CT-based deep learning segmentation of ovarian cancer and the stability of the extracted radiomics features.

Background: Radiomics analysis could provide complementary tissue characterization in ovarian cancer (OC). However, OC segmentation required in radiomics analysis is time-consuming and labour-intensive. In this study, we aim to evaluate the performance of deep learning-based segmentation of OC on contrast-enhanced CT images and the stability of radiomics features extracted from the automated segmentation. Methods: Staging abdominopelvic CT images of 367 patients with OC were retrospectively recruited. The training and cross-validation sets came from center A (n=283), and testing set (n=84) came from centers B and C. The tumours were manually delineated by a board-certified radiologist. Four model architectures provided by no-new-Net (nnU-Net) method were tested in this task. The segmentation performance evaluated by Dice score, Jaccard score, sensitivity and precision were compared among 4 architectures. The Pearson correlation coefficient (ρ), concordance correlation coefficient (ρc) and Bland-Altman plots were used to evaluate the volumetric assessment of OC between manual and automated segmentations. The stability of extracted radiomics features was evaluated by intraclass correlation coefficient (ICC). Results: The 3D U-Net cascade architecture achieved highest median Dice score, Jaccard score, sensitivity and precision for OC segmentation in the testing set, 0.941, 0.890, 0.973 and 0.925, respectively. Tumour volumes of manual and automated segmentations were highly correlated (ρ=0.944 and ρc =0.933). 85.0% of radiomics features had high correlation with ICC >0.8. Conclusions: The presented deep-learning segmentation could provide highly accurate automated segmentation of OC on CT images with high stability of the extracted radiomics features, showing the potential as a batch-processing segmentation tool.

A procedure for producing an anti-AXL nanobody in E. coli.

As one of the receptors of the TAM family, AXL plays a vital role in stem cell maintenance, angiogenesis, immune escape of viruses and drug resistance against tumors. In this study, the truncated extracellular segment containing two immunoglobulin-like domains of human AXL (AXL-IG), which has been confirmed to bind growth arrest specific 6 (GAS6) by structural studies [1], was expressed in a prokaryotic expression system and then purified. Immunizing camelid with the purified AXL-IG as antigen could lead to the production of unique nanobodies composed of only variable domain of heavy chain of heavy-chain antibody (VHH), which are around 15 kD and stable. We screened out a nanobody A-LY01 specific binding to AXL-IG. We further determined the affinity of A-LY01 to AXL-IG and revealed that A-LY01 could specifically recognize full-length AXL on the surface of HEK 293T/17 cells. Our study provides appropriate support for the development of diagnostic reagents and antibody therapeutics targeting AXL.

Multifaceted roles of WRKY transcription factors in abiotic stress and flavonoid biosynthesis.

Increasing biotic and abiotic stresses are seriously impeding the growth and yield of staple crops and threatening global food security. As one of the largest classes of regulators in vascular plants, WRKY transcription factors play critical roles governing flavonoid biosynthesis during stress responses. By binding major W-box cis-elements (TGACCA/T) in target promoters, WRKYs modulate diverse signaling pathways. In this review, we optimized existing WRKY phylogenetic trees by incorporating additional plant species with WRKY proteins implicated in stress tolerance and flavonoid regulation. Based on the improved frameworks and documented results, we aim to deduce unifying themes of distinct WRKY subfamilies governing specific stress responses and flavonoid metabolism. These analyses will generate experimentally testable hypotheses regarding the putative functions of uncharacterized WRKY homologs in tuning flavonoid accumulation to enhance stress resilience.

Tissue Characteristics of Endometrial Carcinoma Analyzed by Quantitative Synthetic MRI and Diffusion-Weighted Imaging.

BACKGROUND: This study investigates the association of T1, T2, proton density (PD) and the apparent diffusion coefficient (ADC) with histopathologic features of endometrial carcinoma (EC). METHODS: One hundred and nine EC patients were prospectively enrolled from August 2019 to December 2020. Synthetic magnetic resonance imaging (MRI) was acquired through one acquisition, in addition to diffusion-weighted imaging (DWI) and other conventional sequences using 1.5T MRI. T1, T2, PD derived from synthetic MRI and ADC derived from DWI were compared among different histopathologic features, namely the depth of myometrial invasion (MI), tumor grade, cervical stromal invasion (CSI) and lymphovascular invasion (LVSI) of EC by the Mann-Whitney U test. Classification models based on the significant MRI metrics were constructed with their respective receiver operating characteristic (ROC) curves, and their micro-averaged ROC was used to evaluate the overall performance of these significant MRI metrics in determining aggressive histopathologic features of EC. RESULTS: EC with MI had significantly lower T2, PD and ADC than those without MI (p = 0.007, 0.006 and 0.043, respectively). Grade 2-3 EC and EC with LVSI had significantly lower ADC than grade 1 EC and EC without LVSI, respectively (p = 0.005, p = 0.020). There were no differences in the MRI metrics in EC with or without CSI. Micro-averaged ROC of the three models had an area under the curve of 0.83. CONCLUSIONS: Synthetic MRI provided quantitative metrics to characterize EC with one single acquisition. Low T2, PD and ADC were associated with aggressive histopathologic features of EC, offering excellent performance in determining aggressive histopathologic features of EC.

Privileged Scaffolds Targeting Bromodomain-containing Protein 4.

In recent years, bromodomain-containing protein 4 (BRD4), a member of the bromodomain and extra terminal domain (BET) family, has been one of the most widely studied targets. BRD4 is a transcriptional regulation factor, which regulates cell transcription, marks mammalian biological mitosis, regulates cell cycle, and plays an important role in the biological process of cancer occurrence and development. It has been demonstrated that the imbalance or dysfunction of BRD4 expression leads to various types of cancers, including testicular gene nuclear protein melanoma, acute myeloid leukemia, colon cancer, breast cancer, liver cancer, and midline cancer. Therefore, inhibition of BRD4 has become a valuable approach in the treatment of these cancers. To date, there are numerous BRD4 inhibitors in preclinical development, some of which have entered human clinical trials. In this review, current progress in the development of privileged scaffolds designed as BRD4 inhibitors will be discussed by focusing on structure-activity relationship, selectivity, and mechanisms of action.

Repeatability of MR fingerprinting in normal cervix and utility in cervical carcinoma.

BACKGROUND: Magnetic resonance fingerprinting (MRF) is a fast-imaging acquisition technique that generates quantitative and co-registered parametric maps. The aim of this feasibility study was to evaluate the agreement between MRF and phantom reference values, scan-rescan repeatability of MRF in normal cervix, and its ability to distinguish cervical carcinoma (CC) from normal cervical tissues. METHODS: An International Society of Magnetic Resonance in Medicine/National Institute of Standards and Technology (ISMRM/NIST) phantom was scanned using MRF 15 times over 65 days. Agreement between MRF and phantom reference T1 and T2 values was assessed by linear regression. Healthy volunteers and patients with suspected CC were prospectively recruited. MRF was repeated twice for healthy volunteers (MRF1 and MRF2). Volumes of interest of normal cervical tissues and CC were delineated on T1 and T2 maps. MRF scan-rescan repeatability was evaluated by Bland-Altman plots, within-subject coefficients of variation (wCV), and intraclass correlation coefficients (ICC). T1 and T2 values were compared between CC and normal cervical tissues using Mann-Whitney U test. Receiver operating characteristic (ROC) analysis was performed to evaluate diagnostic efficiency. RESULTS: Strong correlations were observed between MRF and phantom (R2=0.999 for T1, 0.981 for T2). Twelve healthy volunteers (28.7±5.1 years) and 28 patients with CC (54.6±15.2 years) were recruited for the in-vivo experiments. Repeatability of MRF parameters were wCV <3% for T1, <5% for T2 and ICC ≥0.92 for T1, ≥0.94 for T2. T1 value of CC (1,529±112 ms) was higher than normal mucosa [MRF1: 1,430±129 ms, MRF2: 1,440±130 ms; P=0.031, area under the curve (AUC) ≥0.717] and normal stroma (MRF1: 1,258±101 ms, MRF2: 1,276±105 ms; P<0.001, AUC ≥0.946). T2 value of CC (69±9 ms) was lower than normal mucosa (MRF1: 88±16 ms, MRF2: 87±13 ms; P<0.001, AUC ≥0.854), but was not different from normal stroma (P=0.919). CONCLUSIONS: Excellent agreement was observed between MRF and phantom reference values. MRF exhibited excellent scan-rescan repeatability in normal cervix with potential value in differentiating CC from normal cervical tissues.

CT texture analysis in histological classification of epithelial ovarian carcinoma.

OBJECTIVES: The study aimed to compare the ability of morphological and texture features derived from contrast-enhanced CT in histological subtyping of epithelial ovarian carcinoma (EOC). METHODS: Consecutive 205 patients with newly diagnosed EOC who underwent contrast-enhanced CT were included and dichotomised into high-grade serous carcinoma (HGSC) and non-HGSC. Clinical information including age and cancer antigen 125 (CA-125) was documented. The pre-treatment images were analysed using commercial software, TexRAD, by two independent radiologists. Eight qualitative CT morphological features were evaluated, and 36 CT texture features at 6 spatial scale factors (SSFs) were extracted per patient. Features' reduction was based on kappa score, intra-class correlation coefficient (ICC), univariate ROC analysis and Pearson's correlation test. Texture features with ICC ≥ 0.8 were compared by histological subtypes. Patients were randomly divided into training and testing sets by 8:2. Two random forest classifiers were determined and compared: model 1 incorporating selected morphological and clinical features and model 2 incorporating selected texture and clinical features. RESULTS: HGSC showed specifically higher texture features than non-HGSC (p < 0.05). Both models performed highly in predicting histological subtypes of EOC (model 1: AUC 0.891 and model 2: AUC 0.937), and no statistical significance was found between the two models (p = 0.464). CONCLUSION: CT texture analysis provides objective and quantitative metrics on tumour characteristics with HGSC demonstrating specifically high texture features. The model incorporating texture analysis could classify histology subtypes of EOC with high accuracy and performed as well as morphological features. KEY POINTS: • A number of CT morphological and texture features showed good inter- and intra-observer agreements. • High-grade serous ovarian carcinoma showed specifically higher CT texture features than non-high-grade serous ovarian carcinoma. • CT texture analysis could differentiate histological subtypes of epithelial ovarian carcinoma with high accuracy.

Technical Note: Machine learning approaches for range and dose verification in proton therapy using proton-induced positron emitters.

PURPOSE/OBJECTIVE(S): Online proton range/dose verification based on measurements of proton-induced positron emitters is a promising strategy for quality assurance in proton therapy. Because of the nonlinear correlation between the dose distribution and the activity distribution of positron emitters in addition to the presence of noise, machine learning approaches were proposed to establish their relationship. MATERIALS/METHODS: Simulations were carried out with a spot-scanning proton system using GATE-8.0 and Geant4-10.3 toolkit with a computed tomography (CT)-based patient phantom. The one-dimensional (1D) distributions of positron emitters and radiation dose were obtained. A feedforward neural network classification model comprising two hidden layers, was developed to estimate whether the range is within a preset threshold. A recurrent neural network (RNN) regression model comprising three layers and ten neurons in each hidden layer was developed to estimate dose distribution. The performance was quantitatively studied in terms of mean squared error (MSE) and mean absolute error (MAE) under different signal-to-noise ratio (SNR) values. RESULTS: The feasibility of proton range and dose verification using the proposed neural network framework was demonstrated. The feedforward NN model achieves high classification accuracy close to 100% for individual classes without bias. The RNN model is able to accurately predict the 1D dose distribution for different energies and irradiation positions. When the SNR of the input activity profiles is above 4, the framework is able to predict with an MAE of ~0.60 mm and an MSE of ~0.066. Moreover, the model demonstrates a good capability of generalization. CONCLUSIONS: The RNN model is found to be effective in identifying the relationship between the distributions of dose and positron emitters. The machine learning-based framework and RNN models may be a useful tool to allow for accurate online range and dose verification based on proton-induced positron emitters.