Automatic Detection of Colorectal Polyps Using Transfer Learning

Disease detection on exterior surfaces of buildings using deep learning in China

Urban infrastructure, particularly in ageing cities, faces significant challenges in maintaining building aesthetics and structural integrity. Traditional methods for detecting diseases on building exteriors, such as manual inspections, are often inefficient, costly, and prone to errors, leading to incomplete assessments and delayed maintenance actions. This study explores the application of advanced deep learning techniques to accurately detect diseases on the exterior surfaces of buildings in urban environments, aiming to enhance detection efficiency and accuracy while providing a real-time monitoring solution that can be widely implemented in infrastructure health management. The research implemented a deep learning model that improves feature extraction and accuracy by integrating DenseNet blocks and Swin-Transformer prediction heads, trained and validated using a dataset of 289 high-resolution images collected from diverse urban environments in China. Data augmentation techniques improved the model's robustness against varying conditions. The proposed model achieved a high accuracy rate of 84.42%, a recall of 77.83%, and an F1 score of 0.81, with a detection speed of 55 frames per second. These metrics demonstrate the model's effectiveness in accurately identifying complex damage patterns, such as minute cracks, even within noisy urban environments, significantly outperforming traditional methods. This study highlights the potential of deep learning to transform urban maintenance strategies by offering a practical solution for the real-time detection of diseases on building exteriors, ultimately enhancing the efficiency and accuracy of urban infrastructure monitoring and contributing to improved maintenance practices and timely interventions.

Deep Learning in Endoscopic Ultrasound: A Breakthrough in Detecting Distal Cholangiocarcinoma

INTRODUCTION

Cholangiocarcinoma (CCA) is a highly lethal malignancy originating in the bile ducts, often diagnosed late with poor prognosis. Differentiating benign from malignant biliary tumors remains challenging, necessitating advanced diagnostic techniques.

OBJECTIVE

This study aims to enhance the diagnostic accuracy of endoscopic ultrasound (EUS) for distal cholangiocarcinoma (dCCA) using advanced convolutional neural networks (CCNs) for the classification and segmentation of EUS images, specifically targeting dCCAs, the pancreas, and the bile duct.

MATERIALS AND METHODS

In this retrospective study, EUS images from patients diagnosed with dCCA via biopsy and an EUS-identified bile duct tumor were evaluated. A custom CNN was developed for classification, trained on 156 EUS images. To enhance the model's robustness, image augmentation techniques were applied, generating a total of 1248 images. For tumor and organ segmentation, the DeepLabv3+ network with ResNet50 architecture was utilized, employing Tversky loss to manage unbalanced classes. Performance evaluation included metrics such as accuracy, sensitivity, specificity, and Intersection over Union (IoU). These methods were implemented in collaboration with the ADAPTED Research Group at the Technical University of Cluj-Napoca.

RESULTS

The classification model achieved a high accuracy of 97.82%, with precision and specificity both at 100% and sensitivity at 94.44%. The segmentation models for the pancreas and bile duct demonstrated global accuracies of 84% and 90%, respectively, with robust IoU scores indicating good overlap between predicted and actual contours. The application performed better than the UNet model, particularly in generalization and boundary delineation.

CONCLUSIONS

This study demonstrates the significant potential of AI in EUS imaging for dCCA, presenting a robust tool that enhances diagnostic accuracy and efficiency. The developed MATLAB application serves as a valuable aid for medical professionals, facilitating informed decision-making and improving patient outcomes in the diagnosis of cholangiocarcinoma and related pathologies.

Computer-Assisted Algorithm for Quantification of Fibrosis by Native Cardiac CT: A Pilot Study

Background/Objectives: Recent advances in artificial intelligence, particularly in cardiac imaging, can potentially enhance patients' diagnosis and prognosis and identify novel imaging markers. We propose an automated, computer-aided algorithm utilizing native cardiac computed tomography (CT) imaging to identify myocardial fibrosis. This study aims to evaluate its performance compared to CMR markers of fibrosis in a cohort of patients diagnosed with breast cancer. Methods: The study included patients diagnosed with early HER2+ breast cancer, who presented LV dysfunction (LVEF < 50%) and myocardial fibrosis detected on CMR at the time of diagnosis. The patients were also evaluated by cardiac CT, and the extracted images were processed for the implementation of the automatic, computer-assisted algorithm, which marked as fibrosis every pixel that fell within the range of 60-90 HU. The percentage of pixels with fibrosis was subsequently compared with CMR parameters. Results: A total of eight patients (n = 8) were included in the study. High positive correlations between the algorithm's result and the ECV fraction (r = 0.59, p = 0.126) and native T1 (r = 0.6, p = 0.112) were observed, and a very high positive correlation with LGE of the LV(g) and the LV-LGE/LV mass percentage (r = 0.77, p = 0.025; r = 0.81, p = 0.015). A very high negative correlation was found with GLS (r = -0.77, p = 0.026). The algorithm presented an intraclass correlation coefficient of 1 (95% CI 0.99-1), p < 0.001. Conclusions: The present pilot study proposes a novel promising imaging marker for myocardial fibrosis, generated by an automatic algorithm based on native cardiac CT images.

Artificial Intelligence in the Diagnosis of Colorectal Cancer: A Literature Review

BACKGROUND

The aim of this review is to explore the role of artificial intelligence in the diagnosis of colorectal cancer, how it impacts CRC morbidity and mortality, and why its role in clinical medicine is limited.

METHODS

A targeted, non-systematic review of the published literature relating to colorectal cancer diagnosis was performed with PubMed databases that were scouted to help provide a more defined understanding of the recent advances regarding artificial intelligence and their impact on colorectal-related morbidity and mortality. Articles were included if deemed relevant and including information associated with the keywords.

RESULTS

The advancements in artificial intelligence have been significant in facilitating an earlier diagnosis of CRC. In this review, we focused on evaluating genomic biomarkers, the integration of instruments with artificial intelligence, MR and hyperspectral imaging, and the architecture of neural networks. We found that these neural networks seem practical and yield positive results in initial testing. Furthermore, we explored the use of deep-learning-based majority voting methods, such as bag of words and PAHLI, in improving diagnostic accuracy in colorectal cancer detection. Alongside this, the autonomous and expansive learning ability of artificial intelligence, coupled with its ability to extract increasingly complex features from images or videos without human reliance, highlight its impact in the diagnostic sector. Despite this, as most of the research involves a small sample of patients, a diversification of patient data is needed to enhance cohort stratification for a more sensitive and specific neural model. We also examined the successful application of artificial intelligence in predicting microsatellite instability, showcasing its potential in stratifying patients for targeted therapies.

CONCLUSIONS

Since its commencement in colorectal cancer, artificial intelligence has revealed a multitude of functionalities and augmentations in the diagnostic sector of CRC. Given its early implementation, its clinical application remains a fair way away, but with steady research dedicated to improving neural architecture and expanding its applicational range, there is hope that these advanced neural software could directly impact the early diagnosis of CRC. The true promise of artificial intelligence, extending beyond the medical sector, lies in its potential to significantly influence the future landscape of CRC's morbidity and mortality.

Preoperative automatic reminder systems and impact on quality and compliance with colonoscopy preparation: A multicenter randomized controlled trial

OBJECTIVES

Traditional preoperative reminding services have been applied to enhance the quality of bowel preparation for colonoscopy. In this study we aimed to evaluate the effectiveness of an automated electronic reminder system (E-reminder) on improving bowel preparation and the quality of preoperative education before colonoscopy.

METHODS

From August 2021 to March 2022, 833 outpatients aged 50-75 years who underwent colonoscopy were included and randomly assigned to the E-reminder group and the control group. While the control group received routine preoperative education. The E-reminder group received automatic phone call, text message reminders and web services regarding the details of bowel preparation before the colonoscopic examination. The quality of bowel preparation was evaluated by the Boston Bowel Preparation Scale (BBPS) score and the previously validated objective evaluation scale of automatic BBPS (e-BBPS).

RESULTS

In manual assessment, the rate of adequate bowel preparation was improved in the E-reminder group of intention-to-treat population using BBPS (60.7% vs 54.5%, P = 0.01). The percentage of objective evaluated adequate bowel preparation using e-BBPS in the E-reminder group of per-protocol population was significantly higher than that in the control group (76.9% vs 69.2%, P = 0.02).

CONCLUSIONS

E-reminder was an effective tool to improve the quality of bowel preparation and compliance with medical instructions. It may be regarded as an efficient and convenient education tool, improving the quality of medical service.

A Review Paper about Deep Learning for Medical Image Analysis

Medical imaging refers to the process of obtaining images of internal organs for therapeutic purposes such as discovering or studying diseases. The primary objective of medical image analysis is to improve the efficacy of clinical research and treatment options. Deep learning has revamped medical image analysis, yielding excellent results in image processing tasks such as registration, segmentation, feature extraction, and classification. The prime motivations for this are the availability of computational resources and the resurgence of deep convolutional neural networks. Deep learning techniques are good at observing hidden patterns in images and supporting clinicians in achieving diagnostic perfection. It has proven to be the most effective method for organ segmentation, cancer detection, disease categorization, and computer-assisted diagnosis. Many deep learning approaches have been published to analyze medical images for various diagnostic purposes. In this paper, we review the work exploiting current state-of-the-art deep learning approaches in medical image processing. We begin the survey by providing a synopsis of research works in medical imaging based on convolutional neural networks. Second, we discuss popular pretrained models and general adversarial networks that aid in improving convolutional networks' performance. Finally, to ease direct evaluation, we compile the performance metrics of deep learning models focusing on COVID-19 detection and child bone age prediction.

Hybrid Techniques for Diagnosing Endoscopy Images for Early Detection of Gastrointestinal Disease Based on Fusion Features

Gastrointestinal (GI) diseases, particularly tumours, are considered one of the most widespread and dangerous diseases and thus need timely health care for early detection to reduce deaths. Endoscopy technology is an effective technique for diagnosing GI diseases, thus producing a video containing thousands of frames. However, it is difficult to analyse all the images by a gastroenterologist, and it takes a long time to keep track of all the frames. Thus, artificial intelligence systems provide solutions to this challenge by analysing thousands of images with high speed and effective accuracy. Hence, systems with different methodologies are developed in this work. The first methodology for diagnosing endoscopy images of GI diseases is by using VGG-16 + SVM and DenseNet-121 + SVM. The second methodology for diagnosing endoscopy images of gastrointestinal diseases by artificial neural network (ANN) is based on fused features between VGG-16 and DenseNet-121 before and after high-dimensionality reduction by the principal component analysis (PCA). The third methodology is by ANN and is based on the fused features between VGG-16 and handcrafted features and features fused between DenseNet-121 and the handcrafted features. Herein, handcrafted features combine the features of gray level cooccurrence matrix (GLCM), discrete wavelet transform (DWT), fuzzy colour histogram (FCH), and local binary pattern (LBP) methods. All systems achieved promising results for diagnosing endoscopy images of the gastroenterology data set. The ANN network reached an accuracy, sensitivity, precision, specificity, and an AUC of 98.9%, 98.70%, 98.94%, 99.69%, and 99.51%, respectively, based on fused features of the VGG-16 and the handcrafted.

A Multiscale Polyp Detection Approach for GI Tract Images Based on Improved DenseNet and Single-Shot Multibox Detector

Small bowel polyps exhibit variations related to color, shape, morphology, texture, and size, as well as to the presence of artifacts, irregular polyp borders, and the low illumination condition inside the gastrointestinal GI tract. Recently, researchers developed many highly accurate polyp detection models based on one-stage or two-stage object detector algorithms for wireless capsule endoscopy (WCE) and colonoscopy images. However, their implementation requires a high computational power and memory resources, thus sacrificing speed for an improvement in precision. Although the single-shot multibox detector (SSD) proves its effectiveness in many medical imaging applications, its weak detection ability for small polyp regions persists due to the lack of information complementary between features of low- and high-level layers. The aim is to consecutively reuse feature maps between layers of the original SSD network. In this paper, we propose an innovative SSD model based on a redesigned version of a dense convolutional network (DenseNet) which emphasizes multiscale pyramidal feature maps interdependence called DC-SSDNet (densely connected single-shot multibox detector). The original backbone network VGG-16 of the SSD is replaced with a modified version of DenseNet. The DenseNet-46 front stem is improved to extract highly typical characteristics and contextual information, which improves the model's feature extraction ability. The DC-SSDNet architecture compresses unnecessary convolution layers of each dense block to reduce the CNN model complexity. Experimental results showed a remarkable improvement in the proposed DC-SSDNet to detect small polyp regions achieving an mAP of 93.96%, F1-score of 90.7%, and requiring less computational time.

Comprehensive review of publicly available colonoscopic imaging databases for artificial intelligence research: availability, accessibility, and usability

BACKGROUND AND AIMS

Publicly available databases containing colonoscopic imaging data are valuable resources for artificial intelligence (AI) research. Currently, little is known regarding the available number and content of these databases. This review aimed to describe the availability, accessibility, and usability of publicly available colonoscopic imaging databases, focusing on polyp detection, polyp characterization, and quality of colonoscopy.

METHODS

A systematic literature search was performed in MEDLINE and Embase to identify AI studies describing publicly available colonoscopic imaging databases published after 2010. Second, a targeted search using Google's Dataset Search, Google Search, GitHub, and Figshare was done to identify databases directly. Databases were included if they contained data about polyp detection, polyp characterization, or quality of colonoscopy. To assess accessibility of databases, the following categories were defined: open access, open access with barriers, and regulated access. To assess the potential usability of the included databases, essential details of each database were extracted using a checklist derived from the Checklist for Artificial Intelligence in Medical Imaging.

RESULTS

We identified 22 databases with open access, 3 databases with open access with barriers, and 15 databases with regulated access. The 22 open access databases contained 19,463 images and 952 videos. Nineteen of these databases focused on polyp detection, localization, and/or segmentation; 6 on polyp characterization, and 3 on quality of colonoscopy. Only half of these databases have been used by other researcher to develop, train, or benchmark their AI system. Although technical details were in general well reported, important details such as polyp and patient demographics and the annotation process were under-reported in almost all databases.

CONCLUSIONS

This review provides greater insight on public availability of colonoscopic imaging databases for AI research. Incomplete reporting of important details limits the ability of researchers to assess the usability of current databases.

Multi-Scale Hybrid Network for Polyp Detection in Wireless Capsule Endoscopy and Colonoscopy Images

The trade-off between speed and precision is a key step in the detection of small polyps in wireless capsule endoscopy (WCE) images. In this paper, we propose a hybrid network of an inception v4 architecture-based single-shot multibox detector (Hyb-SSDNet) to detect small polyp regions in both WCE and colonoscopy frames. Medical privacy concerns are considered the main barriers to WCE image acquisition. To satisfy the object detection requirements, we enlarged the training datasets and investigated deep transfer learning techniques. The Hyb-SSDNet framework adopts inception blocks to alleviate the inherent limitations of the convolution operation to incorporate contextual features and semantic information into deep networks. It consists of four main components: (a) multi-scale encoding of small polyp regions, (b) using the inception v4 backbone to enhance more contextual features in shallow and middle layers, and (c) concatenating weighted features of mid-level feature maps, giving them more importance to highly extract semantic information. Then, the feature map fusion is delivered to the next layer, followed by some downsampling blocks to generate new pyramidal layers. Finally, the feature maps are fed to multibox detectors, consistent with the SSD process-based VGG16 network. The Hyb-SSDNet achieved a 93.29% mean average precision (mAP) and a testing speed of 44.5 FPS on the WCE dataset. This work proves that deep learning has the potential to develop future research in polyp detection and classification tasks.

Automatic Detection and Segmentation of Colorectal Cancer with Deep Residual Convolutional Neural Network

Early and automatic detection of colorectal tumors is essential for cancer analysis, and the same is implemented using computer-aided diagnosis (CAD). A computerized tomography (CT) image of the colon is being used to identify colorectal carcinoma. Digital imaging and communication in medicine (DICOM) is a standard medical imaging format to process and analyze images digitally. Accurate detection of tumor cells in the complex digestive tract is necessary for optimal treatment. The proposed work is divided into two phases. The first phase involves the segmentation, and the second phase is the extraction of the colon lesions with the observed segmentation parameters. A deep convolutional neural network (DCNN) based residual network approach for the colon and polyps' segmentation from the CT images is applied over the 2D CT images. The residual stack block is being added to the hidden layers with short skip nuance, which helps to retain spatial information. ResNet-enabled CNN is employed in the current work to achieve complete boundary segmentation of the colon cancer region. The results obtained through segmentation serve as features for further extraction and classification of benign as well as malignant colon cancer. Performance evaluation metrics indicate that the proposed network model has effectively segmented and classified colorectal tumors with dice scores of 91.57% (on average), sensitivity = 98.28, specificity = 98.68, and accuracy = 98.82.

Modelling in Synthesis and Optimization of Active Vaccinal Components

Cancer is the second leading cause of mortality worldwide, behind heart diseases, accounting for 10 million deaths each year. This study focusses on adenocarcinoma, which is a target of a number of anticancer therapies presently being tested in medical and pharmaceutical studies. The innovative study for a therapeutic vaccine comprises the investigation of gold nanoparticles and their influence on the immune response for the annihilation of cancer cells. The model is intended to be realized using Quantitative-Structure Activity Relationship (QSAR) methods, explicitly artificial neural networks combined with fuzzy rules, to enhance automated properties of neural nets with human perception characteristics. Image processing techniques such as morphological transformations and watershed segmentation are used to extract and calculate certain molecular characteristics from hyperspectral images. The quantification of single-cell properties is one of the key resolutions, representing the treatment efficiency in therapy of colon and rectum cancerous conditions. This was accomplished by using manually counted cells as a reference point for comparing segmentation results. The early findings acquired are conclusive for further study; thus, the extracted features will be used in the feature optimization process first, followed by neural network building of the required model.