A comprehensive review of computer-aided whole-slide image analysis: from datasets to feature extraction,segmentation, classification and detection approaches

With the development of Computer-aided Diagnosis (CAD) and image scanning techniques, Whole-slide Image (WSI) scanners are widely used in the field of pathological diagnosis. Therefore, WSI analysis has become the key to modern digital histopathology. Since 2004, WSI has been used widely in CAD. Since machine vision methods are usually based on semi-automatic or fully automatic computer algorithms, they are highly efficient and labor-saving. The combination of WSI and CAD technologies for segmentation, classification, and detection helps histopathologists to obtain more stable and quantitative results with minimum labor costs and improved diagnosis objectivity. This paper reviews the methods of WSI analysis based on machine learning. Firstly, the development status of WSI and CAD methods are introduced. Secondly, we discuss publicly available WSI datasets and evaluation metrics for segmentation, classification, and detection tasks. Then, the latest development of machine learning techniques in WSI segmentation, classification, and detection are reviewed. Finally, the existing methods are studied, and the application prospects of the methods in this field are forecasted.

     

Experimentelle und numerische Untersuchungen zum Tragverhalten von Stahlbetondecken mit kugelförmigen Hohlkörpern

Massive Flachdecken erweisen sich in Hoch‐ und Industriebau häufig als insgesamt überlegenes Deckensystem. Die hohe Eigenlast dieser Decken kann ihren Anwendungsbereich jedoch einschränken. Eine sinnvolle Abhilfe schafft dann die Integration von Hohlkörpern in der neutralen Zone, weil hierdurch eine spürbare Gewichtsreduktion eintritt. Neben der Eigenlast wird auch der Verbrauch der unter ökologischen Gesichtspunkten wesentlichen Ressourcen Betonstahl und Zement deutlich verringert. Die Hohlräume beeinflussen vor allem die Querkrafttragfähigkeit solcher Decken. Vier Versuchsserien, die mit kugelförmigen Hohlkörperdecken des Systems “cobiax” durchgeführt wurden, werden in diesem Beitrag beschrieben. Aus den Versuchen wird ein Abminderungsfaktor zur Beschreibung des Querkrafttragverhaltens abgeleitet, der auch in die kürzlich erteilte allgemeine bauaufsichtliche Zulassung des Deckensystems eingegangen ist. Die Nachrechnung der Versuche mit der Finite‐Elemente‐Methode zeigt eine gute Übereinstimmung von Numerik und Experiment, so dass in der Weiterentwicklung Parameterstudien auf dieser Grundlage zur Ergänzung von Versuchen hilfreich sein werden. Experimental and Numerical Investigation of the Bearing Behaviour of Hollow Core Slabs Massive flat slabs have proven to be the most appropriate ceiling system for structural and industrial engineering. However the high dead load of these slabs might reduce their field of application. This problem can be solved by void formers that are placed in the neutral zone. These block‐outs cause a noticeable reduction of weight. Furthermore, the masses of ecologically important resources like reinforcement steel and cement can be reduced as well. The shear bearing capacity is significantly influenced by these block‐outs. This article describes four test series with spherical void former floors of the system “cobiax”. A reduction factor for the shear bearing capacity is derived from these tests. That factor was also introduced in the technical approval for this slab system which has been issued recently. A comparison to a calculation with the finite element method shows that the numerical results and the results of the tests are quite similar. In future research, parameter studies based on the finite element method might be helpful additional to further tests.     

Two-stage method of obtaining high bulk density sodium tripolyphosphate: Design and mechanism of process

The paper presents a two-step method for obtaining sodium tripolyphosphate (STPP) with a bulk density of about 0.90 kg/dm³ after the first step, using sodium phosphates after spray drying and water as the raw materials. STPP with a bulk density of 0.95–1.00 kg/dm³ was generated in the second stage, using STPP from the first step and water as the raw materials. The paper presents statistical analyses to define the process parameters which significantly affect sodium tripolyphosphate bulk density. The determination of the profile approximation and utility function enabled the optimization of process parameters for obtaining a product with a bulk density of 0.95–1.00 kg/dm³. Mechanisms of increasing bulk density was indicated by studies on the microstructure of the product and phase transformation during the process. The data were empirically verified and satisfactory results were found.     

Mesoporous drug carrier systems for enhanced delivery rate of poorly water-soluble drug: nimodipine

Journal of Porous Materials - Two mesoporous silica materials: MCM-41 and SBA-15 were applied as potential nanocarriers for poorly soluble drug—nimodipine. Drug incorporation was performed...     

Preclinical Study of Immunological Isoxazole Derivatives as a Potential Support for Melanoma Chemotherapy

(1) Background: Melanoma is an aggressive neoplasm derived from melanocyte precursors with a high metastatic potential. Responses to chemotherapy and immunotherapy for melanoma remain weak, underlining the urgent need to develop new therapeutic strategies for the treatment of melanoma. (2) Methods: The viability of NHDF and A375 cell cultures after the administration of the tested isoxazole derivatives was assessed after 24-h and 48-h incubation periods with the test compounds in the MTT test. ROS and NO scavenging analyses, a glycoprotein-P activity analysis, a migration assay, a test of apoptosis, and a multiple-criteria decision analysis were also performed. (3) Results: All compounds that were tested resulted in a slower migration of melanoma neoplastic cells. The mechanism of the antitumor activity of the tested compounds was confirmed—i.e., the pro-apoptotic activity of the compounds in A375 cell cultures. Compound O7K qualified for further research. (4) Conclusions: All the tested compounds inhibited the formation of melanoma metastases and demonstrated the ability to reduce the risk of developing drug resistance in the tumor. The MCDA results showed that O7K showed the strongest antitumor activity.     

Effective elastic properties and residual stresses in directionally solidified eutectic Al<Subscript>2</Subscript>O<Subscript>3</Subscript>/YAG/ZrO<Subscript>2</Subscript> ceramics estimated by finite element analysis

Effective elastic properties and residual stresses were assessed in directionally solidified ternary eutectic ceramic, Al₂O₃/YAG/ZrO₂, by finite element analyses. A 3D finite element model was generated from a CT scan, representative of the microstructure and with a similar volume fraction. Effective elastic properties were calculated by numerical homogenisation. They highlight a quasi-isotropic behaviour of the ternary eutectic ceramics. Despite the difficulties to measure the strain, the dispersion observed in the results and the limited reliability of the materials properties, the results constitute a step towards a better understanding of the material behaviour. Thermal residual stresses induced by the manufacturing were also evaluated. Tensile residual stresses in yttria-stabilised zirconia and compressive residual stresses in YAG and alumina were highlighted. This evaluation also shed light on the influence of the phase morphology in the microstructure. Indeed, the computed spatial distribution of the residual stresses showed that they are different from one position to another due to the variation in phase morphology and also to material properties variability. Therefore, it is important when numerically assessing the thermomechanical properties to take into account the microstructure morphology as well as the variability of material properties.     

A quadratic boundedness approach to a neural network-based simultaneous estimation of actuator and sensor faults

Neural Computing and Applications - The paper is devoted to the problem of a neural network-based robust simultaneous actuator and sensor faults estimator design for the purpose of the fault...     

Deployment of a cloud pipeline for real-time visual inspection using fast streaming high-definition images

We investigate the challenges of building an end-to-end cloud pipeline for real-time intelligent visual inspection system for use in automotive manufacturing. Current methods of visual detection in automotive assembly are highly labor intensive, and thus prone to errors. An automated process is sought that can operate within the real-time constraints of the assembly line and can reduce errors. Components of the cloud pipeline include capture of a large set of high-definition images from a camera setup at the assembly location, transfer and storage of the images as needed, execution of object detection, and notification to a human operator when a fault is detected. The end-to-end execution must complete within a fixed time frame before the next car arrives in the assembly line. In this article, we report the design, development, and experimental evaluation of the tradeoffs of performance, accuracy, and scalability for a cloud system.