A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective.

Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (e.g., social network analysis and recommender systems), computer vision (e.g., object detection and point cloud learning), and natural language processing (e.g., relation extraction and sequence learning), to name a few. With the emergence of Transformers in natural language processing and computer vision, graph Transformers embed a graph structure into the Transformer architecture to overcome the limitations of local neighborhood aggregation while avoiding strict structural inductive biases. In this paper, we present a comprehensive review of GNNs and graph Transformers in computer vision from a task-oriented perspective. Specifically, we divide their applications in computer vision into five categories according to the modality of input data, i.e., 2D natural images, videos, 3D data, vision + language, and medical images. In each category, we further divide the applications according to a set of vision tasks. Such a task-oriented taxonomy allows us to examine how each task is tackled by different GNN-based approaches and how well these approaches perform. Based on the necessary preliminaries, we provide the definitions and challenges of the tasks, in-depth coverage of the representative approaches, as well as discussions regarding insights, limitations, and future directions.

A multimodal integration pipeline for accurate diagnosis, pathogen identification, and prognosis prediction of pulmonary infections.

Pulmonary infections pose formidable challenges in clinical settings with high mortality rates across all age groups worldwide. Accurate diagnosis and early intervention are crucial to improve patient outcomes. Artificial intelligence (AI) has the capability to mine imaging features specific to different pathogens and fuse multimodal features to reach a synergistic diagnosis, enabling more precise investigation and individualized clinical management. In this study, we successfully developed a multimodal integration (MMI) pipeline to differentiate among bacterial, fungal, and viral pneumonia and pulmonary tuberculosis based on a real-world dataset of 24,107 patients. The area under the curve (AUC) of the MMI system comprising clinical text and computed tomography (CT) image scans yielded 0.910 (95% confidence interval [CI]: 0.904-0.916) and 0.887 (95% CI: 0.867-0.909) in the internal and external testing datasets respectively, which were comparable to those of experienced physicians. Furthermore, the MMI system was utilized to rapidly differentiate between viral subtypes with a mean AUC of 0.822 (95% CI: 0.805-0.837) and bacterial subtypes with a mean AUC of 0.803 (95% CI: 0.775-0.830). Here, the MMI system harbors the potential to guide tailored medication recommendations, thus mitigating the risk of antibiotic misuse. Additionally, the integration of multimodal factors in the AI-driven system also provided an evident advantage in predicting risks of developing critical illness, contributing to more informed clinical decision-making. To revolutionize medical care, embracing multimodal AI tools in pulmonary infections will pave the way to further facilitate early intervention and precise management in the foreseeable future.

Assessing the Impact of an Artificial Intelligence-Based Model for Intracranial Aneurysm Detection in CT Angiography on Patient Diagnosis and Outcomes (IDEAL Study)-a protocol for a multicenter, double-blinded randomized controlled trial.

BACKGROUND: This multicenter, double-blinded, randomized controlled trial (RCT) aims to assess the impact of an artificial intelligence (AI)-based model on the efficacy of intracranial aneurysm detection in CT angiography (CTA) and its influence on patients' short-term and long-term outcomes. METHODS: Study design: Prospective, multicenter, double-blinded RCT. SETTINGS: The model was designed for the automatic detection of intracranial aneurysms from original CTA images. PARTICIPANTS: Adult inpatients and outpatients who are scheduled for head CTA scanning. Randomization groups: (1) Experimental Group: Head CTA interpreted by radiologists with the assistance of the True-AI-integrated intracranial aneurysm diagnosis strategy (True-AI arm). (2) Control Group: Head CTA interpreted by radiologists with the assistance of the Sham-AI-integrated intracranial aneurysm diagnosis strategy (Sham-AI arm). RANDOMIZATION: Block randomization, stratified by center, gender, and age group. PRIMARY OUTCOMES: Coprimary outcomes of superiority in patient-level sensitivity and noninferiority in specificity for the True-AI arm to the Sham-AI arm in intracranial aneurysms. SECONDARY OUTCOMES: Diagnostic performance for other intracranial lesions, detection rates, workload of CTA interpretation, resource utilization, treatment-related clinical events, aneurysm-related events, quality of life, and cost-effectiveness analysis. BLINDING: Study participants and participating radiologists will be blinded to the intervention. SAMPLE SIZE: Based on our pilot study, the patient-level sensitivity is assumed to be 0.65 for the Sham-AI arm and 0.75 for the True-AI arm, with specificities of 0.90 and 0.88, respectively. The prevalence of intracranial aneurysms for patients undergoing head CTA in the hospital is approximately 12%. To establish superiority in sensitivity and noninferiority in specificity with a margin of 5% using a one-sided α = 0.025 to ensure that the power of coprimary endpoint testing reached 0.80 and a 5% attrition rate, the sample size was determined to be 6450 in a 1:1 allocation to True-AI or Sham-AI arm. DISCUSSION: The study will determine the precise impact of the AI system on the detection performance for intracranial aneurysms in a double-blinded design and following the real-world effects on patients' short-term and long-term outcomes. TRIAL REGISTRATION: This trial has been registered with the NIH, U.S. National Library of Medicine at ClinicalTrials.gov, ID: NCT06118840 . Registered 11 November 2023.

Mitochondrial One-Carbon Metabolism and Alzheimer's Disease.

Mitochondrial one-carbon metabolism provides carbon units to several pathways, including nucleic acid synthesis, mitochondrial metabolism, amino acid metabolism, and methylation reactions. Late-onset Alzheimer's disease is the most common age-related neurodegenerative disease, characterised by impaired energy metabolism, and is potentially linked to mitochondrial bioenergetics. Here, we discuss the intersection between the molecular pathways linked to both mitochondrial one-carbon metabolism and Alzheimer's disease. We propose that enhancing one-carbon metabolism could promote the metabolic processes that help brain cells cope with Alzheimer's disease-related injuries. We also highlight potential therapeutic avenues to leverage one-carbon metabolism to delay Alzheimer's disease pathology.

Identification of mycoplasma pneumonia in children based on fusion of multi-modal clinical free-text description and structured test data.

Mycoplasma pneumonia may lead to hospitalizations and pose life-threatening risks in children. The automated identification of mycoplasma pneumonia from electronic medical records holds significant potential for improving the efficiency of hospital resource allocation. In this study, we proposed a novel method for identifying mycoplasma pneumonia by integrating multi-modal features derived from both free-text descriptions and structured test data in electronic medical records. Our approach begins with the extraction of free-text and structured data from clinical records through a systematic preprocessing pipeline. Subsequently, we employ a pre-trained transformer language model to extract features from the free-text, while multiple additive regression trees are used to transform features from the structured data. An attention-based fusion mechanism is then applied to integrate these multi-modal features for effective classification. We validated our method using clinic records of 7157 patients, retrospectively collected for training and testing purposes. The experimental results demonstrate that our proposed multi-modal fusion approach achieves significant improvements over other methods across four key performance metrics.

Novel Quantitative Contrast Sensitivity Function Enhances the Prediction of Treatment Outcome and Recurrence in Amblyopia.

Purpose: Although effective amblyopia treatments are available, treatment outcome is unpredictable, and the condition recurs in up to 25% of the patients. We aimed to evaluate whether a large-scale quantitative contrast sensitivity function (CSF) data source, coupled with machine learning (ML) algorithms, can predict amblyopia treatment response and recurrence in individuals. Methods: Visual function measures from traditional chart vision acuity (VA) and novel CSF assessments were used as the main predictive variables in the models. Information from 58 potential predictors was extracted to predict treatment response and recurrence. Six ML methods were applied to construct models. The SHapley Additive exPlanations was used to explain the predictions. Results: A total of 2559 consecutive records of 643 patients with amblyopia were eligible for modeling. Combining variables from VA and CSF assessments gave the highest accuracy for treatment response prediction, with the area under the receiver operating characteristic curve (AUC) of 0.863 and 0.815 for outcome predictions after 3 and 6 months, respectively. Variables from the VA assessment alone predicted the treatment response, with AUC values of 0.723 and 0.675 after 3 and 6 months, respectively. Variables from the CSF assessment gave rise to an AUC of 0.909 for recurrence prediction compared to 0.539 for VA assessment alone, and adding VA variables did not improve predictive performance. The interocular differences in CSF features are significant contributors to recurrence risk. Conclusions: Our models showed CSF data could enhance treatment response prediction and accurately predict amblyopia recurrence, which has the potential to guide amblyopia management by enabling patient-tailored decision making.

Predicting Invasiveness of Lung Adenocarcinoma at Chest CT with Deep Learning Ternary Classification Models.

Background Preoperative discrimination of preinvasive, minimally invasive, and invasive adenocarcinoma at CT informs clinical management decisions but may be challenging for classifying pure ground-glass nodules (pGGNs). Deep learning (DL) may improve ternary classification. Purpose To determine whether a strategy that includes an adjudication approach can enhance the performance of DL ternary classification models in predicting the invasiveness of adenocarcinoma at chest CT and maintain performance in classifying pGGNs. Materials and Methods In this retrospective study, six ternary models for classifying preinvasive, minimally invasive, and invasive adenocarcinoma were developed using a multicenter data set of lung nodules. The DL-based models were progressively modified through framework optimization, joint learning, and an adjudication strategy (simulating a multireader approach to resolving discordant nodule classifications), integrating two binary classification models with a ternary classification model to resolve discordant classifications sequentially. The six ternary models were then tested on an external data set of pGGNs imaged between December 2019 and January 2021. Diagnostic performance including accuracy, specificity, and sensitivity was assessed. The χ2 test was used to compare model performance in different subgroups stratified by clinical confounders. Results A total of 4929 nodules from 4483 patients (mean age, 50.1 years ± 9.5 [SD]; 2806 female) were divided into training (n = 3384), validation (n = 579), and internal (n = 966) test sets. A total of 361 pGGNs from 281 patients (mean age, 55.2 years ± 11.1 [SD]; 186 female) formed the external test set. The proposed strategy improved DL model performance in external testing (P < .001). For classifying minimally invasive adenocarcinoma, the accuracy was 85% and 79%, sensitivity was 75% and 63%, and specificity was 89% and 85% for the model with adjudication (model 6) and the model without (model 3), respectively. Model 6 showed a relatively narrow range (maximum minus minimum) across diagnostic indexes (accuracy, 1.7%; sensitivity, 7.3%; specificity, 0.9%) compared with the other models (accuracy, 0.6%-10.8%; sensitivity, 14%-39.1%; specificity, 5.5%-17.9%). Conclusion Combining framework optimization, joint learning, and an adjudication approach improved DL classification of adenocarcinoma invasiveness at chest CT. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Sohn and Fields in this issue.

Genome-wide CRISPR/Cas9 screen shows that loss of GET4 increases mitochondria-endoplasmic reticulum contact sites and is neuroprotective.

Organelles form membrane contact sites between each other, allowing for the transfer of molecules and signals. Mitochondria-endoplasmic reticulum (ER) contact sites (MERCS) are cellular subdomains characterized by close apposition of mitochondria and ER membranes. They have been implicated in many diseases, including neurodegenerative, metabolic, and cardiac diseases. Although MERCS have been extensively studied, much remains to be explored. To uncover novel regulators of MERCS, we conducted a genome-wide, flow cytometry-based screen using an engineered MERCS reporter cell line. We found 410 genes whose downregulation promotes MERCS and 230 genes whose downregulation decreases MERCS. From these, 29 genes were selected from each population for arrayed screening and 25 were validated from the high population and 13 from the low population. GET4 and BAG6 were highlighted as the top 2 genes that upon suppression increased MERCS from both the pooled and arrayed screens, and these were subjected to further investigation. Multiple microscopy analyses confirmed that loss of GET4 or BAG6 increased MERCS. GET4 and BAG6 were also observed to interact with the known MERCS proteins, inositol 1,4,5-trisphosphate receptors (IP3R) and glucose-regulated protein 75 (GRP75). In addition, we found that loss of GET4 increased mitochondrial calcium uptake upon ER-Ca2+ release and mitochondrial respiration. Finally, we show that loss of GET4 rescues motor ability, improves lifespan and prevents neurodegeneration in a Drosophila model of Alzheimer's disease (Aß42Arc). Together, these results suggest that GET4 is involved in decreasing MERCS and that its loss is neuroprotective.

A deep-learning model for intracranial aneurysm detection on CT angiography images in China: a stepwise, multicentre, early-stage clinical validation study.

BACKGROUND: Artificial intelligence (AI) models in real-world implementation are scarce. Our study aimed to develop a CT angiography (CTA)-based AI model for intracranial aneurysm detection, assess how it helps clinicians improve diagnostic performance, and validate its application in real-world clinical implementation. METHODS: We developed a deep-learning model using 16 546 head and neck CTA examination images from 14 517 patients at eight Chinese hospitals. Using an adapted, stepwise implementation and evaluation, 120 certified clinicians from 15 geographically different hospitals were recruited. Initially, the AI model was externally validated with images of 900 digital subtraction angiography-verified CTA cases (examinations) and compared with the performance of 24 clinicians who each viewed 300 of these cases (stage 1). Next, as a further external validation a multi-reader multi-case study enrolled 48 clinicians to individually review 298 digital subtraction angiography-verified CTA cases (stage 2). The clinicians reviewed each CTA examination twice (ie, with and without the AI model), separated by a 4-week washout period. Then, a randomised open-label comparison study enrolled 48 clinicians to assess the acceptance and performance of this AI model (stage 3). Finally, the model was prospectively deployed and validated in 1562 real-world clinical CTA cases. FINDINGS: The AI model in the internal dataset achieved a patient-level diagnostic sensitivity of 0·957 (95% CI 0·939-0·971) and a higher patient-level diagnostic sensitivity than clinicians (0·943 [0·921-0·961] vs 0·658 [0·644-0·672]; p<0·0001) in the external dataset. In the multi-reader multi-case study, the AI-assisted strategy improved clinicians' diagnostic performance both on a per-patient basis (the area under the receiver operating characteristic curves [AUCs]; 0·795 [0·761-0·830] without AI vs 0·878 [0·850-0·906] with AI; p<0·0001) and a per-aneurysm basis (the area under the weighted alternative free-response receiver operating characteristic curves; 0·765 [0·732-0·799] vs 0·865 [0·839-0·891]; p<0·0001). Reading time decreased with the aid of the AI model (87·5 s vs 82·7 s, p<0·0001). In the randomised open-label comparison study, clinicians in the AI-assisted group had a high acceptance of the AI model (92·6% adoption rate), and a higher AUC when compared with the control group (0·858 [95% CI 0·850-0·866] vs 0·789 [0·780-0·799]; p<0·0001). In the prospective study, the AI model had a 0·51% (8/1570) error rate due to poor-quality CTA images and recognition failure. The model had a high negative predictive value of 0·998 (0·994-1·000) and significantly improved the diagnostic performance of clinicians; AUC improved from 0·787 (95% CI 0·766-0·808) to 0·909 (0·894-0·923; p<0·0001) and patient-level sensitivity improved from 0·590 (0·511-0·666) to 0·825 (0·759-0·880; p<0·0001). INTERPRETATION: This AI model demonstrated strong clinical potential for intracranial aneurysm detection with improved clinician diagnostic performance, high acceptance, and practical implementation in real-world clinical cases. FUNDING: National Natural Science Foundation of China. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

A multicenter clinical AI system study for detection and diagnosis of focal liver lesions.

Early and accurate diagnosis of focal liver lesions is crucial for effective treatment and prognosis. We developed and validated a fully automated diagnostic system named Liver Artificial Intelligence Diagnosis System (LiAIDS) based on a diverse sample of 12,610 patients from 18 hospitals, both retrospectively and prospectively. In this study, LiAIDS achieved an F1-score of 0.940 for benign and 0.692 for malignant lesions, outperforming junior radiologists (benign: 0.830-0.890, malignant: 0.230-0.360) and being on par with senior radiologists (benign: 0.920-0.950, malignant: 0.550-0.650). Furthermore, with the assistance of LiAIDS, the diagnostic accuracy of all radiologists improved. For benign and malignant lesions, junior radiologists' F1-scores improved to 0.936-0.946 and 0.667-0.680 respectively, while seniors improved to 0.950-0.961 and 0.679-0.753. Additionally, in a triage study of 13,192 consecutive patients, LiAIDS automatically classified 76.46% of patients as low risk with a high NPV of 99.0%. The evidence suggests that LiAIDS can serve as a routine diagnostic tool and enhance the diagnostic capabilities of radiologists for liver lesions.

Deep Learning for Chest X-ray Diagnosis: Competition Between Radiologists with or Without Artificial Intelligence Assistance.

This study aimed to assess the performance of a deep learning algorithm in helping radiologist achieve improved efficiency and accuracy in chest radiograph diagnosis. We adopted a deep learning algorithm to concurrently detect the presence of normal findings and 13 different abnormalities in chest radiographs and evaluated its performance in assisting radiologists. Each competing radiologist had to determine the presence or absence of these signs based on the label provided by the AI. The 100 radiographs were randomly divided into two sets for evaluation: one without AI assistance (control group) and one with AI assistance (test group). The accuracy, false-positive rate, false-negative rate, and analysis time of 111 radiologists (29 senior, 32 intermediate, and 50 junior) were evaluated. A radiologist was given an initial score of 14 points for each image read, with 1 point deducted for an incorrect answer and 0 points given for a correct answer. The final score for each doctor was automatically calculated by the backend calculator. We calculated the mean scores of each radiologist in the two groups (the control group and the test group) and calculated the mean scores to evaluate the performance of the radiologists with and without AI assistance. The average score of the 111 radiologists was 597 (587-605) in the control group and 619 (612-626) in the test group (P < 0.001). The time spent by the 111 radiologists on the control and test groups was 3279 (2972-3941) and 1926 (1710-2432) s, respectively (P < 0.001). The performance of the 111 radiologists in the two groups was evaluated by the area under the receiver operating characteristic curve (AUC). The radiologists showed better performance on the test group of radiographs in terms of normal findings, pulmonary fibrosis, heart shadow enlargement, mass, pleural effusion, and pulmonary consolidation recognition, with AUCs of 1.0, 0.950, 0.991, 1.0, 0.993, and 0.982, respectively. The radiologists alone showed better performance in aortic calcification (0.993), calcification (0.933), cavity (0.963), nodule (0.923), pleural thickening (0.957), and rib fracture (0.987) recognition. This competition verified the positive effects of deep learning methods in assisting radiologists in interpreting chest X-rays. AI assistance can help to improve both the efficacy and efficiency of radiologists.

Peri-lesion regions in differentiating suspicious breast calcification-only lesions specifically on contrast enhanced mammography.

PURPOSE: The explore the added value of peri-calcification regions on contrast-enhanced mammography (CEM) in the differential diagnosis of breast lesions presenting as only calcification on routine mammogram. METHODS: Patients who underwent CEM because of suspicious calcification-only lesions were included. The test set included patients between March 2017 and March 2019, while the validation set was collected between April 2019 and October 2019. The calcifications were automatically detected and grouped by a machine learning-based computer-aided system. In addition to extracting radiomic features on both low-energy (LE) and recombined (RC) images from the calcification areas, the peri-calcification regions, which is generated by extending the annotation margin radially with gradients from 1 mm to 9 mm, were attempted. Machine learning (ML) models were built to classify calcifications into malignant and benign groups. The diagnostic matrices were also evaluated by combing ML models with subjective reading. RESULTS: Models for LE (significant features: wavelet-LLL_glcm_Imc2_MLO; wavelet-HLL_firstorder_Entropy_MLO; wavelet-LHH_glcm_DifferenceVariance_CC; wavelet-HLL_glcm_SumEntropy_MLO;wavelet-HLH_glrlm_ShortRunLowGray LevelEmphasis_MLO; original_firstorder_Entropy_MLO; original_shape_Elongation_MLO) and RC (significant features: wavelet-HLH_glszm_GrayLevelNonUniformityNormalized_MLO; wavelet-LLH_firstorder_10Percentile_CC; original_firstorder_Maximum_MLO; wavelet-HHH_glcm_Autocorrelation_MLO; original_shape_Elongation_MLO; wavelet-LHL_glszm_GrayLevelNonUniformityNormalized_MLO; wavelet-LLH_firstorder_RootMeanSquared_MLO) images were set up with 7 features. Areas under the curve (AUCs) of RC models are significantly better than those of LE models with compact and expanded boundary (RC v.s. LE, compact: 0.81 v.s. 0.73, p < 0.05; expanded: 0.89 v.s. 0.81, p < 0.05) and RC models with 3 mm boundary extension yielded the best performance compared to those with other sizes (AUC = 0.89). Combining with radiologists' reading, the 3mm-boundary RC model achieved a sensitivity of 0.871 and negative predictive value of 0.937 with similar accuracy of 0.843 in predicting malignancy. CONCLUSIONS: The machine learning model integrating intra- and peri-calcification regions on CEM has the potential to aid radiologists' performance in predicting malignancy of suspicious breast calcifications.

Integrated non-targeted metabolomics and network pharmacology to reveal the mechanisms of berberine in the long-term treatment of PTZ-induced epilepsy.

AIMS: The increasing resistance to anti-seizure medications (ASMs) and the ambiguous mechanisms of epilepsy highlight the pressing demand for the discovery of pioneering lead compounds. Berberine (BBR) has received significant attention in recent years within the field of chronic metabolic disorders. However, the reports on the treatment of epilepsy with BBR are not systematic and the mechanism remains unclear. MAIN METHODS: In this study, the seizure behaviors of mice were recorded following subcutaneous injection of pentetrazol (PTZ). Non-targeted metabolomics was used to analyze the serum metabolites based on ultra-performance liquid chromatography-quadrupole time-of-flight mass spectrometry (UPLC-Q-TOF/MS). Meanwhile, multivariate statistical methods were used for metabolite identification and pathway analysis. Furthermore, network pharmacology, molecular docking, and quantitative real-time PCR assay were used for the target identification. KEY FINDINGS: BBR had anti-seizure effects on PTZ-induced seizure mice after long-term treatment. Tryptophan metabolism and phenylalanine metabolism were involved in regulating the therapeutic effects of BBR. SIGNIFICANCE: This study reveals the potential mechanism of BBR for epilepsy treatment based on non-targeted metabolomics and network pharmacology, which provides evidence for uncovering the pathogenesis of epilepsy, suggesting that BBR is a potential lead compound for anti-epileptic treatment.

LNAS: a clinically applicable deep-learning system for mediastinal enlarged lymph nodes segmentation and station mapping without regard to the pathogenesis using unenhanced CT images.

BACKGROUND: The accurate identification and evaluation of lymph nodes by CT images is of great significance for disease diagnosis, treatment, and prognosis. PURPOSE: To assess the lymph nodes' segmentation, size, and station by artificial intelligence (AI) for unenhanced chest CT images and evaluate its value in clinical scenarios. MATERIAL AND METHODS: This retrospective study proposed an end-to-end Lymph Nodes Analysis System (LNAS) consisting of three models: the Lymph Node Segmentation model (LNS), the Mediastinal Organ Segmentation model (MOS), and the Lymph Node Station Registration model (LNR). We selected a healthy chest CT image as the template image and annotated 14 lymph node station masks according to the IASLC to build the lymph node station mapping template. The exact contours and stations of the lymph nodes were annotated by two junior radiologists and reviewed by a senior radiologist. Patients aged 18 and above, who had undergone unenhanced chest CT and had at least one suspicious enlarged mediastinal lymph node in imaging reports, were included. Exclusions were patients who had thoracic surgeries in the past 2 weeks or artifacts on CT images affecting lymph node observation by radiologists. The system was trained on 6725 consecutive chest CTs that from Tianjin Medical University General Hospital, among which 6249 patients had suspicious enlarged mediastinal lymph nodes. A total of 519 consecutive chest CTs from Qilu Hospital of Shandong University (Qingdao) were used for external validation. The gold standard for each CT was determined by two radiologists and reviewed by one senior radiologist. RESULTS: The patient-level sensitivity of the LNAS system reached of 93.94% and 92.89% in internal and external test dataset, respectively. And the lesion-level sensitivity (recall) reached 89.48% and 85.97% in internal and external test dataset. For man-machine comparison, AI significantly apparently shortened the average reading time (p < 0.001) and had better lesion-level and patient-level sensitivities. CONCLUSION: AI improved the sensitivity lymph node segmentation by radiologists with an advantage in reading time.

Advances in Deep Learning-Based Medical Image Analysis.

Importance. With the booming growth of artificial intelligence (AI), especially the recent advancements of deep learning, utilizing advanced deep learning-based methods for medical image analysis has become an active research area both in medical industry and academia. This paper reviewed the recent progress of deep learning research in medical image analysis and clinical applications. It also discussed the existing problems in the field and provided possible solutions and future directions.Highlights. This paper reviewed the advancement of convolutional neural network-based techniques in clinical applications. More specifically, state-of-the-art clinical applications include four major human body systems: the nervous system, the cardiovascular system, the digestive system, and the skeletal system. Overall, according to the best available evidence, deep learning models performed well in medical image analysis, but what cannot be ignored are the algorithms derived from small-scale medical datasets impeding the clinical applicability. Future direction could include federated learning, benchmark dataset collection, and utilizing domain subject knowledge as priors.Conclusion. Recent advanced deep learning technologies have achieved great success in medical image analysis with high accuracy, efficiency, stability, and scalability. Technological advancements that can alleviate the high demands on high-quality large-scale datasets could be one of the future developments in this area.