Artificial intelligence to predict oncological outcome directly from hematoxylin and eosin-stained slides in urology.

INTRODUCTION: Artificial intelligence (AI) has been successfully applied for automatic tumor detection and grading in histopathological image analysis in urologic oncology. The aim of this review was to assess the applicability of these approaches in image-based oncological outcome prediction. EVIDENCE ACQUISITION: A systematic literature search was conducted using the databases MEDLINE through PubMed and Web of Science up to April 20, 2021. Studies investigating AI approaches to determine the risk of recurrence, metastasis, or survival directly from H&E-stained tissue sections in prostate, renal cell or urothelial carcinoma were included. Characteristics of the AI approach and performance metrics were extracted and summarized. Risk of bias (RoB) was assessed using the PROBAST tool. EVIDENCE SYNTHESIS: 16 studies yielding a total of 6658 patients and reporting on 17 outcome predictions were included. Six studies focused on renal cell, six on prostate and three on urothelial carcinoma while one study investigated renal cell and urothelial carcinoma. Handcrafted feature extraction was used in five, a convolutional neural network (CNN) in six and a deep feature extraction in four studies. One study compared a CNN with handcrafted feature extraction. In seven outcome predictions, a multivariable comparison with clinicopathological parameters was reported. Five of them showed statistically significant hazard ratios for the AI's model's-prediction. However, RoB was high in 15 outcome predictions and unclear in two. CONCLUSIONS: The included studies are promising but predominantly early pilot studies, therefore primarily highlighting the potential of AI approaches. Additional well-designed studies are needed to assess the actual clinical applicability.

Integration of deep learning-based image analysis and genomic data in cancer pathology: A systematic review.

BACKGROUND: Over the past decade, the development of molecular high-throughput methods (omics) increased rapidly and provided new insights for cancer research. In parallel, deep learning approaches revealed the enormous potential for medical image analysis, especially in digital pathology. Combining image and omics data with deep learning tools may enable the discovery of new cancer biomarkers and a more precise prediction of patient prognosis. This systematic review addresses different multimodal fusion methods of convolutional neural network-based image analyses with omics data, focussing on the impact of data combination on the classification performance. METHODS: PubMed was screened for peer-reviewed articles published in English between January 2015 and June 2021 by two independent researchers. Search terms related to deep learning, digital pathology, omics, and multimodal fusion were combined. RESULTS: We identified a total of 11 studies meeting the inclusion criteria, namely studies that used convolutional neural networks for haematoxylin and eosin image analysis of patients with cancer in combination with integrated omics data. Publications were categorised according to their endpoints: 7 studies focused on survival analysis and 4 studies on prediction of cancer subtypes, malignancy or microsatellite instability with spatial analysis. CONCLUSIONS: Image-based classifiers already show high performances in prognostic and predictive cancer diagnostics. The integration of omics data led to improved performance in all studies described here. However, these are very early studies that still require external validation to demonstrate their generalisability and robustness. Further and more comprehensive studies with larger sample sizes are needed to evaluate performance and determine clinical benefits.

Deep learning can predict lymph node status directly from histology in colorectal cancer.

BACKGROUND: Lymph node status is a prognostic marker and strongly influences therapeutic decisions in colorectal cancer (CRC). OBJECTIVES: The objective of the study is to investigate whether image features extracted by a deep learning model from routine histological slides and/or clinical data can be used to predict CRC lymph node metastasis (LNM). METHODS: Using histological whole slide images (WSIs) of primary tumours of 2431 patients in the DACHS cohort, we trained a convolutional neural network to predict LNM. In parallel, we used clinical data derived from the same cases in logistic regression analyses. Subsequently, the slide-based artificial intelligence predictor (SBAIP) score was included in the regression. WSIs and data from 582 patients of the TCGA cohort were used as the external test set. RESULTS: On the internal test set, the SBAIP achieved an area under receiver operating characteristic (AUROC) of 71.0%, the clinical classifier achieved an AUROC of 67.0% and a combination of the two classifiers yielded an improvement to 74.1%. Whereas the clinical classifier's performance remained stable on the TCGA set, performance of the SBAIP dropped to an AUROC of 61.2%. Performance of the clinical classifier depended strongly on the T stage. CONCLUSION: Deep learning-based image analysis may help predict LNM of patients with CRC using routine histological slides. Combination with clinical data such as T stage might be useful. Strategies to increase performance of the SBAIP on external images should be investigated.

Gastrointestinal cancer classification and prognostication from histology using deep learning: Systematic review.

BACKGROUND: Gastrointestinal cancers account for approximately 20% of all cancer diagnoses and are responsible for 22.5% of cancer deaths worldwide. Artificial intelligence-based diagnostic support systems, in particular convolutional neural network (CNN)-based image analysis tools, have shown great potential in medical computer vision. In this systematic review, we summarise recent studies reporting CNN-based approaches for digital biomarkers for characterization and prognostication of gastrointestinal cancer pathology. METHODS: Pubmed and Medline were screened for peer-reviewed papers dealing with CNN-based gastrointestinal cancer analyses from histological slides, published between 2015 and 2020.Seven hundred and ninety titles and abstracts were screened, and 58 full-text articles were assessed for eligibility. RESULTS: Sixteen publications fulfilled our inclusion criteria dealing with tumor or precursor lesion characterization or prognostic and predictive biomarkers: 14 studies on colorectal or rectal cancer, three studies on gastric cancer and none on esophageal cancer. These studies were categorised according to their end-points: polyp characterization, tumor characterization and patient outcome. Regarding the translation into clinical practice, we identified several studies demonstrating generalization of the classifier with external tests and comparisons with pathologists, but none presenting clinical implementation. CONCLUSIONS: Results of recent studies on CNN-based image analysis in gastrointestinal cancer pathology are promising, but studies were conducted in observational and retrospective settings. Large-scale trials are needed to assess performance and predict clinical usefulness. Furthermore, large-scale trials are required for approval of CNN-based prediction models as medical devices.

Primeira transição do cuidado hospitalar para domiciliar da criança com câncer: orientações da equipe multiprofissional / Primera transición de la atención hospitalaria a la atención domiciliaria de niños con cáncer: directrices del equipo multiprofesional / First transition from hospital care to home care for children with cancer: guidelines of the multi-professional team

Resumo Objetivo Descrever as orientações para a primeira transição do cuidado hospitalar para o domiciliar da criança com câncer sob a ótica da equipe multiprofissional. Método Estudo de abordagem qualitativa do tipo exploratório-descritivo realizado em um Hospital Universitário do Sul do Brasil, com nove profissionais da equipe multiprofissional de uma unidade de internação de oncologia pediátrica entre julho e setembro de 2018. Foram realizadas entrevistas semiestruturadas submetidas a análise de conteúdo temática. Resultados Foram identificadas três categorias temáticas: planejamento multiprofissional para a alta hospitalar da criança com câncer e sua família; a equipe multiprofissional frente ao processo de alta hospitalar; orientações para a primeira alta hospitalar a famílias de crianças com câncer recém diagnosticado. Conclusão/implicações para prática o planejamento e sistematização multiprofissional para as orientações da primeira alta hospitalar são fundamentais para contemplar as necessidades do paciente e suas famílias, tendo o enfermeiro papel central. Mostram-se necessárias melhorias nesse processo.

Resumen Objetivo Describir las principales pautas para la primera transición de la atención hospitalaria al contexto domiciliario de niños con cáncer bajo la óptica del equipo multidisciplinario. Método Estudio cualitativo de tipo exploratorio-descriptivo realizado en un hospital universitario en el sur de Brasil, con nueve profesionales del equipo multiprofesional de una unidad de hospitalización de oncología pediátrica entre julio y septiembre de 2018. Se realizaron entrevistas semiestructuradas que han sido sometidas a análisis de contenido temático. Resultados Se identificaron tres categorías temáticas: planificación multiprofesional para el alta hospitalaria de niños con cáncer y sus familias; el equipo multidisciplinario frente al proceso de alta hospitalaria; pautas para el primer alta hospitalaria para familias de niños con cáncer recién diagnosticado. Conclusión/implicaciones para la práctica la planificación y sistematización multiprofesional en relación a las pautas del primer alta hospitalaria son esenciales para contemplar las necesidades del paciente y sus familias, teniendo la enfermera un papel central. Es necesario implementar mejoras en este proceso.

Abstract Objective To describe the guidelines for the first transition from hospital care to home care of children with cancer from the multi-professional team's perspective. Method A qualitative exploratory-descriptive study conducted in a University Hospital in southern Brazil by nine professionals from the multi-professional team of a pediatric oncology inpatient unit between July and September 2018. Semi-structured interviews were carried out and submitted to thematic content analysis. Results Three theme categories were identified, namely: multi-professional planning for hospital discharge of children with cancer and their family; the multi-professional team facing the discharge process; guidelines for the first hospital discharge for families of children with newly diagnosed cancer. Conclusion/practical implications multi-professional planning and systematization for the guidelines of the first hospital discharge are essential to deliberate the needs of the patient and their families, with the nurse having a central role. Improvements are needed in this process.

The PKA-C3 catalytic subunit is required in two pairs of interneurons for successful mating of Drosophila.

Protein kinase A (PKA) has been shown to play a role in a plethora of cellular processes ranging from development to memory formation. Its activity is mediated by the catalytic subunits whereby many species express several paralogs. Drosophila encodes three catalytic subunits (PKA-C1-3) and whereas PKA-C1 has been well studied, the functions of the other two subunits were unknown. PKA-C3 is the orthologue of mammalian PRKX/Pkare and they are structurally more closely related to each other than to other catalytic subunits within their species. PRKX is expressed in the nervous system in mice but its function is also unknown. We now show that the loss of PKA-C3 in Drosophila causes copulation defects, though the flies are active and show no defects in other courtship behaviours. This phenotype is specifically due to the loss of PKA-C3 because PKA-C1 cannot replace PKA-C3. PKA-C3 is expressed in two pairs of interneurons that send projections to the ventro-lateral protocerebrum and the mushroom bodies and that synapse onto motor neurons in the ventral nerve cord. Rescue experiments show that expression of PKA-C3 in these interneurons is sufficient for copulation, suggesting a role in relaying information from the sensory system to motor neurons to initiate copulation.

Visual Working Memory Requires Permissive and Instructive NO/cGMP Signaling at Presynapses in the Drosophila Central Brain.

The gaseous second messenger nitric oxide (NO) has been shown to regulate memory formation by activating retrograde signaling cascades from post- to presynapse that involve cyclic guanosine monophosphate (cGMP) production to induce synaptic plasticity and transcriptional changes. In this study, we analyzed the role of NO in the formation of a visual working memory that lasts only a few seconds. This memory is encoded in a subset of ring neurons that form the ellipsoid body in the Drosophila brain. Using genetic and pharmacological manipulations, we show that NO signaling is required for cGMP-mediated CREB activation, leading to the expression of competence factors like the synaptic homer protein. Interestingly, this cell-autonomous function can also be fulfilled by hydrogen sulfide (H2S) through a converging pathway, revealing for the first time that endogenously produced H2S has a role in memory processes. Notably, the NO synthase is strictly localized to the axonal output branches of the ring neurons, and this localization seems to be necessary for a second, phasic role of NO signaling. We provide evidence for a model where NO modulates the opening of cGMP-regulated cation channels to encode a short-term memory trace. Local production of NO/cGMP in restricted branches of ring neurons seems to represent the engram for objects, and comparing signal levels between individual ring neurons is used to orient the fly during search behavior. Due to its short half-life, NO seems to be a uniquely suited second messenger to encode working memories that have to be restricted in their duration.

The visual orientation memory of Drosophila requires Foraging (PKG) upstream of Ignorant (RSK2) in ring neurons of the central complex.

Orientation and navigation in a complex environment requires path planning and recall to exert goal-driven behavior. Walking Drosophila flies possess a visual orientation memory for attractive targets which is localized in the central complex of the adult brain. Here we show that this type of working memory requires the cGMP-dependent protein kinase encoded by the foraging gene in just one type of ellipsoid-body ring neurons. Moreover, genetic and epistatic interaction studies provide evidence that Foraging functions upstream of the Ignorant Ribosomal-S6 Kinase 2, thus revealing a novel neuronal signaling pathway necessary for this type of memory in Drosophila.