Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learning.

Studies have shown that colorectal cancer prognosis can be predicted by deep learning-based analysis of histological tissue sections of the primary tumor. So far, this has been achieved using a binary prediction. Survival curves might contain more detailed information and thus enable a more fine-grained risk prediction. Therefore, we established survival curve-based CRC survival predictors and benchmarked them against standard binary survival predictors, comparing their performance extensively on the clinical high and low risk subsets of one internal and three external cohorts. Survival curve-based risk prediction achieved a very similar risk stratification to binary risk prediction for this task. Exchanging other components of the pipeline, namely input tissue and feature extractor, had largely identical effects on model performance independently of the type of risk prediction. An ensemble of all survival curve-based models exhibited a more robust performance, as did a similar ensemble based on binary risk prediction. Patients could be further stratified within clinical risk groups. However, performance still varied across cohorts, indicating limited generalization of all investigated image analysis pipelines, whereas models using clinical data performed robustly on all cohorts.

Development of a bioactive tunable hyaluronic-protein bioconjugate hydrogel for tissue regenerative applications.

Every year, there are approximately 500 000 peripheral nerve injury (PNI) procedures due to trauma in the US alone. Autologous and acellular nerve grafts are among current clinical repair options; however, they are limited largely by the high costs associated with donor nerve tissue harvesting and implant processing, respectively. Therefore, there is a clinical need for an off-the-shelf nerve graft that can recapitulate the native microenvironment of the nerve. In our previous work, we created a hydrogel scaffold that incorporates mechanical and biological cues that mimic the peripheral nerve microenvironment using chemically modified hyaluronic acid (HA). However, with our previous work, the degradation profile and cell adhesivity was not ideal for tissue regeneration, in particular, peripheral nerve regeneration. To improve our previous hydrogel, HA was conjugated with fibrinogen using Michael-addition to assist in cell adhesion and hydrogel degradability. The addition of the fibrinogen linker was found to contribute to faster scaffold degradation via active enzymatic breakdown, compared to HA alone. Additionally, cell count and metabolic activity was significantly higher on HA conjugated fibrinogen compared previous hydrogel formulations. This manuscript discusses the various techniques deployed to characterize our new modified HA fibrinogen chemistry physically, mechanically, and biologically. This work addresses the aforementioned concerns by incorporating controllable degradability and increased cell adhesivity while maintaining incorporation of hyaluronic acid, paving the pathway for use in a variety of applications as a multi-purpose tissue engineering platform.

Small-diameter artery decellularization: Effects of anionic detergent concentration and treatment duration on porcine internal thoracic arteries.

Engineered replacement materials have tremendous potential for vascular applications where over 400,000 damaged and diseased blood vessels are replaced annually in the United States alone. Unlike large diameter blood vessels, which are effectively replaced by synthetic materials, prosthetic small-diameter vessels are prone to early failure, restenosis, and reintervention surgery. We investigated the differential response of varying 0%-6% sodium dodecyl sulfate and sodium deoxycholate anionic detergent concentrations after 24 and 72 h in the presence of DNase using biochemical, histological, and biaxial mechanical analyses to optimize the decellularization process for xenogeneic vascular tissue sources, specifically the porcine internal thoracic artery (ITA). Detergent concentrations greater than 1% were successful at removing cytoplasmic and cell surface proteins but not DNA content after 24 h. A progressive increase in porosity and decrease in glycosaminoglycan (GAG) content was observed with detergent concentration. Augmented porosity was likely due to the removal of both cells and GAGs and could influence recellularization strategies. The treatment duration on the other hand, significantly improved decellularization by reducing DNA content to trace amounts after 72 h. Prolonged treatment times reduced laminin content and influenced the vessel's mechanical behavior in terms of altered circumferential stress and stretch while further increasing porosity. Collectively, DNase with 1% detergent for 72 h provided an effective and efficient decellularization strategy to be employed in the preparation of porcine ITAs as bypass graft scaffolding materials with minor biomechanical and histological penalties.

Roles of Exosomes in Cardiac Fibroblast Activation and Fibrosis.

Alterations in the accumulation and composition of the extracellular matrix are part of the normal tissue repair process. During fibrosis, this process becomes dysregulated and excessive extracellular matrix alters the biomechanical properties and function of tissues involved. Historically fibrosis was thought to be progressive and irreversible; however, studies suggest that fibrosis is a dynamic process whose progression can be stopped and even reversed. This realization has led to an enhanced pursuit of therapeutic agents targeting fibrosis and extracellular matrix-producing cells. In many organs, fibroblasts are the primary cells that produce the extracellular matrix. In response to diverse mechanical and biochemical stimuli, these cells are activated or transdifferentiate into specialized cells termed myofibroblasts that have an enhanced capacity to produce extracellular matrix. It is clear that interactions between diverse cells of the heart are able to modulate fibroblast activation and fibrosis. Exosomes are a form of extracellular vesicle that play an important role in intercellular communication via the cargo that they deliver to target cells. While relatively recently discovered, exosomes have been demonstrated to play important positive and negative roles in the regulation of fibroblast activation and tissue fibrosis. These roles as well as efforts to engineer exosomes as therapeutic tools will be discussed.

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.

Integrating Patient Data Into Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review.

BACKGROUND: Recent years have been witnessing a substantial improvement in the accuracy of skin cancer classification using convolutional neural networks (CNNs). CNNs perform on par with or better than dermatologists with respect to the classification tasks of single images. However, in clinical practice, dermatologists also use other patient data beyond the visual aspects present in a digitized image, further increasing their diagnostic accuracy. Several pilot studies have recently investigated the effects of integrating different subtypes of patient data into CNN-based skin cancer classifiers. OBJECTIVE: This systematic review focuses on the current research investigating the impact of merging information from image features and patient data on the performance of CNN-based skin cancer image classification. This study aims to explore the potential in this field of research by evaluating the types of patient data used, the ways in which the nonimage data are encoded and merged with the image features, and the impact of the integration on the classifier performance. METHODS: Google Scholar, PubMed, MEDLINE, and ScienceDirect were screened for peer-reviewed studies published in English that dealt with the integration of patient data within a CNN-based skin cancer classification. The search terms skin cancer classification, convolutional neural network(s), deep learning, lesions, melanoma, metadata, clinical information, and patient data were combined. RESULTS: A total of 11 publications fulfilled the inclusion criteria. All of them reported an overall improvement in different skin lesion classification tasks with patient data integration. The most commonly used patient data were age, sex, and lesion location. The patient data were mostly one-hot encoded. There were differences in the complexity that the encoded patient data were processed with regarding deep learning methods before and after fusing them with the image features for a combined classifier. CONCLUSIONS: This study indicates the potential benefits of integrating patient data into CNN-based diagnostic algorithms. However, how exactly the individual patient data enhance classification performance, especially in the case of multiclass classification problems, is still unclear. Moreover, a substantial fraction of patient data used by dermatologists remains to be analyzed in the context of CNN-based skin cancer classification. Further exploratory analyses in this promising field may optimize patient data integration into CNN-based skin cancer diagnostics for patients' benefits.

Combining CNN-based histologic whole slide image analysis and patient data to improve skin cancer classification.

BACKGROUND: Clinicians and pathologists traditionally use patient data in addition to clinical examination to support their diagnoses. OBJECTIVES: We investigated whether a combination of histologic whole slides image (WSI) analysis based on convolutional neural networks (CNNs) and commonly available patient data (age, sex and anatomical site of the lesion) in a binary melanoma/nevus classification task could increase the performance compared with CNNs alone. METHODS: We used 431 WSIs from two different laboratories and analysed the performance of classifiers that used the image or patient data individually or three common fusion techniques. Furthermore, we tested a naive combination of patient data and an image classifier: for cases interpreted as 'uncertain' (CNN output score <0.7), the decision of the CNN was replaced by the decision of the patient data classifier. RESULTS: The CNN on its own achieved the best performance (mean ± standard deviation of five individual runs) with AUROC of 92.30% ± 0.23% and balanced accuracy of 83.17% ± 0.38%. While the classification performance was not significantly improved in general by any of the tested fusions, naive strategy of replacing the image classifier with the patient data classifier on slides with low output scores improved balanced accuracy to 86.72% ± 0.36%. CONCLUSION: In most cases, the CNN on its own was so accurate that patient data integration did not provide any benefit. However, incorporating patient data for lesions that were classified by the CNN with low 'confidence' improved balanced accuracy.

Influence of testing parameters on the load-bearing capacity of prosthetic materials used for fixed dental prosthesis: A systematic review / Influência de parâmetros de testes na capacidade de suporte de carga de materiais protéticos utilizados para prótese dentária fixa: uma revisão sistemática

Objective: The aim of this study was to systematically review the literature to assess static fracture strength tests applied for fixed dental prostheses (FDPs) and analyze the impact of periodontal ligament (PDL) simulation on the fracture strength. Material and Methods: Original scientific papers published in MEDLINE (PubMed) database between 01/01/1981 and 10/06/2018 were included in this systematic review. The following MeSH terms, search terms, and their combinations were used:"Dentistry", "Fracture Strength", "Fracture Resistance", "Fixed Dental Prosthesis", "Fixed Partial Denture", "Mechanical Loading". Two reviewers performed screening and analyzed the data. Only the in vitro studies that reported on load-bearing capacity of only FDP materials where mean or median values reported in Newnton (N) were included. Results: The selection process resulted in the 57 studies. In total, 36 articles were identified related to allceramics, 10 were fiber reinforced composite resin (FRC), 8 of composite resin (C) and 5 of metalceramic. As for clinical indications, 3 and 4-unit FDPs were more commonly studied (n=32; with PDL=21, without PDL=11), followed by single crowns (n=13; with PDL=3, without PDL=10), and inlay-retained and cantilever FDPs (n=12; with PDL=8, without PDL=4). Conclusion: An inclination for decreased static fracture strength could be observed with the simulation of PDL but due to insufficient data this could not be generalized for all materials used for FDPs (AU)

Objetivo: O objetivo deste estudo foi revisar sistematicamente a literatura para avaliar os testes de força de fratura estática aplicados para próteses dentárias fixas (FDPs) e analisar o impacto da simulação do ligamento periodontal (PDL) na resistência à fratura. Material e Métodos: Artigos científicos originais publicados na base de dados MEDLINE (PubMed) entre 01/01/1981 e 10/06/2018 foram incluídos nesta revisão sistemática. Foram utilizados os seguintes termos MeSH, termos de pesquisa e suas combinações: "Dentistry", "Fracture Strength", "Fracture Resistance", "Fixed Dental Prosthesis", "Fixed Partial Denture", "Mechanical Loading". Dois revisores realizaram a triagem e analisaram os dados. Apenas os estudos in vitro que reportaram a capacidade de suporte de carga de FDP, com os valores das médias ou medianas relatados em Newton (N) foram incluídos. Resultados: O processo de seleção resultou em 57 estudos. No total, 36 artigos foram identificados relacionados à restaurações totalmente cerâmicas, 10 em resina composta reforçada com fibra (FRC), 8 em resina composta (C) e 5 em metalocerâmica. Quanto às indicações clínicas, os PDF de 3 e 4 unidades foram mais comumente estudados (n = 32; com PDL = 21, sem PDL = 11), seguidos de coroas isoladas (n = 13; com PDL = 3, sem PDL = 10) e FDPs retidas por inlays e com cantilever (n = 12; com PDL = 8, sem PDL = 4). Conclusão: Uma inclinação para a diminuição da resistência à fratura estática pôde ser observada com a simulação do PDL, mas devido a dados insuficientes, isso não pôde ser generalizado para todos os materiais utilizados para as FDPs (AU)

[The Munich Attachment and Effectiveness Study: Study Design and a Case Example]. / Münchner Bindungs- und Wirkungsforschungsprojekt: Studiendesign und ein Einzelfall.

OBJECTIVES: The "Munich Attachment and Effectiveness Study" is a prospective psychotherapy study examining process and outcome of psychoanalytic psychotherapies. The study design and results are exemplified in a single case. METHODS: At 6 points in time audio-taped and transcribed therapy sessions are evaluated using process instruments (e. g. Psychotherapy Process Q-Set PQS) and interviews (e. g. Operationalized Psychodynamic Diagnostics OPD, Heidelberg Structural Change Scale HSCS, Adult Attachment Interview AAI). RESULTS: In the single case, findings from the psychotherapeutic process (e. g. "therapist is empathic" according to PQS) complement the achieved changes. 5 HSCS problem foci reached level of "restructuring", on the Reflective Functioning Scale a marked change of RF took place and the attachment classification changed over time. CONCLUSIONS: The instruments employed in this study corresponded well in assessing change processes in spite of differing theoretical background.