Multi-task deep learning based CT imaging analysis for COVID-19 pneumonia: Classification and segmentation

To develop and externally validate a computed tomography (CT)-based multitask learning model to predict fracture risk. This study was conducted in two parts, using a multitasking learning approach. We developed a cross-sectional vertebral fracture (VF) detection model using abdominal CT scans of 2553 patients aged 50-80 years. Then, we leveraged this detection model within a multitask learning framework to develop a longitudinal VF prediction model over a 5-year follow-up period. External testing was performed on 1506 patients from two independent hospitals. The performance was compared between the single-task and multitask models, bone-only and bone+muscle images, and image-only and clinical models. For the cross-sectional fracture detection model, the mean age of the patients was 76.2 years, and 66.7% were female. In the classification task for detection of VF, the model using both bone and muscle showed an area under the receiver operating characteristic curve (AUROC) of 0.82 in the development set and 0.80 in the external test sets. Using multitask learning, the bone + muscle image model showed a c-index of 0.68 and had superior performance than the bone-only model in the external test set for 2-year, 3-year, and 5-year AUROCs (0.79 vs. 0.75, 0.71 vs. 0.68, and 0.71 vs. 0.68, respectively, all p < 0.01). Also, the multitask model significantly outperformed the Fracture Risk Assessment Tool (FRAX) (c-index: 0.68 vs. 0.66, p < 0.01). The CT-based multitask learning model integrating both bone and muscle data showed superior predictive performance for VFs compared with models using bone images only and traditional clinical models. Question Vertebral fracture risk remains underestimated in many individuals undergoing CT scans for other reasons, highlighting the need for improved opportunistic prediction tools. Findings A multitask deep learning model integrating both bone and muscle features from CT scans demonstrated superior performance compared to bone-only and traditional clinical models, including FRAX. Clinical relevance The proposed model enables accurate vertebral fracture risk prediction using routinely acquired CT scans, facilitating early identification and intervention without the need for additional tests.

BackgroundGenomic prediction in multiple populations can be viewed as a multi-task learning problem where tasks are to derive prediction equations for each population and multi-task learning property can be improved by sharing information across populations. The goal of this study was to develop a multi-task Bayesian learning model for multi-population genomic prediction with a strategy to effectively share information across populations. Simulation studies and real data from Holstein and Ayrshire dairy breeds with phenotypes on five milk production traits were used to evaluate the proposed multi-task Bayesian learning model and compare with a single-task model and a simple data pooling method.ResultsA multi-task Bayesian learning model was proposed for multi-population genomic prediction. Information was shared across populations through a common set of latent indicator variables while SNP effects were allowed to vary in different populations. Both simulation studies and real data analysis showed the effectiveness of the multi-task model in improving genomic prediction accuracy for the smaller Ayshire breed. Simulation studies suggested that the multi-task model was most effective when the number of QTL was small (n = 20), with an increase of accuracy by up to 0.09 when QTL effects were lowly correlated between two populations (ρ = 0.2), and up to 0.16 when QTL effects were highly correlated (ρ = 0.8). When QTL genotypes were included for training and validation, the improvements were 0.16 and 0.22, respectively, for scenarios of the low and high correlation of QTL effects between two populations. When the number of QTL was large (n = 200), improvement was small with a maximum of 0.02 when QTL genotypes were not included for genomic prediction. Reduction in accuracy was observed for the simple pooling method when the number of QTL was small and correlation of QTL effects between the two populations was low. For the real data, the multi-task model achieved an increase of accuracy between 0 and 0.07 in the Ayrshire validation set when 28,206 SNPs were used, while the simple data pooling method resulted in a reduction of accuracy for all traits except for protein percentage. When 246,668 SNPs were used, the accuracy achieved from the multi-task model increased by 0 to 0.03, while using the pooling method resulted in a reduction of accuracy by 0.01 to 0.09. In the Holstein population, the three methods had similar performance.ConclusionsResults in this study suggest that the proposed multi-task Bayesian learning model for multi-population genomic prediction is effective and has the potential to improve the accuracy of genomic prediction.

A multi-task deep learning model for short-term taxi demand forecasting considering spatiotemporal dependences

Metabolic syndrome (MetS) is a complex disorder characterized by a cluster of metabolic abnormalities, including abdominal obesity, hypertension, elevated triglycerides, reduced high-density lipoprotein cholesterol, and impaired glucose tolerance. It poses a significant public health concern, as individuals with MetS are at an increased risk of developing cardiovascular diseases and type 2 diabetes. Early and accurate identification of individuals at risk for MetS is essential. Various machine learning approaches have been employed to predict MetS, such as logistic regression, support vector machines, and several boosting techniques. However, these methods use MetS as a binary status and do not consider that MetS comprises five components. Therefore, a method that focuses on these characteristics of MetS is needed. In this study, we propose a multi-task deep learning model designed to predict MetS and its five components simultaneously. The benefit of multi-task learning is that it can manage multiple tasks with a single model, and learning related tasks may enhance the model's predictive performance. To assess the efficacy of our proposed method, we compared its performance with that of several single-task approaches, including logistic regression, support vector machine, CatBoost, LightGBM, XGBoost and one-dimensional convolutional neural network. For the construction of our multi-task deep learning model, we utilized data from the Korean Association Resource (KARE) project, which includes 352,228 single nucleotide polymorphisms (SNPs) from 7729 individuals. We also considered lifestyle, dietary, and socio-economic factors that affect chronic diseases, in addition to genomic data. By evaluating metrics such as accuracy, precision, F1-score, and the area under the receiver operating characteristic curve, we demonstrate that our multi-task learning model surpasses traditional single-task machine learning models in predicting MetS.

Advanced prediction of pipeline vertical deformation and axial strain via multi-source data fusion and multi-task deep learning

BackgroundDrug combination treatments have proven to be a realistic technique for treating challenging diseases such as cancer by enhancing efficacy and mitigating side effects. To achieve the therapeutic goals of these combinations, it is essential to employ multi-targeted drug combinations, which maximize effectiveness and synergistic effects.ResultsThis paper proposes ‘MultiComb’, a multi-task deep learning (MTDL) model designed to simultaneously predict the synergy and sensitivity of drug combinations. The model utilizes a graph convolution network to represent the Simplified Molecular-Input Line-Entry (SMILES) of two drugs, generating their respective features. Also, three fully connected subnetworks extract features of the cancer cell line. These drug and cell line features are then concatenated and processed through an attention mechanism, which outputs two optimized feature representations for the target tasks. The cross-stitch model learns the relationship between these tasks. At last, each learned task feature is fed into fully connected subnetworks to predict the synergy and sensitivity scores.The proposed model is validated using the O’Neil benchmark dataset, which includes 38 unique drugs combined to form 17,901 drug combination pairs and tested across 37 unique cancer cells. The model’s performance is tested using some metrics like mean square error (MSE\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$MSE$$\\end{document}), mean absolute error (MAE\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$MAE$$\\end{document}), coefficient of determination (R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}^{2}$$\\end{document}), Spearman, and Pearson scores. The mean synergy scores of the proposed model are 232.37, 9.59, 0.57, 0.76, and 0.73 for the previous metrics, respectively. Also, the values for mean sensitivity scores are 15.59, 2.74, 0.90, 0.95, and 0.95, respectively.ConclusionThis paper proposes an MTDL model to predict synergy and sensitivity scores for drug combinations targeting specific cancer cell lines. The MTDL model demonstrates superior performance compared to existing approaches, providing better results.

Integrate domain knowledge in training multi-task cascade deep learning model for benign–malignant thyroid nodule classification on ultrasound images

ObjectivesTo develop and validate a multi-task deep learning (MTDL) model using multiphase contrast-enhanced CT (CECT) for simultaneously assessing histological subtypes, clinical stages, and anatomical complexity grades of solid malignant renal tumors.Materials and methodsThis two-center retrospective study included patients with solid malignant renal tumors and their preoperative kidney CECT images. A progressive layered extraction (PLE)-based MTDL model was trained and externally tested. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA), compared with the results of five radiologists.ResultsAmong 798 patients (mean age, 54 ± 12 years; 279 females; Center A: n = 620, Center B: n = 178), 597 (74.8%) had clear cell renal cell carcinomas (ccRCC), 150 (18.8%) were clinical staging III/IV, and 187 (23.4%) had high anatomical complexity. On the external test set, the MTDL model achieved AUCs of 0.89 (95% CI: 0.82, 0.94) for distinguishing ccRCC from non-ccRCC, 0.87 (95% CI: 0.81, 0.93) for clinical staging (I/II vs. III/IV), and 0.87 (95% CI: 0.82, 0.92) for anatomical complexity grading (low-intermediate vs. high). The MTDL model outperformed single-task deep learning (STDL) in clinical staging (AUC: 0.87 vs. 0.82, p = 0.022), showed higher net benefit on DCA, and demonstrated better diagnostic performance than junior radiologists in histological subtyping and clinical staging. Additionally, it used 68% less memory and was 60% faster than STDL models.ConclusionThe CECT-based MTDL model demonstrated robust performance in simultaneously predicting histological subtypes, clinical stages, and anatomical complexity grades of malignant renal tumors.Key PointsQuestionAccurate preoperative description of the histological subtyping, clinical staging, and anatomical complexity of malignant renal tumors is crucial for treatment decision-making.FindingsBy sharing features, the multi-task deep learning algorithm model enhances clinical staging performance and significantly improves computational efficiency in predicting all three tasks simultaneously.Clinical relevanceThe multi-task deep learning algorithm model enables rapid and accurate comprehensive preoperative evaluation of renal tumors, which assists surgeons in optimizing surgical plans and promotes the advancement of renal tumor management toward precision and efficiency.Graphical

Tumour-stroma interactions, as indicated by tumour-stroma ratio (TSR), offer valuable prognostic stratification information. Current histological assessment of TSR is limited by tissue accessibility and spatial heterogeneity. The authors aimed to develop a multitask deep learning (MDL) model to noninvasively predict TSR and prognosis in colorectal cancer (CRC). In this retrospective study including 2268 patients with resected CRC recruited from four centres, the authors developed an MDL model using preoperative computed tomography (CT) images for the simultaneous prediction of TSR and overall survival. Patients in the training cohort ( n =956) and internal validation cohort (IVC, n =240) were randomly selected from centre I. Patients in the external validation cohort 1 (EVC1, n =509), EVC2 ( n =203), and EVC3 ( n =360) were recruited from other three centres. Model performance was evaluated with respect to discrimination and calibration. Furthermore, the authors evaluated whether the model could predict the benefit from adjuvant chemotherapy. The MDL model demonstrated strong TSR discrimination, yielding areas under the receiver operating curves (AUCs) of 0.855 (95% CI, 0.800-0.910), 0.838 (95% CI, 0.802-0.874), and 0.857 (95% CI, 0.804-0.909) in the three validation cohorts, respectively. The MDL model was also able to predict overall survival and disease-free survival across all cohorts. In multivariable Cox analysis, the MDL score (MDLS) remained an independent prognostic factor after adjusting for clinicopathological variables (all P <0.05). For stage II and stage III disease, patients with a high MDLS benefited from adjuvant chemotherapy [hazard ratio (HR) 0.391 (95% CI, 0.230-0.666), P =0.0003; HR=0.467 (95% CI, 0.331-0.659), P <0.0001, respectively], whereas those with a low MDLS did not. The multitask DL model based on preoperative CT images effectively predicted TSR status and survival in CRC patients, offering valuable guidance for personalized treatment. Prospective studies are needed to confirm its potential to select patients who might benefit from chemotherapy.

Introduction and aimsAccurate estimation of age and sex is crucial in forensic and clinical contexts, however conventional methods are subjective and time-consuming. Panoramic radiographs offer valuable data for automated analysis. Therefore, the aim of this study was to present and evaluate a multi-task deep learning framework based on ForensicNet for simultaneous estimation of chronological age and classification of sex using panoramic radiographs of the Brazilian young population aged 5-15 years.MethodsA total of 2200 high-resolution panoramic radiographs were retrospectively collected, balanced by age and sex. After applying strict inclusion/exclusion criteria, the images were randomly split into training (1320), validation (440), and test (440) sets. A multi-task DL model based on EfficientNet-B3 was implemented with task-specific branches incorporating Convolutional Block Attention Modules (CBAM) to predict age and sex. The model was trained end-to-end using a weighted multi-task loss (α = 0.3 for age, β = 0.7 for sex) and evaluated against five benchmark architectures. Grad-CAM was used for model interpretability.ResultsThe proposed ForensicNet outperformed all baseline models, achieving the lowest mean absolute error and highest coefficient of determination in age prediction, and highest accuracy and area under the curve in sex classification. Grad-CAM visualisations confirmed the model’s focus on anatomically relevant areas. Ablation studies showed that removing CBAM or altering task weights reduced performance.ConclusionsThe proposed ForensicNet-based multi-task deep learning model demonstrated robust performance in both chronological age estimation and sex classification using panoramic radiographs from young Brazilian individuals, supporting its potential forensic and clinical applicability.Clinical relevanceThis framework may assist forensic experts and clinicians by providing fast, objective and reproducible estimations of age and sex from routinely acquired panoramic radiographs, potentially improving identification processes in forensic and pediatric contexts.

Glaucoma is an eye condition that leads to loss of vision and blindness if not diagnosed in time. Diagnosis requires human experts to estimate in a limited time subtle changes in the shape of the optic disc from retinal fundus images. Deep learning methods have been satisfactory in classifying and segmenting diseases in retinal fundus images, assisting in analyzing the increasing amount of images. Model training requires extensive annotations to achieve successful generalization, which can be highly problematic given the costly expert annotations. This work aims at designing and training a novel multi-task deep learning model that leverages the similarities of related eye-fundus tasks and measurements used in glaucoma diagnosis. The model simultaneously learns different segmentation and classification tasks, thus benefiting from their similarity. The evaluation of the method in a retinal fundus glaucoma challenge dataset, including 1200 retinal fundus images from different cameras and medical centers, obtained a 96.76 pm 0.96 AUC performance compared to an 93.56 pm 1.48 obtained by the same backbone network trained to detect glaucoma. Our approach outperforms other multi-task learning models, and its performance pairs with trained experts using ~sim 3.5 times fewer parameters than training each task separately. The data and the code for reproducing our results are publicly available.

Detection of peripherally inserted central catheter (PICC) in chest X-ray images: A multi-task deep learning model

Recently, several deep learning models have been successfully proposed and have been applied to solve different Natural Language Processing (NLP) tasks. However, these models solve the problem based on single-task supervised learning and do not consider the correlation between the tasks. Based on this observation, in this paper, we implemented a multi-task learning model to joint learn two related NLP tasks simultaneously and conducted experiments to evaluate if learning these tasks jointly can improve the system performance compared with learning them individually. In addition, a comparison of our model with the state-of-the-art learning models, including multi-task learning, transfer learning, unsupervised learning and feature based traditional machine learning models is presented. This paper aims to 1) show the advantage of multi-task learning over single-task learning in training related NLP tasks, 2) illustrate the influence of various encoding structures to the proposed single- and multi-task learning models, and 3) compare the performance between multi-task learning and other learning models in literature on textual entailment task and semantic relatedness task.

Introduction: Predicting rare catastrophic events is challenging due to lack of targets. Here we employed a multi-task learning method and demonstrated that substantial gains in accuracy and generalizability was achieved by sharing representations between related tasks Methods: Starting from Taiwan National Health Insurance Research Database, we selected adult people (&gt;20 year) experienced in-hospital cardiac arrest but not out-of-hospital cardiac arrest during 8 years (2003-2010), and built a dataset using de-identified claims of Emergency Department (ED) and hospitalization. Final dataset had 169,287 patients, randomly split into 3 sections, train 70%, validation 15%, and test 15%.Two outcomes, 30-day readmission and 30-day mortality are chosen. We constructed the deep learning system in two steps. We first used a taxonomy mapping system Text2Node to generate a distributed representation for each concept. We then applied a multilevel hierarchical model based on long short-term memory (LSTM) architecture. Multi-task models used gradient similarity to prioritize the desired task over auxiliary tasks. Single-task models were trained for each desired task. All models share the same architecture and are trained with the same input data Results: Each model was optimized to maximize AUROC on the validation set with the final metrics calculated on the held-out test set. We demonstrated multi-task deep learning models outperform single task deep learning models on both tasks. While readmission had roughly 30% positives and showed miniscule improvements, the mortality task saw more improvement between models. We hypothesize that this is a result of the data imbalance, mortality occurred roughly 5% positive; the auxiliary tasks help the model interpret the data and generalize better. Conclusion: Multi-task deep learning models outperform single task deep learning models in predicting 30-day readmission and mortality in in-hospital cardiac arrest patients.

The aim of this study was to determine the invasiveness of ground-glass nodules (GGNs) using a 3D multi-task deep learning network. We propose a novel architecture based on 3D multi-task learning to determine the invasiveness of GGNs. In total, 770 patients with 909 GGNs who underwent lung CT scans were enrolled. The patients were divided into the training (n = 626) and test sets (n = 144). In the test set, invasiveness was classified using deep learning into three categories: atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive pulmonary adenocarcinoma (IA). Furthermore, binary classifications (AAH/AIS/MIA vs. IA) were made by two thoracic radiologists and compared with the deep learning results. In the three-category classification task, the sensitivity, specificity, and accuracy were 65.41%, 82.21%, and 64.9%, respectively. In the binary classification task, the sensitivity, specificity, accuracy, and area under the ROC curve (AUC) values were 69.57%, 95.24%, 87.42%, and 0.89, respectively. In the visual assessment of GGN invasiveness of binary classification by the two thoracic radiologists, the sensitivity, specificity, and accuracy of the senior and junior radiologists were 58.93%, 90.51%, and 81.35% and 76.79%, 55.47%, and 61.66%, respectively. The proposed multi-task deep learning model achieved good classification results in determining the invasiveness of GGNs. This model may help to select patients with invasive lesions who need surgery and the proper surgical methods. • The proposed multi-task model has achieved good classification results for the invasiveness of GGNs. • The proposed network includes a classification and segmentation branch to learn global and regional features, respectively. • The multi-task model could assist doctors in selecting patients with invasive lesions who need surgery and choosing appropriate surgical methods.