Automatic multi-tissue segmentation in pancreatic pathological images with selected multi-scale attention network.

The morphology of tissues in pathological images has been used routinely by pathologists to assess the degree of malignancy of pancreatic ductal adenocarcinoma (PDAC). Automatic and accurate segmentation of tumor cells and their surrounding tissues is often a crucial step to obtain reliable morphological statistics. Nonetheless, it is still a challenge due to the great variation of appearance and morphology. In this paper, a selected multi-scale attention network (SMANet) is proposed to segment tumor cells, blood vessels, nerves, islets and ducts in pancreatic pathological images. The selected multi-scale attention module is proposed to enhance effective information, supplement useful information and suppress redundant information at different scales from the encoder and decoder. It includes selection unit (SU) module and multi-scale attention (MA) module. The selection unit module can effectively filter features. The multi-scale attention module enhances effective information through spatial attention and channel attention, and combines different level features to supplement useful information. This helps learn the information of different receptive fields to improve the segmentation of tumor cells, blood vessels and nerves. An original-feature fusion unit is also proposed to supplement the original image information to reduce the under-segmentation of small tissues such as islets and ducts. The proposed method outperforms state-of-the-arts deep learning algorithms on our PDAC pathological images and achieves competitive results on the GlaS challenge dataset. The mDice and mIoU have reached 0.769 and 0.665 in our PDAC dataset.

Metabolism-based ventilation monitoring and control method for COVID-19 risk mitigation in gymnasiums and alike places.

Gymnasiums, fitness rooms and alike places offer exercise services to citizens, which play positive roles in promoting health and enhancing human immunity. Due to the high metabolic rates during exercises, supplying sufficient ventilation in these places is essential and extremely important especially given the risk of infectious respiratory diseases like COVID-19. Traditional ventilation control methods rely on a single CO2 sensor (often placed at return air duct), which is often difficult to reflect the human metabolic rates accurately, and thus can hardly control the infection risk instantly. Thus, to ensure a safe and healthy environment in places with high metabolism, a real-time metabolism-based ventilation control method is proposed. A computer vision algorithm is developed to monitor human activities (regarding human motion amplitude and speed) and an artificial neural network is established for metabolic prediction. Case studies show that the proposed metabolism-based ventilation control method can reduce the infection probability down to 4.3-6.3% while saving 13% of energy in comparison with the strategy of fixed-fresh-air ventilation. In the development of healthy and sustainable society, gymnasiums and alike exercise places are essential and the proposed ventilation control method is a promising solution to decrease the risk of COVID-19 while preserving features of energy saving and carbon emission reduction.

Deriving external forces via convolutional neural networks for biomedical image segmentation.

Active contours, or snakes, are widely applied on biomedical image segmentation. They are curves defined within an image domain that can move to object boundaries under the influence of internal forces and external forces, in which the internal forces are generally computed from curves themselves and external forces from image data. Designing external forces properly is a key point with active contour algorithms since the external forces play a leading role in the evolution of active contours. One of most popular external forces for active contour models is gradient vector flow (GVF). However, GVF is sensitive to noise and false edges, which limits its application area. To handle this problem, in this paper, we propose using GVF as reference to train a convolutional neural network to derive an external force. The derived external force is then integrated into the active contour models for curve evolution. Three clinical applications, segmentation of optic disk in fundus images, fluid in retinal optical coherence tomography images and fetal head in ultrasound images, are employed to evaluate the proposed method. The results show that the proposed method is very promising since it achieves competitive performance for different tasks compared to the state-of-the-art algorithms.

EFFECT OF OPTIC DISK-FOVEA DISTANCE ON MEASUREMENTS OF INDIVIDUAL MACULAR INTRARETINAL LAYERS IN NORMAL SUBJECTS.

PURPOSE: To investigate the effect of optic disk-fovea distance (DFD) on measurements of macular intraretinal layers using spectral domain optical coherence tomography in normal subjects. METHODS: One hundred and eighty-two eyes from 182 normal subjects were imaged using spectral domain optical coherence tomography. The average thicknesses of eight macular intraretinal layers were measured using an automatic segmentation algorithm. Partial correlation test and multiple regression analysis were used to determine the effect of DFD on thicknesses of intraretinal layers. RESULTS: Disk-fovea distance correlated negatively with the overall average thickness in all the intraretinal layers (r ≤ -0.17, all P ≤ 0.025) except the ganglion cell layer and photoreceptor. In multiple regression analysis, greater DFD was associated with thinner nerve fiber layer (6.78 µm decrease per each millimeter increase in DFD, P < 0.001), thinner ganglion cell-inner plexiform layer (2.16 µm decrease per each millimeter increase in DFD, P = 0.039), thinner ganglion cell complex (8.94 µm decrease per each millimeter increase in DFD, P < 0.001), thinner central macular thickness (18.16 µm decrease per each millimeter increase in DFD, P < 0.001), and thinner total macular thickness (15.94 µm decrease per each millimeter increase in DFD, P < 0.001). CONCLUSION: Thinner measurements of macular intraretinal layers were significantly associated with greater DFD. A clinical assessment of macular intraretinal layers in the evaluation of various macular diseases should always be interpreted in the context of DFD.

Shared-hole graph search with adaptive constraints for 3D optic nerve head optical coherence tomography image segmentation.

Optic nerve head (ONH) is a crucial region for glaucoma detection and tracking based on spectral domain optical coherence tomography (SD-OCT) images. In this region, the existence of a "hole" structure makes retinal layer segmentation and analysis very challenging. To improve retinal layer segmentation, we propose a 3D method for ONH centered SD-OCT image segmentation, which is based on a modified graph search algorithm with a shared-hole and locally adaptive constraints. With the proposed method, both the optic disc boundary and nine retinal surfaces can be accurately segmented in SD-OCT images. An overall mean unsigned border positioning error of 7.27 ± 5.40 µm was achieved for layer segmentation, and a mean Dice coefficient of 0.925 ± 0.03 was achieved for optic disc region detection.

Transcriptome Response to Heavy Metals in Sinorhizobium meliloti CCNWSX0020 Reveals New Metal Resistance Determinants That Also Promote Bioremediation by Medicago lupulina in Metal-Contaminated Soil.

The symbiosis of the highly metal-resistant Sinorhizobium meliloti CCNWSX0020 and Medicago lupulina has been considered an efficient tool for bioremediation of heavy metal-polluted soils. However, the metal resistance mechanisms of S. meliloti CCNWSX00200 have not been elucidated in detail. Here we employed a comparative transcriptome approach to analyze the defense mechanisms of S. meliloti CCNWSX00200 against Cu or Zn exposure. Six highly upregulated transcripts involved in Cu and Zn resistance were identified through deletion mutagenesis, including genes encoding a multicopper oxidase (CueO), an outer membrane protein (Omp), sulfite oxidoreductases (YedYZ), and three hypothetical proteins (a CusA-like protein, a FixH-like protein, and an unknown protein), and the corresponding mutant strains showed various degrees of sensitivity to multiple metals. The Cu-sensitive mutant (ΔcueO) and three mutants that were both Cu and Zn sensitive (ΔyedYZ, ΔcusA-like, and ΔfixH-like) were selected for further study of the effects of these metal resistance determinants on bioremediation. The results showed that inoculation with the ΔcueO mutant severely inhibited infection establishment and nodulation of M. lupulina under Cu stress, while inoculation with the ΔyedYZ and ΔfixH-like mutants decreased just the early infection frequency and nodulation under Cu and Zn stresses. In contrast, inoculation with the ΔcusA-like mutant almost led to loss of the symbiotic capacity of M. lupulina to even grow in uncontaminated soil. Moreover, the antioxidant enzyme activity and metal accumulation in roots of M. lupulina inoculated with all mutants were lower than those with the wild-type strain. These results suggest that heavy metal resistance determinants may promote bioremediation by directly or indirectly influencing formation of the rhizobium-legume symbiosis.IMPORTANCE Rhizobium-legume symbiosis has been promoted as an appropriate tool for bioremediation of heavy metal-contaminated soils. Considering the plant-growth-promoting traits and survival advantage of metal-resistant rhizobia in contaminated environments, more heavy metal-resistant rhizobia and genetically manipulated strains were investigated. In view of the genetic diversity of metal resistance determinants in rhizobia, their effects on phytoremediation by the rhizobium-legume symbiosis must be different and depend on their specific assigned functions. Our work provides a better understanding of the mechanism of heavy metal resistance determinants involved in the rhizobium-legume symbiosis, and in further studies, genetically modified rhizobia harboring effective heavy metal resistance determinants may be engineered for the practical application of rhizobium-legume symbiosis for bioremediation in metal-contaminated soils.

Automatic Three-dimensional Detection of Photoreceptor Ellipsoid Zone Disruption Caused by Trauma in the OCT.

Detection and assessment of the integrity of the photoreceptor ellipsoid zone (EZ) are important because it is critical for visual acuity in retina trauma and other diseases. We have proposed and validated a framework that can automatically analyse the 3D integrity of the EZ in optical coherence tomography (OCT) images. The images are first filtered and automatically segmented into 10 layers, of which EZ is located in the 7(th) layer. For each voxel of the EZ, 57 features are extracted and a principle component analysis is performed to optimize the features. An Adaboost classifier is trained to classify each voxel of the EZ as disrupted or non-disrupted. Finally, blood vessel silhouettes and isolated points are excluded. To demonstrate its effectiveness, the proposed framework was tested on 15 eyes with retinal trauma and 15 normal eyes. For the eyes with retinal trauma, the sensitivity (SEN) was 85.69% ± 9.59%, the specificity (SPE) was 85.91% ± 5.48%, and the balanced accuracy rate (BAR) was 85.80% ± 6.16%. For the normal eyes, the SPE was 99.03% ± 0.73%, and the SEN and BAR levels were not relevant. Our framework has the potential to become a useful tool for studying retina trauma and other conditions involving EZ integrity.

Profile and Determinants of Retinal Optical Intensity in Normal Eyes with Spectral Domain Optical Coherence Tomography.

PURPOSE: To investigate the profile and determinants of retinal optical intensity in normal subjects using 3D spectral domain optical coherence tomography (SD OCT). METHODS: A total of 231 eyes from 231 healthy subjects ranging in age from 18 to 80 years were included and underwent a 3D OCT scan. Forty-four eyes were randomly chosen to be scanned by two operators for reproducibility analysis. Distribution of optical intensity of each layer and regions specified by the Early Treatment of Diabetic Retinopathy Study (ETDRS) were investigated by analyzing the OCT raw data with our automatic graph-based algorithm. Univariate and multivariate analyses were performed between retinal optical intensity and sex, age, height, weight, spherical equivalent (SE), axial length, image quality, disc area and rim/disc area ratio (R/D area ratio). RESULTS: For optical intensity measurements, the intraclass correlation coefficient of each layer ranged from 0.815 to 0.941, indicating good reproducibility. Optical intensity was lowest in the central area of retinal nerve fiber layer, ganglion cell layer, inner plexiform layer, inner nuclear layer, outer plexiform layer and photoreceptor layer, except for the retinal pigment epithelium (RPE). Optical intensity was positively correlated with image quality in all retinal layers (0.553<ß<0.851, p<0.01), and negatively correlated with age in most retinal layers (-0.362<ß<-0.179, p<0.01), except for the RPE (ß = 0.456, p<0.01), outer nuclear layer and photoreceptor layer (p>0.05). There was no relationship between retinal optical intensity and sex, height, weight, SE, axial length, disc area and R/D area ratio. CONCLUSIONS: There was a specific pattern of distribution of retinal optical intensity in different regions. The optical intensity was affected by image quality and age. Image quality can be used as a reference for normalization. The effect of age needs to be taken into consideration when using OCT for diagnosis.

3D Fast Automatic Segmentation of Kidney Based on Modified AAM and Random Forest.

In this paper, a fully automatic method is proposed to segment the kidney into multiple components: renal cortex, renal column, renal medulla and renal pelvis, in clinical 3D CT abdominal images. The proposed fast automatic segmentation method of kidney consists of two main parts: localization of renal cortex and segmentation of kidney components. In the localization of renal cortex phase, a method which fully combines 3D Generalized Hough Transform (GHT) and 3D Active Appearance Models (AAM) is applied to localize the renal cortex. In the segmentation of kidney components phase, a modified Random Forests (RF) method is proposed to segment the kidney into four components based on the result from localization phase. During the implementation, a multithreading technology is applied to speed up the segmentation process. The proposed method was evaluated on a clinical abdomen CT data set, including 37 contrast-enhanced volume data using leave-one-out strategy. The overall true-positive volume fraction and false-positive volume fraction were 93.15%, 0.37% for renal cortex segmentation; 83.09%, 0.97% for renal column segmentation; 81.92%, 0.55% for renal medulla segmentation; and 80.28%, 0.30% for renal pelvis segmentation, respectively. The average computational time of segmenting kidney into four components took 20 seconds.

Comparison of Retinal Thickness Measurements between the Topcon Algorithm and a Graph-Based Algorithm in Normal and Glaucoma Eyes.

PURPOSE: To assess the correlation and agreement between the Topcon built-in algorithm and our graph-based algorithm in measuring the total and regional macular thickness for normal and glaucoma subjects. METHODS: A total of 228 normal eyes and 93 glaucomatous eyes were enrolled in our study. All patients underwent comprehensive ophthalmic examination and Topcon 3D-OCT 2000 scan. One eye was randomly selected for each subject. The thickness of each layer and the total and regional macular thickness on an Early Treatment of Diabetic Retinopathy Study (ETDRS) chart were measured using the Topcon algorithm and our three-dimensional graph-based algorithm. Correlation and agreement analyses between these two algorithms were performed. RESULTS: Our graph search algorithm exhibited a strong correlation with Topcon algorithm. The macular GCC thickness values for normal and glaucoma subjects ranged from 0.86 to 0.91 and from 0.78 to 0.90, and the regional macular thickness values ranged from 0.79 to 0.96 and 0.70 to 0.95, respectively. Small differences were observed between the Topcon algorithm and our graph-based algorithm. The span of 95% limits of agreement of macular GCC thickness was less than 28 µm in both normal and glaucoma subjects, respectively. These limits of total and regional macular thickness were 15.5 µm and 23.1 µm for normal subjects and 29.1 µm and 46.4 µm for glaucoma subjects, respectively. CONCLUSION: Our graph-based algorithm exhibited a high degree of agreement with the Topcon algorithm with respect to thickness measurements in normal and glaucoma subjects. Moreover, our graph-based algorithm can segment the retina into more layers than the Topcon algorithm does.

Automated 3-D retinal layer segmentation of macular optical coherence tomography images with serous pigment epithelial detachments.

Automated retinal layer segmentation of optical coherence tomography (OCT) images has been successful for normal eyes but becomes challenging for eyes with retinal diseases if the retinal morphology experiences critical changes. We propose a method to automatically segment the retinal layers in 3-D OCT data with serous retinal pigment epithelial detachments (PED), which is a prominent feature of many chorioretinal disease processes. The proposed framework consists of the following steps: fast denoising and B-scan alignment, multi-resolution graph search based surface detection, PED region detection and surface correction above the PED region. The proposed technique was evaluated on a dataset with OCT images from 20 subjects diagnosed with PED. The experimental results showed the following. 1) The overall mean unsigned border positioning error for layer segmentation is 7.87±3.36 µm , and is comparable to the mean inter-observer variability ( 7.81±2.56 µm). 2) The true positive volume fraction (TPVF), false positive volume fraction (FPVF) and positive predicative value (PPV) for PED volume segmentation are 87.1%, 0.37%, and 81.2%, respectively. 3) The average running time is 220 s for OCT data of 512 × 64 × 480 voxels.