HALNet: Partial Point Cloud Registration Based on Hybrid Attention and Deep Local Features.

Point cloud registration is an important task in computer vision and robotics which is widely used in 3D reconstruction, target recognition, and other fields. At present, many registration methods based on deep learning have better registration accuracy in complete point cloud registration, but partial registration accuracy is poor. Therefore, a partial point cloud registration network, HALNet, is proposed. Firstly, a feature extraction network consisting mainly of adaptive graph convolution (AGConv), two-dimensional convolution, and convolution block attention (CBAM) is used to learn the features of the initial point cloud. Then the overlapping estimation is used to remove the non-overlapping points of the two point clouds, and the hybrid attention mechanism composed of self-attention and cross-attention is used to fuse the geometric information of the two point clouds. Finally, the rigid transformation is obtained by using the fully connected layer. Five methods with excellent registration performance were selected for comparison. Compared with SCANet, which has the best registration performance among the five methods, the RMSE(R) and MAE(R) of HALNet are reduced by 10.67% and 12.05%. In addition, the results of the ablation experiment verify that the hybrid attention mechanism and fully connected layer are conducive to improving registration performance.

Prognostic impact of deep learning-based quantification in clinical stage 0-I lung adenocarcinoma.

OBJECTIVES: To evaluate the performance of automatic deep learning (DL) algorithm for size, mass, and volume measurements in predicting prognosis of lung adenocarcinoma (LUAD) and compared with manual measurements. METHODS: A total of 542 patients with clinical stage 0-I peripheral LUAD and with preoperative CT data of 1-mm slice thickness were included. Maximal solid size on axial image (MSSA) was evaluated by two chest radiologists. MSSA, volume of solid component (SV), and mass of solid component (SM) were evaluated by DL. Consolidation-to-tumor ratios (CTRs) were calculated. For ground glass nodules (GGNs), solid parts were extracted with different density level thresholds. The prognosis prediction efficacy of DL was compared with that of manual measurements. Multivariate Cox proportional hazards model was used to find independent risk factors. RESULTS: The prognosis prediction efficacy of T-staging (TS) measured by radiologists was inferior to that of DL. For GGNs, MSSA-based CTR measured by radiologists (RMSSA%) could not stratify RFS and OS risk, whereas measured by DL using 0HU (2D-AIMSSA0HU%) could by using different cutoffs. SM and SV measured by DL using 0 HU (AISM0HU% and AISV0HU%) could effectively stratify the survival risk regardless of different cutoffs and were superior to 2D-AIMSSA0HU%. AISM0HU% and AISV0HU% were independent risk factors. CONCLUSION: DL algorithm can replace human for more accurate T-staging of LUAD. For GGNs, 2D-AIMSSA0HU% could predict prognosis rather than RMSSA%. The prediction efficacy of AISM0HU% and AISV0HU% was more accurate than of 2D-AIMSSA0HU% and both were independent risk factors. CLINICAL RELEVANCE STATEMENT: Deep learning algorithm could replace human for size measurements and could better stratify prognosis than manual measurements in patients with lung adenocarcinoma. KEY POINTS: • Deep learning (DL) algorithm could replace human for size measurements and could better stratify prognosis than manual measurements in patients with lung adenocarcinoma (LUAD). • For GGNs, maximal solid size on axial image (MSSA)-based consolidation-to-tumor ratio (CTR) measured by DL using 0 HU could stratify survival risk than that measured by radiologists. • The prediction efficacy of mass- and volume-based CTRs measured by DL using 0 HU was more accurate than of MSSA-based CTR and both were independent risk factors.

Constructing Co-S interface chemical bonds over Co@NC/ZnIn2S4 for an efficient solar-driven photocatalytic H2 evolution.

Developing novel photocatalysts with an intimate interface and sufficient contact is significant for the separation and migration of photogenerated carriers. In this work, a novel Co@NC/ZnIn2S4 heterojunction with a strong Co-S chemical bond was formed at the interface between Co@NC and ZnIn2S4, which accelerated charge separation. Meanwhile, the recombination of the electron-hole pairs was further restricted by the Co@NC/ZnIn2S4 Schottky junction. The Co@NC (5 wt%)/ZnIn2S4 composite exhibited an H2 evolution rate of 33.3 µmol h-1, which is 6.1 times higher than that of the pristine ZnIn2S4, and Co@NC/ZnIn2S4 showed excellent stability in the photocatalytic water splitting reaction. Its apparent quantum yield reached 38% at 420 nm. Furthermore, the Kelvin probe test results showed that the interfacial electric field formed as the driving force for interface charge transfer was oriented from Co@NC to ZnIn2S4. In addition, the Co-S bond as a high-speed channel facilitated the interfacial electron transfer. This work reveals that in situ formed chemical bonds will pave the way for designing high-efficiency heterojunction photocatalysts.

Plasmon Au/K-doped defective graphitic carbon nitride for enhanced hydrogen production.

Knowledge of the photocatalytic H2-evolution mechanism is of critical importance for water splitting, and for designing active catalysts for a sustainable energy supply. In this study, we prepared plasmon Au-modified K-doped defective graphitic carbon nitride (Au/KCNx) and then applied it in photocatalytic hydrogen-production tests. The hydrogen-production rate of the Au/KCNx photocatalyst (8.85 mmol g-1 h-1) was found to be almost 104 times higher than that of Au/g-C3N4 (0.085 mmol g-1 h-1), together with an apparent quantum efficiency of 12.8% at 420 nm. It could significantly improve the photocatalytic activities of the Au/KCNx sample, which was attributed to the synergistic effects of the plasmon effect, potassium doping, and nitrogen vacancy. In addition, the Au/KCNx photocatalyst had a large surface area, which was beneficial for photogenerated carrier separation and transfer. The novel strategy proposed here is a potential new method for the development of graphitic carbon nitride photocatalysts with obviously enhanced activities.

Amino-functionalized MIL-125(Ti) for photodenitrification of pyridine in fuels via coordination activation by unsaturated Ti4+ centers.

Due to their explicit structure, metal-organic frameworks (MOFs) have been supposed to be credible platforms to research the micro-mechanism of heterogeneous photocatalysis. In this study, amino-functionalized MOFs (MIL-125(Ti)-NH2 (denoted as MTi), UiO-66(Zr)-NH2 (denoted as UZr) and MIL-68(In)-NH2 (denoted as MIn)) with three different metal centers were synthesized and applied for the denitrification of simulated fuels under visible light irradiation, during which pyridine was used as a typical nitrogen-containing compound. The results showed that MTi had the best activity among the above three MOFs, and the denitrogenation rate increased to 80% after 4 h of visible light irradiation. On the grounds of the theoretical calculation of pyridine adsorption and actual activity experiments, it can be presumed that the unsaturated Ti4+ metal centers should be the key active sites. Meanwhile, the XPS and in situ infrared results verified that the coordinatively unsaturated Ti4+ sites facilitate the activation of pyridine molecules through the surface -N⋯Ti- coordination species. The coordination-photocatalysis synergism promotes the efficiency of photocatalytic performance and the corresponding mechanism is proposed.

Genome-Wide Analysis and Expression Profiles of the VOZ Gene Family in Quinoa (Chenopodium quinoa).

Vascular plant one zinc-finger (VOZ) proteins are a plant-specific transcription factor family and play important roles in plant development and stress responses. However, little is known about the VOZ genes in quinoa. In the present study, a genome-wide investigation of the VOZ gene family in quinoa was performed, including gene structures, conserved motifs, phylogeny, and expression profiles. A total of four quinoa VOZ genes distributed on three chromosomes were identified. Based on phylogenetic analysis, CqVOZ1 and CqVOZ3 belong to subfamily II, and CqVOZ2 and CqVOZ4 belong to subfamily III. Furthermore, the VOZ transcription factors of quinoa and sugarbeet were more closely related than other species. Except for CqVOZ3, all the other three CqVOZs have four exons and four introns. Analysis of conserved motifs indicated that each CqVOZ member contained seven common motifs. Multiple sequence alignment showed that the CqVOZ genes were highly conserved with consensus sequences, which might be plausibly significant for the preservation of structural integrity of the family proteins. Tissue expression analysis revealed that four CqVOZ genes were highly expressed in inflorescence and relatively low in leaves and stems, suggesting that these genes had obvious tissue expression specificity. The expression profiles of the quinoa CqVOZs under various abiotic stresses demonstrated that these genes were differentially induced by cold stress, salt stress, and drought stress. The transcript level of CqVOZ1 and CqVOZ4 were down-regulated by salt stress and drought stress, while CqVOZ2 and CqVOZ3 were up-regulated by cold, salt, and drought stress, which could be used as abiotic stress resistance candidate genes. This study systematically identifies the CqVOZ genes at the genome-wide level, contributing to a better understanding of the quinoa VOZ transcription factor family and laying a foundation for further exploring the molecular mechanism of development and stress resistance of quinoa.

Characterization of spleen and lymph node cell types via CITE-seq and machine learning methods.

The spleen and lymph nodes are important functional organs for human immune system. The identification of cell types for spleen and lymph nodes is helpful for understanding the mechanism of immune system. However, the cell types of spleen and lymph are highly diverse in the human body. Therefore, in this study, we employed a series of machine learning algorithms to computationally analyze the cell types of spleen and lymph based on single-cell CITE-seq sequencing data. A total of 28,211 cell data (training vs. test = 14,435 vs. 13,776) involving 24 cell types were collected for this study. For the training dataset, it was analyzed by Boruta and minimum redundancy maximum relevance (mRMR) one by one, resulting in an mRMR feature list. This list was fed into the incremental feature selection (IFS) method, incorporating four classification algorithms (deep forest, random forest, K-nearest neighbor, and decision tree). Some essential features were discovered and the deep forest with its optimal features achieved the best performance. A group of related proteins (CD4, TCRb, CD103, CD43, and CD23) and genes (Nkg7 and Thy1) contributing to the classification of spleen and lymph nodes cell types were analyzed. Furthermore, the classification rules yielded by decision tree were also provided and analyzed. Above findings may provide helpful information for deepening our understanding on the diversity of cell types.

Identification of cortical interneuron cell markers in mouse embryos based on machine learning analysis of single-cell transcriptomics.

Mammalian cortical interneurons (CINs) could be classified into more than two dozen cell types that possess diverse electrophysiological and molecular characteristics, and participate in various essential biological processes in the human neural system. However, the mechanism to generate diversity in CINs remains controversial. This study aims to predict CIN diversity in mouse embryo by using single-cell transcriptomics and the machine learning methods. Data of 2,669 single-cell transcriptome sequencing results are employed. The 2,669 cells are classified into three categories, caudal ganglionic eminence (CGE) cells, dorsal medial ganglionic eminence (dMGE) cells, and ventral medial ganglionic eminence (vMGE) cells, corresponding to the three regions in the mouse subpallium where the cells are collected. Such transcriptomic profiles were first analyzed by the minimum redundancy and maximum relevance method. A feature list was obtained, which was further fed into the incremental feature selection, incorporating two classification algorithms (random forest and repeated incremental pruning to produce error reduction), to extract key genes and construct powerful classifiers and classification rules. The optimal classifier could achieve an MCC of 0.725, and category-specified prediction accuracies of 0.958, 0.760, and 0.737 for the CGE, dMGE, and vMGE cells, respectively. The related genes and rules may provide helpful information for deepening the understanding of CIN diversity.

Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases.

Backgrounds: A significant proportion of breast cancer patients showed receptor discordance between primary cancers and breast cancer brain metastases (BCBM), which significantly affected therapeutic decision-making. But it was not always feasible to obtain BCBM tissues. The aim of the present study was to analyze the receptor status of primary breast cancer and matched brain metastases and establish radiomic signatures to predict the receptor status of BCBM. Methods: The receptor status of 80 matched primary breast cancers and resected brain metastases were retrospectively analyzed. Radiomic features were extracted using preoperative brain MRI (contrast-enhanced T1-weighted imaging, T2-weighted imaging, T2 fluid-attenuated inversion recovery, and combinations of these sequences) collected from 68 patients (45 and 23 for training and test sets, respectively) with BCBM excision. Using least absolute shrinkage selection operator and logistic regression model, the machine learning-based radiomic signatures were constructed to predict the estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status of BCBM. Results: Discordance between the primary cancer and BCBM was found in 51.3% of patients, with 27.5%, 27.5%, and 5.0% discordance for ER, PR, and HER2, respectively. Loss of receptor expression was more common (33.8%) than gain (18.8%). The radiomic signatures built using combination sequences had the best performance in the training and test sets. The combination model yielded AUCs of 0.89, 0.88, and 0.87, classification sensitivities of 71.4%, 90%, and 87.5%, specificities of 81.2%, 76.9%, and 71.4%, and accuracies of 78.3%, 82.6%, and 82.6% for ER, PR, and HER2, respectively, in the test set. Conclusions: Receptor conversion in BCBM was common, and radiomic signatures show potential for noninvasively predicting BCBM receptor status.

Identification of Cell Markers and Their Expression Patterns in Skin Based on Single-Cell RNA-Sequencing Profiles.

Atopic dermatitis and psoriasis are members of a family of inflammatory skin disorders. Cellular immune responses in skin tissues contribute to the development of these diseases. However, their underlying immune mechanisms remain to be fully elucidated. We developed a computational pipeline for analyzing the single-cell RNA-sequencing profiles of the Human Cell Atlas skin dataset to investigate the pathological mechanisms of skin diseases. First, we applied the maximum relevance criterion and the Boruta feature selection method to exclude irrelevant gene features from the single-cell gene expression profiles of inflammatory skin disease samples and healthy controls. The retained gene features were ranked by using the Monte Carlo feature selection method on the basis of their importance, and a feature list was compiled. This list was then introduced into the incremental feature selection method that combined the decision tree and random forest algorithms to extract important cell markers and thus build excellent classifiers and decision rules. These cell markers and their expression patterns have been analyzed and validated in recent studies and are potential therapeutic and diagnostic targets for skin diseases because their expression affects the pathogenesis of inflammatory skin diseases.

Exploring the Genomic Patterns in Human and Mouse Cerebellums Via Single-Cell Sequencing and Machine Learning Method.

In mammals, the cerebellum plays an important role in movement control. Cellular research reveals that the cerebellum involves a variety of sub-cell types, including Golgi, granule, interneuron, and unipolar brush cells. The functional characteristics of cerebellar cells exhibit considerable differences among diverse mammalian species, reflecting a potential development and evolution of nervous system. In this study, we aimed to recognize the transcriptional differences between human and mouse cerebellum in four cerebellar sub-cell types by using single-cell sequencing data and machine learning methods. A total of 321,387 single-cell sequencing data were used. The 321,387 cells included 4 cell types, i.e., Golgi (5,048, 1.57%), granule (250,307, 77.88%), interneuron (60,526, 18.83%), and unipolar brush (5,506, 1.72%) cells. Our results showed that by using gene expression profiles as features, the optimal classification model could achieve very high even perfect performance for Golgi, granule, interneuron, and unipolar brush cells, respectively, suggesting a remarkable difference between the genomic profiles of human and mouse. Furthermore, a group of related genes and rules contributing to the classification was identified, which might provide helpful information for deepening the understanding of cerebellar cell heterogeneity and evolution.

Predicting Heart Cell Types by Using Transcriptome Profiles and a Machine Learning Method.

The heart is an essential organ in the human body. It contains various types of cells, such as cardiomyocytes, mesothelial cells, endothelial cells, and fibroblasts. The interactions between these cells determine the vital functions of the heart. Therefore, identifying the different cell types and revealing the expression rules in these cell types are crucial. In this study, multiple machine learning methods were used to analyze the heart single-cell profiles with 11 different heart cell types. The single-cell profiles were first analyzed via light gradient boosting machine method to evaluate the importance of gene features on the profiling dataset, and a ranking feature list was produced. This feature list was then brought into the incremental feature selection method to identify the best features and build the optimal classifiers. The results suggested that the best decision tree (DT) and random forest classification models achieved the highest weighted F1 scores of 0.957 and 0.981, respectively. The selected features, such as NPPA, LAMA2, DLC1, and the classification rules extracted from the optimal DT classifier played a crucial role in cardiac structure and function in recent research and enrichment analysis. In particular, some lncRNAs (LINC02019, NEAT1) were found to be quite important for the recognition of different cardiac cell types. In summary, these findings provide a solid academic foundation for the development of molecular diagnostics and biomarker discovery for cardiac diseases.

Evaluating the fermentation quality and bacterial community of high-moisture whole-plant quinoa silage ensiled with different additives.

AIM: To explore the potential of whole-plant quinoa (WPQ) as a high-protein source for livestock feed, this study evaluated the effects of additives on the fermentation quality and bacterial community of high-moisture WPQ silage. METHODS AND RESULTS: High-moisture WPQ was ensiled with one of the following additives: untreated control (C), fibrolytic enzyme (E), molasses (M), LAB inoculant (L), a combination of fibrolytic enzyme and LAB inoculant (EL) and a combination of molasses and LAB inoculant (ML). The fermentation quality and bacterial community after 60 days of ensiling were analysed. Naturally fermented WPQ exhibited acetic acid-type fermentation dominated by enterobacteria, with low lactic acid content (37.0 g/kg DM), and high pH value (5.65), acetic acid (70.8 g/kg DM) and NH3 -N production (229 g/kg TN). Adding molasses alone or combined with LAB inoculant shifted the fermentation pattern towards increased intensity of lactic acid fermentation, lowering the pH value (<4.56), contents of acetic acid (<46.7 g/kg DM) and NH3 -N (<140 g/kg TN) and total abundance of enterobacteria (<16.0%), and increasing the lactic acid content (>60.5 g/kg DM), lactic/acetic acid ratio (>1.40) and the relative abundance of Lactobacillus (>83.0%). CONCLUSIONS: The results suggested that the lack of fermentable sugar could be the main factor of restricting extensive lactic acid fermentation in WPQ silage. Supplementing fermentable sugar or co-ensiling with materials with high WSC content and low moisture content are expected to be beneficial strategies for producing high-quality WPQ silage. SIGNIFICANCE AND IMPACT OF STUDY: High biomass production and high protein content make WPQ to be an ideal forage source for livestock feed. Results of this study revealed the restricting factor for extensive lactic acid fermentation in WPQ silage, which could be helpful in producing high-quality WPQ silage.

Development and validation of a deep-learning model for detecting brain metastases on 3D post-contrast MRI: a multi-center multi-reader evaluation study.

BACKGROUND: Accurate detection is essential for brain metastasis (BM) management, but manual identification is laborious. This study developed, validated, and evaluated a BM detection (BMD) system. METHODS: Five hundred seventy-three consecutive patients (10 448 lesions) with newly diagnosed BMs and 377 patients without BMs were retrospectively enrolled to develop a multi-scale cascaded convolutional network using 3D-enhanced T1-weighted MR images. BMD was validated using a prospective validation set comprising an internal set (46 patients with 349 lesions; 44 patients without BMs) and three external sets (102 patients with 717 lesions; 108 patients without BMs). The lesion-based detection sensitivity and the number of false positives (FPs) per patient were analyzed. The detection sensitivity and reading time of three trainees and three experienced radiologists from three hospitals were evaluated using the validation set. RESULTS: The detection sensitivity and FPs were 95.8% and 0.39 in the test set, 96.0% and 0.27 in the internal validation set, and ranged from 88.9% to 95.5% and 0.29 to 0.66 in the external sets. The BMD system achieved higher detection sensitivity (93.2% [95% CI, 91.6-94.7%]) than all radiologists without BMD (ranging from 68.5% [95% CI, 65.7-71.3%] to 80.4% [95% CI, 78.0-82.8%], all P < .001). Radiologist detection sensitivity improved with BMD, reaching 92.7% to 95.0%. The mean reading time was reduced by 47% for trainees and 32% for experienced radiologists assisted by BMD relative to that without BMD. CONCLUSIONS: BMD enables accurate BM detection. Reading with BMD improves radiologists' detection sensitivity and reduces their reading times.

Surface Coordination of Pd/ZnIn2S4 toward Enhanced Photocatalytic Activity for Pyridine Denitrification.

New surface coordination photocatalytic systems that are inspired by natural photosynthesis have significant potential to boost fuel denitrification. Despite this, the direct synthesis of efficient surface coordination photocatalysts remains a major challenge. Herein, it is verified that a coordination photocatalyst can be constructed by coupling Pd and CTAB-modified ZnIn2S4 semiconductors. The optimized Pd/ZnIn2S4 showed a superior degradation rate of 81% for fuel denitrification within 240 min, which was 2.25 times higher than that of ZnIn2S4. From the in situ FTIR and XPS spectra of 1% Pd/ZnIn2S4 before and after pyridine adsorption, we find that pyridine can be selectively adsorbed and form Zn⋅⋅⋅C-N or In⋅⋅⋅C-N on the surface of Pd/ZnIn2S4. Meanwhile, the superior electrical conductivity of Pd can be combined with ZnIn2S4 to promote photocatalytic denitrification. This work also explains the surface/interface coordination effect of metal/nanosheets at the molecular level, playing an important role in photocatalytic fuel denitrification.

Correction to: A quantitative imaging biomarker for predicting disease-free-survival-associated histologic subgroups in lung adenocarcinoma.

The original version of this article, published on 21 February 2020, unfortunately contained a mistake.

A quantitative imaging biomarker for predicting disease-free-survival-associated histologic subgroups in lung adenocarcinoma.

OBJECTIVES: Classification of histologic subgroups has significant prognostic value for lung adenocarcinoma patients who undergo surgical resection. However, clinical histopathology assessment is generally performed on only a small portion of the overall tumor from biopsy or surgery. Our objective is to identify a noninvasive quantitative imaging biomarker (QIB) for the classification of histologic subgroups in lung adenocarcinoma patients. METHODS: We retrospectively collected and reviewed 1313 CT scans of patients with resected lung adenocarcinomas from two geographically distant institutions who were seen between January 2014 and October 2017. Three study cohorts, the training, internal validation, and external validation cohorts, were created, within which lung adenocarcinomas were divided into two disease-free-survival (DFS)-associated histologic subgroups, the mid/poor and good DFS groups. A comprehensive machine learning- and deep learning-based analytical system was adopted to identify reproducible QIBs and help to understand QIBs' significance. RESULTS: Intensity-Skewness, a QIB quantifying tumor density distribution, was identified as the optimal biomarker for predicting histologic subgroups. Intensity-Skewness achieved high AUCs (95% CI) of 0.849(0.813,0.881), 0.820(0.781,0.856) and 0.863(0.827,0.895) on the training, internal validation, and external validation cohorts, respectively. A criterion of Intensity-Skewness ≤ 1.5, which indicated high tumor density, showed high specificity of 96% (sensitivity 46%) and 99% (sensitivity 53%) on predicting the mid/poor DFS group in the training and external validation cohorts, respectively. CONCLUSIONS: A QIB derived from routinely acquired CT was able to predict lung adenocarcinoma histologic subgroups, providing a noninvasive method that could potentially benefit personalized treatment decision-making for lung cancer patients. KEY POINTS: • A noninvasive imaging biomarker, Intensity-Skewness, which described the distortion of pixel-intensity distribution within lesions on CT images, was identified as a biomarker to predict disease-free-survival-associated histologic subgroups in lung adenocarcinoma. • An Intensity-Skewness of ≤ 1.5 has high specificity in predicting the mid/poor disease-free survival histologic patient group in both the training cohort and the external validation cohort. • The Intensity-Skewness is a feature that can be automatically computed with high reproducibility and robustness.

Using a single abdominal computed tomography image to differentiate five contrast-enhancement phases: A machine-learning algorithm for radiomics-based precision medicine.

PURPOSE: The clinical adoption of quantitative imaging biomarkers (radiomics) has established the need for high quality contrast-enhancement in medical images. We aimed to develop a machine-learning algorithm for Quality Control of Contrast-Enhancement on CT-scan (CECT-QC). METHOD: Multicenter data from four independent cohorts [A, B, C, D] of patients with measurable liver lesions were analyzed retrospectively (patients:time-points; 503:3397): [A] dynamic CTs from primary liver cancer (60:2359); [B] triphasic CTs from primary liver cancer (31:93); [C] triphasic CTs from hepatocellular carcinoma (121:363); [D] portal venous phase CTs of liver metastasis from colorectal cancer (291:582). Patients from cohort A were randomized to training-set (48:1884) and test-set (12:475). A random forest classifier was trained and tested to identify five contrast-enhancement phases. The input was the mean intensity of the abdominal aorta and the portal vein measured on a single abdominal CT scan image at a single time-point. The output to be predicted was: non-contrast [NCP], early-arterial [E-AP], optimal-arterial [O-AP], optimal-portal [O-PVP], and late-portal [L-PVP]. Clinical utility was assessed in cohorts B, C, and D. RESULTS: The CECT-QC algorithm showed performances of 98 %, 90 %, and 84 % for predicting NCP, O-AP, and O-PVP, respectively. O-PVP was reached in half of patients and was associated with a peak in liver malignancy density. Contrast-enhancement quality significantly influenced radiomics features deciphering the phenotype of liver neoplasms. CONCLUSIONS: A single CT-image can be used to differentiate five contrast-enhancement phases for radiomics-based precision medicine in the most common liver neoplasms occurring in patients with or without liver cirrhosis.

MRI-detected residual retropharyngeal lymph node after intensity-modulated radiotherapy in nasopharyngeal carcinoma: Prognostic value and a nomogram for the pretherapy prediction of it.

BACKGROUND AND PURPOSE: To evaluate the prognostic value of MRI-detected residual retropharyngeal lymph node (RRLN) at three months after intensity-modulated radiotherapy (IMRT) in patients with nasopharyngeal carcinoma (NPC) and second, to establish a nomogram for the pretherapy prediction of RRLN. MATERIALS AND METHODS: We included 1103 patients with NPC from two hospitals (Sun Yat-Sen University Cancer Center [SYSUCC, n = 901] and Dongguan People's Hospital [DGPH, n = 202]). We evaluated the prognostic value of RRLN using Cox regression model in SYSUCC cohort. We developed a nomogram for the pretherapy prediction of RRLN using logistic regression model in SYSUCC training cohort (n = 645). We assessed the performance of this nomogram in an internal validation cohort (SYSUCC validation cohort, n = 256) and an external independent cohort (DGPH validation cohort, n = 202). RESULTS: RRLN was an independent prognostic factor for OS (HR 2.08, 95% CI 1.32-3.29), DFS (HR 2.45, 95% CI 1.75-3.42), DMFS (HR 3.31, 95% CI 2.15-5.09), and LRRFS (HR 3.04, 95% CI 1.70-5.42). We developed a nomogram based on baseline Epstein-Barr virus DNA level and three RLN status-related features (including minimum axial diameter, extracapsular nodal spread, and laterality) that predicted an individual's risk of RRLN. Our nomogram showed good discrimination in the training cohort (C-index = 0.763). The favorable performance of this nomogram was confirmed in the internal and external validation cohorts. CONCLUSION: MRI-detected RRLN at three months after IMRT was an unfavorable prognostic factor for patients with NPC. We developed and validated an easy-to-use nomogram for the pretherapy prediction of RRLN.

Automated Identification of Optimal Portal Venous Phase Timing with Convolutional Neural Networks.

OBJECTIVES: To develop a deep learning-based algorithm to automatically identify optimal portal venous phase timing (PVP-timing) so that image analysis techniques can be accurately performed on post contrast studies. METHODS: 681 CT-scans (training: 479 CT-scans; validation: 202 CT-scans) from a multicenter clinical trial in patients with liver metastases from colorectal cancer were retrospectively analyzed for algorithm development and validation. An additional external validation was performed on a cohort of 228 CT-scans from gastroenteropancreatic neuroendocrine cancer patients. Image acquisition was performed according to each centers' standard CT protocol for single portal venous phase, portal venous acquisition. The reference gold standard for the classification of PVP-timing as either optimal or nonoptimal was based on experienced radiologists' consensus opinion. The algorithm performed automated localization (on axial slices) of the portal vein and aorta upon which a novel dual input Convolutional Neural Network calculated a probability of the optimal PVP-timing. RESULTS: The algorithm automatically computed a PVP-timing score in 3 seconds and reached area under the curve of 0.837 (95% CI: 0.765, 0.890) in validation set and 0.844 (95% CI: 0.786, 0.889) in external validation set. CONCLUSION: A fully automated, deep-learning derived PVP-timing algorithm was developed to classify scans' contrast-enhancement timing and identify scans with optimal PVP-timing. The rapid identification of such scans will aid in the analysis of quantitative (radiomics) features used to characterize tumors and changes in enhancement with treatment in a multitude of settings including quantitative response criteria such as Choi and MASS which rely on reproducible measurement of enhancement.