A deep learning framework for the detection of Plus disease in retinal fundus images of preterm infants

An Interpretable System for Screening the Severity Level of Retinopathy in Premature Infants Using Deep Learning

Accurate evaluation of retinopathy of prematurity (ROP) severity is vital for screening and proper treatment. Current deep-learning-based automated AI systems for assessing ROP severity do not follow clinical guidelines and are opaque. The aim of this study is to develop an interpretable AI system by mimicking the clinical screening process to determine ROP severity level. A total of 6100 RetCam Ⅲ wide-field digital retinal images were collected from Guangdong Women and Children Hospital at Panyu (PY) and Zhongshan Ophthalmic Center (ZOC). A total of 3330 images of 520 pediatric patients from PY were annotated to train an object detection model to detect lesion type and location. A total of 2770 images of 81 pediatric patients from ZOC were annotated for stage, zone, and the presence of plus disease. Integrating stage, zone, and the presence of plus disease according to clinical guidelines yields ROP severity such that an interpretable AI system was developed to provide the stage from the lesion type, the zone from the lesion location, and the presence of plus disease from a plus disease classification model. The ROP severity was calculated accordingly and compared with the assessment of a human expert. Our method achieved an area under the curve (AUC) of 0.95 (95% confidence interval [CI] 0.90-0.98) in assessing the severity level of ROP. Compared with clinical doctors, our method achieved the highest F1 score value of 0.76 in assessing the severity level of ROP. In conclusion, we developed an interpretable AI system for assessing the severity level of ROP that shows significant potential for use in clinical practice for ROP severity level screening.

Automatic zoning for retinopathy of prematurity with a key area location system

Retinopathy of prematurity (ROP) usually occurs in premature or low birth weight infants and has been an important cause of childhood blindness worldwide. Diagnosis and treatment of ROP are mainly based on stage, zone and disease, where the zone is more important than the stage for serious ROP. However, due to the great subjectivity and difference of ophthalmologists in the diagnosis of ROP zoning, it is challenging to achieve accurate and objective ROP zoning diagnosis. To address it, we propose a new key area location (KAL) system to achieve automatic and objective ROP zoning based on its definition, which consists of a key point location network and an object detection network. Firstly, to achieve the balance between real-time and high-accuracy, a lightweight residual heatmap network (LRH-Net) is designed to achieve the location of the optic disc (OD) and macular center, which transforms the location problem into a pixel-level regression problem based on the heatmap regression method and maximum likelihood estimation theory. In addition, to meet the needs of clinical accuracy and real-time detection, we use the one-stage object detection framework Yolov3 to achieve ROP lesion location. Finally, the experimental results have demonstrated that the proposed KAL system has achieved better performance on key point location (6.13 and 17.03 pixels error for OD and macular center location) and ROP lesion location (93.05% for AP50), and the ROP zoning results based on it have good consistency with the results manually labeled by clinicians, which can support clinical decision-making and help ophthalmologists correctly interpret ROP zoning, reducing subjective differences of diagnosis and increasing the interpretability of zoning results.

Identification of novel biomarkers for retinopathy of prematurity in preterm infants by use of innovative technologies and artificial intelligence

Retinopathy of prematurity (ROP) is a leading cause of preventable vision loss in preterm infants. While appropriate screening is crucial for early identification and treatment of ROP, current screening guidelines remain limited by inter-examiner variability in screening modalities, absence of local protocol for ROP screening in some settings, a paucity of resources and an increased survival of younger and smaller infants. This review summarizes the advancements and challenges of current innovative technologies, artificial intelligence (AI), and predictive biomarkers for the diagnosis and management of ROP. We provide a contemporary overview of AI-based models for detection of ROP, its severity, progression, and response to treatment. To address the transition from experimental settings to real-world clinical practice, challenges to the clinical implementation of AI for ROP are reviewed and potential solutions are proposed. The use of optical coherence tomography (OCT) and OCT angiography (OCTA) technology is also explored, providing evaluation of subclinical ROP characteristics that are often imperceptible on fundus examination. Furthermore, we explore several potential biomarkers to reduce the need for invasive procedures, to enhance diagnostic accuracy and treatment efficacy. Finally, we emphasize the need of a symbiotic integration of biologic and imaging biomarkers and AI in ROP screening, where the robustness of biomarkers in early disease detection is complemented by the predictive precision of AI algorithms.

Early prediction of need for invasive mechanical ventilation in the neonatal intensive care unit using artificial intelligence and electronic health records: a clinical study

BACKGROUND

Respiratory support is crucial for newborns with underdeveloped lung. The clinical outcomes of patients depend on the clinician's ability to recognize the status underlying the presented symptoms and signs. With the increasing number of high-risk infants, artificial intelligence (AI) should be considered as a tool for personalized neonatal care. Continuous monitoring of vital signs is essential in cardiorespiratory care. In this study, we developed deep learning (DL) prediction models for rapid and accurate detection of mechanical ventilation requirements in neonates using electronic health records (EHR).

METHODS

We utilized data from the neonatal intensive care unit in a single center, collected between March 3, 2012, and March 4, 2022, including 1,394 patient records used for model development, consisting of 505 and 889 patients with and without invasive mechanical ventilation (IMV) support, respectively. The proposed model architecture includes feature embedding using feature-wise fully connected (FC) layers, followed by three bidirectional long short-term memory (LSTM) layers.

RESULTS

A mean gestational age (GA) was 36.61 ± 3.25 weeks, and the mean birth weight was 2,734.01 ± 784.98 g. The IMV group had lower GA, birth weight, and longer hospitalization duration than the non-IMV group (P < 0.05). Our proposed model, tested on a dataset from March 4, 2019, to March 4, 2022. The mean AUROC of our proposed model for IMV support prediction performance demonstrated 0.861 (95%CI, 0.853-0.869). It is superior to conventional approaches, such as newborn early warning score systems (NEWS), Random Forest, and eXtreme gradient boosting (XGBoost) with 0.611 (95%CI, 0.600-0.622), 0.837 (95%CI, 0.828-0.845), and 0.0.831 (95%CI, 0.821-0.845), respectively. The highest AUPRC value is shown in the proposed model at 0.327 (95%CI, 0.308-0.347). The proposed model performed more accurate predictions as gestational age decreased. Additionally, the model exhibited the lowest alarm rate while maintaining the same sensitivity level.

CONCLUSION

Deep learning approaches can help accurately standardize the prediction of invasive mechanical ventilation for neonatal patients and facilitate advanced neonatal care. The results of predictive, recall, and alarm performances of the proposed model outperformed the other models.

PDC-Net: parallel dilated convolutional network with channel attention mechanism for pituitary adenoma segmentation

Accurate segmentation of the medical image is the basis and premise of intelligent diagnosis and treatment, which has a wide range of clinical application value. However, the robustness and effectiveness of medical image segmentation algorithms remains a challenging subject due to the unbalanced categories, blurred boundaries, highly variable anatomical structures and lack of training samples. For this reason, we present a parallel dilated convolutional network (PDC-Net) to address the pituitary adenoma segmentation in magnetic resonance imaging images. Firstly, the standard convolution block in U-Net is replaced by a basic convolution operation and a parallel dilated convolutional module (PDCM), to extract the multi-level feature information of different dilations. Furthermore, the channel attention mechanism (CAM) is integrated to enhance the ability of the network to distinguish between lesions and non-lesions in pituitary adenoma. Then, we introduce residual connections at each layer of the encoder-decoder, which can solve the problem of gradient disappearance and network performance degradation caused by network deepening. Finally, we employ the dice loss to deal with the class imbalance problem in samples. By testing on the self-established patient dataset from Quzhou People's Hospital, the experiment achieves 90.92% of Sensitivity, 99.68% of Specificity, 88.45% of Dice value and 79.43% of Intersection over Union (IoU).

Artificial intelligence for the diagnosis of retinopathy of prematurity: A systematic review of current algorithms

BACKGROUND/OBJECTIVES

With the increasing survival of premature infants, there is an increased demand to provide adequate retinopathy of prematurity (ROP) services. Wide field retinal imaging (WFDRI) and artificial intelligence (AI) have shown promise in the field of ROP and have the potential to improve the diagnostic performance and reduce the workload for screening ophthalmologists. The aim of this review is to systematically review and provide a summary of the diagnostic characteristics of existing deep learning algorithms.

SUBJECT/METHODS

Two authors independently searched the literature, and studies using a deep learning system from retinal imaging were included. Data were extracted, assessed and reported using PRISMA guidelines.

RESULTS

Twenty-seven studies were included in this review. Nineteen studies used AI systems to diagnose ROP, classify the staging of ROP, diagnose the presence of pre-plus or plus disease, or assess the quality of retinal images. The included studies reported a sensitivity of 71%-100%, specificity of 74-99% and area under the curve of 91-99% for the primary outcome of the study. AI techniques were comparable to the assessment of ophthalmologists in terms of overall accuracy and sensitivity. Eight studies evaluated vascular severity scores and were able to accurately differentiate severity using an automated classification score.

CONCLUSION

Artificial intelligence for ROP diagnosis is a growing field, and many potential utilities have already been identified, including the presence of plus disease, staging of disease and a new automated severity score. AI has a role as an adjunct to clinical assessment; however, there is insufficient evidence to support its use as a sole diagnostic tool currently.

Computer-Aided detection of tuberculosis from X-ray images using CNN and PatternNet classifier

BACKGROUND

Tuberculosis (TB) is a highly infectious disease that mainly affects the human lungs. The gold standard for TB diagnosis is Xpert Mycobacterium tuberculosis/ resistance to rifampicin (MTB/RIF) testing. X-ray, a relatively inexpensive and widely used imaging modality, can be employed as an alternative for early diagnosis of the disease. Computer-aided techniques can be used to assist radiologists in interpreting X-ray images, which can improve the ease and accuracy of diagnosis.

OBJECTIVE

To develop a computer-aided technique for the diagnosis of TB from X-ray images using deep learning techniques.

METHODS

This research paper presents a novel approach for TB diagnosis from X-ray using deep learning methods. The proposed method uses an ensemble of two pre-trained neural networks, namely EfficientnetB0 and Densenet201, for feature extraction. The features extracted using two CNNs are expected to generate more accurate and representative features than a single CNN. A custom-built artificial neural network (ANN) called PatternNet with two hidden layers is utilized to classify the extracted features.

RESULTS

The effectiveness of the proposed method was assessed on two publicly accessible datasets, namely the Montgomery and Shenzhen datasets. The Montgomery dataset comprises 138 X-ray images, while the Shenzhen dataset has 662 X-ray images. The method was further evaluated after combining both datasets. The method performed exceptionally well on all three datasets, achieving high Area Under the Curve (AUC) scores of 0.9978, 0.9836, and 0.9914, respectively, using a 10-fold cross-validation technique.

CONCLUSION

The experiments performed in this study prove the effectiveness of features extracted using EfficientnetB0 and Densenet201 in combination with PatternNet classifier in the diagnosis of tuberculosis from X-ray images.

Accuracy of Deep Learning Algorithms for the Diagnosis of Retinopathy of Prematurity by Fundus Images: A Systematic Review and Meta-Analysis

Background

Retinopathy of prematurity (ROP) occurs in preterm infants and may contribute to blindness. Deep learning (DL) models have been used for ophthalmologic diagnoses. We performed a systematic review and meta-analysis of published evidence to summarize and evaluate the diagnostic accuracy of DL algorithms for ROP by fundus images.

Methods

We searched PubMed, EMBASE, Web of Science, and Institute of Electrical and Electronics Engineers Xplore Digital Library on June 13, 2021, for studies using a DL algorithm to distinguish individuals with ROP of different grades, which provided accuracy measurements. The pooled sensitivity and specificity values and the area under the curve (AUC) of summary receiver operating characteristics curves (SROC) summarized overall test performance. The performances in validation and test datasets were assessed together and separately. Subgroup analyses were conducted between the definition and grades of ROP. Threshold and nonthreshold effects were tested to assess biases and evaluate accuracy factors associated with DL models.

Results

Nine studies with fifteen classifiers were included in our meta-analysis. A total of 521,586 objects were applied to DL models. For combined validation and test datasets in each study, the pooled sensitivity and specificity were 0.953 (95% confidence intervals (CI): 0.946-0.959) and 0.975 (0.973-0.977), respectively, and the AUC was 0.984 (0.978-0.989). For the validation dataset and test dataset, the AUC was 0.977 (0.968-0.986) and 0.987 (0.982-0.992), respectively. In the subgroup analysis of ROP vs. normal and differentiation of two ROP grades, the AUC was 0.990 (0.944-0.994) and 0.982 (0.964-0.999), respectively.

Conclusions

Our study shows that DL models can play an essential role in detecting and grading ROP with high sensitivity, specificity, and repeatability. The application of a DL-based automated system may improve ROP screening and diagnosis in the future.