A deep learning‐based approach for software vulnerability detection using code metrics
Detecting software vulnerabilities traditionally depends on human experts manually defining features, which is tedious and subjective.
Papers
1,138 of 1,138 verified cases.
Autonomous robotic laparoscopic surgery for intestinal anastomosis
Autonomous laparoscopic soft-tissue surgery (intestinal anastomosis) is extremely difficult because it requires imaging, tissue tracking, surgical planning and precise control in deformable environments under motion and vision constraints.
Computational Tools and Resources for CRISPR/Cas Genome Editing
Designing effective and specific sgRNAs for CRISPR/Cas genome editing while avoiding undesired off-target effects.
A review of the application of machine learning in water quality evaluation
Evaluating and managing water quality across surface water, groundwater, drinking water, sewage, and seawater using growing environmental data.
A generalized deep learning framework for whole-slide image segmentation and analysis
Analyzing whole-slide histopathology images for cancer diagnosis is time-consuming because of their large size, heterogeneity, and rising case numbers.
Machine Learning and Deep Learning Approaches for Brain Disease Diagnosis: Principles and Recent Advances
Early detection of variable brain diseases (Alzheimer's, brain tumor, epilepsy, Parkinson's) remains an open diagnostic challenge.
Crop Monitoring Using Satellite/UAV Data Fusion and Machine Learning
Non-destructive, efficient crop monitoring over large areas is needed for precision agriculture, phenotyping, and food-security decisions.
Deep Learning for Hemorrhagic Lesion Detection and Segmentation on Brain CT Images
Locating hemorrhagic strokes in brain CT images is challenging and time-consuming even for experienced radiologists due to high variability in location, contrast, and shape.
Skin Lesions Classification Into Eight Classes for ISIC 2019 Using Deep Convolutional Neural Network and Transfer Learning
Medicine & Health
Cutaneous Melanoma Detection and Management
ai assisted
importance 7/10
scale stated
Eight types of skin lesions look highly similar, causing inaccurate diagnosis and missed early melanoma detection.
Machine learning-powered antibiotics phenotypic drug discovery
Identifying novel antibiotics and determining compound mode of action remains a major drug-discovery challenge, with weak hits often underexploited.
Classification of retinal images with deep learning for early detection of diabetic retinopathy disease
Diabetic retinopathy, a leading cause of blindness in people with diabetes, needs to be detected early from retinal images to prevent vision loss.
Three-Month Real-Time Dengue Forecast Models: An Early Warning System for Outbreak Alerts and Policy Decision Support in Singapore
Singapore, with endemic dengue and no vaccine on the market, needed forecasts of epidemic evolution up to three months ahead to support public health response.
Advancements in Artificial Intelligence in Noninvasive Cardiac Imaging: A Comprehensive Review
Medicine & Health
Artificial Intelligence in Healthcare and Education
ai assisted
importance 7/10
scale stated
A literature review examining how AI can improve analysis, image quality, processing speed and diagnostic accuracy across noninvasive cardiac imaging modalities (echocardiography, MRI, CT, nuclear).
Machine Learning Approaches for Stroke Risk Prediction: Findings from the Suita Study
Stroke is a major public health concern, and predicting who will have one and identifying key risk factors from cohort data remains challenging.
Antibiotic discovery with artificial intelligence for the treatment of Acinetobacter baumannii infections
Multidrug-resistant Acinetobacter baumannii infections are difficult to treat, and new antibiotic candidates are needed against targets such as outer membrane protein W (OmpW).
Multi-Method Diagnosis of CT Images for Rapid Detection of Intracranial Hemorrhages Based on Deep and Hybrid Learning
Intracranial hemorrhage is dangerous with high mortality without rapid diagnosis, and CT images take long and require much expertise to analyze.
Prediction of incident cardiovascular events using machine learning and CMR radiomics
Medicine & Health
Radiomics and Machine Learning in Medical Imaging
ai assisted
importance 7/10
scale stated
Predicting whether patients will develop atrial fibrillation, heart failure, myocardial infarction, or stroke before symptoms occur.
Data-driven enzyme engineering to identify function-enhancing enzymes
Biology & Life Sciences
Enzyme Catalysis and Immobilization
ai assisted
importance 7/10
scale stated
Identifying function-enhancing enzyme variants is a 'holy grail' challenge in protein science.
Spatial transcriptomics inferred from pathology whole-slide images links tumor heterogeneity to survival in breast and lung cancer
State-of-the-art diagnostics lack automated methods to characterize and quantify tumor heterogeneity in a spatial context from pathology whole-slide images.
Novel antimicrobial peptide discovery using machine learning and biophysical selection of minimal bacteriocin domains
Biology & Life Sciences
Antimicrobial Peptides and Activities
ai assisted
importance 7/10
scale stated
Discovering new bacteriocin-derived antimicrobial peptides as antibiotic alternatives is difficult due to diverse mechanisms of action, narrow activity spectra, and challenges isolating natural products.
Revolutionizing sepsis diagnosis using machine learning and deep learning models: a systematic literature review
Sepsis is life-threatening and early detection is difficult; delays significantly worsen patient outcomes.
A hybrid deep learning framework for early detection of diabetic retinopathy using retinal fundus images
Diabetic retinopathy needs to be detected early and its progression monitored from retinal fundus images to guide treatment.
Enhancing the Interpretability of Malaria and Typhoid Diagnosis with Explainable AI and Large Language Models
Medicine & Health
Explainable Artificial Intelligence (XAI)
ai assisted
importance 7/10
scale stated
Malaria and typhoid are hard to diagnose accurately due to similar symptoms, and ML predictions are opaque to healthcare workers.
Accurate de novo design of high-affinity protein binding macrocycles using deep learning
Biology & Life Sciences
Chemical Synthesis and Analysis
partially solved
importance 7/10
scale stated
No robust method existed for de novo design of macrocyclic peptide binders against therapeutic protein targets.