Deep learning

Towards automated organs at risk and target volumes contouring: Defining precision radiation therapy in the modern era

Mon, 2024-07-22 06:00

J Natl Cancer Cent. 2022 Oct 11;2(4):306-313. doi: 10.1016/j.jncc.2022.09.003. eCollection 2022 Dec.

ABSTRACT

Precision radiotherapy is a critical and indispensable cancer treatment means in the modern clinical workflow with the goal of achieving "quality-up and cost-down" in patient care. The challenge of this therapy lies in developing computerized clinical-assistant solutions with precision, automation, and reproducibility built-in to deliver it at scale. In this work, we provide a comprehensive yet ongoing, incomplete survey of and discussions on the recent progress of utilizing advanced deep learning, semantic organ parsing, multimodal imaging fusion, neural architecture search and medical image analytical techniques to address four corner-stone problems or sub-problems required by all precision radiotherapy workflows, namely, organs at risk (OARs) segmentation, gross tumor volume (GTV) segmentation, metastasized lymph node (LN) detection, and clinical tumor volume (CTV) segmentation. Without loss of generality, we mainly focus on using esophageal and head-and-neck cancers as examples, but the methods can be extrapolated to other types of cancers. High-precision, automated and highly reproducible OAR/GTV/LN/CTV auto-delineation techniques have demonstrated their effectiveness in reducing the inter-practitioner variabilities and the time cost to permit rapid treatment planning and adaptive replanning for the benefit of patients. Through the presentation of the achievements and limitations of these techniques in this review, we hope to encourage more collective multidisciplinary precision radiotherapy workflows to transpire.

PMID:39036546 | PMC:PMC11256697 | DOI:10.1016/j.jncc.2022.09.003

Categories: Literature Watch

CSXAI: a lightweight 2D CNN-SVM model for detection and classification of various crop diseases with explainable AI visualization

Mon, 2024-07-22 06:00

Front Plant Sci. 2024 Jul 5;15:1412988. doi: 10.3389/fpls.2024.1412988. eCollection 2024.

ABSTRACT

Plant diseases significantly impact crop productivity and quality, posing a serious threat to global agriculture. The process of identifying and categorizing these diseases is often time-consuming and prone to errors. This research addresses this issue by employing a convolutional neural network and support vector machine (CNN-SVM) hybrid model to classify diseases in four economically important crops: strawberries, peaches, cherries, and soybeans. The objective is to categorize 10 classes of diseases, with six diseased classes and four healthy classes, for these crops using the deep learning-based CNN-SVM model. Several pre-trained models, including VGG16, VGG19, DenseNet, Inception, MobileNetV2, MobileNet, Xception, and ShuffleNet, were also trained, achieving accuracy ranges from 53.82% to 98.8%. The proposed model, however, achieved an average accuracy of 99.09%. While the proposed model's accuracy is comparable to that of the VGG16 pre-trained model, its significantly lower number of trainable parameters makes it more efficient and distinctive. This research demonstrates the potential of the CNN-SVM model in enhancing the accuracy and efficiency of plant disease classification. The CNN-SVM model was selected over VGG16 and other models due to its superior performance metrics. The proposed model achieved a 99% F1-score, a 99.98% Area Under the Curve (AUC), and a 99% precision value, demonstrating its efficacy. Additionally, class activation maps were generated using the Gradient Weighted Class Activation Mapping (Grad-CAM) technique to provide a visual explanation of the detected diseases. A heatmap was created to highlight the regions requiring classification, further validating the model's accuracy and interpretability.

PMID:39036360 | PMC:PMC11257924 | DOI:10.3389/fpls.2024.1412988

Categories: Literature Watch

Lightweight tomato ripeness detection algorithm based on the improved RT-DETR

Mon, 2024-07-22 06:00

Front Plant Sci. 2024 Jul 5;15:1415297. doi: 10.3389/fpls.2024.1415297. eCollection 2024.

ABSTRACT

Tomatoes, widely cherished for their high nutritional value, necessitate precise ripeness identification and selective harvesting of mature fruits to significantly enhance the efficiency and economic benefits of tomato harvesting management. Previous studies on intelligent harvesting often focused solely on identifying tomatoes as the target, lacking fine-grained detection of tomato ripeness. This deficiency leads to the inadvertent harvesting of immature and rotten fruits, resulting in economic losses. Moreover, in natural settings, uneven illumination, occlusion by leaves, and fruit overlap hinder the precise assessment of tomato ripeness by robotic systems. Simultaneously, the demand for high accuracy and rapid response in tomato ripeness detection is compounded by the need for making the model lightweight to mitigate hardware costs. This study proposes a lightweight model named PDSI-RTDETR to address these challenges. Initially, the PConv_Block module, integrating partial convolution with residual blocks, replaces the Basic_Block structure in the legacy backbone to alleviate computing load and enhance feature extraction efficiency. Subsequently, a deformable attention module is amalgamated with intra-scale feature interaction structure, bolstering the capability to extract detailed features for fine-grained classification. Additionally, the proposed slimneck-SSFF feature fusion structure, merging the Scale Sequence Feature Fusion framework with a slim-neck design utilizing GSConv and VoVGSCSP modules, aims to reduce volume of computation and inference latency. Lastly, by amalgamating Inner-IoU with EIoU to formulate Inner-EIoU, replacing the original GIoU to expedite convergence while utilizing auxiliary frames enhances small object detection capabilities. Comprehensive assessments validate that the PDSI-RTDETR model achieves an average precision mAP50 of 86.8%, marking a 3.9% enhancement over the original RT-DETR model, and a 38.7% increase in FPS. Furthermore, the GFLOPs of PDSI-RTDETR have been diminished by 17.6%. Surpassing the baseline RT-DETR and other prevalent methods regarding precision and speed, it unveils its considerable potential for detecting tomato ripeness. When applied to intelligent harvesting robots in the future, this approach can improve the quality of tomato harvesting by reducing the collection of immature and spoiled fruits.

PMID:39036358 | PMC:PMC11257922 | DOI:10.3389/fpls.2024.1415297

Categories: Literature Watch

Intelligent oncology: The convergence of artificial intelligence and oncology

Mon, 2024-07-22 06:00

J Natl Cancer Cent. 2022 Dec 5;3(1):83-91. doi: 10.1016/j.jncc.2022.11.004. eCollection 2023 Mar.

ABSTRACT

With increasingly explored ideologies and technologies for potential applications of artificial intelligence (AI) in oncology, we here describe a holistic and structured concept termed intelligent oncology. Intelligent oncology is defined as a cross-disciplinary specialty which integrates oncology, radiology, pathology, molecular biology, multi-omics and computer sciences, aiming to promote cancer prevention, screening, early diagnosis and precision treatment. The development of intelligent oncology has been facilitated by fast AI technology development such as natural language processing, machine/deep learning, computer vision, and robotic process automation. While the concept and applications of intelligent oncology is still in its infancy, and there are still many hurdles and challenges, we are optimistic that it will play a pivotal role for the future of basic, translational and clinical oncology.

PMID:39036310 | PMC:PMC11256531 | DOI:10.1016/j.jncc.2022.11.004

Categories: Literature Watch

Image Quality Assessment Using Convolutional Neural Network in Clinical Skin Images

Mon, 2024-07-22 06:00

JID Innov. 2024 Apr 27;4(4):100285. doi: 10.1016/j.xjidi.2024.100285. eCollection 2024 Jul.

ABSTRACT

The image quality received for clinical evaluation is often suboptimal. The goal is to develop an image quality analysis tool to assess patient- and primary care physician-derived images using deep learning model. Dataset included patient- and primary care physician-derived images from August 21, 2018 to June 30, 2022 with 4 unique quality labels. VGG16 model was fine tuned with input data, and optimal threshold was determined by Youden's index. Ordinal labels were transformed to binary labels using a majority vote because model distinguishes between 2 categories (good vs bad). At a threshold of 0.587, area under the curve for the test set was 0.885 (95% confidence interval = 0.838-0.933); sensitivity, specificity, positive predictive value, and negative predictive value were 0.829, 0.784, 0.906, and 0.645, respectively. Independent validation of 300 additional images (from patients and primary care physicians) demonstrated area under the curve of 0.864 (95% confidence interval = 0.818-0.909) and area under the curve of 0.902 (95% confidence interval = 0.85-0.95), respectively. The sensitivity, specificity, positive predictive value, and negative predictive value for the 300 images were 0.827, 0.800, 0.959, and 0.450, respectively. We demonstrate a practical approach improving the image quality for clinical workflow. Although users may have to capture additional images, this is offset by the improved workload and efficiency for clinical teams.

PMID:39036289 | PMC:PMC11260318 | DOI:10.1016/j.xjidi.2024.100285

Categories: Literature Watch

Deep learning radiomics based on multimodal imaging for distinguishing benign and malignant breast tumours

Mon, 2024-07-22 06:00

Front Med (Lausanne). 2024 Jul 5;11:1402967. doi: 10.3389/fmed.2024.1402967. eCollection 2024.

ABSTRACT

OBJECTIVES: This study aimed to develop a deep learning radiomic model using multimodal imaging to differentiate benign and malignant breast tumours.

METHODS: Multimodality imaging data, including ultrasonography (US), mammography (MG), and magnetic resonance imaging (MRI), from 322 patients (112 with benign breast tumours and 210 with malignant breast tumours) with histopathologically confirmed breast tumours were retrospectively collected between December 2018 and May 2023. Based on multimodal imaging, the experiment was divided into three parts: traditional radiomics, deep learning radiomics, and feature fusion. We tested the performance of seven classifiers, namely, SVM, KNN, random forest, extra trees, XGBoost, LightGBM, and LR, on different feature models. Through feature fusion using ensemble and stacking strategies, we obtained the optimal classification model for benign and malignant breast tumours.

RESULTS: In terms of traditional radiomics, the ensemble fusion strategy achieved the highest accuracy, AUC, and specificity, with values of 0.892, 0.942 [0.886-0.996], and 0.956 [0.873-1.000], respectively. The early fusion strategy with US, MG, and MRI achieved the highest sensitivity of 0.952 [0.887-1.000]. In terms of deep learning radiomics, the stacking fusion strategy achieved the highest accuracy, AUC, and sensitivity, with values of 0.937, 0.947 [0.887-1.000], and 1.000 [0.999-1.000], respectively. The early fusion strategies of US+MRI and US+MG achieved the highest specificity of 0.954 [0.867-1.000]. In terms of feature fusion, the ensemble and stacking approaches of the late fusion strategy achieved the highest accuracy of 0.968. In addition, stacking achieved the highest AUC and specificity, which were 0.997 [0.990-1.000] and 1.000 [0.999-1.000], respectively. The traditional radiomic and depth features of US+MG + MR achieved the highest sensitivity of 1.000 [0.999-1.000] under the early fusion strategy.

CONCLUSION: This study demonstrated the potential of integrating deep learning and radiomic features with multimodal images. As a single modality, MRI based on radiomic features achieved greater accuracy than US or MG. The US and MG models achieved higher accuracy with transfer learning than the single-mode or radiomic models. The traditional radiomic and depth features of US+MG + MR achieved the highest sensitivity under the early fusion strategy, showed higher diagnostic performance, and provided more valuable information for differentiation between benign and malignant breast tumours.

PMID:39036101 | PMC:PMC11257849 | DOI:10.3389/fmed.2024.1402967

Categories: Literature Watch

High Resolution TOF-MRA Using Compressed Sensing-based Deep Learning Image Reconstruction for the Visualization of Lenticulostriate Arteries: A Preliminary Study

Sun, 2024-07-21 06:00

Magn Reson Med Sci. 2024 Jul 20. doi: 10.2463/mrms.mp.2024-0025. Online ahead of print.

ABSTRACT

PURPOSE: To investigate the visibility of the lenticulostriate arteries (LSAs) in time-of-flight (TOF)-MR angiography (MRA) using compressed sensing (CS)-based deep learning (DL) image reconstruction by comparing its image quality with that obtained by the conventional CS algorithm.

METHODS: Five healthy volunteers were included. High-resolution TOF-MRA images with the reduction (R)-factor of 1 were acquired as full-sampling data. Images with R-factors of 2, 4, and 6 were then reconstructed using CS-DL and conventional CS (the combination of CS and sensitivity conceding; CS-SENSE) reconstruction, respectively. In the quantitative assessment, the number of visible LSAs (identified by two radiologists), length of each depicted LSA (evaluated by one radiological technologist), and normalized mean squared error (NMSE) value were assessed. In the qualitative assessment, the overall image quality and the visibility of the peripheral LSA were visually evaluated by two radiologists.

RESULTS: In the quantitative assessment of the DL-CS images, the number of visible LSAs was significantly higher than those obtained with CS-SENSE in the R-factors of 4 and 6 (Reader 1) and in the R-factor of 6 (Reader 2). The length of the depicted LSAs in the DL-CS images was significantly longer in the R-factor 6 compared to the CS-SENSE result. The NMSE value in CS-DL was significantly lower than in CS-SENSE for R-factors of 4 and 6. In the qualitative assessment of DL-CS images, the overall image quality was significantly higher than that obtained with CS-SENSE in the R-factors 4 and 6 (Reader 1) and in the R-factor 4 (Reader 2). The visibility of the peripheral LSA was significantly higher than that shown by CS-SENSE in all R-factors (Reader 1) and in the R-factors 2 and 4 (Reader 2).

CONCLUSION: CS-DL reconstruction demonstrated preserved image quality for the depiction of LSAs compared to the conventional CS-SENSE when the R-factor is elevated.

PMID:39034144 | DOI:10.2463/mrms.mp.2024-0025

Categories: Literature Watch

Windy events detection in big bioacoustics datasets using a pre-trained Convolutional Neural Network

Sun, 2024-07-21 06:00

Sci Total Environ. 2024 Jul 19:174868. doi: 10.1016/j.scitotenv.2024.174868. Online ahead of print.

ABSTRACT

Passive Acoustic Monitoring (PAM), which involves using autonomous record units for studying wildlife behaviour and distribution, often requires handling big acoustic datasets collected over extended periods. While these data offer invaluable insights about wildlife, their analysis can present challenges in dealing with geophonic sources. A major issue in the process of detection of target sounds is represented by wind-induced noise. This can lead to false positive detections, i.e., energy peaks due to wind gusts misclassified as biological sounds, or false negative, i.e., the wind noise masks the presence of biological sounds. Acoustic data dominated by wind noise makes the analysis of vocal activity unreliable, thus compromising the detection of target sounds and, subsequently, the interpretation of the results. Our work introduces a straightforward approach for detecting recordings affected by windy events using a pre-trained convolutional neural network. This process facilitates identifying wind-compromised data. We consider this dataset pre-processing crucial for ensuring the reliable use of PAM data. We implemented this preprocessing by leveraging YAMNet, a deep learning model for sound classification tasks. We evaluated YAMNet as-is ability to detect wind-induced noise and tested its performance in a Transfer Learning scenario by using our annotated data from the Stony Point Penguin Colony in South Africa. While the classification of YAMNet as-is achieved a precision of 0.71, and recall of 0.66, those metrics strongly improved after the training on our annotated dataset, reaching a precision of 0.91, and recall of 0.92, corresponding to a relative increment of >28 %. Our study demonstrates the promising application of YAMNet in the bioacoustics and ecoacoustics fields, addressing the need for wind-noise-free acoustic data. We released an open-access code that, combined with the efficiency and peak performance of YAMNet, can be used on standard laptops for a broad user base.

PMID:39034006 | DOI:10.1016/j.scitotenv.2024.174868

Categories: Literature Watch

Application and performance enhancement of FAIMS spectral data for deep learning analysis using generative adversarial network reinforcement

Sun, 2024-07-21 06:00

Anal Biochem. 2024 Jul 19:115627. doi: 10.1016/j.ab.2024.115627. Online ahead of print.

ABSTRACT

When using High-field asymmetric ion mobility spectrometry (FAIMS) to process complex mixtures for deep learning analysis, there is a problem of poor recognition performance due to the lack of high-quality data and low sample diversity. In this paper, a Generative Adversarial Network (GAN) method is introduced to simulate and generate highly realistic and diverse spectral for expanding the dataset using real mixture spectral data of 15 classes collected by FAIMS. The mixed datasets were put into VGG and ResNeXt for testing respectively, and the experimental results proved that the best recognition effect was achieved when the ratio of real data to generated data was 1:4: where accuracy improved by 24.19% and 6.43%; precision improved by 23.71% and 6.97%; recall improved by 21.08% and 7.09%; and F1-score improved by 24.50% and 8.23%. The above results strongly demonstrate that GAN can effectively expand the data volume and increase the sample diversity without increasing the additional experimental cost, which significantly enhances the experimental effect of FAIMS spectral for the analysis of complex mixtures.

PMID:39033946 | DOI:10.1016/j.ab.2024.115627

Categories: Literature Watch

Differentiating loss of consciousness causes through artificial intelligence-enabled decoding of functional connectivity

Sun, 2024-07-21 06:00

Neuroimage. 2024 Jul 19:120749. doi: 10.1016/j.neuroimage.2024.120749. Online ahead of print.

ABSTRACT

Differential diagnosis of acute loss of consciousness (LOC) is crucial due to the need for different therapeutic strategies despite similar clinical presentations among etiologies such as nonconvulsive status epilepticus, metabolic encephalopathy, and benzodiazepine intoxication. While altered functional connectivity (FC) plays a pivotal role in the pathophysiology of LOC, there has been a lack of efforts to develop differential diagnosis artificial intelligence (AI) models that feature the distinctive FC change patterns specific to each LOC cause. Three approaches were applied for extracting features for the AI models: three-dimensional FC adjacency matrices, vectorized FC values, and graph theoretical measurements. Deep learning using convolutional neural networks (CNN) and various machine learning algorithms were implemented to compare classification accuracy using electroencephalography (EEG) data with different epoch sizes. The CNN model using FC adjacency matrices achieved the highest accuracy with an AUC of 0.905, with 20-s epoch data being optimal for classifying the different LOC causes. The high accuracy of the CNN model was maintained in a prospective cohort. Key distinguishing features among the LOC causes were found in the delta and theta brain wave bands. This research advances the understanding of LOC's underlying mechanisms and shows promise for enhancing diagnosis and treatment selection. Moreover, the AI models can provide accurate LOC differentiation with a relatively small amount of EEG data in 20-s epochs, which may be clinically useful.

PMID:39033787 | DOI:10.1016/j.neuroimage.2024.120749

Categories: Literature Watch

Improving diagnostic confidence in low-dose dual-energy CTE with low energy level and deep learning reconstruction

Sun, 2024-07-21 06:00

Eur J Radiol. 2024 Jul 10;178:111607. doi: 10.1016/j.ejrad.2024.111607. Online ahead of print.

ABSTRACT

OBJECTIVE: To demonstrate the value of using 50 keV virtual monochromatic images with deep learning image reconstruction (DLIR) in low-dose dual-energy CT enterography (CTE).

METHODS: In this prospective study, 114 participants (62 % M; 41.9 ± 16 years) underwent dual-energy CTE. The early-enteric phase was performed using standard-dose (noise index (NI): 8) and images were reconstructed at 70 keV and 50 keV with 40 % strength ASIR-V (ASIR-V40%). The late-enteric phase used low-dose (NI: 12) and images were reconstructed at 50 keV with ASIR-V40%, and DLIR at medium (DLIR-M) and high strength (DLIR-H). Image standard deviation (SD), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), edge-rise-slope (ERS) were computed. The quantitative comb sign score was calculated for the 27 patients with Crohn's disease. The subjective noise, image contrast, display of rectus artery were scored using a 5-point scale by two radiologists blindly.

RESULTS: Effective dose was reduced by 50 % (P < 0.001) in the late-enteric phase to 3.26 mSv. The lower-dose 50 keV-DLIR-H images (SD:17.7 ± 0.5HU) had similar image noise (P = 0.97) as the standard-dose 70 keV-ASIR-V40% images (SD:17.7 ± 0.73HU), but with higher (P < 0.001) SNR, CNR, ERS and quantitative comb sign score (5.7 ± 0.17, 1.8 ± 0.12, 156.04 ± 5.21 and 5.05 ± 0.73, respectively). Furthermore, the lower-dose 50 keV-DLIR-H images obtained the highest score in the rectus artery visibility (4.27 ± 0.6).

CONCLUSIONS: The 50 keV images in dual-energy CTE with DLIR provides high-quality images, with a 50 % reduction in radiation dose. Images with high contrast and density resolutions significantly enhance the diagnostic confidence of Crohn's disease and are essential for the clinical development of individualized treatment plans.

PMID:39033690 | DOI:10.1016/j.ejrad.2024.111607

Categories: Literature Watch

Improved sleep stage predictions by deep learning of photoplethysmogram and respiration patterns

Sun, 2024-07-21 06:00

Comput Biol Med. 2024 Jul 20;179:108679. doi: 10.1016/j.compbiomed.2024.108679. Online ahead of print.

ABSTRACT

Sleep staging is a crucial tool for diagnosing and monitoring sleep disorders, but the standard clinical approach using polysomnography (PSG) in a sleep lab is time-consuming, expensive, uncomfortable, and limited to a single night. Advancements in sensor technology have enabled home sleep monitoring, but existing devices still lack sufficient accuracy to inform clinical decisions. To address this challenge, we propose a deep learning architecture that combines a convolutional neural network and bidirectional long short-term memory to accurately classify sleep stages. By supplementing photoplethysmography (PPG) signals with respiratory sensor inputs, we demonstrated significant improvements in prediction accuracy and Cohen's kappa (k) for 2- (92.7 %; k = 0.768), 3- (80.2 %; k = 0.714), 4- (76.8 %, k = 0.550), and 5-stage (76.7 %, k = 0.616) sleep classification using raw data. This relatively translatable approach, with a less intensive AI model and leveraging only a few, inexpensive sensors, shows promise in accurately staging sleep. This has potential for diagnosing and managing sleep disorders in a more accessible and practical manner, possibly even at home.

PMID:39033682 | DOI:10.1016/j.compbiomed.2024.108679

Categories: Literature Watch

Automatic segmentation of intraluminal thrombosis of abdominal aortic aneurysms from CT angiography using a mixed-scale-driven multiview perception network (M<sup>2</sup>Net) model

Sun, 2024-07-21 06:00

Comput Biol Med. 2024 Jul 19;179:108838. doi: 10.1016/j.compbiomed.2024.108838. Online ahead of print.

ABSTRACT

Intraluminal thrombosis (ILT) plays a critical role in the progression of abdominal aortic aneurysms (AAA). Understanding the role of ILT can improve the evaluation and management of AAAs. However, compared with highly developed automatic vessel lumen segmentation methods, ILT segmentation is challenging. Angiographic contrast agents can enhance the vessel lumen but cannot improve boundary delineation of the ILT regions; the lack of intrinsic contrast in the ILT structure significantly limits the accurate segmentation of ILT. Additionally, ILT is not evenly distributed within AAAs; its sparsity and scattered distributions in the imaging data pose challenges to the learning process of neural networks. Thus, we propose a multiview fusion approach, allowing us to obtain high-quality ILT delineation from computed tomography angiography (CTA) data. Our multiview fusion network is named Mixed-scale-driven Multiview Perception Network (M2Net), and it consists of two major steps. Following image preprocessing, the 2D mixed-scale ZoomNet segments ILT from each orthogonal view (i.e., Axial, Sagittal, and Coronal views) to enhance the prior information. Then, the proposed context-aware volume integration network (CVIN) effectively fuses the multiview results. Using contrast-enhanced computed tomography angiography (CTA) data from human subjects with AAAs, we evaluated the proposed M2Net. A quantitative analysis shows that the proposed deep-learning M2Net model achieved superior performance (e.g., DICE scores of 0.88 with a sensitivity of 0.92, respectively) compared with other state-of-the-art deep-learning models. In closing, the proposed M2Net model can provide high-quality delineation of ILT in an automated fashion and has the potential to be translated into the clinical workflow.

PMID:39033681 | DOI:10.1016/j.compbiomed.2024.108838

Categories: Literature Watch

Development of a ship-based camera monitoring system for floating marine debris

Sun, 2024-07-21 06:00

Mar Pollut Bull. 2024 Jul 19;206:116722. doi: 10.1016/j.marpolbul.2024.116722. Online ahead of print.

ABSTRACT

This study developed an automatic monitoring system for Floating Marine Debris (FMD) aimed at reducing the labor-intensiveness of traditional visual surveys. It involved creating a comprehensive FMD database using 55.6 h of video footage and numerous annotated images, which facilitated the training of a deep learning model based on the YOLOv8 architecture. Additionally, the study implemented the BoT-SORT algorithm for FMD tracking, significantly enhancing detection accuracy by effectively filtering out disturbances such as sea waves and seabirds, based on the movement patterns observed in FMD trajectories. Tested across 16 voyages in various marine environments, the system demonstrated high accuracy in recognizing different types of FMD, achieving a mean Average Precision (mAP@0.5) of 0.97. In terms of detecting FMD from video footage, the system reached an F1 score of 83.63 %. It showed potential as a viable substitute for manual methods for FMD larger than 20 cm.

PMID:39033599 | DOI:10.1016/j.marpolbul.2024.116722

Categories: Literature Watch

Artificial intelligence model for automated surgical instrument detection and counting: an experimental proof-of-concept study

Sun, 2024-07-21 06:00

Patient Saf Surg. 2024 Jul 21;18(1):24. doi: 10.1186/s13037-024-00406-y.

ABSTRACT

BACKGROUND: Retained surgical items (RSI) are preventable events that pose a significant risk to patient safety. Current strategies for preventing RSIs rely heavily on manual instrument counting methods, which are prone to human error. This study evaluates the feasibility and performance of a deep learning-based computer vision model for automated surgical tool detection and counting.

METHODS: A novel dataset of 1,004 images containing 13,213 surgical tools across 11 categories was developed. The dataset was split into training, validation, and test sets at a 60:20:20 ratio. An artificial intelligence (AI) model was trained on the dataset, and the model's performance was evaluated using standard object detection metrics, including precision and recall. To simulate a real-world surgical setting, model performance was also evaluated in a dynamic surgical video of instruments being moved in real-time.

RESULTS: The model demonstrated high precision (98.5%) and recall (99.9%) in distinguishing surgical tools from the background. It also exhibited excellent performance in differentiating between various surgical tools, with precision ranging from 94.0 to 100% and recall ranging from 97.1 to 100% across 11 tool categories. The model maintained strong performance on a subset of test images containing overlapping tools (precision range: 89.6-100%, and recall range 97.2-98.2%). In a real-time surgical video analysis, the model maintained a correct surgical tool count in all non-transition frames, with a median inference speed of 40.4 frames per second (interquartile range: 4.9).

CONCLUSION: This study demonstrates that using a deep learning-based computer vision model for automated surgical tool detection and counting is feasible. The model's high precision and real-time inference capabilities highlight its potential to serve as an AI safeguard to potentially improve patient safety and reduce manual burden on surgical staff. Further validation in clinical settings is warranted.

PMID:39034409 | DOI:10.1186/s13037-024-00406-y

Categories: Literature Watch

delta-Conotoxin Structure Prediction and Analysis through Large-Scale Comparative and Deep Learning Modeling Approaches

Sun, 2024-07-21 06:00

Adv Sci (Weinh). 2024 Jul 21:e2404786. doi: 10.1002/advs.202404786. Online ahead of print.

ABSTRACT

The δ-conotoxins, a class of peptides produced in the venom of cone snails, are of interest due to their ability to inhibit the inactivation of voltage-gated sodium channels causing paralysis and other neurological responses, but difficulties in their isolation and synthesis have made structural characterization challenging. Taking advantage of recent breakthroughs in computational algorithms for structure prediction that have made modeling especially useful when experimental data is sparse, this work uses both the deep-learning-based algorithm AlphaFold and comparative modeling method RosettaCM to model and analyze 18 previously uncharacterized δ-conotoxins derived from piscivorous, vermivorous, and molluscivorous cone snails. The models provide useful insights into the structural aspects of these peptides and suggest features likely to be significant in influencing their binding and different pharmacological activities against their targets, with implications for drug development. Additionally, the described protocol provides a roadmap for the modeling of similar disulfide-rich peptides by these complementary methods.

PMID:39033537 | DOI:10.1002/advs.202404786

Categories: Literature Watch

A systematic review of deep learning-based spinal bone lesion detection in medical images

Sun, 2024-07-21 06:00

Acta Radiol. 2024 Jul 21:2841851241263066. doi: 10.1177/02841851241263066. Online ahead of print.

ABSTRACT

Spinal bone lesions encompass a wide array of pathologies, spanning from benign abnormalities to aggressive malignancies, such as diffusely localized metastases. Early detection and accurate differentiation of the underlying diseases is crucial for every patient's clinical treatment and outcome, with radiological imaging being a core element in the diagnostic pathway. Across numerous pathologies and imaging techniques, deep learning (DL) models are progressively considered a valuable resource in the clinical setting. This review describes not only the diagnostic performance of these models and the differing approaches in the field of spinal bone malignancy recognition, but also the lack of standardized methodology and reporting that we believe is currently hampering this newly founded area of research. In line with their established and reliable role in lesion detection, this publication focuses on both computed tomography and magnetic resonance imaging, as well as various derivative modalities (i.e. SPECT). After conducting a systematic literature search and subsequent analysis for applicability and quality using a modified QUADAS-2 scoring system, we confirmed that most of the 14 identified studies were plagued by major limitations, such as insufficient reporting of model statistics and data acquisition, a lacking external validation dataset, and potentially biased annotation. Although we experienced these limitations, we nonetheless conclude that the potential of these methods shines through in the presented results. These findings underline the need for more stringent quality controls in DL studies, as well as model development to afford increased insight and progress in this promising novel field.

PMID:39033391 | DOI:10.1177/02841851241263066

Categories: Literature Watch

Deep learning image reconstruction for low-kiloelectron volt virtual monoenergetic images in abdominal dual-energy CT: medium strength provides higher lesion conspicuity

Sun, 2024-07-21 06:00

Acta Radiol. 2024 Jul 21:2841851241262765. doi: 10.1177/02841851241262765. Online ahead of print.

ABSTRACT

BACKGROUND: The best settings of deep learning image reconstruction (DLIR) algorithm for abdominal low-kiloelectron volt (keV) virtual monoenergetic imaging (VMI) have not been determined.

PURPOSE: To determine the optimal settings of the DLIR algorithm for abdominal low-keV VMI.

MATERIAL AND METHODS: The portal-venous phase computed tomography (CT) scans of 109 participants with 152 lesions were reconstructed into four image series: VMI at 50 keV using adaptive statistical iterative reconstruction (Asir-V) at 50% blending (AV-50); and VMI at 40 keV using AV-50 and DLIR at medium (DLIR-M) and high strength (DLIR-H). The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of nine anatomical sites were calculated. Noise power spectrum (NPS) using homogenous region of liver, and edge rise slope (ERS) at five edges were measured. Five radiologists rated image quality and diagnostic acceptability, and evaluated the lesion conspicuity.

RESULTS: The SNR and CNR values, and noise and noise peak in NPS measurements, were significantly lower in DLIR images than AV-50 images in all anatomical sites (all P < 0.001). The ERS values were significantly higher in 40-keV images than 50-keV images at all edges (all P < 0.001). The differences of the peak and average spatial frequency among the four reconstruction algorithms were significant but relatively small. The 40-keV images were rated higher with DLIR-M than DLIR-H for diagnostic acceptance (P < 0.001) and lesion conspicuity (P = 0.010).

CONCLUSION: DLIR provides lower noise, higher sharpness, and more natural texture to allow 40 keV to be a new standard for routine VMI reconstruction for the abdomen and DLIR-M gains higher diagnostic acceptance and lesion conspicuity rating than DLIR-H.

PMID:39033390 | DOI:10.1177/02841851241262765

Categories: Literature Watch

Artificial intelligence-based assessment of leg axis parameters shows excellent agreement with human raters: A systematic review and meta-analysis

Sun, 2024-07-21 06:00

Knee Surg Sports Traumatol Arthrosc. 2024 Jul 21. doi: 10.1002/ksa.12362. Online ahead of print.

ABSTRACT

PURPOSE: The aim of this study was to conduct a systematic review and meta-analysis on the reliability and applicability of artificial intelligence (AI)-based analysis of leg axis parameters. We hypothesized that AI-based leg axis measurements would be less time-consuming and as accurate as those performed by human raters.

METHODS: The study protocol was registered with the International Prospective Register of Systematic Reviews (PROSPERO). PubMed, Epistemonikos, and Web of Science were searched up to 24 February 2024, using a BOOLEAN search strategy. Titles and abstracts of identified records were screened through a stepwise process. Data extraction and quality assessment of the included papers were followed by a frequentist meta-analysis employing a common effect/random effects model with inverse variance and the Sidik-Jonkman heterogeneity estimator.

RESULTS: A total of 13 studies encompassing 3192 patients were included in this meta-analysis. All studies compared AI-based leg axis measurements on long-leg radiographs (LLR) with those performed by human raters. The parameters hip knee ankle angle (HKA), mechanical lateral distal femoral angle (mLDFA), mechanical medial proximal tibial angle (mMPTA), and joint-line convergence angle (JLCA) showed excellent agreement between AI and human raters. The AI system was approximately 3 min faster in reading standing long-leg anteroposterior radiographs (LLRs) compared with human raters.

CONCLUSION: AI-based assessment of leg axis parameters is an efficient, accurate, and time-saving procedure. The quality of AI-based assessment of the investigated parameters does not appear to be affected by the presence of implants or pathological conditions.

LEVEL OF EVIDENCE: Level I.

PMID:39033340 | DOI:10.1002/ksa.12362

Categories: Literature Watch

Inferring Cellular Contractile Forces and Work using Deep Morphology Traction Microscopy

Sun, 2024-07-21 06:00

Biophys J. 2024 Jul 19:S0006-3495(24)00479-X. doi: 10.1016/j.bpj.2024.07.020. Online ahead of print.

ABSTRACT

Traction Force Microscopy (TFM) has emerged as a widely used standard methodology to measure cell-generated traction forces and determine their role in regulating cell behavior. While TFM platforms have enabled many discoveries, their implementation remains limited due to complex experimental procedures, specialized substrates, and the ill-posed inverse problem where low magnitude high-frequency noise in the displacement field severely contaminates the resulting traction measurements. Here, we introduce Deep Morphology Traction Microscopy (DeepMorphoTM), a Deep Learning alternative to conventional TFM approaches. DeepMorphoTM first infers cell-induced substrate displacement solely from a sequence of cell shapes and subsequently computes cellular traction forces, thus avoiding the requirement of a specialized fiducial-marked deformable substrate or force-free reference image. Rather, this technique drastically simplifies the overall experimental methodology, imaging, and analysis needed to conduct cell contractility measurements. We demonstrate that DeepMorphoTM quantitatively matches conventional TFM results, while offering stability against the biological variability in cell contractility for a given cell shape. Without high-frequency noise in the inferred displacement, DeepMorphoTM also resolves the ill-posedness of traction computation, increasing the consistency and accuracy of traction analysis. We demonstrate the accurate extrapolation across several cell types and substrate materials, suggesting robustness of the methodology. Accordingly, we present DeepMorphoTM as a capable yet simpler alternative to conventional TFM for characterizing cellular contractility in 2D.

PMID:39033326 | DOI:10.1016/j.bpj.2024.07.020

Categories: Literature Watch

Pages