An interpretable machine learning system for colorectal cancer diagnosis from pathology slides.

Considering the profound transformation affecting pathology practice, we aimed to develop a scalable artificial intelligence (AI) system to diagnose colorectal cancer from whole-slide images (WSI). For this, we propose a deep learning (DL) system that learns from weak labels, a sampling strategy that reduces the number of training samples by a factor of six without compromising performance, an approach to leverage a small subset of fully annotated samples, and a prototype with explainable predictions, active learning features and parallelisation. Noting some problems in the literature, this study is conducted with one of the largest WSI colorectal samples dataset with approximately 10,500 WSIs. Of these samples, 900 are testing samples. Furthermore, the robustness of the proposed method is assessed with two additional external datasets (TCGA and PAIP) and a dataset of samples collected directly from the proposed prototype. Our proposed method predicts, for the patch-based tiles, a class based on the severity of the dysplasia and uses that information to classify the whole slide. It is trained with an interpretable mixed-supervision scheme to leverage the domain knowledge introduced by pathologists through spatial annotations. The mixed-supervision scheme allowed for an intelligent sampling strategy effectively evaluated in several different scenarios without compromising the performance. On the internal dataset, the method shows an accuracy of 93.44% and a sensitivity between positive (low-grade and high-grade dysplasia) and non-neoplastic samples of 0.996. On the external test samples varied with TCGA being the most challenging dataset with an overall accuracy of 84.91% and a sensitivity of 0.996.

ASSESSMENT OF RISK FACTORS FOR SURGERY TREATMENT OF CROHN'S DISEASE: A HOSPITAL COHORT.

BACKGROUND: New therapies have revolutionized the treatment of Crohn's disease (CD), but in some countries, the surgery rate has not changed, the frequency of emergency surgery is underestimated, and surgical risk is poorly studied. AIMS: The aim of this study was to identify risk factors and clinical indications for primary surgery in CD patients at the tertiary hospital. METHODS: This was a retrospective cohort of a prospectively collected database of 107 patients with CD from 2015 to 2021. The main outcomes were the incidence of surgery treatment, types of procedures performed, surgical recurrence, surgery free time, and risk factors for surgery. RESULTS: Surgical intervention was performed in 54.2% of the patients, and most of the procedures were emergency surgeries (68.9%). The elective procedures (31.1%) were performed over 11 years after diagnosis. The main indications for surgery were ileal stricture (34.5%) and anorectal fistulas (20.7%). The most frequent procedure was enterectomy (24.1%). Recurrence surgery was most common in emergency procedures (OR 2.1; 95%CI 1.6-6.6). Montreal phenotype L1 stricture behavior (RR 1.3; 95%CI 1.0-1.8, p=0.04) and perianal disease (RR 1.43; 95%CI 1.2-1.7) increased the risk of emergency surgeries. The multiple linear regression showed age at diagnosis as a risk factor for surgery (p=0.004). The study of surgery free time showed no difference in the Kaplan-Meier curve for Montreal classification (p=0.73). CONCLUSIONS: The risk factors for operative intervention were strictures in ileal and jejunal diseases, age at diagnosis, perianal disease, and emergency indications.

The Impact of Patient Experience on Loyalty in the Context of Medical-Aesthetic Health Services.

The purpose of this study was to determine the antecedents and consequences of patient experience in the context of medical-aesthetic health services. A quantitative study was conducted and data was collected through online surveys. Moreover, data were provided in the field via the administration of questionnaires to patients of medical clinics. The data were analyzed according to structural equation modeling procedures. The results showed that both the relational (communication and involvement) and functional (environment, tangibles, processes, outcomes, competence, monetary cost) dimensions of care have a direct and positive impact on customer experience (CE). This study shows the prevalence of the functional dimension when compared to the relational one, which more strongly influences a patient's CE. Moreover, CE positively impacts perceived quality, overall satisfaction, and loyalty behaviors.

A CAD system for automatic dysplasia grading on H&E cervical whole-slide images.

Cervical cancer is the fourth most common female cancer worldwide and the fourth leading cause of cancer-related death in women. Nonetheless, it is also among the most successfully preventable and treatable types of cancer, provided it is early identified and properly managed. As such, the detection of pre-cancerous lesions is crucial. These lesions are detected in the squamous epithelium of the uterine cervix and are graded as low- or high-grade intraepithelial squamous lesions, known as LSIL and HSIL, respectively. Due to their complex nature, this classification can become very subjective. Therefore, the development of machine learning models, particularly directly on whole-slide images (WSI), can assist pathologists in this task. In this work, we propose a weakly-supervised methodology for grading cervical dysplasia, using different levels of training supervision, in an effort to gather a bigger dataset without the need of having all samples fully annotated. The framework comprises an epithelium segmentation step followed by a dysplasia classifier (non-neoplastic, LSIL, HSIL), making the slide assessment completely automatic, without the need for manual identification of epithelial areas. The proposed classification approach achieved a balanced accuracy of 71.07% and sensitivity of 72.18%, at the slide-level testing on 600 independent samples, which are publicly available upon reasonable request.

Oral Hygiene in Patients with Stroke: A Best Practice Implementation Project Protocol.

Oral hygiene has been shown to reduce adverse events and promote the quality of life of patients with stroke. However, a stroke can result in the impairment of physical, sensory, and cognitive abilities, and comprise self-care. Although nurses recognize its benefits, there are areas for improvement in the implementation of the best evidence-based recommendations. The aim is to promote compliance with the best evidence-based recommendations on oral hygiene in patients with stroke. This project will follow the JBI Evidence Implementation approach. The JBI Practical Application of Clinical Evidence System (JBI PACES) and the Getting Research into Practice (GRiP) audit and feedback tool will be used. The implementation process will be divided into three phases: (i) establishing a project team and undertaking the baseline audit; (ii) providing feedback to the healthcare team, identifying barriers to the implementation of best practices, and co-designing and implementing strategies using GRIP, and (iii) undertaking a follow-up audit to assess the outcomes and plan for sustainability. So, the successful adoption of the best evidence-based recommendations on oral hygiene in patients with stroke will reduce the adverse events related to poor oral care and may improve patients' quality of care. This implementation project has great transferability potential to other contexts.

Assessment of risk factors for surgery treatment of crohn's disease: a hospital cohort / Avaliação dos fatores de risco para tratamento cirúrgico na doença de crohn: uma coorte hospitalar

ABSTRACT BACKGROUND New therapies have revolutionized the treatment of Crohn's disease (CD), but in some countries, the surgery rate has not changed, the frequency of emergency surgery is underestimated, and surgical risk is poorly studied. AIMS: The aim of this study was to identify risk factors and clinical indications for primary surgery in CD patients at the tertiary hospital. METHODS: This was a retrospective cohort of a prospectively collected database of 107 patients with CD from 2015 to 2021. The main outcomes were the incidence of surgery treatment, types of procedures performed, surgical recurrence, surgery free time, and risk factors for surgery. RESULTS: Surgical intervention was performed in 54.2% of the patients, and most of the procedures were emergency surgeries (68.9%). The elective procedures (31.1%) were performed over 11 years after diagnosis. The main indications for surgery were ileal stricture (34.5%) and anorectal fistulas (20.7%). The most frequent procedure was enterectomy (24.1%). Recurrence surgery was most common in emergency procedures (OR 2.1; 95%CI 1.6-6.6). Montreal phenotype L1 stricture behavior (RR 1.3; 95%CI 1.0-1.8, p=0.04) and perianal disease (RR 1.43; 95%CI 1.2-1.7) increased the risk of emergency surgeries. The multiple linear regression showed age at diagnosis as a risk factor for surgery (p=0.004). The study of surgery free time showed no difference in the Kaplan-Meier curve for Montreal classification (p=0.73). CONCLUSIONS: The risk factors for operative intervention were strictures in ileal and jejunal diseases, age at diagnosis, perianal disease, and emergency indications.

RESUMO RACIONAL Novas terapias revolucionaram o tratamento da Doença de Crohn, mas em alguns países a taxa de cirurgias não se modificou, a frequência de cirurgias de emergência é subestimada e o risco cirúrgico é pouco estudado. OBJETIVOS Analisar fatores de risco e as indicações para cirurgia primária em pacientes com doença de Crohn, em Hospital terciário. MÉTODOS: Análise de banco de dados coletado prospectivamente, de 107 pacientes com doença de Crohn de 2015 a 2021. Os principais desfechos foram a incidência de tratamento cirúrgico, tipos de procedimentos realizados, recidiva cirúrgica, tempo livre de cirurgia e fatores de risco. RESULTADOS: A intervenção cirúrgica foi realizada em 54.2% dos pacientes, sendo a maioria dos procedimentos cirúrgicos de urgência (68.9%). Os procedimentos eletivos (31.1%) foram realizados mais de 11 anos após o diagnóstico. As principais indicações cirúrgicas foram estenose ileal (34,5%) e fístula anorretal (20,7%), sendo o procedimento mais frequente a enterectomia (24,1%). As cirurgias para recidiva foram mais comuns em procedimentos de urgência (OR 2,1; IC95% 1,6-6,6). O fenótipo de comportamento estenosante Montreal L1 (RR = 1,3; IC 95%: 1,0-1,8, p=0,04) e a doença perianal (RR 1,43; IC95% 1,2-1,7) aumentaram o risco de cirurgias de emergência. A regressão linear múltipla mostrou a idade ao diagnóstico como fator de risco para cirurgia (p=0,004). O estudo do tempo livre de cirurgia não mostrou diferença na curva de Kaplan Meier para a classificação Montreal (p=0,73). CONCLUSÕES: Os principais fatores de risco para intervenções cirúrgicas foram estenoses em doenças ileais e jejunais, idade ao diagnóstico, doença perianal e indicações de urgência.

Quality Control in Digital Pathology: Automatic Fragment Detection and Counting.

Manual assessment of fragments during the pro-cessing of pathology specimens is critical to ensure that the material available for slide analysis matches that captured during grossing without losing valuable material during this process. However, this step is still performed manually, resulting in lost time and delays in making the complete case available for evaluation by the pathologist. To overcome this limitation, we developed an autonomous system that can detect and count the number of fragments contained on each slide. We applied and compared two different methods: conventional machine learning methods and deep convolutional network methods. For conventional machine learning methods, we tested a two-stage approach with a supervised classifier followed by unsupervised hierarchical clustering. In addition, Fast R-CNN and YOLOv5, two state-of-the-art deep learning models for detection, were used and compared. All experiments were performed on a dataset comprising 1276 images of colorec-tal biopsy and polypectomy specimens manually labeled for fragment/set detection. The best results were obtained with the YOLOv5 architecture with a map@0.5 of 0.977 for fragment/set detection.

Outbreak caused by the SARS-CoV-2 Omicron variant in the psychiatric ward of a general hospital in Brazil.

BACKGROUND: An outbreak of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Omicron variant was detected in the psychiatric ward of a general hospital in Brasília, Brazil. METHODS: We report the investigation, clinical outcomes, viral sequencing, and control measures applied to outbreak containment. RESULTS: The overall attack rate was 95% (23/24) in a period of 13 days. Among the cases, 78% (18/23) were vaccinated and 17% (4/23) required intensive care. The Omicron variant was isolated from the 19 sequenced samples. CONCLUSIONS: The findings highlight the potential harm that highly transmissible variants may generate among hospitalized populations, particularly those with comorbidities.

Telehealth Adoption in an Outpatient Oncology Ward: A Best Practice Implementation Project.

Telehealth is increasingly taking place to support the transition of care and self-management of people living with cancer in outpatient oncology settings. Despite its recognised value, the scientific evidence points to disparities with regard to implementation of telehealth that might compromise the equity of access. Following the Joanna Briggs Institute (JBI) implementation approach, this project aims to promote the implementation of best practice recommendations for telehealth adoption in an outpatient oncology setting. Assisted by the Practical Application of Clinical Evidence System (PACES), the implementation process comprises three phases of (i) a baseline audit, (ii) feedback to the healthcare team and establishment of implementation strategies with the Getting Research into Practice (GRiP) tool, and (iii) a follow-up audit. The project is expected to allow the identification of barriers and facilitators for the implementation of telehealth in outpatient oncology and develop a strategy plan for its adoption, with the involvement of end-users and stakeholders. The successful adoption of telehealth according to the best available evidence will likely enhance equity of access to healthcare and quality of care at a distance.

iMIL4PATH: A Semi-Supervised Interpretable Approach for Colorectal Whole-Slide Images.

Colorectal cancer (CRC) diagnosis is based on samples obtained from biopsies, assessed in pathology laboratories. Due to population growth and ageing, as well as better screening programs, the CRC incidence rate has been increasing, leading to a higher workload for pathologists. In this sense, the application of AI for automatic CRC diagnosis, particularly on whole-slide images (WSI), is of utmost relevance, in order to assist professionals in case triage and case review. In this work, we propose an interpretable semi-supervised approach to detect lesions in colorectal biopsies with high sensitivity, based on multiple-instance learning and feature aggregation methods. The model was developed on an extended version of the recent, publicly available CRC dataset (the CRC+ dataset with 4433 WSI), using 3424 slides for training and 1009 slides for evaluation. The proposed method attained 90.19% classification ACC, 98.8% sensitivity, 85.7% specificity, and a quadratic weighted kappa of 0.888 at slide-based evaluation. Its generalisation capabilities are also studied on two publicly available external datasets.

Digital Pathology Implementation in Private Practice: Specific Challenges and Opportunities.

Digital pathology (DP) is being deployed in many pathology laboratories, but most reported experiences refer to public health facilities. In this paper, we report our experience in DP transition at a high-volume private laboratory, addressing the main challenges in DP implementation in a private practice setting and how to overcome these issues. We started our implementation in 2020 and we are currently scanning 100% of our histology cases. Pre-existing sample tracking infrastructure facilitated this process. We are currently using two high-capacity scanners (Aperio GT450DX) to digitize all histology slides at 40×. Aperio eSlide Manager WebViewer viewing software is bidirectionally linked with the laboratory information system. Scanning error rate, during the test phase, was 2.1% (errors detected by the scanners) and 3.5% (manual quality control). Pre-scanning phase optimizations and vendor feedback and collaboration were crucial to improve WSI quality and are ongoing processes. Regarding pathologists' validation, we followed the Royal College of Pathologists recommendations for DP implementation (adapted to our practice). Although private sector implementation of DP is not without its challenges, it will ultimately benefit from DP safety and quality-associated features. Furthermore, DP deployment lays the foundation for artificial intelligence tools integration, which will ultimately contribute to improving patient care.

Outbreak caused by the SARS-CoV-2 Omicron variant in the psychiatric ward of a general hospital in Brazil

ABSTRACT Background: An outbreak of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Omicron variant was detected in the psychiatric ward of a general hospital in Brasília, Brazil. Methods: We report the investigation, clinical outcomes, viral sequencing, and control measures applied to outbreak containment. Results: The overall attack rate was 95% (23/24) in a period of 13 days. Among the cases, 78% (18/23) were vaccinated and 17% (4/23) required intensive care. The Omicron variant was isolated from the 19 sequenced samples. Conclusions: The findings highlight the potential harm that highly transmissible variants may generate among hospitalized populations, particularly those with comorbidities.

CAD systems for colorectal cancer from WSI are still not ready for clinical acceptance.

Most oncological cases can be detected by imaging techniques, but diagnosis is based on pathological assessment of tissue samples. In recent years, the pathology field has evolved to a digital era where tissue samples are digitised and evaluated on screen. As a result, digital pathology opened up many research opportunities, allowing the development of more advanced image processing techniques, as well as artificial intelligence (AI) methodologies. Nevertheless, despite colorectal cancer (CRC) being the second deadliest cancer type worldwide, with increasing incidence rates, the application of AI for CRC diagnosis, particularly on whole-slide images (WSI), is still a young field. In this review, we analyse some relevant works published on this particular task and highlight the limitations that hinder the application of these works in clinical practice. We also empirically investigate the feasibility of using weakly annotated datasets to support the development of computer-aided diagnosis systems for CRC from WSI. Our study underscores the need for large datasets in this field and the use of an appropriate learning methodology to gain the most benefit from partially annotated datasets. The CRC WSI dataset used in this study, containing 1,133 colorectal biopsy and polypectomy samples, is available upon reasonable request.

Survey of Kudoa spp. (Myxozoa, Cnidaria) in fishes from the Madeira Archipelago and the Portuguese mainland coast: detection of Kudoa thyrsites in new hosts Scomber colias and Micromesistius poutassou.

Myxozoan parasites of the genus Kudoa Meglitsch, 1947 are associated with post-mortem tissue degradation that causes great financial losses to commercial fisheries. Kudoa thyrsites (Gilchrist, 1924) is a species with a very wide host range including commercial tunas, mackerels, salmonids and flatfishes. A sample of 190 fishes of 18 species from the Madeira Archipelago and 30 Atlantic chub mackerel, Scomber colias Gmelin, and 30 blue whiting, Micromesistius poutassou (Risso), from the Portuguese mainland coast were examined for the presence of species of Kudoa. The prevalence of Kudoa spp. was 80% in M. poutassou and 60% in S. colias. No spore was detected in S. colias from Madeira, which was confirmed by specific PCR screening of the muscle from all individuals of S. colias. SSU rDNA analysis revealed that M. poutassou and S. colias from the Portuguese mainland coast were infected with K. thyrsites, an economically important myxozoan parasite. Both sequences were identical with sequences of the eastern Atlantic K. thyrsites genotype, including that from the type host of this parasite. This is the first report of K. thyrsites from M. poutassou and S. colias. The fact that spores of species of Kudoa were not detected in fishes screened in the Madeira Archipelago may be explained by various ecological factors, such as the absence of a continental shelf, a short insular shelf, and oceanic waters with low productivity, all resulting in reduced abundance of benthic organisms. Consequently, it is possible that as yet unknown annelid definitive hosts of Kudoa spp. are absent or very rare near Madeiran coasts.

Accuracy of Oral 67Gallium Citrate Scintigraphy in assessment of inflammatory activity of Crohn's disease.

AIM: The main goal in Crohn´s disease (CD) is a sustained suppression of inflammatory activity associated with mucosa healing in endoscopic evaluation. During clinical routine, there are small numbers of good markers to monitor inflammatory activity under treatment. We postulated that Oral 67Gallium Citrate Scintigraphy is able to mark inflammatory disease in mucosa and deep inflammation in CD, when used in oral form. OBJECTIVE: Measure the accuracy of Oral 67Gallium Citrate Scintigraphy in intestinal inflammatory activity of Crohn´s disease. PATIENTS AND METHODS: In a prospective consecutive cross-sectional study from January 2018 to June 2019, the ileocolonic region of 32 patients with CD were studied by dividing into four regions of interest (ROI) from the ileum to the rectum. A total of 128 intestinal segments were analyzed in cluster data. Accuracy values of Oral 67Gallium Scintigraphy and colonoscopy tests were evaluated with the histological reference test. Values of the respective receiver operating characteristic (ROC) curves were obtained  and compared. The reliability between the tests was evaluated by Kappa statistical with the segment-level analyses using variance adjustments. All statistical analyses were performed with a test significance level of 0.05. RESULTS: The study population included 32 patients with CD (10 men, 22 women; average age 39 years). Disease time was five years on average. Anti-TNFs treatment was found in 71%. The most found phenotype of the Montreal classification was L3. Differences in ROC curves for colonoscopy (0.94) and Oral 67Ga Scintigraphy (0.96) did not show significant value (p = 0.32). The sensitivity of scintigraphy to detect intestinal inflammatory activity in CD was 64%, specificity of 96% and accuracy of 84%. A high agreement was found between oral scintigraphy and histological measurements with kappa = 0.64. CONCLUSIONS: Oral 67Ga Scintigraphy had similar accuracy and agreement compared to colonoscopy in the identification of inflammatory activity in Crohn´s Disease. This new approach may be useful and less invasive for long term follow-ups.

Spontaneous Pulmonary Hematoma as a Complication of Anticoagulant Therapy / Hematoma pulmonar espontáneo como complicación del tratamiento anticoagulante

No disponible

Angiolymphoid Hyperplasia With Eosinophilia of the Lung / Hiperplasia angiolinfoide con eosinofilia del pulmón

No disponible