J Med Chem. 2024 Jun 5. doi: 10.1021/acs.jmedchem.4c00828. Online ahead of print.

ABSTRACT

While large-scale artificial intelligence (AI) models for protein structure prediction and design are advancing rapidly, the translation of deep learning models for practical macromolecular drug development remains limited. This investigation aims to bridge this gap by combining cutting-edge methodologies to create a novel peptide-based PROTAC drug development paradigm. Using ProteinMPNN and RFdiffusion, we identified binding peptides for androgen receptor (AR) and Von Hippel-Lindau (VHL), followed by computational modeling with Alphafold2-multimer and ZDOCK to predict spatial interrelationships. Experimental validation confirmed the designed peptide's binding ability to AR and VHL. Transdermal microneedle patching technology was seamlessly integrated for the peptide PROTAC drug delivery in androgenic alopecia treatment. In summary, our approach provides a generic method for generating peptide PROTACs and offers a practical application for designing potential therapeutic drugs for androgenetic alopecia. This showcases the potential of interdisciplinary approaches in advancing drug development and personalized medicine.

PMID:38836467 | DOI:10.1021/acs.jmedchem.4c00828

Diagn Interv Radiol. 2024 Jun 3. doi: 10.4274/dir.2024.242652. Online ahead of print.

ABSTRACT

PURPOSE: This study aimed to detect supratentorial cortical and subcortical morphological changes in pediatric patients with infratentorial tumors.

METHODS: The study included 24 patients aged 4-18 years who were diagnosed with primary infratentorial tumors and 41 age- and gender-matched healthy controls. Synthetic magnetization-prepared rapid gradient echo images of brain magnetic resonance imaging were generated using deep learning algorithms applied to T2-axial images. The cortical thickness, surface area, volume, and local gyrification index (LGI), as well as subcortical gray matter volumes, were automatically calculated. Surface-based morphometry parameters for the patient and control groups were compared using the general linear model, and volumes between subcortical structures were compared using the t-test and Mann-Whitney U test.

RESULTS: In the patient group, cortical thinning was observed in the left supramarginal, and cortical thickening was observed in the left caudal middle frontal (CMF), left fusiform, left lateral orbitofrontal, left lingual gyrus, right CMF, right posterior cingulate, and right superior frontal (P < 0.050). The patient group showed a volume reduction in the pars triangularis, paracentral, precentral, and supramarginal gyri of the left hemisphere (P < 0.05). A decreased surface area was observed in the bilateral superior frontal and cingulate gyri (P < 0.05). The patient group exhibited a decreased LGI in the right precentral and superior temporal gyri, left supramarginal, and posterior cingulate gyri and showed an increased volume in the bilateral caudate nucleus and hippocampus, while a volume reduction was observed in the bilateral putamen, pallidum, and amygdala (P < 0.05). The ventricular volume and tumor volume showed a positive correlation with the cortical thickness in the bilateral CMF while demonstrating a negative correlation with areas exhibiting a decreased LGI (P < 0.05).

CONCLUSION: Posterior fossa tumors lead to widespread morphological changes in cortical structures, with the most prominent pattern being hypogyria.

CLINICAL SIGNIFICANCE: This study illuminates the neurological impacts of infratentorial tumors in children, providing a foundation for future therapeutic strategies aimed at mitigating these adverse cortical and subcortical changes and improving patient outcomes.

PMID:38836466 | DOI:10.4274/dir.2024.242652

J Mater Chem B. 2024 Jun 5. doi: 10.1039/d4tb00809j. Online ahead of print.

ABSTRACT

Physical eutectogels as a newly emerging type of conductive gel have gained extensive interest for the next generation multifunctional electronic devices. Nevertheless, some obstacles, including weak mechanical performance, low self-adhesive strength, lack of self-healing capacity, and low conductivity, hinder their practical use in wearable strain sensors. Herein, lignin as a green filler and a multifunctional hydrogen bond donor was directly dissolved in a deep eutectic solvent (DES) composed of acrylic acid (AA) and choline chloride, and lignin-reinforced physical eutectogels (DESL) were obtained by the polymerization of AA. Due to the unique features of lignin and DES, the prepared DESL eutectogels exhibit good transparency, UV shielding capacity, excellent mechanical performance, outstanding self-adhesiveness, superior self-healing properties, and high conductivity. Based on the aforementioned integrated functions, a wearable strain sensor displaying a wide working range (0-1500%), high sensitivity (GF = 18.15), rapid responsiveness, and excellent stability and durability (1000 cycles) and capable of detecting diverse human motions was fabricated. Additionally, by combining DESL sensors with a deep learning technique, a gesture recognition system with accuracy as high as 98.8% was achieved. Overall, this work provides an innovative idea for constructing multifunction-integrated physical eutectogels for application in wearable electronics.

PMID:38836422 | DOI:10.1039/d4tb00809j

J Stroke. 2024 May;26(2):312-320. doi: 10.5853/jos.2023.03426. Epub 2024 May 30.

ABSTRACT

BACKGROUND AND PURPOSE: The accurate prediction of functional outcomes in patients with acute ischemic stroke (AIS) is crucial for informed clinical decision-making and optimal resource utilization. As such, this study aimed to construct an ensemble deep learning model that integrates multimodal imaging and clinical data to predict the 90-day functional outcomes after AIS.

METHODS: We used data from the Korean Stroke Neuroimaging Initiative database, a prospective multicenter stroke registry to construct an ensemble model integrated individual 3D convolutional neural networks for diffusion-weighted imaging and fluid-attenuated inversion recovery (FLAIR), along with a deep neural network for clinical data, to predict 90-day functional independence after AIS using a modified Rankin Scale (mRS) of 3-6. To evaluate the performance of the ensemble model, we compared the area under the curve (AUC) of the proposed method with that of individual models trained on each modality to identify patients with AIS with an mRS score of 3-6.

RESULTS: Of the 2,606 patients with AIS, 993 (38.1%) achieved an mRS score of 3-6 at 90 days post-stroke. Our model achieved AUC values of 0.830 (standard cross-validation [CV]) and 0.779 (time-based CV), which significantly outperformed the other models relying on single modalities: b-value of 1,000 s/mm2 (P<0.001), apparent diffusion coefficient map (P<0.001), FLAIR (P<0.001), and clinical data (P=0.004).

CONCLUSION: The integration of multimodal imaging and clinical data resulted in superior prediction of the 90-day functional outcomes in AIS patients compared to the use of a single data modality.

PMID:38836278 | DOI:10.5853/jos.2023.03426

J Stroke. 2024 May;26(2):300-311. doi: 10.5853/jos.2024.00535. Epub 2024 May 30.

ABSTRACT

BACKGROUND AND PURPOSE: Accurate classification of ischemic stroke subtype is important for effective secondary prevention of stroke. We used diffusion-weighted image (DWI) and atrial fibrillation (AF) data to train a deep learning algorithm to classify stroke subtype.

METHODS: Model development was done in 2,988 patients with ischemic stroke from three centers by using U-net for infarct segmentation and EfficientNetV2 for subtype classification. Experienced neurologists (n=5) determined subtypes for external test datasets, while establishing a consensus for clinical trial datasets. Automatically segmented infarcts were fed into the model (DWI-only algorithm). Subsequently, another model was trained, with AF included as a categorical variable (DWI+AF algorithm). These models were tested: (1) internally against the opinion of the labeling experts, (2) against fresh external DWI data, and (3) against clinical trial dataset.

RESULTS: In the training-and-validation datasets, the mean (±standard deviation) age was 68.0±12.5 (61.1% male). In internal testing, compared with the experts, the DWI-only and the DWI+AF algorithms respectively achieved moderate (65.3%) and near-strong (79.1%) agreement. In external testing, both algorithms again showed good agreements (59.3%-60.7% and 73.7%-74.0%, respectively). In the clinical trial dataset, compared with the expert consensus, percentage agreements and Cohen's kappa were respectively 58.1% and 0.34 for the DWI-only vs. 72.9% and 0.57 for the DWI+AF algorithms. The corresponding values between experts were comparable (76.0% and 0.61) to the DWI+AF algorithm.

CONCLUSION: Our model trained on a large dataset of DWI (both with or without AF information) was able to classify ischemic stroke subtypes comparable to a consensus of stroke experts.

PMID:38836277 | DOI:10.5853/jos.2024.00535

Front Radiol. 2024 May 21;4:1386906. doi: 10.3389/fradi.2024.1386906. eCollection 2024.

ABSTRACT

INTRODUCTION: This study is a retrospective evaluation of the performance of deep learning models that were developed for the detection of COVID-19 from chest x-rays, undertaken with the goal of assessing the suitability of such systems as clinical decision support tools.

METHODS: Models were trained on the National COVID-19 Chest Imaging Database (NCCID), a UK-wide multi-centre dataset from 26 different NHS hospitals and evaluated on independent multi-national clinical datasets. The evaluation considers clinical and technical contributors to model error and potential model bias. Model predictions are examined for spurious feature correlations using techniques for explainable prediction.

RESULTS: Models performed adequately on NHS populations, with performance comparable to radiologists, but generalised poorly to international populations. Models performed better in males than females, and performance varied across age groups. Alarmingly, models routinely failed when applied to complex clinical cases with confounding pathologies and when applied to radiologist defined "mild" cases.

DISCUSSION: This comprehensive benchmarking study examines the pitfalls in current practices that have led to impractical model development. Key findings highlight the need for clinician involvement at all stages of model development, from data curation and label definition, to model evaluation, to ensure that all clinical factors and disease features are appropriately considered during model design. This is imperative to ensure automated approaches developed for disease detection are fit-for-purpose in a clinical setting.

PMID:38836218 | PMC:PMC11148230 | DOI:10.3389/fradi.2024.1386906

Proc SPIE Int Soc Opt Eng. 2024 Feb;12925:129251O. doi: 10.1117/12.3006547. Epub 2024 Apr 1.

ABSTRACT

Deep learning CT reconstruction (DLR) has become increasingly popular as a method for improving image quality and reducing radiation exposure. Due to their nonlinear nature, these algorithms result in resolution and noise performance which are object-dependent. Therefore, traditional CT phantoms, which lack realistic tissue morphology, have become inadequate for assessing clinical imaging performance. We propose to utilize 3D-printed PixelPrint phantoms, which exhibit lifelike attenuation profiles, textures, and structures, as a better tool for evaluating DLR performance. In this study, we evaluate a DLR algorithm (Precise Image (PI), Philips Healthcare) using a custom PixelPrint lung phantom and perform head-to-head comparisons between DLR, iterative reconstruction, and filtered back projection (FBP) with scans acquired at a broad range of radiation exposures (CTDIvol: 0.5, 1, 2, 4, 6, 9, 12, 15, 19, and 20 mGy). We compared the performance of each resultant image using noise, peak signal to noise ratio (PSNR), structural similarity index (SSIM), feature-based similarity index (FSIM), information theoretic-based statistic similarity measure (ISSM) and universal image quality index (UIQ). Iterative reconstruction at 9 mGy matches the image quality of FBP at 12 mGy (diagnostic reference level) for all metrics, demonstrating a dose reduction capability of 25%. Meanwhile, DLR matches the image quality of diagnostic reference level FBP images at doses between 4 - 9 mGy, demonstrating dose reduction capabilities between 25% and 67%. This study shows that DLR allows for reduced radiation dose compared to both FBP and iterative reconstruction without compromising image quality. Furthermore, PixelPrint phantoms offer more realistic testing conditions compared to traditional phantoms in the evaluation of novel CT technologies. This, in turn, promotes the translation of new technologies, such as DLR, into clinical practice.

PMID:38836183 | PMC:PMC11148728 | DOI:10.1117/12.3006547

Front Neurol. 2024 May 20;15:1389731. doi: 10.3389/fneur.2024.1389731. eCollection 2024.

ABSTRACT

INTRODUCTION: Long-term electroencephalography (EEG) monitoring is advised to patients with refractory epilepsy who have a failure of anti-seizure medication and therapy. However, its real-life application is limited mainly due to the use of multiple EEG channels. We proposed a patient-specific deep learning-based single-channel seizure detection approach using the long-term scalp EEG recordings of the Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) dataset, in conjunction with neurologists' confirmation of spatial seizure characteristics of individual patients.

METHODS: We constructed 18-, 4-, and single-channel seizure detectors for 13 patients. Neurologists selected a specific channel among four channels, two close to the behind-the-ear and two at the forehead for each patient, after reviewing the patient's distinctive seizure locations with seizure re-annotation.

RESULTS: Our multi- and single-channel detectors achieved an average sensitivity of 97.05-100%, false alarm rate of 0.22-0.40/h, and latency of 2.1-3.4 s for identification of seizures in continuous EEG recordings. The results demonstrated that seizure detection performance of our single-channel approach was comparable to that of our multi-channel ones.

DISCUSSION: We suggest that our single-channel approach in conjunction with clinical designation of the most prominent seizure locations has a high potential for wearable seizure detection on long-term EEG recordings for patients with refractory epilepsy.

PMID:38836000 | PMC:PMC11148866 | DOI:10.3389/fneur.2024.1389731

Adv Neural Inf Process Syst. 2023 Dec;36:80608-80621.

ABSTRACT

Accurate reconstruction of cortical surfaces from brain magnetic resonance images (MRIs) remains a challenging task due to the notorious partial volume effect in brain MRIs and the cerebral cortex's thin and highly folded patterns. Although many promising deep learning-based cortical surface reconstruction methods have been developed, they typically fail to model the interdependence between inner (white matter) and outer (pial) cortical surfaces, which can help generate cortical surfaces with spherical topology. To robustly reconstruct the cortical surfaces with topological correctness, we develop a new deep learning framework to jointly reconstruct the inner, outer, and their in-between (midthickness) surfaces and estimate cortical thickness directly from 3D MRIs. Our method first estimates the midthickness surface and then learns three diffeomorphic flows jointly to optimize the midthickness surface and deform it inward and outward to the inner and outer cortical surfaces respectively, regularized by topological correctness. Our method also outputs a cortex thickness value for each surface vertex, estimated from its diffeomorphic deformation trajectory. Our method has been evaluated on two large-scale neuroimaging datasets, including ADNI and OASIS, achieving state-of-the-art cortical surface reconstruction performance in terms of accuracy, surface regularity, and computation efficiency.

PMID:38835722 | PMC:PMC11149912

Front Pharmacol. 2024 May 21;15:1398231. doi: 10.3389/fphar.2024.1398231. eCollection 2024.

ABSTRACT

Synthetic lethality (SL) is widely used to discover the anti-cancer drug targets. However, the identification of SL interactions through wet experiments is costly and inefficient. Hence, the development of efficient and high-accuracy computational methods for SL interactions prediction is of great significance. In this study, we propose MPASL, a multi-perspective learning knowledge graph attention network to enhance synthetic lethality prediction. MPASL utilizes knowledge graph hierarchy propagation to explore multi-source neighbor nodes related to genes. The knowledge graph ripple propagation expands gene representations through existing gene SL preference sets. MPASL can learn the gene representations from both gene-entity perspective and entity-entity perspective. Specifically, based on the aggregation method, we learn to obtain gene-oriented entity embeddings. Then, the gene representations are refined by comparing the various layer-wise neighborhood features of entities using the discrepancy contrastive technique. Finally, the learned gene representation is applied in SL prediction. Experimental results demonstrated that MPASL outperforms several state-of-the-art methods. Additionally, case studies have validated the effectiveness of MPASL in identifying SL interactions between genes.

PMID:38835667 | PMC:PMC11148462 | DOI:10.3389/fphar.2024.1398231

Eur Radiol. 2024 Jun 4. doi: 10.1007/s00330-024-10816-2. Online ahead of print.

ABSTRACT

OBJECTIVE: To assess the diagnostic performance of post-contrast CT for predicting moderate hepatic steatosis in an older adult cohort undergoing a uniform CT protocol, utilizing hepatic and splenic attenuation values.

MATERIALS AND METHODS: A total of 1676 adults (mean age, 68.4 ± 10.2 years; 1045M/631F) underwent a CT urothelial protocol that included unenhanced, portal venous, and 10-min delayed phases through the liver and spleen. Automated hepatosplenic segmentation for attenuation values (in HU) was performed using a validated deep-learning tool. Unenhanced liver attenuation < 40.0 HU, corresponding to > 15% MRI-based proton density fat, served as the reference standard for moderate steatosis.

RESULTS: The prevalence of moderate or severe steatosis was 12.9% (216/1676). The diagnostic performance of portal venous liver HU in predicting moderate hepatic steatosis (AUROC = 0.943) was significantly better than the liver-spleen HU difference (AUROC = 0.814) (p < 0.001). Portal venous phase liver thresholds of 80 and 90 HU had a sensitivity/specificity for moderate steatosis of 85.6%/89.6%, and 94.9%/74.7%, respectively, whereas a liver-spleen difference of -40 HU and -10 HU had a sensitivity/specificity of 43.5%/90.0% and 92.1%/52.5%, respectively. Furthermore, livers with moderate-severe steatosis demonstrated significantly less post-contrast enhancement (mean, 35.7 HU vs 47.3 HU; p < 0.001).

CONCLUSION: Moderate steatosis can be reliably diagnosed on standard portal venous phase CT using liver attenuation values alone. Consideration of splenic attenuation appears to add little value. Moderate steatosis not only has intrinsically lower pre-contrast liver attenuation values (< 40 HU), but also enhances less, typically resulting in post-contrast liver attenuation values of 80 HU or less.

CLINICAL RELEVANCE STATEMENT: Moderate steatosis can be reliably diagnosed on post-contrast CT using liver attenuation values alone. Livers with at least moderate steatosis enhance less than those with mild or no steatosis, which combines with the lower intrinsic attenuation to improve detection.

KEY POINTS: The liver-spleen attenuation difference is frequently utilized in routine practice but appears to have performance limitations. The liver-spleen attenuation difference is less effective than liver attenuation for moderate steatosis. Moderate and severe steatosis can be identified on standard portal venous phase CT using liver attenuation alone.

PMID:38834787 | DOI:10.1007/s00330-024-10816-2

Anal Chim Acta. 2024 Jul 11;1312:342696. doi: 10.1016/j.aca.2024.342696. Epub 2024 May 6.

ABSTRACT

BACKGROUND: Hemoglobin (Hb) is an important protein in red blood cells and a crucial diagnostic indicator of diseases, e.g., diabetes, thalassemia, and anemia. However, there is a rare report on methods for the simultaneous screening of diabetes, anemia, and thalassemia. Isoelectric focusing (IEF) is a common separative tool for the separation and analysis of Hb. However, the current analysis of IEF images is time-consuming and cannot be used for simultaneous screening. Therefore, an artificial intelligence (AI) of IEF image recognition is desirable for accurate, sensitive, and low-cost screening.

RESULTS: Herein, we proposed a novel comprehensive method based on microstrip isoelectric focusing (mIEF) for detecting the relative content of Hb species. There was a good coincidence between the quantitation of Hb via a conventional automated hematology analyzer and the one via mIEF with R2 = 0.9898. Nevertheless, our results showed that the accuracy of disease diagnosis based on the quantification of Hb species alone is as low as 69.33 %, especially for the simultaneous screening of multiple diseases of diabetes, anemia, alpha-thalassemia, and beta-thalassemia. Therefore, we introduced a ResNet1D-based diagnosis model for the improvement of screening accuracy of multiple diseases. The results showed that the proposed model could achieve a high accuracy of more than 90 % and a good sensitivity of more than 96 % for each disease, indicating the overwhelming advantage of the mIEF method combined with deep learning in contrast to the pure mIEF method.

SIGNIFICANCE: Overall, the presented method of mIEF with deep learning enabled, for the first time, the absolute quantitative detection of Hb, relative quantitation of Hb species, and simultaneous screening of diabetes, anemia, alpha-thalassemia, and beta-thalassemia. The AI-based diagnosis assistant system combined with mIEF, we believe, will help doctors and specialists perform fast and precise disease screening in the future.

PMID:38834281 | DOI:10.1016/j.aca.2024.342696

Radiother Oncol. 2024 Jun 2:110368. doi: 10.1016/j.radonc.2024.110368. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: To optimize our previously proposed TransRP, a model integrating CNN (convolutional neural network) and ViT (Vision Transformer) designed for recurrence-free survival prediction in oropharyngeal cancer and to extend its application to the prediction of multiple clinical outcomes, including locoregional control (LRC), Distant metastasis-free survival (DMFS) and overall survival (OS).

MATERIALS AND METHODS: Data was collected from 400 patients (300 for training and 100 for testing) diagnosed with oropharyngeal squamous cell carcinoma (OPSCC) who underwent (chemo)radiotherapy at University Medical Center Groningen. Each patient's data comprised pre-treatment PET/CT scans, clinical parameters, and clinical outcome endpoints, namely LRC, DMFS and OS. The prediction performance of TransRP was compared with CNNs when inputting image data only. Additionally, three distinct methods (m1-3) of incorporating clinical predictors into TransRP training and one method (m4) that uses TransRP prediction as one parameter in a clinical Cox model were compared.

RESULTS: TransRP achieved higher test C-index values of 0.61, 0.84 and 0.70 than CNNs for LRC, DMFS and OS, respectively. Furthermore, when incorporating TransRP's prediction into a clinical Cox model (m4), a higher C-index of 0.77 for OS was obtained. Compared with a clinical routine risk stratification model of OS, our model, using clinical variables, radiomics and TransRP prediction as predictors, achieved larger separations of survival curves between low, intermediate and high risk groups.

CONCLUSION: TransRP outperformed CNN models for all endpoints. Combining clinical data and TransRP prediction in a Cox model achieved better OS prediction.

PMID:38834153 | DOI:10.1016/j.radonc.2024.110368

Bone. 2024 Jun 2:117142. doi: 10.1016/j.bone.2024.117142. Online ahead of print.

ABSTRACT

Gaucher disease is one of the most common lysosomal storage disorders. Osteonecrosis is a principal clinical manifestation of Gaucher disease and often leads to joint collapse and fractures. T1-weighted (T1w) modality in MRI is widely used to monitor bone involvement in Gaucher disease and to diagnose osteonecrosis. However, objective and quantitative methods for characterizing osteonecrosis are still limited. In this work, we present a deep learning-based quantification approach for the segmentation of osteonecrosis and the extraction of characteristic parameters. We first constructed two independent U-net models to segment the osteonecrosis and bone marrow unaffected by osteonecrosis (UBM) in spine and femur respectively, based on T1w images from patients in the UK national Gaucherite study database. We manually delineated parcellation maps including osteonecrosis and UBM from 364 T1w images (176 for spine, 188 for femur) as the training datasets, and the trained models were subsequently applied to all the 917 T1w images in the database. To quantify the segmentation, we calculated morphological parameters including the volume of osteonecrosis, the volume of UBM, and the fraction of total marrow occupied by osteonecrosis. Then, we examined the correlation between calculated features and the bone marrow burden score for marrow infiltration of the corresponding image, and no strong correlation was found. In addition, we analyzed the influence of splenectomy and the interval between the age at first symptom and the age of onset of treatment on the quantitative measurements of osteonecrosis. The results are consistent with previous studies, showing that prior splenectomy is closely associated with the fractional volume of osteonecrosis, and there is a positive relationship between the duration of untreated disease and the quantifications of osteonecrosis. We propose this technique as an efficient and reliable tool for assessing the extent of osteonecrosis in MR images of patients and improving prediction of clinically important adverse events.

PMID:38834102 | DOI:10.1016/j.bone.2024.117142

J Environ Manage. 2024 Jun 3;362:121260. doi: 10.1016/j.jenvman.2024.121260. Online ahead of print.

ABSTRACT

Accurate multi-step ahead flood forecasting is crucial for flood prevention and mitigation efforts as well as optimizing water resource management. In this study, we propose a Runoff Process Vectorization (RPV) method and integrate it with three Deep Learning (DL) models, namely Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Transformer, to develop a series of RPV-DL flood forecasting models, namely RPV-LSTM, RPV-TCN, and RPV-Transformer models. The models are evaluated using observed flood runoff data from nine typical basins in the middle Yellow River region. The key findings are as follows: Under the same lead time conditions, the RPV-DL models outperform the DL models in terms of Nash-Sutcliffe efficiency coefficient, root mean square error, and relative error for peak flows in the nine typical basins of the middle Yellow River region. Based on the comprehensive evaluation results of the train and test periods, the RPV-DL model outperforms the DL model by an average of 2.82%-22.21% in terms of NSE across nine basins, with RMSE and RE reductions of 10.86-28.81% and 36.14%-51.35%, respectively. The vectorization method significantly improves the accuracy of DL flood forecasting, and the RPV-DL models exhibit better predictive performance, particularly when the lead time is 4h-6h. When the lead time is 4-6h, the percentage improvement in NSE is 9.77%, 15.07%, and 17.94%. The RPV-TCN model shows superior performance in overcoming forecast errors among the nine basins. The research findings provide scientific evidence for flood prevention and mitigation efforts in river basins.

PMID:38833924 | DOI:10.1016/j.jenvman.2024.121260

Comput Med Imaging Graph. 2024 May 20;116:102399. doi: 10.1016/j.compmedimag.2024.102399. Online ahead of print.

ABSTRACT

Lung cancer screening (LCS) using annual computed tomography (CT) scanning significantly reduces mortality by detecting cancerous lung nodules at an earlier stage. Deep learning algorithms can improve nodule malignancy risk stratification. However, they have typically been used to analyse single time point CT data when detecting malignant nodules on either baseline or incident CT LCS rounds. Deep learning algorithms have the greatest value in two aspects. These approaches have great potential in assessing nodule change across time-series CT scans where subtle changes may be challenging to identify using the human eye alone. Moreover, they could be targeted to detect nodules developing on incident screening rounds, where cancers are generally smaller and more challenging to detect confidently. Here, we show the performance of our Deep learning-based Computer-Aided Diagnosis model integrating Nodule and Lung imaging data with clinical Metadata Longitudinally (DeepCAD-NLM-L) for malignancy prediction. DeepCAD-NLM-L showed improved performance (AUC = 88%) against models utilizing single time-point data alone. DeepCAD-NLM-L also demonstrated comparable and complementary performance to radiologists when interpreting the most challenging nodules typically found in LCS programs. It also demonstrated similar performance to radiologists when assessed on out-of-distribution imaging dataset. The results emphasize the advantages of using time-series and multimodal analyses when interpreting malignancy risk in LCS.

PMID:38833895 | DOI:10.1016/j.compmedimag.2024.102399

Oral Oncol. 2024 Jun 3;155:106873. doi: 10.1016/j.oraloncology.2024.106873. Online ahead of print.

ABSTRACT

OBJECTIVES: We aim to develop a YOLOX-based convolutional neural network model for the precise detection of multiple oral lesions, including OLP, OLK, and OSCC, in patient photos.

MATERIALS AND METHODS: We collected 1419 photos for model development and evaluation, conducting both a comparative analysis to gauge the model's capabilities and a multicenter evaluation to assess its diagnostic aid, where 24 participants from 14 centers across the nation were invited. We further integrated this model into a mobile application for rapid and accurate diagnostics.

RESULTS: In the comparative analysis, our model overperformed the senior group (comprising three most experienced experts with more than 10 years of experience) in macro-average recall (85 % vs 77.5 %), precision (87.02 % vs 80.29 %), and specificity (95 % vs 92.5 %). In the multicenter model-assisted diagnosis evaluation, the dental, general, and community hospital groups showed significant improvement when aided by the model, reaching a level comparable to the senior group, with all macro-average metrics closely aligning or even surpassing with those of the latter (recall of 78.67 %, 74.72 %, 83.54 % vs 77.5 %, precision of 80.56 %, 76.42 %, 85.15 % vs 80.29 %, specificity of 92.89 %, 91.57 %, 94.51 % vs 92.5 %).

CONCLUSION: Our model exhibited a high proficiency in detection of oral lesions, surpassing the performance of highly experienced specialists. The model can also help specialists and general dentists from dental and community hospitals in diagnosing oral lesions, reaching the level of highly experienced specialists. Moreover, our model's integration into a mobile application facilitated swift and precise diagnostic procedures.

PMID:38833826 | DOI:10.1016/j.oraloncology.2024.106873

Comput Biol Med. 2024 May 29;177:108677. doi: 10.1016/j.compbiomed.2024.108677. Online ahead of print.

ABSTRACT

Intracranial pressure (ICP) is commonly monitored to guide treatment in patients with serious brain disorders such as traumatic brain injury and stroke. Established methods to assess ICP are resource intensive and highly invasive. We hypothesized that ICP waveforms can be computed noninvasively from three extracranial physiological waveforms routinely acquired in the Intensive Care Unit (ICU): arterial blood pressure (ABP), photoplethysmography (PPG), and electrocardiography (ECG). We evaluated over 600 h of high-frequency (125 Hz) simultaneously acquired ICP, ABP, ECG, and PPG waveform data in 10 patients admitted to the ICU with critical brain disorders. The data were segmented in non-overlapping 10-s windows, and ABP, ECG, and PPG waveforms were used to train deep learning (DL) models to re-create concurrent ICP. The predictive performance of six different DL models was evaluated in single- and multi-patient iterations. The mean average error (MAE) ± SD of the best-performing models was 1.34 ± 0.59 mmHg in the single-patient and 5.10 ± 0.11 mmHg in the multi-patient analysis. Ablation analysis was conducted to compare contributions from single physiologic sources and demonstrated statistically indistinguishable performances across the top DL models for each waveform (MAE±SD 6.33 ± 0.73, 6.65 ± 0.96, and 7.30 ± 1.28 mmHg, respectively, for ECG, PPG, and ABP; p = 0.42). Results support the preliminary feasibility and accuracy of DL-enabled continuous noninvasive ICP waveform computation using extracranial physiological waveforms. With refinement and further validation, this method could represent a safer and more accessible alternative to invasive ICP, enabling assessment and treatment in low-resource settings.

PMID:38833800 | DOI:10.1016/j.compbiomed.2024.108677

Eur J Radiol. 2024 May 25;176:111533. doi: 10.1016/j.ejrad.2024.111533. Online ahead of print.

ABSTRACT

PURPOSE: To develop and validate an end-to-end model for automatically predicting hematoma expansion (HE) after spontaneous intracerebral hemorrhage (sICH) using a novel deep learning framework.

METHODS: This multicenter retrospective study collected cranial noncontrast computed tomography (NCCT) images of 490 patients with sICH at admission for model training (n = 236), internal testing (n = 60), and external testing (n = 194). A HE-Mind model was designed to predict HE, which consists of a densely connected U-net for segmentation process, a multi-instance learning strategy for resolving label ambiguity and a Siamese network for classification process. Two radiomics models based on support vector machine or logistic regression and two deep learning models based on residual network or Swin transformer were developed for performance comparison. Reader experiments including physician diagnosis mode and artificial intelligence mode were conducted for efficiency comparison.

RESULTS: The HE-Mind model showed better performance compared to the comparative models in predicting HE, with areas under the curve of 0.849 and 0.809 in the internal and external test sets respectively. With the assistance of the HE-Mind model, the predictive accuracy and work efficiency of the emergency physician, junior radiologist, and senior radiologist were significantly improved, with accuracies of 0.768, 0.789, and 0.809 respectively, and reporting times of 7.26 s, 5.08 s, and 3.99 s respectively.

CONCLUSIONS: The HE-Mind model could rapidly and automatically process the NCCT data and predict HE after sICH within three seconds, indicating its potential to assist physicians in the clinical diagnosis workflow of HE.

PMID:38833770 | DOI:10.1016/j.ejrad.2024.111533

Microb Cell Fact. 2024 Jun 4;23(1):164. doi: 10.1186/s12934-024-02439-5.

ABSTRACT

BACKGROUND: Optically active D-amino acids are widely used as intermediates in the synthesis of antibiotics, insecticides, and peptide hormones. Currently, the two-enzyme cascade reaction is the most efficient way to produce D-amino acids using enzymes DHdt and DCase, but DCase is susceptible to heat inactivation. Here, to enhance the enzymatic activity and thermal stability of DCase, a rational design software "Feitian" was developed based on kcat prediction using the deep learning approach.

RESULTS: According to empirical design and prediction of "Feitian" software, six single-point mutants with high kcat value were selected and successfully constructed by site-directed mutagenesis. Out of six, three mutants (Q4C, T212S, and A302C) showed higher enzymatic activity than the wild-type. Furthermore, the combined triple-point mutant DCase-M3 (Q4C/T212S/A302C) exhibited a 4.25-fold increase in activity (29.77 ± 4.52 U) and a 2.25-fold increase in thermal stability as compared to the wild-type, respectively. Through the whole-cell reaction, the high titer of D-HPG (2.57 ± 0.43 mM) was produced by the mutant Q4C/T212S/A302C, which was about 2.04-fold of the wild-type. Molecular dynamics simulation results showed that DCase-M3 significantly enhances the rigidity of the catalytic site and thus increases the activity of DCase-M3.

CONCLUSIONS: In this study, an efficient rational design software "Feitian" was successfully developed with a prediction accuracy of about 50% in enzymatic activity. A triple-point mutant DCase-M3 (Q4C/T212S/A302C) with enhanced enzymatic activity and thermostability was successfully obtained, which could be applied to the development of a fully enzymatic process for the industrial production of D-HPG.

PMID:38834993 | DOI:10.1186/s12934-024-02439-5