Robust, credible, and interpretable AI-based histopathological prostate cancer grading.

Background: Prostate cancer (PCa) is among the most common cancers in men and its diagnosis requires the histopathological evaluation of biopsies by human experts. While several recent artificial intelligence-based (AI) approaches have reached human expert-level PCa grading, they often display significantly reduced performance on external datasets. This reduced performance can be caused by variations in sample preparation, for instance the staining protocol, section thickness, or scanner used. Another limiting factor of contemporary AI-based PCa grading is the prediction of ISUP grades, which leads to the perpetuation of human annotation errors. Methods: We developed the p rostate c ancer a ggressiveness index (PCAI), an AI-based PCa detection and grading framework that is trained on objective patient outcome, rather than subjective ISUP grades. We designed PCAI as a clinical application, containing algorithmic modules that offer robustness to data variation, medical interpretability, and a measure of prediction confidence. To train and evaluate PCAI, we generated a multicentric, retrospective, observational trial consisting of six cohorts with 25,591 patients, 83,864 images, and 5 years of median follow-up from 5 different centers and 3 countries. This includes a high-variance dataset of 8,157 patients and 28,236 images with variations in sample thickness, staining protocol, and scanner, allowing for the systematic evaluation and optimization of model robustness to data variation. The performance of PCAI was assessed on three external test cohorts from two countries, comprising 2,255 patients and 9,437 images. Findings: Using our high-variance datasets, we show how differences in sample processing, particularly slide thickness and staining time, significantly reduce the performance of AI-based PCa grading by up to 6.2 percentage points in the concordance index (C-index). We show how a select set of algorithmic improvements, including domain adversarial training, conferred robustness to data variation, interpretability, and a measure of credibility to PCAI. These changes lead to significant prediction improvement across two biopsy cohorts and one TMA cohort, systematically exceeding expert ISUP grading in C-index and AUROC by up to 22 percentage points. Interpretation: Data variation poses serious risks for AI-based histopathological PCa grading, even when models are trained on large datasets. Algorithmic improvements for model robustness, interpretability, credibility, and training on high-variance data as well as outcome-based severity prediction gives rise to robust models with above ISUP-level PCa grading performance.

Texture Transfer in Dielectric Layers via Nanocrystalline Networks: Insights from in Situ 4D-STEM.

Transition metal oxide dielectric layers have emerged as promising candidates for various relevant applications, such as supercapacitors or memory applications. However, the performance and reliability of these devices can critically depend on their microstructure, which can be strongly influenced by thermal processing and substrate-induced strain. To gain a more in-depth understanding of the microstructural changes, we conducted in situ transmission electron microscopy (TEM) studies of amorphous HfO2 dielectric layers grown on highly textured (111) substrates. Our results indicate that the minimum required phase transition temperature is 180 °C and that the developed crystallinity is affected by texture transfer. Using in situ TEM and 4D-STEM can provide valuable insights into the fundamental mechanisms underlying the microstructural evolution of dielectric layers and could pave the way for the development of more reliable and efficient devices for future applications.

Using AI and Gd-EOB-DTPA-enhanced MR imaging to assess liver function, comparing the MELIF score with the ALBI score.

Monitoring disease progression is particularly important for determining the optimal treatment strategy in patients with liver disease. Especially for patients with diseases that have a reversible course, there is a lack of suitable tools for monitoring liver function. The development and establishment of such tools is very important, especially in view of the expected increase in such diseases in the future. Image-based liver function parameters, such as the T1 relaxometry-based MELIF score, are ideally suited for this purpose. The determination of this new liver function score is fully automated by software developed with AI technology. In this study, the MELIF score is compared with the widely used ALBI score. The ALBI score was used as a benchmark, as it has been shown to better capture the progression of less severe liver disease than the MELD and Child‒Pugh scores. In this study, we retrospectively determined the ALBI and MELIF scores for 150 patients, compared these scores with the corresponding MELD and Child‒Pugh scores (Pearson correlation), and examined the ability of these scores to discriminate between good and impaired liver function (AUC: MELIF 0.8; ALBI 0.77) and to distinguish between patients with and without cirrhosis (AUC: MELIF 0.83, ALBI 0.79). The MELIF score performed more favourably than the ALBI score and may also be suitable for monitoring mild disease progression. Thus, the MELIF score is promising for closing the gap in the available early-stage liver disease monitoring tools (i.e., identification of liver disease at a potentially reversible stage before chronic liver disease develops).

Crystal and Electronic Structure of Oxygen Vacancy Stabilized Rhombohedral Hafnium Oxide.

Hafnium oxide is an outstanding candidate for next-generation nonvolatile memory solutions such as OxRAM (oxide-based resistive memory) and FeRAM (ferroelectric random access memory). A key parameter for OxRAM is the controlled oxygen deficiency in HfO2-x which eventually is associated with structural changes. Here, we expand the view on the recently identified (semi-)conducting low-temperature pseudocubic phase of reduced hafnium oxide by further X-ray diffraction analysis and density functional theory (DFT) simulation and reveal its rhombohedral nature. By performing total energy and electronic structure calculations, we investigate phase stability and band structure modifications in the presence of oxygen vacancies. With increasing oxygen vacancy concentration, the material transforms from the well-known monoclinic structure to a (pseudocubic) polar rhombohedral r-HfO2-x structure. The DFT analysis shows that r-HfO2-x is not merely epitaxy-induced but may exist as a relaxed compound. Furthermore, the electronic structure of r-HfO2-x as determined by X-ray photoelectron spectroscopy and UV/Vis spectroscopy corresponds very well with the DFT-based prediction of a conducting defect band. The existence of a substoichiometric (semi-)conducting phase of HfO2-x is obviously an important ingredient to understand the mechanism of resistive switching in hafnium-oxide-based OxRAM.

Fast Fitting of the Dynamic Memdiode Model to the Conduction Characteristics of RRAM Devices Using Convolutional Neural Networks.

In this paper, the use of Artificial Neural Networks (ANNs) in the form of Convolutional Neural Networks (AlexNET) for the fast and energy-efficient fitting of the Dynamic Memdiode Model (DMM) to the conduction characteristics of bipolar-type resistive switching (RS) devices is investigated. Despite an initial computationally intensive training phase the ANNs allow obtaining a mapping between the experimental Current-Voltage (I-V) curve and the corresponding DMM parameters without incurring a costly iterative process as typically considered in error minimization-based optimization algorithms. In order to demonstrate the fitting capabilities of the proposed approach, a complete set of I-Vs obtained from Y2O3-based RRAM devices, fabricated with different oxidation conditions and measured with different current compliances, is considered. In this way, in addition to the intrinsic RS variability, extrinsic variation is achieved by means of external factors (oxygen content and damage control during the set process). We show that the reported method provides a significant reduction of the fitting time (one order of magnitude), especially in the case of large data sets. This issue is crucial when the extraction of the model parameters and their statistical characterization are required.

Structural and Electrical Response of Emerging Memories Exposed to Heavy Ion Radiation.

Hafnium oxide- and GeSbTe-based functional layers are promising candidates in material systems for emerging memory technologies. They are also discussed as contenders for radiation-harsh environment applications. Testing the resilience against ion radiation is of high importance to identify materials that are feasible for future applications of emerging memory technologies like oxide-based, ferroelectric, and phase-change random-access memory. Induced changes of the crystalline and microscopic structure have to be considered as they are directly related to the memory states and failure mechanisms of the emerging memory technologies. Therefore, we present heavy ion irradiation-induced effects in emerging memories based on different memory materials, in particular, HfO2-, HfZrO2-, as well as GeSbTe-based thin films. This study reveals that the initial crystallinity, composition, and microstructure of the memory materials have a fundamental influence on their interaction with Au swift heavy ions. With this, we provide a test protocol for irradiation experiments of hafnium oxide- and GeSbTe-based emerging memories, combining structural investigations by X-ray diffraction on a macroscopic, scanning transmission electron microscopy on a microscopic scale, and electrical characterization of real devices. Such fundamental studies can be also of importance for future applications, considering the transition of digital to analog memories with a multitude of resistance states.

Controlling the Formation of Conductive Pathways in Memristive Devices.

Resistive random-access memories are promising candidates for novel computer architectures such as in-memory computing, multilevel data storage, and neuromorphics. Their working principle is based on electrically stimulated materials changes that allow access to two (digital), multiple (multilevel), or quasi-continuous (analog) resistive states. However, the stochastic nature of forming and switching the conductive pathway involves complex atomistic defect configurations resulting in considerable variability. This paper reveals that the intricate interplay of 0D and 2D defects can be engineered to achieve reproducible and controlled low-voltage formation of conducting filaments. The author find that the orientation of grain boundaries in polycrystalline HfOx is directly related to the required forming voltage of the conducting filaments, unravelling a neglected origin of variability. Based on the realistic atomic structure of grain boundaries obtained from ultra-high resolution imaging combined with first-principles calculations including local strain, this paper shows how oxygen vacancy segregation energies and the associated electronic states in the vicinity of the Fermi level govern the formation of conductive pathways in memristive devices. These findings are applicable to non-amorphous valence change filamentary type memristive device. The results demonstrate that a fundamental atomistic understanding of defect chemistry is pivotal to design memristors as key element of future electronics.

MELIF, a Fully Automated Liver Function Score Calculated from Gd-EOB-DTPA-Enhanced MR Images: Diagnostic Performance vs. the MELD Score.

In the management of patients with chronic liver disease, the assessment of liver function is essential for treatment planning. Gd-EOB-DTPA-enhanced MRI allows for both the acquisition of anatomical information and regional liver function quantification. The objective of this study was to demonstrate and evaluate the diagnostic performance of two fully automatically generated imaging-based liver function scores that take the whole liver into account. T1 images from the native and hepatobiliary phases and the corresponding T1 maps from 195 patients were analyzed. A novel artificial-intelligence-based software prototype performed image segmentation and registration, calculated the reduction rate of the T1 relaxation time for the whole liver (rrT1liver) and used it to calculate a personalized liver function score, then generated a unified score-the MELIF score-by combining the liver function score with a patient-specific factor that included weight, height and liver volume. Both scores correlated strongly with the MELD score, which is used as a reference for global liver function. However, MELIF showed a stronger correlation than the rrT1liver score. This study demonstrated that the fully automated determination of total liver function, regionally resolved, using MR liver imaging is feasible, providing the opportunity to use the MELIF score as a diagnostic marker in future prospective studies.

Assessment of Liver Function With MRI: Where Do We Stand?

Liver disease and hepatocellular carcinoma (HCC) have become a global health burden. For this reason, the determination of liver function plays a central role in the monitoring of patients with chronic liver disease or HCC. Furthermore, assessment of liver function is important, e.g., before surgery to prevent liver failure after hepatectomy or to monitor the course of treatment. Liver function and disease severity are usually assessed clinically based on clinical symptoms, biopsy, and blood parameters. These are rather static tests that reflect the current state of the liver without considering changes in liver function. With the development of liver-specific contrast agents for MRI, noninvasive dynamic determination of liver function based on signal intensity or using T1 relaxometry has become possible. The advantage of this imaging modality is that it provides additional information about the vascular structure, anatomy, and heterogeneous distribution of liver function. In this review, we summarized and discussed the results published in recent years on this technique. Indeed, recent data show that the T1 reduction rate seems to be the most appropriate value for determining liver function by MRI. Furthermore, attention has been paid to the development of automated tools for image analysis in order to uncover the steps necessary to obtain a complete process flow from image segmentation to image registration to image analysis. In conclusion, the published data show that liver function values obtained from contrast-enhanced MRI images correlate significantly with the global liver function parameters, making it possible to obtain both functional and anatomic information with a single modality.

Enhanced Conductivity and Microstructure in Highly Textured TiN1-x /c-Al2O3 Thin Films.

Titanium nitride thin films are used as an electrode material in superconducting (SC) applications and in oxide electronics. By controlling the defect density in the TiN thin film, the electrical properties of the film can achieve low resistivities and a high critical temperature (T c) close to bulk values. Generally, low defect densities are achieved by stoichiometric growth and a low grain boundary density. Due to the low lattice mismatch of 0.7%, the best performing TiN layers are grown epitaxially on MgO substrates. Here, we report for the first time a T c of 4.9 K for ultrathin (23 nm), highly textured (111), and stoichiometric TiN films grown on 8.75% lattice mismatch c-cut Al2O3 (sapphire) substrates. We demonstrate that with the increasing nitrogen deficiency, the (111) lattice constant increases, which is accompanied by a decrease in T c. For highly N deficient TiN thin films, no superconductivity could be observed. In addition, a dissociation of grain boundaries (GBs) by the emission of stacking faults could be observed, indicating a combination of two sources for electron scattering defects in the system: (a) volume defects created by nitrogen deficiency and (b) defects created by the presence of GBs. For all samples, the average grain boundary distance is kept constant by a miscut of the c-cut sapphire substrate, which allows us to distinguish the effect of nitrogen deficiency and grain boundary density. These properties and surface roughness govern the electrical performance of the films and influence the compatibility as an electrode material in the respective application. This study aims to provide detailed and scale-bridging insights into the structural and microstructural response to nitrogen deficiency in the c-Al2O3/TiN system, as it is a promising candidate for applications in state-of-the-art systems such as oxide electronic thin film stacks or SC applications.

Defect-Stabilized Substoichiometric Polymorphs of Hafnium Oxide with Semiconducting Properties.

Hafnium oxide plays an important role as a dielectric material in various thin-film electronic devices such as transistors and resistive or ferroelectric memory. The crystallographic and electronic structure of the hafnia layer often depends critically on its composition and defect structure. Here, we report two novel defect-stabilized polymorphs of substoichiometric HfO2-x with semiconducting properties that are of particular interest for resistive switching digital or analog memory devices. The thin-film samples are synthesized by molecular beam epitaxy with oxygen engineering that allows us to cover the whole range of metallic Hf with oxygen interstitials to HfO2. The crystal and defect structures, in particular of a cubic low-temperature phase c-HfO1.7 and a hexagonal phase hcp-HfO0.7 are identified by X-ray diffraction, in vacuo electron spectroscopic, and transmission electron microscopic methods. With the help of UV/Vis transmission data, we propose a consistent band structure model for the whole oxidation range involving oxygen vacancy-induced in-gap defect states. Our comprehensive study of engineered hafnia thin films has an impact on the design of resistive memory devices and can be transferred to chemically similar suboxide systems.