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: multitask convolutional prediction; memory transmembrane deep learning; neural networks; topology long short-term structure secondary topic_lifescience prediction]
Artificial intelligence in liver diseases: Improving diagnostics, prognostics and response prediction. JHEP Rep., (4)4:100443, Elsevier BV, April 2022. [PUMA: a disease; HCC, or intelligence; liver multivariable non-alcoholic multimodal ML, artificial WSIs, images; prediction support integration TACE, DICOM, AI, network; deep neural Digital Diagnosis; MVI, transarterial fatty microvascular convolutional in learning; imaging; Communications invasion; NAFLD, chemoembolisation; hepatocellular Reporting steatohepatitis; Transparent Individual slide machine Prognosis Artificial data for NASH, whole Medicine; TRIPOD, of CNN, and Imaging carcinoma; diagnostic system; model]
Artificial intelligence predicts immune and inflammatory gene signatures directly from hepatocellular carcinoma histology. J. Hepatol., (77)1:116--127, Elsevier BV, July 2022. [PUMA: image artificial immune intelligence; pathology; gene deep learning; signatures; slide whole]
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 intelligence; learning; therapy for Deep mutations; Bladder cancer; Molecular fibroblast receptor testing growth factor FGFR3]
Automatic lung segmentation and quantification of aeration in computed tomography of the chest using 3D transfer learning. Front. Physiol., (12):725865, 2021. [PUMA: ARDS; index; recruitment; segmentation; uNet transfer lung deep learning; COVID-19; Jaccard]
Benchmarking weakly-supervised deep learning pipelines for whole slide classification in computational pathology. Med. Image Anal., (79)102474:102474, Elsevier BV, July 2022. [PUMA: Convolutional Artificial intelligence; Multiple-Instance deep neural networks; learning Weakly-supervised Learning; transformers; pathology; Vision Computational]
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: metastasis; inflamed intelligence; deep learning; bowel predictive LNM adipose pT2 pT1 digital biomarker; cancer; artificial AI; pathology; colorectal and prediction new tissue; early]
Deep learning improves pancreatic cancer diagnosis using RNA-based variants. Cancers (Basel), (13)11:2654, MDPI AG, May 2021. [PUMA: cancer; pancreatitis; study transcriptome-wide deep learning; topic_lifescience association pancreatic chronic]
Deep reinforcement learning with artificial microswimmers. Emerging Topics in Artificial Intelligence (ETAI) 2022, (12204):104--110, 2022. [PUMA: microswimmers artificial learning reinforcement Deep]
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: discovery; library; cheminformatics; deep network; neural biochemical open-source BCL; drug design; topic_lifescience QSAR;]
Leptin deficiency-caused behavioral change - A comparative analysis using EthoVision and DeepLabCut. Front. Neurosci., (17):1052079, March 2023. [PUMA: deep learning; behavioral analysis; DeepLabCut; EthoVision; obesity]
Memory-efficient deep learning on a SpiNNaker 2 prototype. Front. Neurosci., (12):840, Frontiers Media SA, November 2018. [PUMA: footprint; energy parallelism; memory pruning; SpiNNaker; efficient deep hardware; sparsity rewiring;]
Model soups improve performance of dermoscopic skin cancer classifiers. Eur. J. Cancer, (173):307--316, Elsevier BV, September 2022. [PUMA: Artificial intelligence; learning; Deep Melanoma; soups; Dermatology; Robustness Calibration; Ensembles; topic_lifescience Model Generalisation; Nevus;]
Neural network-assisted humanisation of COVID-19 hamster transcriptomic data reveals matching severity states in human disease. eBioMedicine, (108):105312, 2024. [PUMA: Disease Cross-species model, learning Deep matching, Single-cell RNA-seq, COVID-19, analysis, state Hamster] URL
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: genetic artificail (AI); pathway; deep learning; cancer genes; pathway TCGA; intelligence]
Robust path following on rivers using bootstrapped reinforcement learning. Ocean Engineering, (298):117207, 2024. [PUMA: Path waterways Autonomous Restricted vessel learning; surface reinforcement Deep following;] URL
Self-organized free-flight arrival for urban air mobility. Transportation Research Part C: Emerging Technologies, (167):104806, 2024. [PUMA: Urban mobility eVTOL air learning reinforcement Deep] URL
Spatial–temporal recurrent reinforcement learning for autonomous ships. Neural Networks, (165):634-653, 2023. [PUMA: COLREG Autonomous learning, surface vehicle reinforcement Recurrency, Deep] URL
SpheroScan: a user-friendly deep learning tool for spheroid image analysis. Gigascience, (12)Oxford University Press (OUP), December 2022. [PUMA: 3D image deep R-CNN; learning; high-throughput analysis; segmentation spheroids; Image screening; Mask]
Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain. NeuroImage, (261):119504, 2022. [PUMA: Ageing, Cardiovascular a.i., mri, deep Explainable Brain-age, Structural learning risk factors,] URL
Uncertainty estimation in medical image classification: Systematic review. JMIR Med. Inform., (10)8:e36427, August 2022. [PUMA: image out-of-distribution medical detection; deep learning; imaging; classification; calibration; network uncertainty estimation topic_lifescience]
Vessel-following model for inland waterways based on deep reinforcement learning. Ocean Eng., (281)114679:114679, Elsevier BV, August 2023. [PUMA: waterways inland deep Vessel-following learning reinforcement model]
Weakly supervised annotation-free cancer detection and prediction of genotype in routine histopathology. J. Pathol., (256)1:50--60, Wiley, January 2022. [PUMA: Lynch intelligence; deep learning; digital instability cancer; artificial syndrome; pathology; colorectal microsatellite computational]