Large-scale pancreatic cancer detection via non-contrast CT and deep learning.

Pancreatic ductal adenocarcinoma (PDAC), the most deadly solid malignancy, is typically detected late and at an inoperable stage. Early or incidental detection is associated with prolonged survival, but screening asymptomatic individuals for PDAC using a single test remains unfeasible due to the low prevalence and potential harms of false positives. Non-contrast computed tomography (CT), routinely performed for clinical indications, offers the potential for large-scale screening, however, identification of PDAC using non-contrast CT has long been considered impossible. Here, we develop a deep learning approach, pancreatic cancer detection with artificial intelligence (PANDA), that can detect and classify pancreatic lesions with high accuracy via non-contrast CT. PANDA is trained on a dataset of 3,208 patients from a single center. PANDA achieves an area under the receiver operating characteristic curve (AUC) of 0.986-0.996 for lesion detection in a multicenter validation involving 6,239 patients across 10 centers, outperforms the mean radiologist performance by 34.1% in sensitivity and 6.3% in specificity for PDAC identification, and achieves a sensitivity of 92.9% and specificity of 99.9% for lesion detection in a real-world multi-scenario validation consisting of 20,530 consecutive patients. Notably, PANDA utilized with non-contrast CT shows non-inferiority to radiology reports (using contrast-enhanced CT) in the differentiation of common pancreatic lesion subtypes. PANDA could potentially serve as a new tool for large-scale pancreatic cancer screening.

Dynamic boundary-insensitive loss for magnetic resonance medical image segmentation.

PURPOSE: A deep learning method has achieved great success in MR medical image segmentation. One challenge in applying deep learning segmentation models to clinical practice is their poor generalization mainly due to limited labeled training samples, inter-site heterogeneity of different datasets, and ambiguous boundary definition, etc. The objective of this work is to develop a dynamic boundary-insensitive (DBI) loss to address this poor generalization caused by an uncertain boundary. METHODS: The DBI loss is designed to assign higher penalties to misclassified voxels farther from the boundaries in each training iteration to reduce the sensitivity of the segmentation model to the uncertain boundary. The weighting factor of the DBI loss can be adjusted adaptively without any manual setting and adjustment. Extensive experiments were conducted to verify the performance of our DBI loss and its variant, DiceDBI, on four heterogeneous prostate MRI datasets for prostate zonal segmentation and whole prostate segmentation. RESULTS: Experimental results show that our DBI loss, when combined with Dice loss, outperforms all competing loss functions in dice similarity coefficient (DSC) and improves the segmentation performance across all datasets consistently, especially on unseen datasets and when segmenting small or narrow targets. CONCLUSIONS: The proposed DiceDBI loss will be valuable for enhancement of the generalization performance of the segmentation model.

Genotyping of Enterocytozoon bieneusi among captive long-tailed macaques (Macaca fascicularis) in Hainan Province: High genetic diversity and zoonotic potential.

Enterocytozoon bieneusi is a potentially important zoonotic pathogen. However, there is no information on E. bieneusi infection of captive long-tailed macaques (Macaca fascicularis) in Hainan Province, China. Here 193 fecal specimens of M. fascicularis were collected from a breeding base in Hainan Province, China, housing non-human primates for experimental use. E. bieneusi was identified and genotyped by nested PCR analysis of the internal transcribed spacer (ITS) region of the rRNA gene. A total of 59 (30.6%) specimens were PCR-positive for E. bieneusi and 16 ITS genotypes were identified including nine known genotypes: Type IV (n = 19), D (n = 11), CM1 (n = 8), PigEBITS7 (n = 4), Pongo2 (n = 4), Peru8 (n = 3), Peru11 (n = 1), WL21 (n = 1) and CM2 (n = 1) and seven novel genotypes HNM-I to HNM-VII (one each). Importantly, genotypes D, Type IV, Peru8, PigEBITS7, and Peru11, which were the predominant (38/59, 64.4%) genotypes identified among captive M. fascicularis in this study, are also well-known human-pathogenic genotypes. All the genotypes of E. bieneusi identified here, including the seven novel ones, belonged to zoonotic Group 1. This is the first report of the identification of E. bieneusi in M. fascicularis in Hainan Province, China. The finding that the numerous known human-pathogenic types and seven novel genotypes of E. bieneusi all belong to zoonotic Group 1 indicates the possibility of transmission of this important pathogenic parasite between M. fascicularis and humans.

Molecular prevalence and subtyping of Cryptosporidium hominis among captive long-tailed macaques (Macaca fascicularis) and rhesus macaques (Macaca mulatta) from Hainan Island, southern China.

BACKGROUND: Cryptosporidium is an important zoonotic parasite that is commonly found in non-human primates (NHPs). Consequently, there is the potential for transmission of this pathogen from NHPs to humans. However, molecular characterization of the isolates of Cryptosporidium from NHPs remains relatively poor. The aim of the present work was to (i) determine the prevalence; and (ii) perform a genetic characterization of the Cryptosporidium isolated from captive Macaca fascicularis and M. mulatta on Hainan Island in southern China. METHODS: A total of 223 fresh fecal samples were collected from captive M. fascicularis (n = 193) and M. mulatta (n = 30). The fecal specimens were examined for the presence of Cryptosporidium spp. by polymerase chain reaction (PCR) and sequencing of the partial small subunit (SSU) rRNA gene. The Cryptosporidium-positive specimens were subtyped by analyzing the 60-kDa glycoprotein (gp60) gene sequence. RESULTS: Cryptosporidium spp. were detected in 5.7% (11/193) of M. fascicularis. All of the 11 Cryptosporidium isolates were identified as C. hominis. Subtyping of nine of these isolates identified four unique gp60 subtypes of C. hominis. These included IaA20R3a (n = 1), IoA17a (n = 1), IoA17b (n = 1), and IiA17 (n = 6). Notably, subtypes IaA20R3a, IoA17a, and IoA17b were novel subtypes which have not been reported previously. CONCLUSIONS: To our knowledge, this is the first reported detection of Cryptosporidium in captive M. fascicularis from Hainan Island. The molecular characteristics and subtypes of the isolates here provide novel insights into the genotypic variation in C. hominis.

The clinical value of combination of immune checkpoint inhibitors in cancer patients: A meta-analysis of efficacy and safety.

The use of immune checkpoint inhibitors (ICIs) in combination therapy is an emerging trend in tumor immunology. However, the value of combination immunotherapy remains controversial, because of the toxic effects induced by combination. The added benefit of each additional drug has not been assessed against the added toxicity. We searched for clinical trials that evaluated ICI monotherapies and combination therapies in lung cancer and melanoma patients. The overall response rate (ORR), grade 3/4 treatment-related adverse event rate, overall survival (OS), and progression-free survival (PFS) were extracted from the most recently published studies to determine the relative risk (RR), hazard ratios (HRs), and 95% confidence intervals (CIs). Seven randomized controlled trials and one open-label study were identified (n = 3,097). Treatments included combinations of several ICIs, a combination of an ICI and dacarbazine, two combinations of an ICI, paclitaxel and carboplatin, and a combination of an ICI and gp100 vaccine. Higher ORR (RR: 1.51, 95% CI: 1.03-2.20, p = 0.034), OS (HR: 0.86, 95% CI: 0.78-0.95, p = 0.000), and PFS (HR: 0.93, 95% CI: 0.72-1.14, p = 0.000) values were observed in combination therapy than in monotherapy. In addition, the toxicity of combination ICI immunotherapy was higher (RR: 1.50, 95% CI: 1.03-2.19, p = 0.036) than that of monotherapy. This meta-analysis showed that the addition of nivolumab to ipilimumab better benefits PFS and ORR. Adding sargramostim was associated with better OS and safety. The efficacy and safety of a nivolumab-ipilimumab-sargramostim combination should be investigated further.

A self-adaptive distance regularized level set evolution method for optical disk segmentation.

The optic disc (OD) is one of the important anatomic structures on the retina, the changes of which shape and area may indicate disease processes, thus needs computerized quantification assistance. In this study, we proposed a self-adaptive distance regularized level set evolution method for OD segmentation without the periodically re-initializing steps in the level set function execution to a signed distance function during the evolution. In that framework, preprocessing of an image was performed using Fourier correlation coefficient filtering to obtain initial boundary as the beginning contour, then, an accurate boundary of the optic disc was obtained using the self-adaptive distance regularized level set evolution method. One hundred eye fundus color numerical images from public database were selected to validate our algorithm. Therefore, we believe that such automatic OD segmentation method could assist the ophthalmologist to segment OD more efficiently, which is of significance for future computer-aided early detection of glaucoma and retinopathy diseases.

[Spatiotemporal trends and the impact factors of acid rain in Anhui Province].

The observational data of acid rain at seven stations in Anhui province operated by China Meteorological Administration (CMA), as well as the coal consumptions in Anhui and some surrounding provinces along with satellite measured tropospheric NO2 columns, were used to analyze the spatiotemporal trends of acid rain in Anhui and the potential reasons of the increasing occurrence frequency of acid rain. In addition, the technique of back-trajectory-cluster analysis was used to examine the impacts of transport patterns on the precipitation acidity in Anhui. The occurrence frequency shows the lowest in summer and the highest in autumn, with 3-year average pH < 5.6 during 2006-2008 at all stations, hereinto, pH values are between 5.0 and 4.5 in Hefei, Anqing, Maanshan and Bengbu. In spatial, acid rain were the most severe in southern to middle Anhui and mitigated to north. The distributions of pH were concentrative at Fuyang, Tongling and Huangshan, with more than 75% occurred between 6.00-7.50 (Fuyang), 5.00-6.00 (Tongling) and 5.00-6.50 (Huangshan); quite dispersive at other stations, with the maximum at 4.00-4.50 (Hefei and Anqing), 5.00-5.50 (Maanshan) and 5.50-6.00 (Bengbu). The occurrence frequencies of acid rain increased evidently at all stations comparing with those in the end of 1990s. The results of back-trajectories-cluster analysis show that the acid rain is closely related with the regional-range transport of acid rain precursors at each station. The air-masses from southeast and northeast, especially those passing through Jiangsu and Zhejiang, associated with the highest frequencies of acid rain with pH < 5.0, indicating that the industrial emissions in the economy developed areas of Yangtze Delta play key roles in acid rain in Anhui province. In addition, statistics shows that the occurrence frequency of acid rain in Hefei was highly correlated with the trends of the provincial coal consumptions in Anhui, Jiangsu and Zhejiang, also tropospheric NO2 column content over Anhui province and surrounding areas with all correlation coefficients > 0.7, suggesting the close relationship between the quick increasing acid rain in Hefei and the regional pollutant emissions.