Med Image Anal. 2024 Mar 12;94:103141. doi: 10.1016/j.media.2024.103141. Online ahead of print.

ABSTRACT

In the context of automatic medical image segmentation based on statistical learning, raters' variability of ground truth segmentations in training datasets is a widely recognized issue. Indeed, the reference information is provided by experts but bias due to their knowledge may affect the quality of the ground truth data, thus hindering creation of robust and reliable datasets employed in segmentation, classification or detection tasks. In such a framework, automatic medical image segmentation would significantly benefit from utilizing some form of presegmentation during training data preparation process, which could lower the impact of experts' knowledge and reduce time-consuming labeling efforts. The present manuscript proposes a superpixels-driven procedure for annotating medical images. Three different superpixeling methods with two different number of superpixels were evaluated on three different medical segmentation tasks and compared with manual annotations. Within the superpixels-based annotation procedure medical experts interactively select superpixels of interest, apply manual corrections, when necessary, and then the accuracy of the annotations, the time needed to prepare them, and the number of manual corrections are assessed. In this study, it is proven that the proposed procedure reduces inter- and intra-rater variability leading to more reliable annotations datasets which, in turn, may be beneficial for the development of more robust classification or segmentation models. In addition, the proposed approach reduces time needed to prepare the annotations.

PMID:38489896 | DOI:10.1016/j.media.2024.103141

Methods. 2024 Mar 13:S1046-2023(24)00068-9. doi: 10.1016/j.ymeth.2024.03.005. Online ahead of print.

ABSTRACT

The multipotent stem cells of our body have been largely harnessed in biotherapeutics. However, as they are derived from multiple anatomical sources, from different tissues, human mesenchymal stem cells (hMSCs) are a heterogeneous population showing ambiguity in their in vitro behavior. Intra-clonal population heterogeneity has also been identified and pre-clinical mechanistic studies suggest that these cumulatively depreciate the therapeutic effects of hMSC transplantation. Although various biomarkers identify these specific stem cell populations, recent artificial intelligence-based methods have capitalized on the cellular morphologies of hMSCs, opening a new approach to understand their attributes. A robust and rapid platform is required to accommodate and eliminate the heterogeneity observed in the cell population, to standardize the quality of hMSC therapeutics globally. Here, we report our primary findings of morphological heterogeneity observed within and across two sources of hMSCs namely, stem cells from human exfoliated deciduous teeth (SHEDs) and human Wharton jelly mesenchymal stem cells (hWJ MSCs), using real-time single-cell images generated on immunophenotyping by imaging flow cytometry (IFC). We used the ImageJ software for identification and comparison between the two types of hMSCs using statistically significant morphometric descriptors that are biologically relevant. To expand on these insights, we have further applied deep learning methods and successfully report the development of a Convolutional Neural Network-based image classifier. In our research, we introduced a machine learning methodology to streamline the entire procedure, utilizing convolutional neural networks and transfer learning for binary classification, achieving an accuracy rate of 97.54%. We have also critically discussed the challenges, comparisons between solutions and future directions of machine learning in hMSC classification in biotherapeutics.

PMID:38490594 | DOI:10.1016/j.ymeth.2024.03.005

Bioresour Technol. 2024 Mar 13:130590. doi: 10.1016/j.biortech.2024.130590. Online ahead of print.

ABSTRACT

Comprehensive and dynamic studies of cellulose pyrolysis reaction mechanisms are crucial in designing experiments and processes with enhanced safety, efficiency, and sustainability. The details of the pyrolysis mechanism are not readily available from experiments but can be better described via molecular dynamics (MD) simulations. However, the large size of cellulose molecules challenges accurate ab initio MD simulations, while existing reactive force field parameters lack precision. In this work, precise ab initio deep learning potentials field (DPLF) are developed and applied in MD simulations to facilitate the study of cellulose pyrolysis mechanisms. The formation mechanism and production rate of both valuable and greenhouse products from cellulose at temperatures larger than 1073 K are comprehensively described. This study underscores the critical role of advanced simulation techniques, particularly DLPF, in achieving efficient and accurate understanding of cellulose pyrolysis mechanisms, thus promoting wider industrial applications.

PMID:38490462 | DOI:10.1016/j.biortech.2024.130590

Int J Cardiol. 2024 Mar 13:131970. doi: 10.1016/j.ijcard.2024.131970. Online ahead of print.

ABSTRACT

The crucial pathophysiological and prognostic roles of the right ventricle in various diseases have been well-established. Nonetheless, conventional cardiovascular imaging modalities are frequently associated with intrinsic limitations when evaluating right ventricular (RV) morphology and function. The integration of artificial intelligence (AI) in multimodality imaging presents a promising avenue to circumvent these obstacles, paving the way for future fully automated imaging paradigms. This review aimed to address the current challenges faced by clinicians and researchers in integrating RV imaging and AI technology, to provide a comprehensive overview of the current applications of AI in RV imaging, and to offer insights into future directions, opportunities, and potential challenges in this rapidly advancing field.

PMID:38490268 | DOI:10.1016/j.ijcard.2024.131970

Acta Radiol. 2024 Mar 15:2841851241229185. doi: 10.1177/02841851241229185. Online ahead of print.

ABSTRACT

BACKGROUND: Transcatheter arterial chemoembolization (TACE) is a mainstay treatment for intermediate and advanced hepatocellular carcinoma (HCC), with the potential to enhance patient survival. Preoperative prediction of postoperative response to TACE in patients with HCC is crucial.

PURPOSE: To develop a deep neural network (DNN)-based nomogram for the non-invasive and precise prediction of TACE response in patients with HCC.

MATERIAL AND METHODS: We retrospectively collected clinical and imaging data from 110 patients with HCC who underwent TACE surgery. Radiomics features were extracted from specific imaging methods. We employed conventional machine-learning algorithms and a DNN-based model to construct predictive probabilities (RScore). Logistic regression helped identify independent clinical risk factors, which were integrated with RScore to create a nomogram. We evaluated diagnostic performance using various metrics.

RESULTS: Among the radiomics models, the DNN_LASSO-based one demonstrated the highest predictive accuracy (area under the curve [AUC] = 0.847, sensitivity = 0.892, specificity = 0.791). Peritumoral enhancement and alkaline phosphatase were identified as independent risk factors. Combining RScore with these clinical factors, a DNN-based nomogram exhibited superior predictive performance (AUC = 0.871, sensitivity = 0.844, specificity = 0.873).

CONCLUSION: In this study, we successfully developed a deep learning-based nomogram that can noninvasively and accurately predict TACE response in patients with HCC, offering significant potential for improving the clinical management of HCC.

PMID:38489805 | DOI:10.1177/02841851241229185

Retina. 2024 Mar 14. doi: 10.1097/IAE.0000000000004106. Online ahead of print.

ABSTRACT

BACKGROUND: Around 30% of non-exudative macular neovascularizations(NE-MNVs) exudate within 2 years from diagnosis in patients with age-related macular degeneration(AMD).The aim of the study is to develop a deep learning classifier based on optical coherence tomography(OCT) and OCT angiography(OCTA) to identify NE-MNVs at risk of exudation.

METHODS: AMD patients showing OCTA and fluorescein angiography (FA) documented NE-MNV with a 2-years minimum imaging follow-up were retrospectively selected. Patients showing OCT B-scan-documented MNV exudation within the first 2 years formed the EX-GROUP while the others formed QU-GROUP.ResNet-101, Inception-ResNet-v2 and DenseNet-201 were independently trained on OCTA and OCT B-scan images. Combinations of the 6 models were evaluated with major and soft voting techniques.

RESULTS: Eighty-nine (89) eyes of 89 patients with a follow-up of 5.7 ± 1.5 years were recruited(35 EX GROUP and 54 QU GROUP). Inception-ResNet-v2 was the best performing among the 3 single convolutional neural networks(CNNs).The major voting model resulting from the association of the 3 different CNNs resulted in improvement of performance both for OCTA and OCT B-scan (both significantly higher than human graders' performance). Soft voting model resulting from the combination of OCTA and OCT B-scan based major voting models showed a testing accuracy of 94.4%. Peripheral arcades and large vessels on OCTA enface imaging were more prevalent in QU GROUP.

CONCLUSIONS: Artificial intelligence shows high performances in identifications of NE-MNVs at risk for exudation within the first 2 years of follow up, allowing better customization of follow up timing and avoiding treatment delay. Better results are obtained with the combination of OCTA and OCT B-scan image analysis.

PMID:38489765 | DOI:10.1097/IAE.0000000000004106

Phys Rev Lett. 2024 Mar 1;132(9):096401. doi: 10.1103/PhysRevLett.132.096401.

ABSTRACT

Calculating perturbation response properties of materials from first principles provides a vital link between theory and experiment, but is bottlenecked by the high computational cost. Here, a general framework is proposed to perform density functional perturbation theory (DFPT) calculations by neural networks, greatly improving the computational efficiency. Automatic differentiation is applied on neural networks, facilitating accurate computation of derivatives. High efficiency and good accuracy of the approach are demonstrated by studying electron-phonon coupling and related physical quantities. This work brings deep-learning density functional theory and DFPT into a unified framework, creating opportunities for developing ab initio artificial intelligence.

PMID:38489617 | DOI:10.1103/PhysRevLett.132.096401

Int J Surg. 2024 Mar 15. doi: 10.1097/JS9.0000000000001266. Online ahead of print.

ABSTRACT

BACKGROUND: Deep learning (DL)-assisted detection and segmentation of intracranial hemorrhage stroke in noncontrast computed tomography (NCCT) scans are well-established, but evidence on this topic is lacking.

MATERIALS AND METHODS: PubMed and Embase databases were searched from their inception to November 2023 to identify related studies. The primary outcomes included sensitivity, specificity, and the Dice Similarity Coefficient (DSC); while the secondary outcomes were positive predictive value (PPV), negative predictive value (NPV), precision, area under the receiver operating characteristic curve (AUROC), processing time, and volume of bleeding. Random-effect model and bivariate model were used to pooled independent effect size and diagnostic meta-analysis data, respectively.

RESULTS: A total of 36 original studies were included in this meta-analysis. Pooled results indicated that DL technologies have a comparable performance in intracranial hemorrhage detection and segmentation with high values of sensitivity (0.89, 95% CI: 0.88-0.90), specificity (0.91, 95% CI: 0.89-0.93), AUROC (0.94, 95% CI: 0.93-0.95), PPV (0.92, 95% CI: 0.91-0.93), NPV (0.94, 95% CI: 0.91-0.96), precision (0.83, 95% CI: 0.77-0.90), DSC (0.84, 95% CI: 0.82-0.87). There is no significant difference between manual labeling and DL technologies in hemorrhage quantification (MD 0.08, 95% CI: -5.45-5.60, P=0.98), but the latter takes less process time than manual labeling (WMD 2.26, 95% CI: 1.96-2.56, P=0.001).

CONCLUSION: This systematic review has identified a range of DL algorithms that the performance was comparable to experienced clinicians in hemorrhage lesions identification, segmentation, and quantification but with greater efficiency and reduced cost. It is highly emphasized that multicenter randomized controlled clinical trials will be needed to validate the performance of these tools in the future, paving the way for fast and efficient decision-making during clinical procedure in patients with acute hemorrhagic stroke.

PMID:38489547 | DOI:10.1097/JS9.0000000000001266

PLOS Digit Health. 2024 Mar 15;3(3):e0000460. doi: 10.1371/journal.pdig.0000460. eCollection 2024 Mar.

ABSTRACT

The purpose of this study is to demonstrate the use of a deep learning model in quantitatively evaluating clinical findings typically subject to uncertain evaluations by physicians, using binary test results based on routine protocols. A chest X-ray is the most commonly used diagnostic tool for the detection of a wide range of diseases and is generally performed as a part of regular medical checkups. However, when it comes to findings that can be classified as within the normal range but are not considered disease-related, the thresholds of physicians' findings can vary to some extent, therefore it is necessary to define a new evaluation method and quantify it. The implementation of such methods is difficult and expensive in terms of time and labor. In this study, a total of 83,005 chest X-ray images were used to diagnose the common findings of pleural thickening and scoliosis. A novel method for quantitatively evaluating the probability that a physician would judge the images to have these findings was established. The proposed method successfully quantified the variation in physicians' findings using a deep learning model trained only on binary annotation data. It was also demonstrated that the developed method could be applied to both transfer learning using convolutional neural networks for general image analysis and a newly learned deep learning model based on vector quantization variational autoencoders with high correlations ranging from 0.89 to 0.97.

PMID:38489375 | DOI:10.1371/journal.pdig.0000460

PLoS One. 2024 Mar 15;19(3):e0299549. doi: 10.1371/journal.pone.0299549. eCollection 2024.

ABSTRACT

Insulin secretion from pancreatic β-cells is integral in maintaining the delicate equilibrium of blood glucose levels. Calcium is known to be a key regulator and triggers the release of insulin. This sub-cellular process can be monitored and tracked through live-cell imaging and subsequent cell segmentation, registration, tracking, and analysis of the calcium level in each cell. Current methods of analysis typically require the manual outlining of β-cells, involve multiple software packages, and necessitate multiple researchers-all of which tend to introduce biases. Utilizing deep learning algorithms, we have therefore created a pipeline to automatically segment and track thousands of cells, which greatly reduces the time required to gather and analyze a large number of sub-cellular images and improve accuracy. Tracking cells over a time-series image stack also allows researchers to isolate specific calcium spiking patterns and spatially identify those of interest, creating an efficient and user-friendly analysis tool. Using our automated pipeline, a previous dataset used to evaluate changes in calcium spiking activity in β-cells post-electric field stimulation was reanalyzed. Changes in spiking activity were found to be underestimated previously with manual segmentation. Moreover, the machine learning pipeline provides a powerful and rapid computational approach to examine, for example, how calcium signaling is regulated by intracellular interactions.

PMID:38489336 | DOI:10.1371/journal.pone.0299549

J Alzheimers Dis. 2024 Mar 10. doi: 10.3233/JAD-231271. Online ahead of print.

ABSTRACT

BACKGROUND: The growing number of older adults in recent decades has led to more prevalent geriatric diseases, such as strokes and dementia. Therefore, Alzheimer's disease (AD), as the most common type of dementia, has become more frequent too.

BACKGROUND: Objective: The goals of this work are to present state-of-the-art studies focused on the automatic diagnosis and prognosis of AD and its early stages, mainly mild cognitive impairment, and predicting how the research on this topic may change in the future.

METHODS: Articles found in the existing literature needed to fulfill several selection criteria. Among others, their classification methods were based on artificial neural networks (ANNs), including deep learning, and data not from brain signals or neuroimaging techniques were used. Considering our selection criteria, 42 articles published in the last decade were finally selected.

RESULTS: The most medically significant results are shown. Similar quantities of articles based on shallow and deep ANNs were found. Recurrent neural networks and transformers were common with speech or in longitudinal studies. Convolutional neural networks (CNNs) were popular with gait or combined with others in modular approaches. Above one third of the cross-sectional studies utilized multimodal data. Non-public datasets were frequently used in cross-sectional studies, whereas the opposite in longitudinal ones. The most popular databases were indicated, which will be helpful for future researchers in this field.

CONCLUSIONS: The introduction of CNNs in the last decade and their superb results with neuroimaging data did not negatively affect the usage of other modalities. In fact, new ones emerged.

PMID:38489188 | DOI:10.3233/JAD-231271

Interdiscip Sci. 2024 Mar 15. doi: 10.1007/s12539-024-00617-y. Online ahead of print.

ABSTRACT

Survival analysis, as a widely used method for analyzing and predicting the timing of event occurrence, plays a crucial role in the medicine field. Medical professionals utilize survival models to gain insight into the effects of patient covariates on the disease, and the correlation with the effectiveness of different treatment strategies. This knowledge is essential for the development of treatment plans and the enhancement of treatment approaches. Conventional survival models, such as the Cox proportional hazards model, require a significant amount of feature engineering or prior knowledge to facilitate personalized modeling. To address these limitations, we propose a novel residual-based self-attention deep neural network for survival modeling, called ResDeepSurv, which combines the benefits of neural networks and the Cox proportional hazards regression model. The model proposed in our study simulates the distribution of survival time and the correlation between covariates and outcomes, but does not impose strict assumptions on the basic distribution of survival data. This approach effectively accounts for both linear and nonlinear risk functions in survival data analysis. The performance of our model in analyzing survival data with various risk functions is on par with or even superior to that of other existing survival analysis methods. Furthermore, we validate the superior performance of our model in comparison to currently existing methods by evaluating multiple publicly available clinical datasets. Through this study, we prove the effectiveness of our proposed model in survival analysis, providing a promising alternative to traditional approaches. The application of deep learning techniques and the ability to capture complex relationships between covariates and survival outcomes without relying on extensive feature engineering make our model a valuable tool for personalized medicine and decision-making in clinical practice.

PMID:38489147 | DOI:10.1007/s12539-024-00617-y

Abdom Radiol (NY). 2024 Mar 15. doi: 10.1007/s00261-024-04232-9. Online ahead of print.

ABSTRACT

PURPOSE: To explore the value of deep learning-based multi-parametric magnetic resonance imaging (mp-MRI) nomogram in predicting the Ki-67 expression in rectal cancer.

METHODS: The data of 491 patients with rectal cancer from two centers were retrospectively analyzed and divided into training, internal validation, and external validation sets. They were categorized into high- and low-expression group based on postoperative pathological Ki-67 expression. Each patient's mp-MRI data were analyzed to extract and select the most relevant features of deep learning, and a deep learning model was constructed. Independent predictive risk factors were identified and incorporated into a clinical model, and the clinical and deep learning models were combined to obtain a nomogram for the prediction of Ki-67 expression. The performance characteristics of the DL-model, clinical model, and nomogram were assessed using ROCs, calibration curve, decision curve, and clinical impact curve analysis.

RESULTS: The strongest deep learning features were extracted and screened from mp-MRI data. Two independent predictive factors, namely Magnetic Resonance Imaging T (mrT) staging and differentiation degree, were identified through clinical feature selection. Three models were constructed: a deep learning (DL)-model, a clinical model, and a nomogram. The AUCs of clinical model in the training, internal validation, and external validation set were 0.69, 0.78, and 0.67, respectively. The AUCs of the deep model and nomogram ranged from 0.88 to 0.98. The prediction performance of the deep learning model and nomogram was significantly better than the clinical model (P < 0.001).

CONCLUSION: The nomogram based on deep learning can help clinicians accurately and conveniently predict the expression status of Ki-67 in rectal cancer.

PMID:38489038 | DOI:10.1007/s00261-024-04232-9

Sci China Life Sci. 2024 Mar 12. doi: 10.1007/s11427-023-2504-1. Online ahead of print.

ABSTRACT

Antimicrobial resistance (AMR) poses a critical threat to global health and development, with environmental factors-particularly in urban areas-contributing significantly to the spread of antibiotic resistance genes (ARGs). However, most research to date has been conducted at a local level, leaving significant gaps in our understanding of the global status of antibiotic resistance in urban environments. To address this issue, we thoroughly analyzed a total of 86,213 ARGs detected within 4,728 metagenome samples, which were collected by the MetaSUB International Consortium involving diverse urban environments in 60 cities of 27 countries, utilizing a deep-learning based methodology. Our findings demonstrated the strong geographical specificity of urban environmental resistome, and their correlation with various local socioeconomic and medical conditions. We also identified distinctive evolutionary patterns of ARG-related biosynthetic gene clusters (BGCs) across different countries, and discovered that the urban environment represents a rich source of novel antibiotics. Our study provides a comprehensive overview of the global urban environmental resistome, and fills a significant gap in our knowledge of large-scale urban antibiotic resistome analysis.

PMID:38489008 | DOI:10.1007/s11427-023-2504-1

Elife. 2024 Mar 15;12:RP92614. doi: 10.7554/eLife.92614.

ABSTRACT

Nondestructive pathology based on three-dimensional (3D) optical microscopy holds promise as a complement to traditional destructive hematoxylin and eosin (H&E) stained slide-based pathology by providing cellular information in high throughput manner. However, conventional techniques provided superficial information only due to shallow imaging depths. Herein, we developed open-top two-photon light sheet microscopy (OT-TP-LSM) for intraoperative 3D pathology. An extended depth of field two-photon excitation light sheet was generated by scanning a nondiffractive Bessel beam, and selective planar imaging was conducted with cameras at 400 frames/s max during the lateral translation of tissue specimens. Intrinsic second harmonic generation was collected for additional extracellular matrix (ECM) visualization. OT-TP-LSM was tested in various human cancer specimens including skin, pancreas, and prostate. High imaging depths were achieved owing to long excitation wavelengths and long wavelength fluorophores. 3D visualization of both cells and ECM enhanced the ability of cancer detection. Furthermore, an unsupervised deep learning network was employed for the style transfer of OT-TP-LSM images to virtual H&E images. The virtual H&E images exhibited comparable histological characteristics to real ones. OT-TP-LSM may have the potential for histopathological examination in surgical and biopsy applications by rapidly providing 3D information.

PMID:38488831 | DOI:10.7554/eLife.92614

Adv Sci (Weinh). 2024 Mar 15:e2307837. doi: 10.1002/advs.202307837. Online ahead of print.

ABSTRACT

Endo-microscopy is crucial for real-time 3D visualization of internal tissues and subcellular structures. Conventional methods rely on axial movement of optical components for precise focus adjustment, limiting miniaturization and complicating procedures. Meta-device, composed of artificial nanostructures, is an emerging optical flat device that can freely manipulate the phase and amplitude of light. Here, an intelligent fluorescence endo-microscope is developed based on varifocal meta-lens and deep learning (DL). The breakthrough enables in vivo 3D imaging of mouse brains, where varifocal meta-lens focal length adjusts through relative rotation angle. The system offers key advantages such as invariant magnification, a large field-of-view, and optical sectioning at a maximum focal length tuning range of ≈2 mm with 3 µm lateral resolution. Using a DL network, image acquisition time and system complexity are significantly reduced, and in vivo high-resolution brain images of detailed vessels and surrounding perivascular space are clearly observed within 0.1 s (≈50 times faster). The approach will benefit various surgical procedures, such as gastrointestinal biopsies, neural imaging, brain surgery, etc.

PMID:38488694 | DOI:10.1002/advs.202307837

J Appl Clin Med Phys. 2024 Mar 15:e14327. doi: 10.1002/acm2.14327. Online ahead of print.

ABSTRACT

PURPOSE: This study aimed to develop a hybrid multi-channel network to detect multileaf collimator (MLC) positional errors using dose difference (DD) maps and gamma maps generated from low-resolution detectors in patient-specific quality assurance (QA) for Intensity Modulated Radiation Therapy (IMRT).

METHODS: A total of 68 plans with 358 beams of IMRT were included in this study. The MLC leaf positions of all control points in the original IMRT plans were modified to simulate four types of errors: shift error, opening error, closing error, and random error. These modified plans were imported into the treatment planning system (TPS) to calculate the predicted dose, while the PTW seven29 phantom was utilized to obtain the measured dose distributions. Based on the measured and predicted dose, DD maps and gamma maps, both with and without errors, were generated, resulting in a dataset with 3222 samples. The network's performance was evaluated using various metrics, including accuracy, sensitivity, specificity, precision, F1-score, ROC curves, and normalized confusion matrix. Besides, other baseline methods, such as single-channel hybrid network, ResNet-18, and Swin-Transformer, were also evaluated as a comparison.

RESULTS: The experimental results showed that the multi-channel hybrid network outperformed other methods, demonstrating higher average precision, accuracy, sensitivity, specificity, and F1-scores, with values of 0.87, 0.89, 0.85, 0.97, and 0.85, respectively. The multi-channel hybrid network also achieved higher AUC values in the random errors (0.964) and the error-free (0.946) categories. Although the average accuracy of the multi-channel hybrid network was only marginally better than that of ResNet-18 and Swin Transformer, it significantly outperformed them regarding precision in the error-free category.

CONCLUSION: The proposed multi-channel hybrid network exhibits a high level of accuracy in identifying MLC errors using low-resolution detectors. The method offers an effective and reliable solution for promoting quality and safety of IMRT QA.

PMID:38488663 | DOI:10.1002/acm2.14327

J Phys Chem Lett. 2024 Mar 15:3238-3248. doi: 10.1021/acs.jpclett.4c00280. Online ahead of print.

ABSTRACT

It is crucial to unravel the structural factors influencing the dynamics of the amorphous solids. Deep learning aids in navigating these complexities, while transparency issues persist. Drawing inspiration from the successful application of prototype neural networks in image analysis, this study introduces a novel machine learning approach to address interpretability challenges in glassy research. Distinguishing from traditional machine learning models, the proposed neural network tries to learn distant structural motifs for solid-like atoms and liquid-like atoms. Such learned structural motifs constrain the underlying structural space and thus can serve as a breakthrough in explaining how structural differences impact dynamics. We further used the proposed model to explore the correlation between the local structure and activation energy in the CuZr alloys. Building upon this interpretable model, we demonstrated significant structural differences among atoms with different activation energies. Our interpretable model is a data-driven solution that provides a pathway to reveal the origin of structural heterogeneity in amorphous alloys.

PMID:38488506 | DOI:10.1021/acs.jpclett.4c00280

Transl Vis Sci Technol. 2024 Mar 1;13(3):12. doi: 10.1167/tvst.13.3.12.

ABSTRACT

PURPOSE: To evaluate the diagnostic performance of a robotically aligned optical coherence tomography (RAOCT) system coupled with a deep learning model in detecting referable posterior segment pathology in OCT images of emergency department patients.

METHODS: A deep learning model, RobOCTNet, was trained and internally tested to classify OCT images as referable versus non-referable for ophthalmology consultation. For external testing, emergency department patients with signs or symptoms warranting evaluation of the posterior segment were imaged with RAOCT. RobOCTNet was used to classify the images. Model performance was evaluated against a reference standard based on clinical diagnosis and retina specialist OCT review.

RESULTS: We included 90,250 OCT images for training and 1489 images for internal testing. RobOCTNet achieved an area under the curve (AUC) of 1.00 (95% confidence interval [CI], 0.99-1.00) for detection of referable posterior segment pathology in the internal test set. For external testing, RAOCT was used to image 72 eyes of 38 emergency department patients. In this set, RobOCTNet had an AUC of 0.91 (95% CI, 0.82-0.97), a sensitivity of 95% (95% CI, 87%-100%), and a specificity of 76% (95% CI, 62%-91%). The model's performance was comparable to two human experts' performance.

CONCLUSIONS: A robotically aligned OCT coupled with a deep learning model demonstrated high diagnostic performance in detecting referable posterior segment pathology in a cohort of emergency department patients.

TRANSLATIONAL RELEVANCE: Robotically aligned OCT coupled with a deep learning model may have the potential to improve emergency department patient triage for ophthalmology referral.

PMID:38488431 | DOI:10.1167/tvst.13.3.12

Cancer Med. 2024 Mar;13(5):e7104. doi: 10.1002/cam4.7104.

ABSTRACT

BACKGROUND: Microvascular invasion (MVI) is an independent prognostic factor that is associated with early recurrence and poor survival after resection of hepatocellular carcinoma (HCC). However, the traditional pathology approach is relatively subjective, time-consuming, and heterogeneous in the diagnosis of MVI. The aim of this study was to develop a deep-learning model that could significantly improve the efficiency and accuracy of MVI diagnosis.

MATERIALS AND METHODS: We collected H&E-stained slides from 753 patients with HCC at the First Affiliated Hospital of Zhejiang University. An external validation set with 358 patients was selected from The Cancer Genome Atlas database. The deep-learning model was trained by simulating the method used by pathologists to diagnose MVI. Model performance was evaluated with accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve.

RESULTS: We successfully developed a MVI artificial intelligence diagnostic model (MVI-AIDM) which achieved an accuracy of 94.25% in the independent external validation set. The MVI positive detection rate of MVI-AIDM was significantly higher than the results of pathologists. Visualization results demonstrated the recognition of micro MVIs that were difficult to differentiate by the traditional pathology. Additionally, the model provided automatic quantification of the number of cancer cells and spatial information regarding MVI.

CONCLUSIONS: We developed a deep learning diagnostic model, which performed well and improved the efficiency and accuracy of MVI diagnosis. The model provided spatial information of MVI that was essential to accurately predict HCC recurrence after surgery.

PMID:38488408 | DOI:10.1002/cam4.7104