Med Phys. 2024 Jul 12. doi: 10.1002/mp.17287. Online ahead of print.

ABSTRACT

BACKGROUND: The reliable and efficient estimation of uncertainty in artificial intelligence (AI) models poses an ongoing challenge in many fields such as radiation therapy. AI models are intended to automate manual steps involved in the treatment planning workflow. We focus in this study on dose prediction models that predict an optimal dose trade-off for each new patient for a specific treatment modality. They can guide physicians in the optimization, be part of automatic treatment plan generation or support decision in treatment indication. Most common uncertainty estimation methods are based on Bayesian approximations, like Monte Carlo dropout (MCDO) or Deep ensembling (DE). These two techniques, however, have a high inference time (i.e., require multiple inference passes) and might not work for detecting out-of-distribution (OOD) data (i.e., overlapping uncertainty estimate for in-distribution (ID) and OOD).

PURPOSE: In this study, we present a direct uncertainty estimation method and apply it for a dose prediction U-Net architecture. It can be used to flag OOD data and give information on the quality of the dose prediction.

METHODS: Our method consists in the addition of a branch decoding from the bottleneck which reconstructs the CT scan given as input. The input reconstruction error can be used as a surrogate of the model uncertainty. For the proof-of-concept, our method is applied to proton therapy dose prediction in head and neck cancer patients. A dataset of 60 oropharyngeal patients was used to train the network using a nested cross-validation approach with 11 folds (training: 50 patients, validation: 5 patients, test: 5 patients). For the OOD experiment, we used 10 extra patients with a different head and neck sub-location. Accuracy, time-gain, and OOD detection are analyzed for our method in this particular application and compared with the popular MCDO and DE.

RESULTS: The additional branch did not reduce the accuracy of the dose prediction model. The median absolute error is close to zero for the target volumes and less than 1% of the dose prescription for organs at risk. Our input reconstruction method showed a higher Pearson correlation coefficient with the prediction error (0.620) than DE (0.447) and MCDO (between 0.599 and 0.612). Moreover, our method allows an easier identification of OOD (no overlap for ID and OOD data and a Z-score of 34.05). The uncertainty is estimated simultaneously to the regression task, therefore requires less time and computational resources.

CONCLUSIONS: This study shows that the error in the CT scan reconstruction can be used as a surrogate of the uncertainty of the model. The Pearson correlation coefficient with the dose prediction error is slightly higher than state-of-the-art techniques. OOD data can be more easily detected and the uncertainty metric is computed simultaneously to the regression task, therefore faster than MCDO or DE. The code and pretrained model are available on the gitlab repository: https://gitlab.com/ai4miro/ct-reconstruction-for-uncertainty-quatification-of-hdunet.

PMID:38996043 | DOI:10.1002/mp.17287

PLoS One. 2024 Jul 12;19(7):e0306073. doi: 10.1371/journal.pone.0306073. eCollection 2024.

ABSTRACT

Analyzing tissue microstructure is essential for understanding complex biological systems in different species. Tissue functions largely depend on their intrinsic tissue architecture. Therefore, studying the three-dimensional (3D) microstructure of tissues, such as the liver, is particularly fascinating due to its conserved essential roles in metabolic processes and detoxification. Here, we present TiMiGNet, a novel deep learning approach for virtual 3D tissue microstructure reconstruction using Generative Adversarial Networks and fluorescence microscopy. TiMiGNet overcomes challenges such as poor antibody penetration and time-intensive procedures by generating accurate, high-resolution predictions of tissue components across large volumes without the need of paired images as input. We applied TiMiGNet to analyze tissue microstructure in mouse and human liver tissue. TiMiGNet shows high performance in predicting structures like bile canaliculi, sinusoids, and Kupffer cell shapes from actin meshwork images. Remarkably, using TiMiGNet we were able to computationally reconstruct tissue structures that cannot be directly imaged due experimental limitations in deep dense tissues, a significant advancement in deep tissue imaging. Our open-source virtual prediction tool facilitates accessible and efficient multi-species tissue microstructure analysis, accommodating researchers with varying expertise levels. Overall, our method represents a powerful approach for studying tissue microstructure, with far-reaching applications in diverse biological contexts and species.

PMID:38995963 | DOI:10.1371/journal.pone.0306073

PLoS One. 2024 Jul 12;19(7):e0300442. doi: 10.1371/journal.pone.0300442. eCollection 2024.

ABSTRACT

PURPOSE: Radical surgery is the primary treatment for early-stage resectable lung cancer, yet recurrence after curative surgery is not uncommon. Identifying patients at high risk of recurrence using preoperative computed tomography (CT) images could enable more aggressive surgical approaches, shorter surveillance intervals, and intensified adjuvant treatments. This study aims to analyze lung cancer sites in CT images to predict potential recurrences in high-risk individuals.

METHODS: We retrieved anonymized imaging and clinical data from an institutional database, focusing on patients who underwent curative pulmonary resections for non-small cell lung cancers. Our study used a deep learning model, the Mask Region-based Convolutional Neural Network (MRCNN), to predict cancer locations and assign recurrence classification scores. To find optimized trained weighted values in the model, we developed preprocessing python codes, adjusted dynamic learning rate, and modifying hyper parameter in the model.

RESULTS: The model training completed; we performed classifications using the validation dataset. The results, including the confusion matrix, demonstrated performance metrics: bounding box (0.390), classification (0.034), mask (0.266), Region Proposal Network (RPN) bounding box (0.341), and RPN classification (0.054). The model successfully identified lung cancer recurrence sites, which were then accurately mapped onto chest CT images to highlight areas of primary concern.

CONCLUSION: The trained model allows clinicians to focus on lung regions where cancer recurrence is more likely, acting as a significant aid in the detection and diagnosis of lung cancer. Serving as a clinical decision support system, it offers substantial support in managing lung cancer patients.

PMID:38995927 | DOI:10.1371/journal.pone.0300442

Dentomaxillofac Radiol. 2024 Jul 12:twae031. doi: 10.1093/dmfr/twae031. Online ahead of print.

ABSTRACT

OBJECTIVES: To assess the performance of deep learning (DL) in the detection, classification, and segmentation of maxillary sinus diseases.

MATERIALS AND METHODS: An electronic search was conducted by two reviewers on databases including PubMed, Scopus, Cochrane, and IEEE. All English papers published no later than February 7, 2024, were evaluated. Studies related to DL for diagnosing maxillary sinus diseases were also searched in journals manually.

RESULTS: 14 of 1167 studies were eligible according to the inclusion criteria. All studies trained DL models based on radiographic images. Six studies applied to detection tasks, one focused on classification, two segmented lesions, and five studies made a combination of 2 types of DL models. The accuracy of the DL algorithms ranged from 75.7% to 99.7%, and the area under curves (AUC) varied between 0.7 and 0.997.

CONCLUSION: DL can accurately deal with the tasks of diagnosing maxillary sinus diseases. Students, residents, and dentists could be assisted by DL algorithms to diagnose and make rational decisions on implant treatment related to maxillary sinuses.

PMID:38995816 | DOI:10.1093/dmfr/twae031

J Alzheimers Dis. 2024 Jun 29. doi: 10.3233/JAD-231389. Online ahead of print.

ABSTRACT

BACKGROUND: Alzheimer's disease (AD) is a neurodegenerative disorder caused by a complex interplay of various factors. However, a satisfactory cure for AD remains elusive. Pharmacological interventions based on drug targets are considered the most cost-effective therapeutic strategy. Therefore, it is paramount to search potential drug targets and drugs for AD.

OBJECTIVE: We aimed to provide novel targets and drugs for the treatment of AD employing transcriptomic data of AD and normal control brain tissues from a new perspective.

METHODS: Our study combined the use of a multi-layer perceptron (MLP) with differential expression analysis, variance assessment and molecular docking to screen targets and drugs for AD.

RESULTS: We identified the seven differentially expressed genes (DEGs) with the most significant variation (ANKRD39, CPLX1, FABP3, GABBR2, GNG3, PPM1E, and WDR49) in transcriptomic data from AD brain. A newly built MLP was used to confirm the association between the seven DEGs and AD, establishing these DEGs as potential drug targets. Drug databases and molecular docking results indicated that arbaclofen, baclofen, clozapine, arbaclofen placarbil, BML-259, BRD-K72883421, and YC-1 had high affinity for GABBR2, and FABP3 bound with oleic, palmitic, and stearic acids. Arbaclofen and YC-1 activated GABAB receptor through PI3K/AKT and PKA/CREB pathways, respectively, thereby promoting neuronal anti-apoptotic effect and inhibiting p-tau and Aβ formation.

CONCLUSIONS: This study provided a new strategy for the identification of targets and drugs for the treatment of AD using deep learning. Seven therapeutic targets and ten drugs were selected by using this method, providing new insight for AD treatment.

PMID:38995776 | DOI:10.3233/JAD-231389

Br J Radiol. 2024 Jul 12:tqae129. doi: 10.1093/bjr/tqae129. Online ahead of print.

ABSTRACT

OBJECTIVES: To investigate an interpretable radiomics model consistent with clinical decision-making process and realize automatic prediction of tumor-infiltrating lymphocytes (TILs) levels in breast cancer (BC) from ultrasound (US) images.

METHODS: A total of 378 patients with invasive BC confirmed by pathological results were retrospectively enrolled in this study. Radiomics features were extracted guided by the BI-RADS lexicon from the regions of interest(ROIs) segmented with deep learning models. After features selected using the least absolute shrinkage and selection operator(LASSO) regression, four machine learning classifiers were used to establish the radiomics signature(Rad-score). Then, the integrated model was developed on the basis of the best Rad-score incorporating the independent clinical factors for TILs levels prediction.

RESULTS: Tumors were segmented using the deep learning models with accuracy of 97.2%, sensitivity of 93.4%, specificity of 98.1%, and the posterior areas were also obtained. Eighteen morphology and texture related features were extracted from the ROIs and fourteen features were selected to construct the Rad-score models. Combined with independent clinical characteristics, the integrated model achieved an area under the curve (AUC) of 0.889(95% CI,0.739,0.990) in the validation cohort and outperformed the traditional radiomics model with AUC of 0.756(0.649-0862) depended on hundreds of feature items.

CONCLUSIONS: This study established a promising model for TILs levels prediction with numerable interpretable features and showed great potential to help decision-making and clinical applications.

ADVANCES IN KNOWLEDGE: Imaging-based biomarkers has provides non-invasive ways for TILs levels evaluation in BC. Our model combining the BI-RADS guided radiomics features and clinical data outperformed the traditional radiomics approaches.

PMID:38995740 | DOI:10.1093/bjr/tqae129

J Med Internet Res. 2024 Jul 12;26:e48535. doi: 10.2196/48535.

ABSTRACT

BACKGROUND: With the progressive increase in aging populations, the use of opportunistic computed tomography (CT) scanning is increasing, which could be a valuable method for acquiring information on both muscles and bones of aging populations.

OBJECTIVE: The aim of this study was to develop and externally validate opportunistic CT-based fracture prediction models by using images of vertebral bones and paravertebral muscles.

METHODS: The models were developed based on a retrospective longitudinal cohort study of 1214 patients with abdominal CT images between 2010 and 2019. The models were externally validated in 495 patients. The primary outcome of this study was defined as the predictive accuracy for identifying vertebral fracture events within a 5-year follow-up. The image models were developed using an attention convolutional neural network-recurrent neural network model from images of the vertebral bone and paravertebral muscles.

RESULTS: The mean ages of the patients in the development and validation sets were 73 years and 68 years, and 69.1% (839/1214) and 78.8% (390/495) of them were females, respectively. The areas under the receiver operator curve (AUROCs) for predicting vertebral fractures were superior in images of the vertebral bone and paravertebral muscles than those in the bone-only images in the external validation cohort (0.827, 95% CI 0.821-0.833 vs 0.815, 95% CI 0.806-0.824, respectively; P<.001). The AUROCs of these image models were higher than those of the fracture risk assessment models (0.810 for major osteoporotic risk, 0.780 for hip fracture risk). For the clinical model using age, sex, BMI, use of steroids, smoking, possible secondary osteoporosis, type 2 diabetes mellitus, HIV, hepatitis C, and renal failure, the AUROC value in the external validation cohort was 0.749 (95% CI 0.736-0.762), which was lower than that of the image model using vertebral bones and muscles (P<.001).

CONCLUSIONS: The model using the images of the vertebral bone and paravertebral muscle showed better performance than that using the images of the bone-only or clinical variables. Opportunistic CT screening may contribute to identifying patients with a high fracture risk in the future.

PMID:38995678 | DOI:10.2196/48535

Methods Mol Biol. 2024;2836:157-181. doi: 10.1007/978-1-0716-4007-4_10.

ABSTRACT

Proteomics, the study of proteins within biological systems, has seen remarkable advancements in recent years, with protein isoform detection emerging as one of the next major frontiers. One of the primary challenges is achieving the necessary peptide and protein coverage to confidently differentiate isoforms as a result of the protein inference problem and protein false discovery rate estimation challenge in large data. In this chapter, we describe the application of artificial intelligence-assisted peptide property prediction for database search engine rescoring by Oktoberfest, an approach that has proven effective, particularly for complex samples and extensive search spaces, which can greatly increase peptide coverage. Further, it illustrates a method for increasing isoform coverage by the PickedGroupFDR approach that is designed to excel when applied on large data. Real-world examples are provided to illustrate the utility of the tools in the context of rescoring, protein grouping, and false discovery rate estimation. By implementing these cutting-edge techniques, researchers can achieve a substantial increase in both peptide and isoform coverage, thus unlocking the potential of protein isoform detection in their studies and shedding light on their roles and functions in biological processes.

PMID:38995541 | DOI:10.1007/978-1-0716-4007-4_10

Methods Mol Biol. 2024;2836:135-155. doi: 10.1007/978-1-0716-4007-4_9.

ABSTRACT

The increasing complexity and volume of mass spectrometry (MS) data have presented new challenges and opportunities for proteomics data analysis and interpretation. In this chapter, we provide a comprehensive guide to transforming MS data for machine learning (ML) training, inference, and applications. The chapter is organized into three parts. The first part describes the data analysis needed for MS-based experiments and a general introduction to our deep learning model SpeCollate-which we will use throughout the chapter for illustration. The second part of the chapter explores the transformation of MS data for inference, providing a step-by-step guide for users to deduce peptides from their MS data. This section aims to bridge the gap between data acquisition and practical applications by detailing the necessary steps for data preparation and interpretation. In the final part, we present a demonstrative example of SpeCollate, a deep learning-based peptide database search engine that overcomes the problems of simplistic simulation of theoretical spectra and heuristic scoring functions for peptide-spectrum matches by generating joint embeddings for spectra and peptides. SpeCollate is a user-friendly tool with an intuitive command-line interface to perform the search, showcasing the effectiveness of the techniques and methodologies discussed in the earlier sections and highlighting the potential of machine learning in the context of mass spectrometry data analysis. By offering a comprehensive overview of data transformation, inference, and ML model applications for mass spectrometry, this chapter aims to empower researchers and practitioners in leveraging the power of machine learning to unlock novel insights and drive innovation in the field of mass spectrometry-based omics.

PMID:38995540 | DOI:10.1007/978-1-0716-4007-4_9

Langenbecks Arch Surg. 2024 Jul 12;409(1):213. doi: 10.1007/s00423-024-03411-y.

ABSTRACT

PURPOSE: Laparoscopic distal gastrectomy (LDG) is a difficult procedure for early career surgeons. Artificial intelligence (AI)-based surgical step recognition is crucial for establishing context-aware computer-aided surgery systems. In this study, we aimed to develop an automatic recognition model for LDG using AI and evaluate its performance.

METHODS: Patients who underwent LDG at our institution in 2019 were included in this study. Surgical video data were classified into the following nine steps: (1) Port insertion; (2) Lymphadenectomy on the left side of the greater curvature; (3) Lymphadenectomy on the right side of the greater curvature; (4) Division of the duodenum; (5) Lymphadenectomy of the suprapancreatic area; (6) Lymphadenectomy on the lesser curvature; (7) Division of the stomach; (8) Reconstruction; and (9) From reconstruction to completion of surgery. Two gastric surgeons manually assigned all annotation labels. Convolutional neural network (CNN)-based image classification was further employed to identify surgical steps.

RESULTS: The dataset comprised 40 LDG videos. Over 1,000,000 frames with annotated labels of the LDG steps were used to train the deep-learning model, with 30 and 10 surgical videos for training and validation, respectively. The classification accuracies of the developed models were precision, 0.88; recall, 0.87; F1 score, 0.88; and overall accuracy, 0.89. The inference speed of the proposed model was 32 ps.

CONCLUSION: The developed CNN model automatically recognized the LDG surgical process with relatively high accuracy. Adding more data to this model could provide a fundamental technology that could be used in the development of future surgical instruments.

PMID:38995411 | DOI:10.1007/s00423-024-03411-y

Allergy. 2024 Jul 12. doi: 10.1111/all.16227. Online ahead of print.

ABSTRACT

BACKGROUND: There is evidence that global anthropogenic climate change may be impacting floral phenology and the temporal and spatial characteristics of aero-allergenic pollen. Given the extent of current and future climate uncertainty, there is a need to strengthen predictive pollen forecasts.

METHODS: The study aims to use CatBoost (CB) and deep learning (DL) models for predicting the daily total pollen concentration up to 14 days in advance for 23 cities, covering all five continents. The model includes the projected environmental parameters, recent concentrations (1, 2 and 4 weeks), and the past environmental explanatory variables, and their future values.

RESULTS: The best pollen forecasts include Mexico City (R2(DL_7) ≈ .7), and Santiago (R2(DL_7) ≈ .8) for the 7th forecast day, respectively; while the weakest pollen forecasts are made for Brisbane (R2(DL_7) ≈ .4) and Seoul (R2(DL_7) ≈ .1) for the 7th forecast day. The global order of the five most important environmental variables in determining the daily total pollen concentrations is, in decreasing order: the past daily total pollen concentration, future 2 m temperature, past 2 m temperature, past soil temperature in 28-100 cm depth, and past soil temperature in 0-7 cm depth. City-related clusters of the most similar distribution of feature importance values of the environmental variables only slightly change on consecutive forecast days for Caxias do Sul, Cape Town, Brisbane, and Mexico City, while they often change for Sydney, Santiago, and Busan.

CONCLUSIONS: This new knowledge of the ecological relationships of the most remarkable variables importance for pollen forecast models according to clusters, cities and forecast days is important for developing and improving the accuracy of airborne pollen forecasts.

PMID:38995241 | DOI:10.1111/all.16227

Radiol Imaging Cancer. 2024 Jul;6(4):e230149. doi: 10.1148/rycan.230149.

ABSTRACT

Purpose To compare two deep learning-based commercially available artificial intelligence (AI) systems for mammography with digital breast tomosynthesis (DBT) and benchmark them against the performance of radiologists. Materials and Methods This retrospective study included consecutive asymptomatic patients who underwent mammography with DBT (2019-2020). Two AI systems (Transpara 1.7.0 and ProFound AI 3.0) were used to evaluate the DBT examinations. The systems were compared using receiver operating characteristic (ROC) analysis to calculate the area under the ROC curve (AUC) for detecting malignancy overall and within subgroups based on mammographic breast density. Breast Imaging Reporting and Data System results obtained from standard-of-care human double-reading were compared against AI results with use of the DeLong test. Results Of 419 female patients (median age, 60 years [IQR, 52-70 years]) included, 58 had histologically proven breast cancer. The AUC was 0.86 (95% CI: 0.85, 0.91), 0.93 (95% CI: 0.90, 0.95), and 0.98 (95% CI: 0.96, 0.99) for Transpara, ProFound AI, and human double-reading, respectively. For Transpara, a rule-out criterion of score 7 or lower yielded 100% (95% CI: 94.2, 100.0) sensitivity and 60.9% (95% CI: 55.7, 66.0) specificity. The rule-in criterion of higher than score 9 yielded 96.6% sensitivity (95% CI: 88.1, 99.6) and 78.1% specificity (95% CI: 73.8, 82.5). For ProFound AI, a rule-out criterion of lower than score 51 yielded 100% sensitivity (95% CI: 93.8, 100) and 67.0% specificity (95% CI: 62.2, 72.1). The rule-in criterion of higher than score 69 yielded 93.1% (95% CI: 83.3, 98.1) sensitivity and 82.0% (95% CI: 77.9, 86.1) specificity. Conclusion Both AI systems showed high performance in breast cancer detection but lower performance compared with human double-reading. Keywords: Mammography, Breast, Oncology, Artificial Intelligence, Deep Learning, Digital Breast Tomosynthesis © RSNA, 2024.

PMID:38995172 | DOI:10.1148/rycan.230149

Adv Sci (Weinh). 2024 Jul 12:e2402918. doi: 10.1002/advs.202402918. Online ahead of print.

ABSTRACT

Assessing changes in protein-protein binding affinity due to mutations helps understanding a wide range of crucial biological processes within cells. Despite significant efforts to create accurate computational models, predicting how mutations affect affinity remains challenging due to the complexity of the biological mechanisms involved. In the present work, a geometric deep learning framework called MuToN is introduced for quantifying protein binding affinity change upon residue mutations. The method, designed with geometric attention networks, is mechanism-aware. It captures changes in the protein binding interfaces of mutated complexes and assesses the allosteric effects of amino acids. Experimental results highlight MuToN's superiority compared to existing methods. Additionally, MuToN's flexibility and effectiveness are illustrated by its precise predictions of binding affinity changes between SARS-CoV-2 variants and the ACE2 complex.

PMID:38995072 | DOI:10.1002/advs.202402918

Protein Sci. 2024 Aug;33(8):e5104. doi: 10.1002/pro.5104.

ABSTRACT

Despite ferritin's critical role in regulating cellular and systemic iron levels, our understanding of the structure and assembly mechanism of isoferritins, discovered over eight decades ago, remains limited. Unveiling how the composition and molecular architecture of hetero-oligomeric ferritins confer distinct functionality to isoferritins is essential to understanding how the structural intricacies of H and L subunits influence their interactions with cellular machinery. In this study, ferritin heteropolymers with specific H to L subunit ratios were synthesized using a uniquely engineered plasmid design, followed by high-resolution cryo-electron microscopy analysis and deep learning-based amino acid modeling. Our structural examination revealed unique architectural features during the self-assembly mechanism of heteropolymer ferritins and demonstrated a significant preference for H-L heterodimer formation over H-H or L-L homodimers. Unexpectedly, while dimers seem essential building blocks in the protein self-assembly process, the overall mechanism of ferritin self-assembly is observed to proceed randomly through diverse pathways. The physiological significance of these findings is discussed including how ferritin microheterogeneity could represent a tissue-specific adaptation process that imparts distinctive tissue-specific functions to isoferritins.

PMID:38995055 | DOI:10.1002/pro.5104

mSphere. 2024 Jul 12:e0034624. doi: 10.1128/msphere.00346-24. Online ahead of print.

ABSTRACT

In the process of oxygen reduction, reactive oxygen species (ROS) are generated as intermediates, including superoxide anion (O2-), hydrogen peroxide (H2O2), and hydroxyl radicals (OH-). ROS can be destructive, and an imbalance between oxidants and antioxidants in the body can lead to pathological inflammation. Inappropriate ROS production can cause oxidative damage, disrupting the balance in the body and potentially leading to DNA damage in intestinal epithelial cells and beneficial bacteria. Microorganisms have evolved various enzymes to mitigate the harmful effects of ROS. Accurately predicting the types of ROS-scavenging enzymes (ROSes) is crucial for understanding the oxidative stress mechanisms and formulating strategies to combat diseases related to the "gut-organ axis." Currently, there are no available ROSes databases (DBs). In this study, we propose a systematic workflow comprising three modules and employ a hierarchical multi-task deep learning approach to collect, expand, and explore ROSes-related entries. Based on this, we have developed the human gut microbiota ROSes DB (http://39.101.72.186/), which includes 7,689 entries. This DB provides user-friendly browsing and search features to support various applications. With the assistance of ROSes DB, various communication-based microbial interactions can be explored, further enabling the construction and analysis of the evolutionary and complex networks of ROSes DB in human gut microbiota species.IMPORTANCEReactive oxygen species (ROS) is generated during the process of oxygen reduction, including superoxide anion, hydrogen peroxide, and hydroxyl radicals. ROS can potentially cause damage to cells and DNA, leading to pathological inflammation within the body. Microorganisms have evolved various enzymes to mitigate the harmful effects of ROS, thereby maintaining a balance of microorganisms within the host. The study highlights the current absence of a ROSes DB, emphasizing the crucial importance of accurately predicting the types of ROSes for understanding oxidative stress mechanisms and developing strategies for diseases related to the "gut-organ axis." This research proposes a systematic workflow and employs a multi-task deep learning approach to establish the human gut microbiota ROSes DB. This DB comprises 7,689 entries and serves as a valuable tool for researchers to delve into the role of ROSes in the human gut microbiota.

PMID:38995053 | DOI:10.1128/msphere.00346-24

Int J Med Robot. 2024 Aug;20(4):e2664. doi: 10.1002/rcs.2664.

ABSTRACT

BACKGROUND: This study aimed to develop a novel deep convolutional neural network called Dual-path Double Attention Transformer (DDA-Transformer) designed to achieve precise and fast knee joint CT image segmentation and to validate it in robotic-assisted total knee arthroplasty (TKA).

METHODS: The femoral, tibial, patellar, and fibular segmentation performance and speed were evaluated and the accuracy of component sizing, bone resection and alignment of the robotic-assisted TKA system constructed using this deep learning network was clinically validated.

RESULTS: Overall, DDA-Transformer outperformed six other networks in terms of the Dice coefficient, intersection over union, average surface distance, and Hausdorff distance. DDA-Transformer exhibited significantly faster segmentation speeds than nnUnet, TransUnet and 3D-Unet (p < 0.01). Furthermore, the robotic-assisted TKA system outperforms the manual group in surgical accuracy.

CONCLUSIONS: DDA-Transformer exhibited significantly improved accuracy and robustness in knee joint segmentation, and this convenient and stable knee joint CT image segmentation network significantly improved the accuracy of the TKA procedure.

PMID:38994900 | DOI:10.1002/rcs.2664

World J Gastrointest Oncol. 2024 Jun 15;16(6):2404-2418. doi: 10.4251/wjgo.v16.i6.2404.

ABSTRACT

BACKGROUND: Research on gastrointestinal mucosal adenocarcinoma (GMA) is limited and controversial, and there is no reference tool for predicting postoperative survival.

AIM: To investigate the prognosis of GMA and develop predictive model.

METHODS: From the Surveillance, Epidemiology, and End Results database, we collected clinical information on patients with GMA. After random sampling, the patients were divided into the discovery (70% of the total, for model training), validation (20%, for model evaluation), and completely blind test cohorts (10%, for further model evaluation). The main assessment metric was the area under the receiver operating characteristic curve (AUC). All collected clinical features were used for Cox proportional hazard regression analysis to determine factors influencing GMA's prognosis.

RESULTS: This model had an AUC of 0.7433 [95% confidence intervals (95%CI): 0.7424-0.7442] in the discovery cohort, 0.7244 (GMA: 0.7234-0.7254) in the validation cohort, and 0.7388 (95%CI: 0.7378-0.7398) in the test cohort. We packaged it into Windows software for doctors' use and uploaded it. Mucinous gastric adenocarcinoma had the worst prognosis, and these were protective factors of GMA: Regional nodes examined [hazard ratio (HR): 0.98, 95%CI: 0.97-0.98, P < 0.001)] and chemotherapy (HR: 0.62, 95%CI: 0.58-0.66, P < 0.001).

CONCLUSION: The deep learning-based tool developed can accurately predict the overall survival of patients with GMA postoperatively. Combining surgery, chemotherapy, and adequate lymph node dissection during surgery can improve patient outcomes.

PMID:38994138 | PMC:PMC11236227 | DOI:10.4251/wjgo.v16.i6.2404

Radiol Bras. 2024 Jun 26;57:e20230096en. doi: 10.1590/0100-3984.2023.0096-en. eCollection 2024 Jan-Dec.

ABSTRACT

OBJECTIVE: To develop a natural language processing application capable of automatically identifying benign gallbladder diseases that require surgery, from radiology reports.

MATERIALS AND METHODS: We developed a text classifier to classify reports as describing benign diseases of the gallbladder that do or do not require surgery. We randomly selected 1,200 reports describing the gallbladder from our database, including different modalities. Four radiologists classified the reports as describing benign disease that should or should not be treated surgically. Two deep learning architectures were trained for classification: a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) network. In order to represent words in vector form, the models included a Word2Vec representation, with dimensions of 300 or 1,000. The models were trained and evaluated by dividing the dataset into training, validation, and subsets (80/10/10).

RESULTS: The CNN and BiLSTM performed well in both dimensional spaces. For the 300- and 1,000-dimensional spaces, respectively, the F1-scores were 0.95945 and 0.95302 for the CNN model, compared with 0.96732 and 0.96732 for the BiLSTM model.

CONCLUSION: Our models achieved high performance, regardless of the architecture and dimensional space employed.

PMID:38993952 | PMC:PMC11235066 | DOI:10.1590/0100-3984.2023.0096-en

Front Plant Sci. 2024 Jun 26;15:1349209. doi: 10.3389/fpls.2024.1349209. eCollection 2024.

ABSTRACT

Counting nematodes is a labor-intensive and time-consuming task, yet it is a pivotal step in various quantitative nematological studies; preparation of initial population densities and final population densities in pot, micro-plot and field trials for different objectives related to management including sampling and location of nematode infestation foci. Nematologists have long battled with the complexities of nematode counting, leading to several research initiatives aimed at automating this process. However, these research endeavors have primarily focused on identifying single-class objects within individual images. To enhance the practicality of this technology, there's a pressing need for an algorithm that cannot only detect but also classify multiple classes of objects concurrently. This study endeavors to tackle this challenge by developing a user-friendly Graphical User Interface (GUI) that comprises multiple deep learning algorithms, allowing simultaneous recognition and categorization of nematode eggs and second stage juveniles of Meloidogyne spp. In total of 650 images for eggs and 1339 images for juveniles were generated using two distinct imaging systems, resulting in 8655 eggs and 4742 Meloidogyne juveniles annotated using bounding box and segmentation, respectively. The deep-learning models were developed by leveraging the Convolutional Neural Networks (CNNs) machine learning architecture known as YOLOv8x. Our results showed that the models correctly identified eggs as eggs and Meloidogyne juveniles as Meloidogyne juveniles in 94% and 93% of instances, respectively. The model demonstrated higher than 0.70 coefficient correlation between model predictions and observations on unseen images. Our study has showcased the potential utility of these models in practical applications for the future. The GUI is made freely available to the public through the author's GitHub repository (https://github.com/bresilla/nematode_counting). While this study currently focuses on one genus, there are plans to expand the GUI's capabilities to include other economically significant genera of plant parasitic nematodes. Achieving these objectives, including enhancing the models' accuracy on different imaging systems, may necessitate collaboration among multiple nematology teams and laboratories, rather than being the work of a single entity. With the increasing interest among nematologists in harnessing machine learning, the authors are confident in the potential development of a universal automated nematode counting system accessible to all. This paper aims to serve as a framework and catalyst for initiating global collaboration toward this important goal.

PMID:38993936 | PMC:PMC11238600 | DOI:10.3389/fpls.2024.1349209

Front Transplant. 2023 Jun 23;2:1206085. doi: 10.3389/frtra.2023.1206085. eCollection 2023.

ABSTRACT

An accurate estimation of liver fat content is necessary to predict how a donated liver will function after transplantation. Currently, a pathologist needs to be available at all hours of the day, even at remote hospitals, when an organ donor is procured. Even among expert pathologists, the estimation of liver fat content is operator-dependent. Here we describe the development of a low-cost, end-to-end artificial intelligence platform to evaluate liver fat content on a donor liver biopsy slide in real-time. The hardware includes a high-resolution camera, display, and GPU to acquire and process donor liver biopsy slides. A deep learning model was trained to label and quantify fat globules in liver tissue. The algorithm was deployed on the device to enable real-time quantification and characterization of fat content for transplant decision-making. This information is displayed on the device and can also be sent to a cloud platform for further analysis.

PMID:38993883 | PMC:PMC11235317 | DOI:10.3389/frtra.2023.1206085