Self-organized free-flight arrival for urban air mobility. Transportation Research Part C: Emerging Technologies, (167):104806, 2024. [PUMA: Deep Urban air eVTOL learning mobility reinforcement] URL
Vessel-following model for inland waterways based on deep reinforcement learning. Ocean Eng., (281)114679:114679, Elsevier BV, August 2023. [PUMA: Vessel-following deep inland learning model reinforcement waterways]
Spatial–temporal recurrent reinforcement learning for autonomous ships. Neural Networks, (165):634-653, 2023. [PUMA: Autonomous COLREG Deep Recurrency, learning, reinforcement surface vehicle] URL
Robust path following on rivers using bootstrapped reinforcement learning. Ocean Engineering, (298):117207, 2024. [PUMA: Autonomous Deep Path Restricted following; learning; reinforcement surface vessel waterways] URL
Neural network-assisted humanisation of COVID-19 hamster transcriptomic data reveals matching severity states in human disease. eBioMedicine, (108):105312, 2024. [PUMA: COVID-19, Cross-species Deep Disease Hamster RNA-seq, Single-cell analysis, learning matching, model, state] URL
Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain. NeuroImage, (261):119504, 2022. [PUMA: Ageing, Brain-age, Cardiovascular Explainable Structural a.i., deep factors, learning mri, risk] URL
Automatic lung segmentation and quantification of aeration in computed tomography of the chest using 3D transfer learning. Front. Physiol., (12):725865, 2021. [PUMA: ARDS; COVID-19; Jaccard deep index; learning; lung recruitment; segmentation; transfer uNet]
Artificial intelligence in liver diseases: Improving diagnostics, prognostics and response prediction. JHEP Rep., (4)4:100443, Elsevier BV, April 2022. [PUMA: AI, Artificial CNN, Communications DICOM, Diagnosis; Digital HCC, Imaging Individual ML, MVI, Medicine; NAFLD, NASH, Prognosis Reporting TACE, TRIPOD, Transparent WSIs, a and artificial carcinoma; chemoembolisation; convolutional data deep diagnostic disease; fatty for hepatocellular images; imaging; in integration intelligence; invasion; learning; liver machine microvascular model multimodal multivariable network; neural non-alcoholic of or prediction slide steatohepatitis; support system; transarterial whole]
Model soups improve performance of dermoscopic skin cancer classifiers. Eur. J. Cancer, (173):307--316, Elsevier BV, September 2022. [PUMA: Artificial Calibration; Deep Dermatology; Ensembles; Generalisation; Melanoma; Model Nevus; Robustness intelligence; learning; soups; topic_lifescience]
A multitask deep-learning method for predicting membrane associations and secondary structures of proteins. J. Proteome Res., (20)8:4089--4100, American Chemical Society (ACS), August 2021. [PUMA: convolutional deep learning; long memory multitask networks; neural prediction prediction; secondary short-term structure topic_lifescience topology transmembrane]
Uncertainty estimation in medical image classification: Systematic review. JMIR Med. Inform., (10)8:e36427, August 2022. [PUMA: calibration; classification; deep detection; estimation image imaging; learning; medical network out-of-distribution topic_lifescience uncertainty]
Benchmarking weakly-supervised deep learning pipelines for whole slide classification in computational pathology. Med. Image Anal., (79)102474:102474, Elsevier BV, July 2022. [PUMA: Artificial Computational Convolutional Learning; Multiple-Instance Vision Weakly-supervised deep intelligence; learning networks; neural pathology; transformers;]
Memory-efficient deep learning on a SpiNNaker 2 prototype. Front. Neurosci., (12):840, Frontiers Media SA, November 2018. [PUMA: SpiNNaker; deep efficient energy footprint; hardware; memory parallelism; pruning; rewiring; sparsity]
Deep learning improves pancreatic cancer diagnosis using RNA-based variants. Cancers (Basel), (13)11:2654, MDPI AG, May 2021. [PUMA: association cancer; chronic deep learning; pancreatic pancreatitis; study topic_lifescience transcriptome-wide]
Artificial intelligence-based detection of FGFR3 mutational status directly from routine histology in bladder cancer: A possible preselection for molecular testing?. Eur. Urol. Focus, (8)2:472--479, Elsevier BV, March 2022. [PUMA: Artificial Bladder Deep FGFR3 Molecular cancer; factor fibroblast for growth intelligence; learning; mutations; receptor testing therapy]
Artificial intelligence predicts immune and inflammatory gene signatures directly from hepatocellular carcinoma histology. J. Hepatol., (77)1:116--127, Elsevier BV, July 2022. [PUMA: artificial deep gene image immune intelligence; learning; pathology; signatures; slide whole]
Introduction to the BioChemical Library (BCL): An application-based open-source toolkit for integrated cheminformatics and machine learning in computer-aided drug discovery. Front. Pharmacol., (13):833099, Frontiers Media SA, February 2022. [PUMA: BCL; QSAR; biochemical cheminformatics; deep design; discovery; drug library; network; neural open-source topic_lifescience]
Predicting mutational status of driver and suppressor genes directly from histopathology with Deep Learning: A systematic study across 23 solid tumor types. Front. Genet., (12):806386, 2021. [PUMA: (AI); TCGA; artificail cancer deep genes; genetic intelligence learning; pathway pathway;]
Weakly supervised annotation-free cancer detection and prediction of genotype in routine histopathology. J. Pathol., (256)1:50--60, Wiley, January 2022. [PUMA: Lynch artificial cancer; colorectal computational deep digital instability intelligence; learning; microsatellite pathology; syndrome;]
Deep learning identifies inflamed fat as a risk factor for lymph node metastasis in early colorectal cancer. J. Pathol., (256)3:269--281, Wiley, March 2022. [PUMA: AI; LNM adipose and artificial biomarker; bowel cancer; colorectal deep digital early inflamed intelligence; learning; metastasis; new pT1 pT2 pathology; prediction predictive tissue;]