the treatment of non–small cell lung cancer (NSCLC), where an imaging modality capable of longitudinally monitoring treatment response could provide early prediction of the outcome. In this study, we sought to investigate the feasibility of using intravoxel incoherent motion (IVIM) diffusion MRI to quantitatively assess the efficacy of the treatments of a vascular-disrupting agent CA4P or its combination with bevacizumab on experimental NSCLC tumors. CA4P caused a strong but reversible effect on tumor vasculature; all perfusion-related parameters—D*, f, fD*, and Ktrans—initially showed a decrease of 30% to 60% at 2 hours and then fully recovered to baseline on day 2 for CA4P treatment or on days 4 to 8 for CA4P + bevacizumab treatment; the diffusion coefficient in tumors decreased initially at 2 hours and then increased from day 2 to day 8. We observed a good correlation between IVIM parameters and dynamic contrast-enhanced MRI (DCE-MRI; Ktrans). We also found that the relative change in f and fD* at 2 hours correlated well with changes in tumor volume on day 8. In conclusion, our results suggest that IVIM is a promising alternative to DCE-MRI for the assessment of the change in tumor perfusion as a result of antivascular agents and can be used to predict the efficacy of antivascular therapies without the need for contrast media injection. Cancer Res; 77(13); 3491–501. ©2017 AACR.

Molecular imaging enables the visualization and quantitative analysis of the alterations of biological procedures at molecular and/or cellular level, which is of great significance for early detection of cancer. In recent years, deep leaning has been widely used in medical imaging analysis, as it overcomes the limitations of visual assessment and traditional machine learning techniques by extracting hierarchical features with powerful representation capability. Research on cancer molecular images using deep learning techniques is also increasing dynamically. Hence, in this paper, we review the applications of deep learning in molecular imaging in terms of tumor lesion segmentation, tumor classification, and survival prediction. We also outline some future directions in which researchers may develop more powerful deep learning models for better performance in the applications in cancer molecular imaging.

Recently, an emerging trend in medical image classification is to combine radiomics framework with deep learning classification network in an integrated system. Although this combination is efficient in some tasks, the deep learning-based classification network is often difficult to capture an effective representation of lesion regions, and prone to face the challenge of overfitting, leading to unreliable features and inaccurate results, especially when the sizes of the lesions are small or the training dataset is small. In addition, these combinations mostly lack an effective feature selection mechanism, which makes it difficult to obtain the optimal feature selection. In this paper, we introduce a novel and effective deep semantic segmentation feature-based radiomics (DSFR) framework to overcome the above-mentioned challenges, which consists of two modules: the deep semantic feature extraction module and the feature selection module. Specifically, the extraction module is utilized to extract hierarchical semantic features of the lesions from a trained segmentation network. The feature selection module aims to select the most representative features by using a novel feature similarity adaptation algorithm. Experiments are extensively conducted to evaluate our method in two clinical tasks: the pathological grading prediction in pancreatic neuroendocrine neoplasms (pNENs), and the prediction of thrombolytic therapy efficacy in deep venous thrombosis (DVT). Experimental results on both tasks demonstrate that the proposed method consistently outperforms the state-of-the-art approaches by a large margin.

In this study, we proposed an automated method based on convolutional neural network (CNN) for nasopharyngeal carcinoma (NPC) segmentation on dual-sequence magnetic resonance imaging (MRI). T1-weighted (T1W) and T2-weighted (T2W) MRI images were collected from 44 NPC patients. We developed a dense connectivity embedding U-net (DEU) and trained the network based on the two-dimensional dual-sequence MRI images in the training dataset and applied post-processing to remove the false positive results. In order to justify the effectiveness of dual-sequence MRI images, we performed an experiment with different inputs in eight randomly selected patients. We evaluated DEU's performance by using a 10-fold cross-validation strategy and compared the results with the previous studies. The Dice similarity coefficient (DSC) of the method using only T1W, only T2W and dual-sequence of 10-fold cross-validation as different inputs were 0.620 ± 0.0642, 0.642 ± 0.118 and 0.721 ± 0.036, respectively. The median DSC in 10-fold cross-validation experiment with DEU was 0.735. The average DSC of seven external subjects was 0.87. To summarize, we successfully proposed and verified a fully automatic NPC segmentation method based on DEU and dual-sequence MRI images with accurate and stable performance. If further verified, our proposed method would be of use in clinical practice of NPC.

In recent years, diagnostic and therapeutic approaches for rheumatoid arthritis (RA) have continued to improve. However, in the advanced stages of the disease, patients are unable to achieve long-term clinical remission and often suffer from systemic multi-organ damage and severe complications. Patients with RA usually have no overt clinical manifestations in the early stages, and by the time a definitive diagnosis is made, the disease is already at an advanced stage. RA is diagnosed clinically and with laboratory tests, including the blood markers C-reactive protein (CRP) and erythrocyte sedimentation rate (ESR) and the autoantibodies rheumatoid factor (RF) and anticitrullinated protein antibodies (ACPA). However, the presence of RF and ACPA autoantibodies is associated with aggravated disease, joint damage, and increased mortality, and these autoantibodies have low specificity and sensitivity. The etiology of RA is unknown, with the pathogenesis involving multiple factors and clinical heterogeneity. The early diagnosis, subtype classification, and prognosis of RA remain challenging, and studies to develop minimally invasive or non-invasive biomarkers in the form of biofluid biopsies are becoming more common. Non-coding RNA (ncRNA) molecules are composed of long non-coding RNAs, small nucleolar RNAs, microRNAs, and circular RNAs, which play an essential role in disease onset and progression and can be used in the early diagnosis and prognosis of RA. In this review of the diagnostic and prognostic approaches to RA disease, we provide an overview of the current knowledge on the subject, focusing on recent advances in mRNA–ncRNA as diagnostic and prognostic biomarkers from the biofluid to the tissue level.