Deep learning and capsule endoscopy: Automatic multi-brand and multi-device panendoscopic detection of vascular lesions.

Background and study aims Capsule endoscopy (CE) is commonly used as the initial exam for suspected mid-gastrointestinal bleeding after normal upper and lower endoscopy. Although the assessment of the small bowel is the primary focus of CE, detecting upstream or downstream vascular lesions may also be clinically significant. This study aimed to develop and test a convolutional neural network (CNN)-based model for panendoscopic automatic detection of vascular lesions during CE. Patients and methods A multicentric AI model development study was based on 1022 CE exams. Our group used 34655 frames from seven types of CE devices, of which 11091 were considered to have vascular lesions (angiectasia or varices) after triple validation. We divided data into a training and a validation set, and the latter was used to evaluate the model's performance. At the time of division, all frames from a given patient were assigned to the same dataset. Our primary outcome measures were sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and an area under the precision-recall curve (AUC-PR). Results Sensitivity and specificity were 86.4% and 98.3%, respectively. PPV was 95.2%, while the NPV was 95.0%. Overall accuracy was 95.0%. The AUC-PR value was 0.96. The CNN processed 115 frames per second. Conclusions This is the first proof-of-concept artificial intelligence deep learning model developed for pan-endoscopic automatic detection of vascular lesions during CE. The diagnostic performance of this CNN in multi-brand devices addresses an essential issue of technological interoperability, allowing it to be replicated in multiple technological settings.

A Case of Success: Complete Response to Radium-223 in Metastatic Castration-Resistant Prostate Cancer.

Radium-223 dichloride (Ra223) is the first targeted alpha agent approved for treating metastatic castration-resistant prostate cancer (mCRPC) with bone-exclusive disease. A benefit in overall survival and time to the first symptomatic skeletal-related event was shown in the Alpharadin in Symptomatic Prostate Cancer Patients (ALSYMPCA) trial. However, this trial did not describe a bone scan response to Ra223, and there is no universal consensus about how it should be monitored. Furthermore, a scintigraphy flare phenomenon may lead to false-positive tracer uptake in responsive cases, thereby misleading the interpretation of imaging results.  We present the case of a 67-year-old male with mCRPC and exclusive bone disease treated with Ra223. The bone scintigraphy after the end of the treatment showed an apparent aggravation of the lesions, corresponding to a flare phenomenon, with an almost complete resolution after three months. The patient maintained a scintigraphic response for seven months.

Partial replacement of mineral fertilisers with animal manures in an apple orchard: Effects on GHG emission.

Partial replacement of mineral fertilisers (MF) with animal manures is a good alternative to reduce MF use and increase both nutrient cycling in agriculture and soil organic matter. However, the adoption of this practice must not lead to increased environmental impacts. In this two-year study conducted in an apple orchard, MF were partially replaced with various animal manures, including cattle slurry (CS), acidified cattle slurry (ACS), solid cattle manure (CsM), or poultry manure (PM), and their impacts on greenhouse gas emission (GHG: CO2, N2O and CH4) were examined. A control (CTRL) receiving only MF served as the baseline, representing the conventional scenario in orchard fertilisation. Overall, replacing MF with manures increased GHG emissions, with the magnitude of the impacts depending on the specific characteristics of the manures and the amount of nutrients and organic matter applied. Comparing to the CTRL, application of ACS and CS led to higher CH4 and N2O emissions, while PM application increased both N2O and CO2 emissions. In contrast, replacement with PM and CsM decreased CH4 emissions. Nevertheless, results varied between the two years, influenced by several factors, including soil conditions. While acidification showed potential to mitigate CH4 emissions, it also led to increased N2O emissions compared to CS, particularly in 2022, suggesting the need for further investigation to avoid emission trade-offs. Replacement with CS (20.49 t CO2-eq ha-1) and CsM (20.30 t CO2-eq ha-1) showed comparable global warming potential (GWP) to the conventional scenario (CTRL, 19.49 t CO2-eq ha-1), highlighting their potential as viable MF substitutes.

Revolutionizing Women's Health: A Comprehensive Review of Artificial Intelligence Advancements in Gynecology.

Artificial intelligence has yielded remarkably promising results in several medical fields, namely those with a strong imaging component. Gynecology relies heavily on imaging since it offers useful visual data on the female reproductive system, leading to a deeper understanding of pathophysiological concepts. The applicability of artificial intelligence technologies has not been as noticeable in gynecologic imaging as in other medical fields so far. However, due to growing interest in this area, some studies have been performed with exciting results. From urogynecology to oncology, artificial intelligence algorithms, particularly machine learning and deep learning, have shown huge potential to revolutionize the overall healthcare experience for women's reproductive health. In this review, we aim to establish the current status of AI in gynecology, the upcoming developments in this area, and discuss the challenges facing its clinical implementation, namely the technological and ethical concerns for technology development, implementation, and accountability.

From Data to Insights: How Is AI Revolutionizing Small-Bowel Endoscopy?

The role of capsule endoscopy and enteroscopy in managing various small-bowel pathologies is well-established. However, their broader application has been hampered mainly by their lengthy reading times. As a result, there is a growing interest in employing artificial intelligence (AI) in these diagnostic and therapeutic procedures, driven by the prospect of overcoming some major limitations and enhancing healthcare efficiency, while maintaining high accuracy levels. In the past two decades, the applicability of AI to gastroenterology has been increasing, mainly because of the strong imaging component. Nowadays, there are a multitude of studies using AI, specifically using convolutional neural networks, that prove the potential applications of AI to these endoscopic techniques, achieving remarkable results. These findings suggest that there is ample opportunity for AI to expand its presence in the management of gastroenterology diseases and, in the future, catalyze a game-changing transformation in clinical activities. This review provides an overview of the current state-of-the-art of AI in the scope of small-bowel study, with a particular focus on capsule endoscopy and enteroscopy.

Immune-related serious adverse events with immune checkpoint inhibitors: Systematic review and network meta-analysis.

PURPOSE: Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, though uncertainty exists regarding their immune-related safety. The objective of this study was to assess the comparative safety profile (odds ratio) of ICIs and estimate the absolute rate of immune-related serious adverse events (irSAEs) in cancer patients undergoing treatment with ICIs. METHODS: We searched for randomized trials till February 2021, including all ICIs for all cancers. Primary outcome was overall irSAEs, and secondary outcomes were pneumonitis, colitis, hepatitis, hypophysitis, myocarditis, nephritis, and pancreatitis. We conducted Bayesian network meta-analyses, estimated absolute rates and ranked treatments according to the surface under the cumulative ranking curve (SUCRA). RESULTS: We included 96 trials (52,811 participants, median age 62 years). Risk of bias was high in most trials. Most cancers were non-small cell lung cancer (28 trials) and melanoma (15 trials). The worst-ranked ICI was ipilimumab (SUCRA 14%; event rate 848/10,000 patients) while the best-ranked ICI was atezolizumab (SUCRA 82%; event rate 119/10,000 patients). CONCLUSION: Each ICI showed a unique safety profile, with certain events more frequently observed with specific ICIs, which should be considered when managing cancer patients.

Deep Learning in High-Resolution Anoscopy: Assessing the Impact of Staining and Therapeutic Manipulation on Automated Detection of Anal Cancer Precursors.

INTRODUCTION: High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell carcinoma (ASCC) precursors. Preliminary studies on the application of artificial intelligence (AI) models to this modality have revealed promising results. However, the impact of staining techniques and anal manipulation on the effectiveness of these algorithms has not been evaluated. We aimed to develop a deep learning system for automatic differentiation of high-grade squamous intraepithelial lesion vs low-grade squamous intraepithelial lesion in HRA images in different subsets of patients (nonstained, acetic acid, lugol, and after manipulation). METHODS: A convolutional neural network was developed to detect and differentiate high-grade and low-grade anal squamous intraepithelial lesions based on 27,770 images from 103 HRA examinations performed in 88 patients. Subanalyses were performed to evaluate the algorithm's performance in subsets of images without staining, acetic acid, lugol, and after manipulation of the anal canal. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve were calculated. RESULTS: The convolutional neural network achieved an overall accuracy of 98.3%. The algorithm had a sensitivity and specificity of 97.4% and 99.2%, respectively. The accuracy of the algorithm for differentiating high-grade squamous intraepithelial lesion vs low-grade squamous intraepithelial lesion varied between 91.5% (postmanipulation) and 100% (lugol) for the categories at subanalysis. The area under the curve ranged between 0.95 and 1.00. DISCUSSION: The introduction of AI to HRA may provide an accurate detection and differentiation of ASCC precursors. Our algorithm showed excellent performance at different staining settings. This is extremely important because real-time AI models during HRA examinations can help guide local treatment or detect relapsing disease.

Artificial Intelligence and Panendoscopy-Automatic Detection of Clinically Relevant Lesions in Multibrand Device-Assisted Enteroscopy.

Device-assisted enteroscopy (DAE) is capable of evaluating the entire gastrointestinal tract, identifying multiple lesions. Nevertheless, DAE's diagnostic yield is suboptimal. Convolutional neural networks (CNN) are multi-layer architecture artificial intelligence models suitable for image analysis, but there is a lack of studies about their application in DAE. Our group aimed to develop a multidevice CNN for panendoscopic detection of clinically relevant lesions during DAE. In total, 338 exams performed in two specialized centers were retrospectively evaluated, with 152 single-balloon enteroscopies (Fujifilm®, Porto, Portugal), 172 double-balloon enteroscopies (Olympus®, Porto, Portugal) and 14 motorized spiral enteroscopies (Olympus®, Porto, Portugal); then, 40,655 images were divided in a training dataset (90% of the images, n = 36,599) and testing dataset (10% of the images, n = 4066) used to evaluate the model. The CNN's output was compared to an expert consensus classification. The model was evaluated by its sensitivity, specificity, positive (PPV) and negative predictive values (NPV), accuracy and area under the precision recall curve (AUC-PR). The CNN had an 88.9% sensitivity, 98.9% specificity, 95.8% PPV, 97.1% NPV, 96.8% accuracy and an AUC-PR of 0.97. Our group developed the first multidevice CNN for panendoscopic detection of clinically relevant lesions during DAE. The development of accurate deep learning models is of utmost importance for increasing the diagnostic yield of DAE-based panendoscopy.

Löfgren Syndrome: A Mosaic of Sarcoidosis Phenotypes.

Sarcoidosis is an autoimmune multisystemic granulomatous disease with an unknown etiology. Löfgren syndrome (LS), an infrequent initial presentation of acute sarcoidosis, is characterized by the classic triad of acute arthritis, erythema nodosum (EN), and bilateral hilar lymphadenopathy (BHL). The presence of this triad offers high diagnostic specificity for sarcoidosis, eliminating the need for a confirmatory biopsy. Typically, LS follows a predictable, self-limiting clinical course. However, atypical presentations require early suspicion and closer monitoring. This case report highlights an unusual clinical manifestation of LS, marked by an incomplete presentation with acute panniculitis and joint lesions in the absence of EN. Acute sarcoidosis should be considered among the differential diagnoses when these clinical manifestations are present, and chest radiography should be performed to rule out BHL. In atypical cases, the disease course becomes less predictable, as exemplified in our case, where recurrence of the disease may occur, necessitating consistent monitoring.

AI-Driven Colon Cleansing Evaluation in Capsule Endoscopy: A Deep Learning Approach.

Gastroenterology is increasingly moving towards minimally invasive diagnostic modalities. The diagnostic exploration of the colon via capsule endoscopy, both in specific protocols for colon capsule endoscopy and during panendoscopic evaluations, is increasingly regarded as an appropriate first-line diagnostic approach. Adequate colonic preparation is essential for conclusive examinations as, contrary to a conventional colonoscopy, the capsule moves passively in the colon and does not have the capacity to clean debris. Several scales have been developed for the classification of bowel preparation for colon capsule endoscopy. Nevertheless, their applications are limited by suboptimal interobserver agreement. Our group developed a deep learning algorithm for the automatic classification of colonic bowel preparation, according to an easily applicable classification. Our neural network achieved high performance levels, with a sensitivity of 91%, a specificity of 97% and an overall accuracy of 95%. The algorithm achieved a good discriminating capacity, with areas under the curve ranging between 0.92 and 0.97. The development of these algorithms is essential for the widespread adoption of capsule endoscopy for the exploration of the colon, as well as for the adoption of minimally invasive panendoscopy.

Diagnostic Performance of Deep Learning Models for Gastric Intestinal Metaplasia Detection in Narrow-band Images.

Gastric Intestinal Metaplasia (GIM) is one of the precancerous conditions in the gastric carcinogenesis cascade and its optical diagnosis during endoscopic screening is challenging even for seasoned endoscopists. Several solutions leveraging pre-trained deep neural networks (DNNs) have been recently proposed in order to assist human diagnosis. In this paper, we present a comparative study of these architectures in a new dataset containing GIM and non-GIM Narrow-band imaging still frames. We find that the surveyed DNNs perform remarkably well on average, but still measure sizeable inter-fold variability during cross-validation. An additional ad-hoc analysis suggests that these baseline architectures may not perform equally well at all scales when diagnosing GIM.Clinical relevance- Enhanching a clinician's ability to detect and localize intestinal metaplasia can be a crucial tool for gastric cancer management policies.

Smart Endoscopy Is Greener Endoscopy: Leveraging Artificial Intelligence and Blockchain Technologies to Drive Sustainability in Digestive Health Care.

The surge in the implementation of artificial intelligence (AI) in recent years has permeated many aspects of our life, and health care is no exception. Whereas this technology can offer clear benefits, some of the problems associated with its use have also been recognised and brought into question, for example, its environmental impact. In a similar fashion, health care also has a significant environmental impact, and it requires a considerable source of greenhouse gases. Whereas efforts are being made to reduce the footprint of AI tools, here, we were specifically interested in how employing AI tools in gastroenterology departments, and in particular in conjunction with capsule endoscopy, can reduce the carbon footprint associated with digestive health care while offering improvements, particularly in terms of diagnostic accuracy. We address the different ways that leveraging AI applications can reduce the carbon footprint associated with all types of capsule endoscopy examinations. Moreover, we contemplate how the incorporation of other technologies, such as blockchain technology, into digestive health care can help ensure the sustainability of this clinical speciality and by extension, health care in general.

The Future of Minimally Invasive Capsule Panendoscopy: Robotic Precision, Wireless Imaging and AI-Driven Insights.

In the early 2000s, the introduction of single-camera wireless capsule endoscopy (CE) redefined small bowel study. Progress continued with the development of double-camera devices, first for the colon and rectum, and then, for panenteric assessment. Advancements continued with magnetic capsule endoscopy (MCE), particularly when assisted by a robotic arm, designed to enhance gastric evaluation. Indeed, as CE provides full visualization of the entire gastrointestinal (GI) tract, a minimally invasive capsule panendoscopy (CPE) could be a feasible alternative, despite its time-consuming nature and learning curve, assuming appropriate bowel cleansing has been carried out. Recent progress in artificial intelligence (AI), particularly in the development of convolutional neural networks (CNN) for CE auxiliary reading (detecting and diagnosing), may provide the missing link in fulfilling the goal of establishing the use of panendoscopy, although prospective studies are still needed to validate these models in actual clinical scenarios. Recent CE advancements will be discussed, focusing on the current evidence on CNN developments, and their real-life implementation potential and associated ethical challenges.

Deep Learning for Automatic Diagnosis and Morphologic Characterization of Malignant Biliary Strictures Using Digital Cholangioscopy: A Multicentric Study.

Digital single-operator cholangioscopy (D-SOC) has enhanced the ability to diagnose indeterminate biliary strictures (BSs). Pilot studies using artificial intelligence (AI) models in D-SOC demonstrated promising results. Our group aimed to develop a convolutional neural network (CNN) for the identification and morphological characterization of malignant BSs in D-SOC. A total of 84,994 images from 129 D-SOC exams in two centers (Portugal and Spain) were used for developing the CNN. Each image was categorized as either a normal/benign finding or as malignant lesion (the latter dependent on histopathological results). Additionally, the CNN was evaluated for the detection of morphologic features, including tumor vessels and papillary projections. The complete dataset was divided into training and validation datasets. The model was evaluated through its sensitivity, specificity, positive and negative predictive values, accuracy and area under the receiver-operating characteristic and precision-recall curves (AUROC and AUPRC, respectively). The model achieved a 82.9% overall accuracy, 83.5% sensitivity and 82.4% specificity, with an AUROC and AUPRC of 0.92 and 0.93, respectively. The developed CNN successfully distinguished benign findings from malignant BSs. The development and application of AI tools to D-SOC has the potential to significantly augment the diagnostic yield of this exam for identifying malignant strictures.

Markov-Based Neural Networks for Heart Sound Segmentation: Using Domain Knowledge in a Principled Way.

This work considers the problem of segmenting heart sounds into their fundamental components. We unify statistical and data-driven solutions by introducing Markov-based Neural Networks (MNNs), a hybrid end-to-end framework that exploits Markov models as statistical inductive biases for an Artificial Neural Network (ANN) discriminator. We show that an MNN leveraging a simple one-dimensional Convolutional ANN significantly outperforms two recent purely data-driven solutions for this task in two publicly available datasets: PhysioNet 2016 (Sensitivity: 0.947 ±0.02; Positive Predictive Value : 0.937 ±0.025) and the CirCor DigiScope 2022 (Sensitivity: 0.950 ±0.008; Positive Predictive Value: 0.943 ±0.012). We also propose a novel gradient-based unsupervised learning algorithm that effectively makes the MNN adaptive to unseen datum sampled from unknown distributions. We perform a cross dataset analysis and show that an MNN pre-trained in the CirCor DigiScope 2022 can benefit from an average improvement of 3.90% Positive Predictive Value on unseen observations from the PhysioNet 2016 dataset using this method.

Immunotherapy around the Clock: Impact of Infusion Timing on Stage IV Melanoma Outcomes.

Although the impact of circadian timing on immunotherapy has yet to be integrated into clinical practice, chronoimmunotherapy is an emerging and promising field as circadian oscillations are observed in immune cell numbers as well as the expression of immunotherapy targets, e.g., programmed cell death protein-1 and its ligand programmed death ligand 1. Concurrent retrospective studies suggest that morning infusions may lead to higher effectiveness of immune checkpoint inhibitors in melanoma, non-small cell lung cancer, and kidney cancer. This paper discusses the results of a retrospective study (2016-2022) exploring the impact of infusion timing on the outcomes of all 73 patients with stage IV melanoma receiving immunotherapy at a particular medical center. While the median overall survival (OS) was 24.2 months (95% confidence interval [CI] 9.04-39.8), for a median follow-up of 15.3 months, our results show that having more than 75% of infusions in the afternoon results in shorter median OS (14.9 vs. 38.1 months; hazard ratio 0.45 [CI 0.23-0.86]; p < 0.01) with more expressive impacts on particular subgroups: women, older patients, and patients with a lower tumor burden at the outset of immunotherapy. Our findings highlight the potential benefits of follow-up validation in prospective and translational randomized studies.

Breast Sarcomas, Phyllodes Tumors, and Desmoid Tumors: Turning the Magnifying Glass on Rare and Aggressive Entities.

Breast sarcomas (BSs), phyllodes tumors (PTs), and desmoid tumors (DTs) are rare entities that arise from connective tissue. BSs can be classified as either primary or secondary, whether they develop de novo or after radiation exposure or lymphedema. PIK3CA seems to play an important common role in different BS. Malignant PTs show similar behavior to BSs, while DTs are locally aggressive but rarely metastasize. BSs usually present as unilateral, painless, rapidly growing masses with rare nodal involvement. The diagnosis should be based on magnetic resonance imaging and a core needle biopsy. Staging should comprise a chest computed tomography (CT) scan (except for benign PT and DT), while abdominal and pelvic CT scans and bone scans should be added in certain subtypes. The mainstay of treatment for localized BS is surgery, with margin goals that vary according to subtype. Radiotherapy and chemotherapy can be used as neoadjuvant or adjuvant approaches, but their use in these settings is not standard. Advanced BS should be treated with systemic therapy, consistent with recommendations for advanced soft tissue sarcomas of other topographies. Given the rarity and heterogeneity of these entities, multidisciplinary and multi-institutional collaboration and treatment at reference centers are critical.

Deep Learning and Minimally Invasive Endoscopy: Automatic Classification of Pleomorphic Gastric Lesions in Capsule Endoscopy.

INTRODUCTION: Capsule endoscopy (CE) is a minimally invasive examination for evaluating the gastrointestinal tract. However, its diagnostic yield for detecting gastric lesions is suboptimal. Convolutional neural networks (CNNs) are artificial intelligence models with great performance for image analysis. Nonetheless, their role in gastric evaluation by wireless CE (WCE) has not been explored. METHODS: Our group developed a CNN-based algorithm for the automatic classification of pleomorphic gastric lesions, including vascular lesions (angiectasia, varices, and red spots), protruding lesions, ulcers, and erosions. A total of 12,918 gastric images from 3 different CE devices (PillCam Crohn's; PillCam SB3; OMOM HD CE system) were used from the construction of the CNN: 1,407 from protruding lesions; 994 from ulcers and erosions; 822 from vascular lesions; and 2,851 from hematic residues and the remaining images from normal mucosa. The images were divided into a training (split for three-fold cross-validation) and validation data set. The model's output was compared with a consensus classification by 2 WCE-experienced gastroenterologists. The network's performance was evaluated by its sensitivity, specificity, accuracy, positive predictive value and negative predictive value, and area under the precision-recall curve. RESULTS: The trained CNN had a 97.4% sensitivity; 95.9% specificity; and positive predictive value and negative predictive value of 95.0% and 97.8%, respectively, for gastric lesions, with 96.6% overall accuracy. The CNN had an image processing time of 115 images per second. DISCUSSION: Our group developed, for the first time, a CNN capable of automatically detecting pleomorphic gastric lesions in both small bowel and colon CE devices.

Anthracyclines versus No Anthracyclines in the Neoadjuvant Strategy for HER2+ Breast Cancer: Real-World Evidence.

BACKGROUND AND OBJECTIVES: Deescalation strategies omitting anthracyclines (AC) have been explored in early human epidermal growth factor receptor 2-positive breast cancer (HER2+ EBC), showing similar efficacy regarding pathological complete response (pCR) and long-term outcomes as AC-containing regimens. The standard treatment for this tumor subtype is based on chemotherapy and dual HER2 blockade with trastuzumab and pertuzumab, with AC-containing regimens remaining a frequent option for these patients, even in non-high-risk cases. The primary aim of this study was to assess and compare the effectiveness of neoadjuvant regimens with and without AC used in the treatment of HER2+ EBC in the clinical practice according to the pCR achieved with each. METHODS: This retrospective multicentric study included patients with HER2+ EBC from Portuguese, Spanish, and Chilean hospitals (January 2018-December 2021). Patients receiving neoadjuvant therapy (NAT) with dual HER2 blockade (trastuzumab and pertuzumab), followed by surgery, were included. Statistical analysis used chi-squared/Fisher's exact test for associations, multivariate logistic regression for pCR, and Kaplan-Meier method for event-free survival (EFS). IBM SPSS Statistics 29.0 analyzed the data. RESULTS: The study included 371 patients from eight hospitals. Among them, 237 received sequential AC and taxane-based chemotherapy with 4 cycles of trastuzumab and pertuzumab, while 134 received 6 cycles of TCHP (docetaxel, carboplatinum, trastuzumab, and pertuzumab). The average age of the patients was 52.8 years and 52.7 years, respectively. Omitting AC from the neoadjuvant approach did not preclude achieving pCR [p = 0.246, 95% confidence interval (CI) 0.235-0.257] and was safe regardless of patient characteristics. Relapse rates were 6.8% (16 patients) in the AC group and 4.5% (6 patients) in the TCHP group. Over a median follow-up of 2.9 years, the estimated 3-year EFS was 92.5% in the AC group and 95.4% in the TCHP group (hazard ratio 0.602, 95% CI 0.234-1.547, p = 0.292, favoring TCHP). CONCLUSION: This study reports real-world evidence showing similar pCR and EFS outcomes with treatment regimens with and without AC and raises awareness of possible overtreatment and long-term toxicity in some patients with HER2+ EBC with the use of AC.