Search

Abstract Background Multiple first-line treatment options have been developed for advanced non-small cell lung cancer (NSCLC) in each subgroup determined by predictive biomarkers, specifically driver oncogene and programmed cell death ligand-1 (PD-L1) status. However, the methodology for optimal treatment selection in individual patients is not established. This study aimed to develop artificial intelligence (AI)-based personalized survival prediction model according to treatment selection. Methods The prediction model was built based on random survival forest (RSF) algorithm using patient characteristics, anticancer treatment histories, and radiomics features of the primary tumor. The predictive accuracy was validated with external test data and compared with that of cox proportional hazard (CPH) model. Results A total of 459 patients (training, n = 299; test, n = 160) with advanced NSCLC were enrolled. The algorithm identified following features as significant factors associated with survival: age, sex, performance status, Brinkman index, comorbidity of chronic obstructive pulmonary disease, histology, stage, driver oncogene status, tumor PD-L1 expression, administered anticancer agent, six markers of blood test (sodium, lactate dehydrogenase, etc.), and three radiomics features associated with tumor texture, volume, and shape. The C-index of RSF model for test data was 0.841, which was higher than that of CPH model (0.775, P

The demand for Ni-based alloys, particularly Alloy 718, is increasing in the gas turbine industry due to their high-temperature resistance and chemical stability. However, Alloy 718 is challenging to cut, owing to its susceptibility to work-harden, its high cutting resistance, and its poor thermal conductivity. Ultrasonic elliptical vibration cutting (UEVC) can be performed on steel materials using diamond tools, which is facilitated by elliptical vibration of the tool. This approach helps suppress heat generation at the tool tip and prevents chemical decomposition. In this study, we explored the precision cutting of Alloy 718 using UEVC with planar cutting and a single-crystal diamond flat tool. We achieved a surface roughness Ra of 8.4 nm at a cutting speed of 2.0 mm/s. We compared surface roughness under various conditions, including cutting speeds, the amplitude of elliptical vibration, and cutting depth, to investigate the effect of these parameters on surface roughness. Additionally, we studied the geometry and thickness of chips under these conditions using scanning electron microscopy (SEM) images. Our findings indicated flow-type chip shapes in all conditions, signifying stable ductile-regime cutting. Moreover, tool life was investigated by observing the cutting edge, which exhibited slight wear, maintaining a mirror surface for a cutting distance of approximately 50 m. These findings reveal an effective method for high-precision surface fabrication of Alloy 718, elucidating the cutting mechanism and the feasible cutting distance.

Abstract FRET-based sensors are utilized for real-time measurements of cellular tension. However, transfection of the sensor gene shows low efficacy and is only effective for a short period. Reporter mice expressing such sensors have been developed, but sensor fluorescence has not been measured successfully using conventional confocal microscopy. Therefore, methods for spatiotemporal measurement of cellular tension in vivo or ex vivo are still limited. We established a reporter mouse line expressing FRET-based actinin tension sensors consisting of EGFP as the donor and mCherry as the acceptor and whose FRET ratio change is observable with confocal microscopy. Tension-induced changes in FRET signals were monitored in the aorta and tail tendon fascicles, as well as aortic smooth muscle cells isolated from these mice. The pattern of FRET changes was distinctive, depending on tissue type. Indeed, aortic smooth muscle cells exhibit different sensitivity to macroscopic tensile strain in situ and in an isolated state. This mouse strain will enable novel types of biomechanical investigations of cell functions in important physiological events.

Platelets have an active energy metabolism mediated by mitochondria. However, the role of mitochondria in platelet adhesion, activation, and thrombus formation under blood flow conditions remains to be elucidated. Blood specimens were obtained from healthy adult volunteers. The consumption of glucose molecules by platelets was measured after 24 hours. Platelet adhesion, activation, and thrombus formation on collagen fibrils and immobilized von Willebrand factor (VWF) at a wall shear rate of 1,500 s−1 were detected by fluorescence microscopy with an ultrafast laser confocal unit in the presence or absence of mitochondrial functional inhibitors of carbonyl cyanide 4-(trifluoromethoxy) phenylhydrazone (FCCP), antimycin A, and oligomycin. Consumption of glucose molecules within the first 24 h of 4.21 × 10−15 ± 4.46 x 10−15 (n = 6) increased to 13.82 × 10−15 ± 3.46 x 10−15 (n = 4) in the presence of FCCP, 12.11 × 10−15 ± 2.33 x 10−15 (n = 4) in the presence of antimycin A, and 11.87 × 10−15 ± 3.56 x 10−15 (n = 4) in the presence of oligomycin (p

Abstract Deep learning is being employed in disease detection and classification based on medical images for clinical decision making. It typically requires large amounts of labelled data; however, the sample size of such medical image datasets is generally small. This study proposes a novel training framework for building deep learning models of disease detection and classification with small datasets. Our approach is based on a hierarchical classification method where the healthy/disease information from the first model is effectively utilized to build subsequent models for classifying the disease into its sub-types via a transfer learning method. To improve accuracy, multiple input datasets were used, and a stacking ensembled method was employed for final classification. To demonstrate the method’s performance, a labelled dataset extracted from volumetric ophthalmic optical coherence tomography data for 156 healthy and 798 glaucoma eyes was used, in which glaucoma eyes were further labelled into four sub-types. The average weighted accuracy and Cohen’s kappa for three randomized test datasets were 0.839 and 0.809, respectively. Our approach outperformed the flat classification method by 9.7% using smaller training datasets. The results suggest that the framework can perform accurate classification with a small number of medical images.

Abstract Background To effectively detect and investigate various cell-related diseases, it is essential to understand cell behaviour. The ability to detection mitotic cells is a fundamental step in diagnosing cell-related diseases. Convolutional neural networks (CNNs) have been successfully applied to object detection tasks, however, when applied to mitotic cell detection, most existing methods generate high false-positive rates due to the complex characteristics that differentiate normal cells from mitotic cells. Cell size and orientation variations in each stage make detecting mitotic cells difficult in 2D approaches. Therefore, effective extraction of the spatial and temporal features from mitotic data is an important and challenging task. The computational time required for detection is another major concern for mitotic detection in 4D microscopic images. Results In this paper, we propose a backbone feature extraction network named full scale connected recurrent deep layer aggregation (RDLA++) for anchor-free mitotic detection. We utilize a 2.5D method that includes 3D spatial information extracted from several 2D images from neighbouring slices that form a multi-stream input. Conclusions Our proposed technique addresses the scale variation problem and can efficiently extract spatial and temporal features from 4D microscopic images, resulting in improved detection accuracy and reduced computation time compared with those of other state-of-the-art methods.

Abstract The purpose of this study was to develop and evaluate a novel elbow arthroscopy system with superimposed bone and nerve visualization using preoperative computed tomography (CT) and magnetic resonance imaging (MRI) data. We obtained bone and nerve segmentation data by CT and MRI, respectively, of the elbow of a healthy human volunteer and cadaveric Japanese monkey. A life size 3-dimensional (3D) model of human organs and frame was constructed using a stereo-lithographic 3D printer. Elbow arthroscopy was performed using the elbow of a cadaveric Japanese monkey. The augmented reality (AR) range of error during rotation of arthroscopy was examined at 20 mm scope–object distances. We successfully performed AR arthroscopy using the life-size 3D elbow model and the elbow of the cadaveric Japanese monkey by making anteromedial and posterior portals. The target registration error was 1.63 ± 0.49 mm (range 1–2.7 mm) with respect to the rotation angle of the lens cylinder from 40° to − 40°. We attained reasonable accuracy and demonstrated the operation of the designed system. Given the multiple applications of AR-enhanced arthroscopic visualization, it has the potential to be a next-generation technology for arthroscopy. This technique will contribute to the reduction of serious complications associated with elbow arthroscopy.

Abstract The diagnosis of gastrointestinal stromal tumor (GIST) using conventional endoscopy is difficult because submucosal tumor (SMT) lesions like GIST are covered by a mucosal layer. Near-infrared hyperspectral imaging (NIR-HSI) can obtain optical information from deep inside tissues. However, far less progress has been made in the development of techniques for distinguishing deep lesions like GIST. This study aimed to investigate whether NIR-HSI is suitable for distinguishing deep SMT lesions. In this study, 12 gastric GIST lesions were surgically resected and imaged with an NIR hyperspectral camera from the aspect of the mucosal surface. Thus, the images were obtained ex-vivo. The site of the GIST was defined by a pathologist using the NIR image to prepare training data for normal and GIST regions. A machine learning algorithm, support vector machine, was then used to predict normal and GIST regions. Results were displayed using color-coded regions. Although 7 specimens had a mucosal layer (thickness 0.4–2.5 mm) covering the GIST lesion, NIR-HSI analysis by machine learning showed normal and GIST regions as color-coded areas. The specificity, sensitivity, and accuracy of the results were 73.0%, 91.3%, and 86.1%, respectively. The study suggests that NIR-HSI analysis may potentially help distinguish deep lesions.

Abstract Introduction The use of optical coherence tomography (OCT) images is increasing in the medical treatment of age-related macular degeneration (AMD), and thus, the amount of data requiring analysis is increasing. Advances in machine-learning techniques may facilitate processing of large amounts of medical image data. Among deep-learning methods, convolution neural networks (CNNs) show superior image recognition ability. This study aimed to build deep-learning models that could distinguish AMD from healthy OCT scans and to distinguish AMD with and without exudative changes without using a segmentation algorithm. Methods This was a cross-sectional observational clinical study. A total of 1621 spectral domain (SD)-OCT images of patients with AMD and a healthy control group were studied. The first CNN model was trained and validated using 1382 AMD images and 239 normal images. The second transfer-learning model was trained and validated with 721 AMD images with exudative changes and 661 AMD images without any exudate. The attention area of the CNN was described as a heat map by class activation mapping (CAM). In the second model, which classified images into AMD with or without exudative changes, we compared the learning stabilization of models using or not using transfer learning. Results Using the first CNN model, we could classify AMD and normal OCT images with 100% sensitivity, 91.8% specificity, and 99.0% accuracy. In the second, transfer-learning model, we could classify AMD as having or not having exudative changes, with 98.4% sensitivity, 88.3% specificity, and 93.9% accuracy. CAM successfully described the heat-map area on the OCT images. Including the transfer-learning model in the second model resulted in faster stabilization than when the transfer-learning model was not included. Conclusion Two computational deep-learning models were developed and evaluated here; both models showed good performance. Automation of the interpretation process by using deep-learning models can save time and improve efficiency. Trial Registration No15073.

Abstract Background We aimed to investigate the deformation of the outer nuclear layer using optical coherence tomography in patients with epiretinal membrane (ERM) and its relationship with metamorphopsia. Methods Thirty-nine eyes from 39 patients with ERM were included in the study. Patients with the subtypes of pseudo macula hole and lamellar hole were excluded. Twenty-one fellow eyes without macular disease were included as normal controls. Forty-nine B-scan images were obtained in the range of 20 degrees around the macula using SD-OCT. The outer nuclear layer (ONL) was evaluated as a three-dimensional image (3D-ONL) reconstructed using the distance between the ONL and retinal pigment epithelium (RPE) line. The deformation of the ONL was figured at the reference plane and evaluation plane (ONL-B). The characteristic parameters of the ONL-B were defined as circularity, area ratio, and axis ratio. The correlations between these parameters and visual acuity and MCHART score ratio (MH/MV) were then evaluated. Results ONL height was significantly higher in ERM patients than in normal controls (54.1 ± 5.3 μm and 84.1 ± 12.9 μm, respectively; P

PurposeAbnormalities of the running pattern of choroidal vessel have been reported in eyes with pachychoroid diseases. However, it is difficult for clinicians to judge the running pattern with high reproducibility. Thus, the purpose of this study was to compare the degree of concordance of the running pattern of the choroidal vessels between that determined by artificial intelligence (AI) to that determined by experienced clinicians.MethodsThe running pattern of the choroidal vessels in en face images of Haller's layer of 413 normal and pachychoroid diseased eyes was classified as symmetrical or asymmetrical by human raters and by three supervised machine learning models; the support vector machine (SVM), Xception, and random forest models. The data from the human raters were used as the supervised data. The accuracy rates of the human raters and the certainty of AI's answers were compared using confidence scores (CSs).ResultsThe choroidal vascular running pattern could be determined by each AI model with an area under the curve better than 0.94. The random forest method was able to discriminate with the highest accuracy among the three AIs. In the CS analyses, the percentage of certainty was highest (66.4%) and that of uncertainty was lowest (6.1%) in the agreement group. On the other hand, the rate of uncertainty was highest (27.3%) in the disagreement group.ConclusionAI algorithm can automatically classify with ambiguous criteria the presence or absence of a symmetrical blood vessel running pattern of the choroid. The classification was as good as that of supervised humans in accuracy and reproducibility.

The olfactory bulb is arranged in glomeruli defined by their olfactory receptor expression. The authors identify an olfactory receptor for fox odour, TMT, and show that activation of the glomerulus expressing that receptor in mice leads to immobility, but does not lead to other fear behaviours.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

In this study, a laparoscopic imaging device and a light source able to select wavelengths by bandpass filters were developed to perform multispectral imaging (MSI) using over 1000 nm near-infrared (OTN-NIR) on regions under a laparoscope. Subsequently, MSI (wavelengths: 1000–1400 nm) was performed using the built device on nine live mice before and after tumor implantation. The normal and tumor pixels captured within the mice were used as teaching data sets, and the tumor-implanted mice data were classified using a neural network applied following a leave-one-out cross-validation procedure. The system provided a specificity of 89.5%, a sensitivity of 53.5%, and an accuracy of 87.8% for subcutaneous tumor discrimination. Aggregated true-positive (TP) pixels were confirmed in all tumor-implanted mice, which indicated that the laparoscopic OTN-NIR MSI could potentially be applied in vivo for classifying target lesions such as cancer in deep tissues.

From cells to organisms, every living system is three-dimensional (3D), but the performance of fluorescence microscopy has been largely limited when attempting to obtain an overview of systems’ dynamic processes in three dimensions. Recently, advanced light-sheet illumination technologies, allowing drastic improvement in spatial discrimination, volumetric imaging times, and phototoxicity/photobleaching, have been making live imaging to collect precise and reliable 3D information increasingly feasible. In particular, lattice light-sheet microscopy (LLSM), using an ultrathin light-sheet, enables whole-cell 3D live imaging of cellular processes, including mitosis, at unprecedented spatiotemporal resolution for extended periods of time. This technology produces immense and complex data, including a significant amount of information, raising new challenges for big image data analysis and new possibilities for data utilization. Once the data are digitally archived in a computer, the data can be reused for various purposes by anyone at any time. Such an information science approach has the potential to revolutionize the use of bioimage data, and provides an alternative method for cell biology research in a data-driven manner. In this article, we introduce examples of analyzing digital mitotic spindles and discuss future perspectives in cell biology.

A novel method to measure the deformation of a urethane-foam object using an X-ray computed tomography (X-ray CT) technique was proposed and examined. The proposed method is made up of following two steps. First, X-ray sensitive ‘contrast media’ were drawn in lattice-like manner on top and bottom surfaces and internal planes of urethane-foam, which enabled visualization of the drawn positions in CT images. Second, position data of contrast media were then converted into the numerical values in a prescribed coordinate to measure the deformation. It was found that the contrast media successfully visualized outer and internal displacement with the urethane-foam deformation, and the comprehensive error of measurement was 0.3 mm in root mean square. As a trial for further practical purpose, the deformation of the urethane-foam mattress with a human-body model on it was measured using this method. A urethane-foam mattress with contrast media was prepared, a human trunk model was set on the mattress, and the mattress with the model was subjected to X-ray CT. The deformation state at surface of, and especially inside of, the mattress could be visualized and measured. We concluded that the proposed method could bring us an information on deformation state of the urethane-foam and the urethane-foam mattress as numerical values.

Collective cell migration is observed during morphogenesis, angiogenesis, and wound healing, and this type of cell migration also contributes to efficient metastasis in some kinds of cancers. Because collectively migrating cells are much better organized than a random assemblage of individual cells, there seems to be a kind of order in migrating clusters. Extensive research has identified a large number of molecules involved in collective cell migration, and these factors have been analyzed using dramatic advances in imaging technology. To date, however, it remains unclear how myriad cells are integrated as a single unit. Recently, we observed unbalanced collective cell migrations that can be likened to either precision dancing or awa-odori, Japanese traditional dancing similar to the style at Rio Carnival, caused by the impairment of the conformational change of JRAB/MICAL-L2. This review begins with a brief history of image-based computational analyses on cell migration, explains why quantitative analysis of the stylization of collective cell behavior is difficult, and finally introduces our recent work on JRAB/MICAL-L2 as a successful example of the multidisciplinary approach combining cell biology, live imaging, and computational biology. In combination, these methods have enabled quantitative evaluations of the “dancing style” of collective cell migration.

PURPOSE:To develop a method to quantify, based on swept-source optical coherence tomography (OCT), the 3D structure of the laminar pores in patients with glaucoma. METHODS:This retrospective study examined 160 laminar pores from 8 eyes of 8 cases: 4 normal subjects and 4 open-angle glaucoma (OAG) patients. We reconstructed 3D volume data for a 3 x 3 mm disc, using a method similar to OCT angiography, and segmented the structure of the lamina cribrosa. Then, we manually segmented each laminar pore in sequential C-scan images (>90 slices at 2.6-micron intervals) with VCAT5 (RIKEN, Japan). We compared the control and OAG subjects with the Mann-Whitney U test. Differences were considered significant at p < 0.05. RESULTS:We found that the laminar pores of the OAG patients had a significantly smaller average cross-sectional area, smaller 3D volume (adjusted to the average thickness of the lamina cribrosa), and higher true sphericity, and lower principal value (P1, 2, 3) of the 3D structure data (all: p < 0.0001). The topographic distribution of damaged laminar pores was consistent with the damaged area of the macular map. CONCLUSION:We successfully developed a method to quantify the 3D structure of the laminar pores; providing a useful tool to assess lamina cribrosa-associated risk factors for glaucoma. These findings promise to benefit future investigations into the pathomechanisms of glaucoma.

This study aimed to develop a machine learning-based algorithm for objective classification of the optic disc in patients with open-angle glaucoma (OAG), using quantitative parameters obtained from ophthalmic examination instruments.This study enrolled 163 eyes of 105 OAG patients (age: 62.3 ± 12.6, mean deviation of Humphrey field analyzer: -8.9 ± 7.5 dB). The eyes were classified into Nicolela's 4 optic disc types by 3 glaucoma specialists. Randomly, 114 eyes were selected for training data and 49 for test data. A neural network (NN) was trained with the training data and evaluated with the test data. We used 91 types of quantitative data, including 7 patient background characteristics, 48 quantified OCT (swept-source OCT; DRI OCT Atlantis, Topcon) values, including optic disc topography and circumpapillary retinal nerve fiber layer thickness (cpRNFLT), and 36 blood flow parameters from laser speckle flowgraphy, to build the machine learning classification model. To extract the important features among 91 parameters, minimum redundancy maximum relevance and a genetic feature selection were used.The validated accuracy against test data for the NN was 87.8% (Cohen's Kappa = 0.83). The important features in the NN were horizontal disc angle, spherical equivalent, cup area, age, 6-sector superotemporal cpRNFLT, average cup depth, average nasal rim disc ratio, maximum cup depth, and superior-quadrant cpRNFLT.The proposed machine learning system has proved to be good identifiers for different disc types with high accuracy. Additionally, the calculated confidence levels reported here should be very helpful for OAG care.

Genome information, which is three-dimensionally organized within cells as chromatin, is searched and read by various proteins for diverse cell functions. Although how the protein factors find their targets remains unclear, the dynamic and flexible nature of chromatin is likely crucial. Using a combined approach of fluorescence correlation spectroscopy, single-nucleosome imaging, and Monte Carlo computer simulations, we demonstrate local chromatin dynamics in living mammalian cells. We show that similar to interphase chromatin, dense mitotic chromosomes also have considerable chromatin accessibility. For both interphase and mitotic chromatin, we observed local fluctuation of individual nucleosomes (∼50 nm movement/30 ms), which is caused by confined Brownian motion. Inhibition of these local dynamics by crosslinking impaired accessibility in the dense chromatin regions. Our findings show that local nucleosome dynamics drive chromatin accessibility. We propose that this local nucleosome fluctuation is the basis for scanning genome information.

Computer simulation techniques for cardiac beating motions potentially have many applications and a broad audience. However, most existing methods require enormous computational costs and often show unstable behavior for extreme parameter sets, which interrupts smooth simulation study and make it difficult to apply them to interactive applications. To address this issue, we present an efficient and robust framework for simulating the cardiac beating motion. The global cardiac motion is generated by the accumulation of local myocardial fiber contractions. We compute such local-to-global deformations using a kinematic approach; we divide a heart mesh model into overlapping local regions, contract them independently according to fiber orientation, and compute a global shape that satisfies contracted shapes of all local regions as much as possible. A comparison between our method and a physics-based method showed that our method can generate motion very close to that of a physics-based simulation. Our kinematic method has high controllability; the simulated ventricle-wall-contraction speed can be easily adjusted to that of a real heart by controlling local contraction timing. We demonstrate that our method achieves a highly realistic beating motion of a whole heart in real time on a consumer-level computer. Our method provides an important step to bridge a gap between cardiac simulations and interactive applications.

BACKGROUND: Activation of caspases is crucial for the execution of apoptosis. Although the caspase cascade associated with activation of the initiator caspase-8 (CASP8) has been investigated in molecular and biochemical detail, the dynamics of CASP8 activation are not fully understood. METHODOLOGY/PRINCIPAL FINDINGS: We have established a biosensor based on fluorescence resonance energy transfer (FRET) for visualizing apoptotic signals associated with CASP8 activation at the single-cell level. Our dual FRET (dual-FRET) system, comprising a triple fusion fluorescent protein, enabled us to simultaneously monitor the activation of CASP8 and its downstream effector, caspase-3 (CASP3) in single live cells. With the dual-FRET-based biosensor, we detected distinct activation patterns of CASP8 and CASP3 in response to various apoptotic stimuli in mammalian cells, resulting in the positive feedback amplification of CASP8 activation. We reproduced these observations by in vitro reconstitution of the cascade, with a recombinant protein mixture that included procaspases. Furthermore, using a plasma membrane-bound FRET-based biosensor, we captured the spatiotemporal dynamics of CASP8 activation by the diffusion process, suggesting the focal activation of CASP8 is sufficient to propagate apoptotic signals through death receptors. CONCLUSIONS: Our new FRET-based system visualized the activation process of both initiator and effector caspases in a single apoptotic cell and also elucidated the necessity of an amplification loop for full activation of CASP8.

Increased information on the encoded mammalian genome is expected to facilitate an integrated understanding of complex anatomical structure and function based on the knowledge of gene products. Determination of gene expression-anatomy associations is crucial for this understanding. To elicit the association in the three-dimensional (3D) space, we introduce a novel technique for comprehensive mapping of endogenous gene expression into a web-accessible standard space: Transcriptome Tomography. The technique is based on conjugation of sequential tissue-block sectioning, all fractions of which are used for molecular measurements of gene expression densities, and the block- face imaging, which are used for 3D reconstruction of the fractions. To generate a 3D map, tissues are serially sectioned in each of three orthogonal planes and the expression density data are mapped using a tomographic technique. This rapid and unbiased mapping technique using a relatively small number of original data points allows researchers to create their own expression maps in the broad anatomical context of the space. In the first instance we generated a dataset of 36,000 maps, reconstructed from data of 61 fractions measured with microarray, covering the whole mouse brain (ViBrism: http://vibrism.riken.jp/3dviewer/ex/index.html) in one month. After computational estimation of the mapping accuracy we validated the dataset against existing data with respect to the expression location and density. To demonstrate the relevance of the framework, we showed disease related expression of Huntington's disease gene and Bdnf. Our tomographic approach is applicable to analysis of any biological molecules derived from frozen tissues, organs and whole embryos, and the maps are spatially isotropic and well suited to the analysis in the standard space (e.g. Waxholm Space for brain-atlas databases). This will facilitate research creating and using open-standards for a molecular-based understanding of complex structures; and will contribute to new insights into a broad range of biological and medical questions.