Predicting prostate cancer grade reclassification on active surveillance using a deep Learning-Based grading algorithm.

Deep learning (DL)-based algorithms to determine prostate cancer (PCa) Grade Group (GG) on biopsy slides have not been validated by comparison to clinical outcomes. We used a DL-based algorithm, AIRAProstate, to re-grade initial prostate biopsies in two independent PCa active surveillance (AS) cohorts. In a cohort initially diagnosed with GG1 PCa using only systematic biopsies (n = 138), upgrading of the initial biopsy to ≥GG2 by AIRAProstate was associated with rapid or extreme grade reclassification on AS (odds ratio 3.3, p = .04), whereas upgrading of the initial biopsy by contemporary uropathologist reviews was not associated with this outcome. In a contemporary validation cohort that underwent prostate magnetic resonance imaging before initial biopsy (n = 169), upgrading of the initial biopsy (all contemporary GG1 by uropathologist grading) by AIRAProstate was associated with grade reclassification on AS (hazard ratio 1.7, p = .03). These results demonstrate the utility of a DL-based grading algorithm in PCa risk stratification for AS.

Deep Learning-Based Spermatogenic Staging in Tissue Sections of Cynomolgus Macaque Testes.

The indirect assessment of adverse effects on fertility in cynomolgus monkeys requires that tissue sections of the testis be microscopically evaluated with awareness of the stage of spermatogenesis that a particular cross-section of a seminiferous tubule is in. This difficult and subjective task could very much benefit from automation. Using digital whole slide images (WSIs) from tissue sections of testis, we have developed a deep learning model that can annotate the stage of each tubule with high sensitivity, precision, and accuracy. The model was validated on six WSI using a six-stage spermatogenic classification system. Whole slide images contained an average number of 4938 seminiferous tubule cross-sections. On average, 78% of these tubules were staged with 29% in stage I-IV, 12% in stage V-VI, 4% in stage VII, 19% in stage VIII-IX, 18% in stage X-XI, and 17% in stage XII. The deep learning model supports pathologists in conducting a stage-aware evaluation of the testis. It also allows derivation of a stage-frequency map. The diagnostic value of this stage-frequency map is still unclear, as further data on its variability and relevance need to be generated for testes with spermatogenic disturbances.

A deep learning system for prostate cancer diagnosis and grading in whole slide images of core needle biopsies.

Gleason grading, a risk stratification method for prostate cancer, is subjective and dependent on experience and expertise of the reporting pathologist. Deep Learning (DL) systems have shown promise in enhancing the objectivity and efficiency of Gleason grading. However, DL networks exhibit domain shift and reduced performance on Whole Slide Images (WSI) from a source other than training data. We propose a DL approach for segmenting and grading epithelial tissue using a novel training methodology that learns domain agnostic features. In this retrospective study, we analyzed WSI from three cohorts of prostate cancer patients. 3741 core needle biopsies (CNBs) received from two centers were used for training. The κquad (quadratic-weighted kappa) and AUC were measured for grade group comparison and core-level detection accuracy, respectively. Accuracy of 89.4% and κquad of 0.92 on the internal test set of 425 CNB WSI and accuracy of 85.3% and κquad of 0.96 on an external set of 1201 images, was observed. The system showed an accuracy of 83.1% and κquad of 0.93 on 1303 WSI from the third institution (blind evaluation). Our DL system, used as an assistive tool for CNB review, can potentially improve the consistency and accuracy of grading, resulting in better patient outcomes.

Activation Strategy of MoS2 as HER Electrocatalyst through Doping-Induced Lattice Strain, Band Gap Engineering, and Active Crystal Plane Design.

Doping engineering emerges as a contemporary technique to investigate the catalytic performance of MoS2. Cation and anion co-doping appears as an advanced route toward electrocatalytic hydrogen evolution reaction (HER). V and N as dopants in MoS2 (VNMS) build up a strain inside the crystal structure and narrow down the optical band gaps manifesting the shifting of the absorbance band toward lower energy and improved catalytic performance. FE-SEM, HR-TEM, and XRD analysis confirmed that V and N doping decreases agglomeration possibility, particle size, developed strain, and crystal defects during crystal growth. Frequency shift and peak broadening in Raman spectra confirmed the doping induced strain generation in MoS2 leading to the modification of acidic and alkaline HER (51 and 110 mV @ 10 mAcm-2, respectively) performance. The improved donor density in VNMS was confirmed by the Mott-Schottky analysis. Enhanced electrical conductivity and optimized electronic structures facilities H* adsorption/desorption in the catalytically active (001) plane of cation and anion co-doped MoS2.

Deep Learning-Based Spermatogenic Staging Assessment for Hematoxylin and Eosin-Stained Sections of Rat Testes.

In preclinical toxicology studies, a "stage-aware" histopathological evaluation of testes is recognized as the most sensitive method to detect effects on spermatogenesis. A stage-aware evaluation requires the pathologist to be able to identify the different stages of the spermatogenic cycle. Classically, this evaluation has been performed using periodic acid-Schiff (PAS)-stained sections to visualize the morphology of the developing spermatid acrosome, but due to the complexity of the rat spermatogenic cycle and the subtlety of the criteria used to distinguish between the 14 stages of the cycle, staging of tubules is not only time consuming but also requires specialized training and practice to become competent. Using different criteria, based largely on the shape and movement of the elongating spermatids within the tubule and pooling some of the stages, it is possible to stage tubules using routine hematoxylin and eosin (H&E)-stained sections, thereby negating the need for a special PAS stain. These criteria have been used to develop an automated method to identify the stages of the rat spermatogenic cycle in digital images of H&E-stained Wistar rat testes. The algorithm identifies the spermatogenic stage of each tubule, thereby allowing the pathologist to quickly evaluate the testis in a stage-aware manner and rapidly calculate the stage frequencies.

Cobalt Sulfide/Nickel Sulfide Heterostructure Directly Grown on Nickel Foam: An Efficient and Durable Electrocatalyst for Overall Water Splitting Application.

Fabrication of high-performance noble-metal-free bifunctional electrocatalysts for both hydrogen evolution reaction (HER) and oxygen evolution reaction (OER) in water is a promising strategy toward future carbon-neutral economy. Herein, a one-pot hydrothermal synthesis of cobalt sulfide/nickel sulfide heterostructure supported by nickel foam (CoS x/Ni3S2@NF) was performed. The Ni foam acted as the three-dimensional conducting substrate as well as the source of nickel for Ni3S2. The formation of CoS x/Ni3S2@NF was confirmed by X-ray diffraction and X-ray photoelectron spectroscopy. The formation of CoS x/Ni3S2@NF facilitated easy charge transport and showed synergistic electrocatalytic effect toward HER, OER, and overall water splitting in alkaline medium. Remarkably, CoS x/Ni3S2@NF showed catalytic activity comparable with that of benchmarking electrocatalysts Pt/C and RuO2. For CoS x/Ni3S2@NF, overpotentials of 204 and 280 mV were required to achieve current densities of 10 and 20 mA cm-2 for HER and OER, respectively, in 1.0 M KOH solution. A two-electrode system was formulated for overall water splitting reaction, which showed current densities of 10 and 50 mA cm-2 at 1.572 and 1.684 V, respectively. The prepared catalyst exhibited excellent durability in HER and OER catalyzing conditions and also in overall water splitting operation. Therefore, CoS x/Ni3S2@NF could be a promising noble-metal-free electrocatalyst for overall water splitting application.

Investigation of the surface plasmon polariton and electrochemical properties of covalent and non-covalent functionalized reduced graphene oxide.

The surface electronic properties of graphene oxide (GO) were modified through reduction and functionalization. Non-covalent functionalization was found to be superior compared to covalent functionalization due to the formation of few-layer graphene with a low defect content and average crystalline length. Because of the restoration of sp2 hybridization, non-covalently functionalized reduced graphene oxide (rGO) showed a better plasmonic response compared to GO, rGO and covalently functionalized rGO. Due to the available π electrons from the sp2 network of graphene as well as surface functionality, non-covalent functionalized rGO exhibited elevated donor density. Furthermore, due to the synergistic effect of surface electronic properties as well as adsorption and recombination at the barrier, superior charge transfer was achieved at the electrode-electrolyte interface for non-covalent functionalized rGO.

Band Gap Engineering of Boron Nitride by Graphene and Its Application as Positive Electrode Material in Asymmetric Supercapacitor Device.

Nanostructured hexagonal boron nitride (h-BN)/reduced graphene oxide (RGO) composite is prepared by insertion of h-BN into the graphene oxide through hydrothermal reaction. Formation of the super lattice is confirmed by the existence of two separate UV-visible absorption edges corresponding to two different band gaps. The composite materials show enhanced electrical conductivity as compared to the bulk h-BN. A high specific capacitance of ∼824 F g(-1) is achieved at a current density of 4 A g(-1) for the composite in three-electrode electrochemical measurement. The potential window of the composite electrode lies in the range from -0.1 to 0.5 V in 6 M aqueous KOH electrolyte. The operating voltage is increased to 1.4 V in asymmetric supercapacitor (ASC) device where the thermally reduced graphene oxide is used as the negative electrode and the h-BN/RGO composite as the positive electrode. The ASC exhibits a specific capacitance of 145.7 F g(-1) at a current density of 6 A g(-1) and high energy density of 39.6 W h kg(-1) corresponding to a large power density of ∼4200 W kg(-1). Therefore, a facile hydrothermal route is demonstrated for the first time to utilize h-BN-based composite materials as energy storage electrode materials for supercapacitor applications.

Development of high energy density supercapacitor through hydrothermal synthesis of RGO/nano-structured cobalt sulphide composites.

Co9S8/reduced graphene oxide (RGO) composites were prepared on nickel foam substrate through hydrothermal reaction and used directly as supercapacitor electrode. The field emission scanning electron microscopy analysis of the composites showed the formation of Co9S8 nano-rods on the RGO surfaces. The average crystal size of the Co9S8 nano rods grown on the RGO sheets were ∼25-36 nm as calculated from x-ray diffraction analysis. The reduction of graphene oxide (GO) was confirmed by Raman and x-ray photoelectron spectroscopy analysis. The electrical conductivity of the Co9S8/RGO composite was recorded as 1690 S m(-1) at room temperature, which is much higher than that of pure GO further confirming the hydrothermal reduction of GO. Cyclic voltammetry, galvanostatic charge-discharge and electrochemical impedance spectroscopy were investigated to check the electrochemical performances of the Co9S8/RGO composites. The Co9S8/RGO composites supported on nickel foam showed very high specific capacitance (Sc)(1349 F g(-1) at a current density of 2.2 A g(-1)), energy density (68.6 W h kg(-1)) and power density (1319 W kg(-1)) in 6 M KOH electrolyte. The retention in Sc of the composite electrode was found to be ∼96% after 1000 charge-discharge cycles.

Covalent surface modification of chemically derived graphene and its application as supercapacitor electrode material.

A simple and effective method using 6-amino-4-hydroxy-2-naphthalenesulfonic acid (ANS) for the synthesis of water dispersible graphene has been described. Ultraviolet-visible (UV-vis) spectroscopy reveals that ANS-modified reduced graphene oxide (ANS-rGO) obeys Beers law at moderate concentrations. Fourier transform infrared and X-ray photoelectron spectroscopies provide quantitative information regarding the removal of oxygen functional groups from graphene oxide (GO) and the appearance of new functionalities in ANS-rGO. The electrochemical performances of ANS-rGO have been determined by cyclic voltammetry, charge-discharge and electrochemical impedance spectroscopy analysis. Charge-discharge experiments show that ANS-rGO is an outstanding supercapacitor electrode material due to its high specific capacitance (375 F g(-1) at a current density of 1.3 A g(-1)) and very good electrochemical cyclic stability (∼97.5% retention in specific capacitance after 1000 charge-discharge cycles). ANS-rGO exhibits promising characteristics with a very high power density (1328 W kg(-1)) and energy density (213 W h kg(-1)).