Assessment of glomerular morphological patterns by deep learning algorithms

Background Compilation of different morphological lesion signatures is characteristic of renal pathology. Previous studies have documented the potential value of artificial intelligence (AI) in recognizing relatively clear-cut glomerular structures and patterns, such as segmental or global sclerosis or mesangial hypercellularity. This study aimed to test the capacity of deep learning algorithms to recognize complex glomerular structural changes that reflect common diagnostic dilemmas in nephropathology. Methods For this purpose, we defined nine classes of glomerular morphological patterns and trained twelve convolutional neuronal network (CNN) models on these. The two-step training process was done on a first dataset defined by an expert nephropathologist (12,253 images) and a second consensus dataset (11,142 images) defined by three experts in the field. Results The efficacy of CNN training was evaluated using another set with 180 consensus images, showing convincingly good classification results (kappa-values 0.838–0.938). Furthermore, we elucidated the image areas decisive for CNN-based decision making by class activation maps. Finally, we demonstrated that the algorithm could decipher glomerular disease patterns coinciding in a single glomerulus (e.g. necrosis along with mesangial and endocapillary hypercellularity). Conclusions In summary, our model, focusing on glomerular lesions detectable by conventional microscopy, is the first sui generis to deploy deep learning as a reliable and promising tool in recognition of even discrete and/or overlapping morphological changes. Our results provide a stimulus for ongoing projects that integrate further input levels next to morphology (such as immunohistochemistry, electron microscopy, and clinical information) to develop a novel tool applicable for routine diagnostic nephropathology.

Expert opinion on current and emerging treatments in dermatophytosis

<p class="abstract">Dermatophytosis continues to be a worldwide public health problem, predominantly in developing countries like India. Early diagnosis and appropriate management are imperative to enhance patient outcomes and improve quality of life of individuals with dermatophytosis. Multiple focused group discussions involving 76 dermatologists across 36 cities in India were conducted to provide a consensus clinical viewpoint of expert dermatologists to gain insights toward effective diagnosis and management of Indian subjects with dermatophytosis. These discussions mainly aimed at reviewing current literature on prevalence, etiology, diagnosis and management of dermatophytosis and highlighting variations in diagnostic and treatment approaches in routine clinical practice. The current article summarizes the experts’ clinical viewpoint on overall management of dermatophytosis. Diagnosis of dermatophytosis involves clinical observation, microscopic examination and dermoscopy. Molecular techniques have certain advantages over conventional microscopy and culture methods but are associated with issues of cost and technique complexity. Oral itraconazole 200 mg–400 mg daily and terbinafine 500 mg/day could be considered for recalcitrant tinea infections. Topical azoles like luliconazole, sertaconazole, and terbinafine could be beneficial. A combination of oral and topical antifungal drugs is effective in patients with steroid-modified and difficult-to-treat tinea infections. Also, patient counselling and use of adjunctive therapies like antihistamines, retinoids, and moisturizers are essential for managing tinea infections. </p><p class="abstract"> </p>

Digital Pathology Using Primary Case Sign-Out

The applicability of the identified findings and the potential impact on patient outcomes for any individual diagnostic setting was unclear. In the majority of the identified studies, the authors reported diagnostic accuracy and clinical utility outcomes that supported digital pathology systems as a valuable diagnostic modality, comparable to conventional microscopy. These studies lacked statistical power calculations, making the accuracy of these statements unclear. One systematic review and 1 diagnostic study reported clinical utility outcomes of digital pathology. This evidence supported digital pathology using primary case sign-out for accurate prognosis of patient outcomes; however, the clinical utility compared to conventional microscopy was unclear in the identified evidence. One systematic review and 13 diagnostic cohort studies reported on the diagnostic accuracy of whole slide image (WSI). The identified outcomes indicated that WSI is a valuable diagnostic modality; however, a large range of diagnostic accuracy in different settings, and a lack of clear statistical power in all studies make comparator conclusions to conventional microscopy unclear. One systematic review and 4 diagnostic cohort studies reported diagnostic areas that can present challenges for a digital pathology implementation, the most common being the interpretation and grading of dysplasia. One identified systematic review stressed the importance of whole-system validation to identify strengths and weaknesses of specific digital pathology implementations. The range of diagnostic accuracy across studies also indicated that implementation of digital pathology primary case sign-out systems is associated with unclear diagnostic accuracy until appropriately validated. No relevant cost-effectiveness evidence for digital pathology using primary case sign-out was identified.

Ptychography Reduces Spectral Distortions Intrinsic to Conventional Zone-Plate-Based X-Ray Spectromicroscopy

Scanning transmission X-ray microscopy is a powerful method for mapping chemical phases in nano-materials. The point spread function (PSF) of a conventional zone-plate-based microscope limits the achievable spatial resolution and also results in spatially resolved spectra that do not accurately reflect the spatial heterogeneity of the samples when the scale of the detail approaches the probe size. X-ray ptychography, a coherent-scattering-based imaging scheme that effectively removes the probe from the image data, returns accurate spectra from regions smaller than the probe size. We show through simulation how the long tails on the PSF of an x-ray optic can cause spectral distortion near a boundary between two spectrally distinct regions. The resulting apparent point spectra can appear mixed, with the species on one side of the boundary seeming to be present on the other even at a distance from the boundary equal to several times the spatial resolution. We further demonstrate the effect experimentally and show that ptychographic microscopy can return the expected spectra from a model system, whereas conventional microscopy does not.

Videoconference microscopy is a reliable alternative to conventional microscopy in the evaluation of Barrett’s esophagus: Zooming into a new era

Telepathology, practicing pathology from a distance, allows experts to review cases without the need to transfer glass slides. Due to significant intra- and inter-observer variabilities in the histological evaluation of Barrett’s esophagus (BE), current guidelines recommend expert consultation in cases of dysplasia. We aimed to determine whether telepathology using microscope videoconferencing can be reliably used for evaluation of BE. Biopsies from 62 patients with endoscopic findings of salmon colored mucosa extending ≥1 cm proximal to the gastroesophageal junction were randomly selected to represent benign esophagus, non-dysplastic BE, low-grade dysplasia, high-grade dysplasia, and adenocarcinoma. Three gastrointestinal-trained pathologists reviewed the cases via videoconference microscopy followed by conventional microscopy. Intra-observer and pairwise inter-observer agreements between the conventional microscopy and videoconference methodologies were calculated for each of the three pathologists using Fleiss-Cohen weighted kappa (K) analysis. The intra-observer agreement for each pathologist’s assessment of videoconference microscopy and glass slide readings showed very good reliability (K = 0.94, 95% confidence interval = 0.89–0.99; 0.88, 95% confidence interval = 0.79–0.98; 0.93, 95% confidence interval = 0.90–0.97). Mean pairwise inter-observer agreement was 0.90 for videoconference and 0.91 for conventional microscopy. Diagnosis and grading of BE using videoconference microscopy show similar reliability as conventional microscopy. Based on our findings, we propose that videoconferencing pathology is a valid instrument for evaluating BE.

Current Challenges in Deciphering Sutton Nevi—Literature Review and Personal Experience

Halo nevi, known as leukoderma acquisitum centrifugum, Sutton nevus, leukopigmentary nevus, perinevoid vitiligo, or perinevoid leukoderma, together with vitiligo and melanoma-associated hypopigmentation, belong to the group of dermatoses designated as immunological leukodermas. The etiology and pathogenesis of halo nevi has not been fully elucidated. There are several mechanisms through which a lymphocytic infiltrate can induce tumoral regression. In this review, we aimed to update the knowledge about Sutton nevi starting with the clinical appearance and dermoscopic features, continuing with information regarding conventional microscopy, immunohistochemistry, and the immunological mechanisms responsible for the occurrence of halo nevi. We also included in the article original unpublished results when discussing dermoscopic, pathologic and immunohistochemical results in halo nevi. Sutton nevi are valuable models for studying antitumor reactions that the human body can generate. The slow and effective mechanism against a melanocytic skin tumor can teach us important lessons about both autoimmune diseases and anticancer defenses.

Versatile, do-it-yourself, low-cost spinning disk confocal microscope

Confocal microscopy is an invaluable tool for 3D imaging of biological specimens, however, accessibility is often limited to core facilities due to the high cost of the hardware. We describe an inexpensive do-it-yourself (DIY) spinning disk confocal microscope (SDCM) module based on a commercially fabricated chromium photomask that can be added on to a laser-illuminated epifluorescence microscope. The SDCM achieves strong performance across a wide wavelength range (~400-800 nm) as demonstrated through a series of biological imaging applications that include conventional microscopy (immunofluorescence, small-molecule stains, and fluorescence in situ hybridization) and super-resolution microscopy (single-molecule localization microscopy and expansion microscopy). This low-cost and simple DIY SDCM is well-documented and should help increase accessibility to confocal microscopy for researchers.

Super-Resolution Imaging with Graphene

Super-resolution optical imaging is a consistent research hotspot for promoting studies in nanotechnology and biotechnology due to its capability of overcoming the diffraction limit, which is an intrinsic obstacle in pursuing higher resolution for conventional microscopy techniques. In the past few decades, a great number of techniques in this research domain have been theoretically proposed and experimentally demonstrated. Graphene, a special two-dimensional material, has become the most meritorious candidate and attracted incredible attention in high-resolution imaging domain due to its distinctive properties. In this article, the working principle of graphene-assisted imaging devices is summarized, and recent advances of super-resolution optical imaging based on graphene are reviewed for both near-field and far-field applications.

Molecular Tools for Diagnosis and Surveillance of Soil-Transmitted Helminths in Endemic Areas

Soil-transmitted helminths (STH) including the hookworms Necator americanus and Ancylostoma spp., Ascaris lumbricoides, and Trichuris trichiura affect over 1.5 billion people worldwide and are estimated to have caused 1.9 million disability-adjusted life years (DALYs). With the concerted effort in expanding and improving targeted mass drug administration (MDA) programs over the past decade, along with decreasing prevalence, infections in several endemic areas tend to be of low intensity. Conventional microscopy-based methods recommended for the detection of STH in parasitological surveys have been shown to be less sensitive in these low-intensity settings. As communities progress towards STH elimination through MDA and improved sanitation, there is a pressing need for highly sensitive techniques that detect the true prevalence of STH to evaluate the effectiveness of ongoing programs and interventions. Molecular methods that involve analysis of DNA rather than the morphology of the organism are highly sensitive and specific, allowing for both quantitation and species discrimination. The following review discusses different sample collection strategies, pre-processing steps, DNA extraction platforms, and nucleic acid detection methods available for diagnosis and surveillance of STH. We have contrasted the utility of these molecular tools against conventional microscopy-based methods currently used in most endemic settings. While the detection methods are primarily qPCR based, several newer technologies have also become available along with automation and increased throughput, making these molecular tools increasingly cost-effective and potentially amenable for use in low-resource settings.