Multi-task Deep Learning Model Research Articles

A commentary on "A CT-based multitask deep learning model for predicting tumor stroma ratio and treatment outcomes in patients with colorectal cancer: a multicenter cohort study".

A commentary on "A CT-based multitask deep learning model for predicting tumor stroma ratio and treatment outcomes in patients with colorectal cancer: a multicenter cohort study".

A multi-task deep learning framework for forecasting sparse demand of demand responsive transit

Demand Responsive Transport (DRT) is a flexible transportation service that adjusts its routes and schedules in real time based on user requests. Real-time demand forecasting has become a timely issue since the resolution of transportation planning has increased to provide flexible services to users. Although many previous studies have been conducted to design the demand forecasting model using the mobility service historical data, there are more considerations when predicting real-time demand for on-demand mobility services. Therefore, this study aims to develop a demand forecasting model for DRT services addressing two issues. First, repeated calls for service and abandoned requests are converted into the unit of demand to capture served and potential demand. Second, given the sparsity of DRT historical data, a multi-task deep learning model is proposed to predict both the probability and volume of demand simultaneously to mitigate the data sparsity problem. A zero-inflated loss function was introduced to consider the skewed demand distribution. To attain our goals, the historical dataset of the I-MOD service trial in Yeongjongdo, Inchon, Korea was used. The performance of the proposed model is compared against several baseline models, demonstrating its superiority in forecasting demand for mobility services. The results show that a multi-task structure can alleviate the data sparsity problem by excluding where demand is not generated from the forecasting problem. The proposed models can provide insights into real-time demand forecasting with sparse demand.

Multicentric development and validation of a multi-scale and multi-task deep learning model for comprehensive lower extremity alignment analysis

Osteoarthritis of the knee, a widespread cause of knee disability, is commonly treated in orthopedics due to its rising prevalence. Lower extremity misalignment, pivotal in knee injury etiology and management, necessitates comprehensive mechanical alignment evaluation via frequently-requested weight-bearing long leg radiographs (LLR). Despite LLR’s routine use, current analysis techniques are error-prone and time-consuming. To address this, we conducted a multicentric study to develop and validate a deep learning (DL) model for fully automated leg alignment assessment on anterior–posterior LLR, targeting enhanced reliability and efficiency. The DL model, developed using 594 patients’ LLR and a 60%/10%/30% data split for training, validation, and testing, executed alignment analyses via a multi-step process, employing a detection network and nine specialized networks. It was designed to assess all vital anatomical and mechanical parameters for standard clinical leg deformity analysis and preoperative planning. Accuracy, reliability, and assessment duration were compared with three specialized orthopedic surgeons across two distinct institutional datasets (136 and 143 radiographs). The algorithm exhibited equivalent performance to the surgeons in terms of alignment accuracy (DL: 0.21 ± 0.18°to 1.06 ± 1.3°vs. OS: 0.21 ± 0.16°to 1.72 ± 1.96°), interrater reliability (ICC DL: 0.90 ± 0.05 to 1.0 ± 0.0 vs. ICC OS: 0.90 ± 0.03 to 1.0 ± 0.0), and clinically acceptable accuracy (DL: 53.9%–100% vs OS 30.8%–100%). Further, automated analysis significantly reduced analysis time compared to manual annotation (DL: 22 ± 0.6 s vs. OS; 101.7 ± 7 s, p ≤ 0.01). By demonstrating that our algorithm not only matches the precision of expert surgeons but also significantly outpaces them in both speed and consistency of measurements, our research underscores a pivotal advancement in harnessing AI to enhance clinical efficiency and decision-making in orthopaedics.

Fully Automated Identification of Lymph Node Metastases and Lymphovascular Invasion in Endometrial Cancer From Multi-Parametric MRI by Deep Learning.

Early and accurate identification of lymphatic node metastasis (LNM) and lymphatic vascular space invasion (LVSI) for endometrial cancer (EC) patients is important for treatment design, but difficult on multi-parametric MRI (mpMRI) images. To develop a deep learning (DL) model to simultaneously identify of LNM and LVSI of EC from mpMRI images. Retrospective. Six hundred twenty-one patients with histologically proven EC from two institutions, including 111 LNM-positive and 168 LVSI-positive, divided into training, internal, and external test cohorts of 398, 169, and 54 patients, respectively. T2-weighted imaging (T2WI), contrast-enhanced T1WI (CE-T1WI), and diffusion-weighted imaging (DWI) were scanned with turbo spin-echo, gradient-echo, and two-dimensional echo-planar sequences, using either a 1.5 T or 3 T system. EC lesions were manually delineated on T2WI by two radiologists and used to train an nnU-Net model for automatic segmentation. A multi-task DL model was developed to simultaneously identify LNM and LVSI positive status using the segmented EC lesion regions and T2WI, CE-T1WI, and DWI images as inputs. The performance of the model for LNM-positive diagnosis was compared with those of three radiologists in the external test cohort. Dice similarity coefficient (DSC) was used to evaluate segmentation results. Receiver Operating Characteristic (ROC) analysis was used to assess the performance of LNM and LVSI status identification. P value <0.05 was considered significant. EC lesion segmentation model achieved mean DSC values of 0.700 ± 0.25 and 0.693 ± 0.21 in the internal and external test cohorts, respectively. For LNM positive/LVSI positive identification, the proposed model achieved AUC values of 0.895/0.848, 0.806/0.795, and 0.804/0.728 in the training, internal, and external test cohorts, respectively, and better than those of three radiologists (AUC = 0.770/0.648/0.674). The proposed model has potential to help clinicians to identify LNM and LVSI status of EC patients and improve treatment planning. 3 TECHNICAL EFFICACY: Stage 2.

Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images.

Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans. Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets (n = 212, 111, 110). The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter-rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C-index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA-TACE improved RFS only in patients predicted to have high MVI risk and low survival scores (p < .001). Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.

A computed tomography-based multitask deep learning model for predicting tumour stroma ratio and treatment outcomes in patients with colorectal cancer: a multicentre cohort study.

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.

Predicting hematoma expansion in acute spontaneous intracerebral hemorrhage: integrating clinical factors with a multitask deep learning model for non-contrast head CT

PurposeTo predict hematoma growth in intracerebral hemorrhage patients by combining clinical findings with non-contrast CT imaging features analyzed through deep learning.MethodsThree models were developed to predict hematoma expansion (HE) in 572 patients. We utilized multi-task learning for both hematoma segmentation and prediction of expansion: the Image-to-HE model processed hematoma slices, extracting features and computing a normalized DL score for HE prediction. The Clinical-to-HE model utilized multivariate logistic regression on clinical variables. The Integrated-to-HE model combined image-derived and clinical data. Significant clinical variables were selected using forward selection in logistic regression. The two models incorporating clinical variables were statistically validated.ResultsFor hematoma detection, the diagnostic performance of the developed multi-task model was excellent (AUC, 0.99). For expansion prediction, three models were evaluated for predicting HE. The Image-to-HE model achieved an accuracy of 67.3%, sensitivity of 81.0%, specificity of 64.0%, and an AUC of 0.76. The Clinical-to-HE model registered an accuracy of 74.8%, sensitivity of 81.0%, specificity of 73.3%, and an AUC of 0.81. The Integrated-to-HE model, merging both image and clinical data, excelled with an accuracy of 81.3%, sensitivity of 76.2%, specificity of 82.6%, and an AUC of 0.83. The Integrated-to-HE model, aligning closest to the diagonal line and indicating the highest level of calibration, showcases superior performance in predicting HE outcomes among the three models.ConclusionThe integration of clinical findings with non-contrast CT imaging features analyzed through deep learning showed the potential for improving the prediction of HE in acute spontaneous intracerebral hemorrhage patients.

Age and sex estimation in cephalometric radiographs based on multitask convolutional neural networks

ObjectivesAge and sex characteristics are evident in cephalometric radiographs (CRs), yet their accurate estimation remains challenging due to the complexity of these images. This study aimed to harness deep learning to automate age and gender estimation from CRs, potentially simplifying their interpretation. Study DesignWe compared the performance of 4 deep learning models (SVM, R-net, VGG16-SingleTask, and our proposed VGG16-MultiTask) in estimating age and sex from the testing dataset, utilizing a VGG16-based multitask deep learning model on 4,557 CRs. Gradient-weighted class activation mapping (Grad-CAM) was incorporated to identify sex. Performance was assessed using mean absolute error (MAE), specificity, sensitivity, F1 score, and the area under the curve (AUC) in receiver operating characteristic analysis. ResultsThe VGG16-MultiTask model outperformed the others, with the lowest MAE (0.864±1.602) and highest sensitivity (0.85), specificity (0.88), F1 score (0.863), and AUC (0.93), demonstrating superior precision and robust performance. ConclusionsThe VGG multitask model demonstrates significant potential in enhancing age and sex estimation from cephalometric analysis, underscoring the role of AI in improving biomedical interpretations.

CG-CFPANet: a multi-task network for built-up area extraction from SDGSAT-1 and Sentinel-2 remote sensing images

ABSTRACT Accurate extraction of built-up areas is helpful to urban development and map updating. Nighttime light (NTL) data can capture the lighting signal of ground objects. However, most built-up area extraction is conducted on public limited coarse spatial resolution NTL images. The Sustainable Development Science Satellite-1 (SDGSAT-1) provides 10 m spatial resolution panchromatic NTL images, making it possible to map detailed urban lighting structures. In urban extraction, the boundaries of urban areas are easily confused with background objects due to the similar spectral and textual features. To address this problem, we proposed a multi-task deep learning model, CG-CFPANet, to extract illuminated built-up areas by synthesizing SDGSAT-1 NTL data and optical remote sensing images. In CG-CFPANet, a convolutional feature pyramid attention (CFPA) module for better contextual recognition and a concatenation group (CG) module to merge the two remote sensing images are developed. Our proposed CG-CFPANet achieved 1.3% higher precision in built-up area extraction than ten other recently proposed network structures: UNet, UNet++, PSPNet, DeeplabV3, FCN, ExtremeC3Net, SegNet, BiseNet, Res2-UNet, and CBRNet. It shows higher applicability for large-scale built-up area extraction.

Exploring the Value of MRI Measurement of Hippocampal Volume for Predicting the Occurrence and Progression of Alzheimer's Disease Based on Artificial Intelligence Deep Learning Technology and Evidence-Based Medicine Meta-Analysis.

Alzheimer's disease (AD), a major dementia cause, lacks effective treatment. MRI-based hippocampal volume measurement using artificial intelligence offers new insights into early diagnosis and intervention in AD progression. This study, involving 483 AD patients, 756 patients with mild cognitive impairment (MCI), and 968 normal controls (NC), investigated the predictive capability of MRI-based hippocampus volume measurements for AD risk using artificial intelligence and evidence-based medicine. Utilizing data from ADNI and OASIS-brains databases, three convolutional neural networks (InceptionResNetv2, Densenet169, and SEResNet50) were employed for automated AD classification based on structural MRI imaging. A multitask deep learning model and a densely connected 3D convolutional network were utilized. Additionally, a systematic meta-analysis explored the value of MRI-based hippocampal volume measurement in predicting AD occurrence and progression, drawing on 23 eligible articles from PubMed and Embase databases. InceptionResNetv2 outperformed other networks, achieving 99.75% accuracy and 100% AUC for AD-NC classification and 99.16% accuracy and 100% AUC for MCI-NC classification. Notably, at a 512×512 size, InceptionResNetv2 demonstrated a classification accuracy of 94.29% and an AUC of 98% for AD-NC and 97.31% accuracy and 98% AUC for MCI-NC. The study concludes that MRI-based hippocampal volume changes effectively predict AD onset and progression, facilitating early intervention and prevention.

A multi-task learning model for predicting drugs combination synergy by analyzing drug–drug interactions and integrated multi-view graph data

This paper proposes a multi-task deep learning model for determining drug combination synergistic by simultaneously output synergy scores and synergy class labels. Initially, the two drugs are represented using a Simplified Molecular-Input Line-Entry (SMILE) system. Chemical structural features of the drugs are extracted from the SMILE using the RedKit package. Additionally, an improved Multi-view representation is proposed to extract graph-based drug features. Furthermore, the cancer cell line is represented by gene expression. Then, a three fully connected layers are learned to extract cancer cell line features. To investigate the impact of drug interactions on cell lines, the drug interaction features are extracted from a pretrained drugs interaction network and fed into an attention mechanism along with the cancer cell line features, resulting in the output of affected cancer cell line features. Subsequently, the drug and cell line features are concatenated and fed into an attention mechanism, which produces a two-feature representation for the two predicted tasks. The relationship between the two tasks is learned using the cross-stitch algorithm. Finally, each task feature is inputted into a fully connected subnetwork to predict the synergy score and synergy label. The proposed model ‘MutliSyn’ is evaluated using the O'Neil cancer dataset, comprising 38 unique drugs combined to form 22,737 drug combination pairs, tested on 39 cancer cell lines. For the synergy score, the model achieves a mean square error (MSE) of 219.14, a root mean square error (RMSE) of 14.75, and a Pearson score of 0.76. Regarding the synergy class label, the model achieves an area under the ROC curve (ROC-AUC) of 0.95, an area under the precision-recall curve (PR-AUC) of 0.85, precision of 0.93, kappa of 0.61, and accuracy of 0.90.

Multitask Deep Learning Enabling a Synergy for Cadmium and Methane Mitigation with Biochar Amendments in Paddy Soils.

Biochar has demonstrated significant promise in addressing heavy metal contamination and methane (CH4) emissions in paddy soils; however, achieving a synergy between these two goals is challenging due to various variables, including the characteristics of biochar and soil properties that influence biochar's performance. Here, we successfully developed an interpretable multitask deep learning (MTDL) model by employing a tensor tracking paradigm to facilitate parameter sharing between two separate data sets, enabling a synergy between Cd and CH4 mitigation with biochar amendments. The characteristics of biochar contribute similar weightings of 67.9% and 62.5% to Cd and CH4 mitigation, respectively, but their relative importance in determining biochar's performance varies significantly. Notably, this MTDL model excels in custom-tailoring biochar to synergistically mitigate Cd and CH4 in paddy soils across a wide geographic range, surpassing traditional machine learning models. Our findings deepen our understanding of the interactive effects of Cd and CH4 mitigation with biochar amendments in paddy soils, and they also potentially extend the application of artificial intelligence in sustainable environmental remediation, especially when dealing with multiple objectives.

A multi-task deep learning model for EGFR genotyping prediction and GTV segmentation of brain metastasis

BackgroundThe precise prediction of epidermal growth factor receptor (EGFR) mutation status and gross tumor volume (GTV) segmentation are crucial goals in computer-aided lung adenocarcinoma brain metastasis diagnosis. However, these two tasks present continuous difficulties due to the nonuniform intensity distributions, ambiguous boundaries, and variable shapes of brain metastasis (BM) in MR images.The existing approaches for tackling these challenges mainly rely on single-task algorithms, which overlook the interdependence between these two tasks.MethodsTo comprehensively address these challenges, we propose a multi-task deep learning model that simultaneously enables GTV segmentation and EGFR subtype classification. Specifically, a multi-scale self-attention encoder that consists of a convolutional self-attention module is designed to extract the shared spatial and global information for a GTV segmentation decoder and an EGFR genotype classifier. Then, a hybrid CNN-Transformer classifier consisting of a convolutional block and a Transformer block is designed to combine the global and local information. Furthermore, the task correlation and heterogeneity issues are solved with a multi-task loss function, aiming to balance the above two tasks by incorporating segmentation and classification loss functions with learnable weights.ResultsThe experimental results demonstrate that our proposed model achieves excellent performance, surpassing that of single-task learning approaches. Our proposed model achieves a mean Dice score of 0.89 for GTV segmentation and an EGFR genotyping accuracy of 0.88 on an internal testing set, and attains an accuracy of 0.81 in the EGFR genotype prediction task and an average Dice score of 0.85 in the GTV segmentation task on the external testing set. This shows that our proposed method has outstanding performance and generalization.ConclusionWith the introduction of an efficient feature extraction module, a hybrid CNN-Transformer classifier, and a multi-task loss function, the proposed multi-task deep learning network significantly enhances the performance achieved in both GTV segmentation and EGFR genotyping tasks. Thus, the model can serve as a noninvasive tool for facilitating clinical treatment.

3MO Multimodal data fusion for improved risk stratification of breast cancer with multi-task 3D deep learning model: A multicenter study

3MO Multimodal data fusion for improved risk stratification of breast cancer with multi-task 3D deep learning model: A multicenter study

A transformer-based multi-task deep learning model for simultaneous infiltrated brain area identification and segmentation of gliomas

BackgroundThe anatomical infiltrated brain area and the boundaries of gliomas have a significant impact on clinical decision making and available treatment options. Identifying glioma-infiltrated brain areas and delineating the tumor manually is a laborious and time-intensive process. Previous deep learning-based studies have mainly been focused on automatic tumor segmentation or predicting genetic/histological features. However, few studies have specifically addressed the identification of infiltrated brain areas. To bridge this gap, we aim to develop a model that can simultaneously identify infiltrated brain areas and perform accurate segmentation of gliomas.MethodsWe have developed a transformer-based multi-task deep learning model that can perform two tasks simultaneously: identifying infiltrated brain areas segmentation of gliomas. The multi-task model leverages shaped location and boundary information to enhance the performance of both tasks. Our retrospective study involved 354 glioma patients (grades II-IV) with single or multiple brain area infiltrations, which were divided into training (N = 270), validation (N = 30), and independent test (N = 54) sets. We evaluated the predictive performance using the area under the receiver operating characteristic curve (AUC) and Dice scores.ResultsOur multi-task model achieved impressive results in the independent test set, with an AUC of 94.95% (95% CI, 91.78–97.58), a sensitivity of 87.67%, a specificity of 87.31%, and accuracy of 87.41%. Specifically, for grade II-IV glioma, the model achieved AUCs of 95.25% (95% CI, 91.09–98.23, 84.38% sensitivity, 89.04% specificity, 87.62% accuracy), 98.26% (95% CI, 95.22–100, 93.75% sensitivity, 98.15% specificity, 97.14% accuracy), and 93.83% (95%CI, 86.57–99.12, 92.00% sensitivity, 85.71% specificity, 87.37% accuracy) respectively for the identification of infiltrated brain areas. Moreover, our model achieved a mean Dice score of 87.60% for the whole tumor segmentation.ConclusionsExperimental results show that our multi-task model achieved superior performance and outperformed the state-of-the-art methods. The impressive performance demonstrates the potential of our work as an innovative solution for identifying tumor-infiltrated brain areas and suggests that it can be a practical tool for supporting clinical decision making.

Sequence signal reconstruction based multi-task deep learning for sleep staging on single-channel EEG

The temporal context information between sleep stage sequence contains sleep transition rules, which is important for improving sleep staging performance. Existing multi-task learning methods reconstruct EEG signals from one sleep stage, ignoring the importance of sequential temporal context in capturing long-term dependencies to enhance representation learning. To address these issues, we propose a multi-task deep learning model to jointly reconstruct sequence signal and segment time series. The model enhances the ability of time series segmentation task to capture sequential temporal context and improves the performance of single-channel EEG by optimizing the common encoder for sequence signal reconstruction task. In addition, we design a one-dimensional channel attention module to enhance the feature representation extracted for sleep sequence signal. The experimental results on four datasets show that the multi-task deep learning model can improve the generalization using sequence signal reconstruction. Compared with other state-of-the-art methods, the method proposed in this study obtained competitive performance in terms of metrics such as accuracy, which is 85.6% on the 2013 version of Sleep-EDF Database Expanded, 83.4% on the 2018 version of Sleep-EDF Database Expanded, 85.6% on Sleep Heart Health Study, and 77.4% on CAP Sleep Database.

Development and Validation of a Model to Quantify Injury Severity in Real Time

Quantifying injury severity is integral to trauma care benchmarking, decision-making, and research, yet the most prevalent metric to quantify injury severity-Injury Severity Score (ISS)- is impractical to use in real time. To develop and validate a practical model that uses a limited number of injury patterns to quantify injury severity in real time through 3 intuitive outcomes. In this cohort study for prediction model development and validation, training, development, and internal validation cohorts comprised 223 545, 74 514, and 74 514 admission encounters, respectively, of adults (age ≥18 years) with a primary diagnosis of traumatic injury hospitalized more than 2 days (2017-2018 National Inpatient Sample). The external validation cohort comprised 3855 adults admitted to a level I trauma center who met criteria for the 2 highest of the institution's 3 trauma activation levels. Three outcomes were hospital length of stay, probability of discharge disposition to a facility, and probability of inpatient mortality. The prediction performance metric for length of stay was mean absolute error. Prediction performance metrics for discharge disposition and inpatient mortality were average precision, precision, recall, specificity, F1 score, and area under the receiver operating characteristic curve (AUROC). Calibration was evaluated using calibration plots. Shapley addictive explanations analysis and bee swarm plots facilitated model explainability analysis. The Length of Stay, Disposition, Mortality (LDM) Injury Index (the model) comprised a multitask deep learning model trained, developed, and internally validated on a data set of 372 573 traumatic injury encounters (mean [SD] age = 68.7 [19.3] years, 56.6% female). The model used 176 potential injuries to output 3 interpretable outcomes: the predicted hospital length of stay, probability of discharge to a facility, and probability of inpatient mortality. For the external validation set, the ISS predicted length of stay with mean absolute error was 4.16 (95% CI, 4.13-4.20) days. Compared with the ISS, the model had comparable external validation set discrimination performance (facility discharge AUROC: 0.67 [95% CI, 0.67-0.68] vs 0.65 [95% CI, 0.65-0.66]; recall: 0.59 [95% CI, 0.58-0.61] vs 0.59 [95% CI, 0.58-0.60]; specificity: 0.66 [95% CI, 0.66-0.66] vs 0.62 [95%CI, 0.60-0.63]; mortality AUROC: 0.83 [95% CI, 0.81-0.84] vs 0.82 [95% CI, 0.82-0.82]; recall: 0.74 [95% CI, 0.72-0.77] vs 0.75 [95% CI, 0.75-0.76]; specificity: 0.81 [95% CI, 0.81-0.81] vs 0.76 [95% CI, 0.75-0.77]). The model had excellent calibration for predicting facility discharge disposition, but overestimated inpatient mortality. Explainability analysis found the inputs influencing model predictions matched intuition. In this cohort study using a limited number of injury patterns, the model quantified injury severity using 3 intuitive outcomes. Further study is required to evaluate the model at scale.

Multitask deep learning on mammography to predict extensive intraductal component in invasive breast cancer.

To develop a multitask deep learning (DL) algorithm to automatically classify mammography imaging findings and predict the existence of extensive intraductal component (EIC) in invasive breast cancer. Mammograms with invasive breast cancers from 2010 to 2019 were downloaded for two radiologists performing image segmentation and imaging findings annotation. Images were randomly split into training, validation, and test datasets. A multitask approach was performed on the EfficientNet-B0 neural network mainly to predict EIC and classify imaging findings. Three more models were trained for comparison, including a single-task model (predicting EIC), a two-task model (predicting EIC and cell receptor status), and a three-task model (combining the abovementioned tasks). Additionally, these models were trained in a subgroup of invasive ductal carcinoma. The DeLong test was used to examine the difference in model performance. This study enrolled 1459 breast cancers on 3076 images. The EIC-positive rate was 29.0%. The three-task model was the best DL model with an area under the curve (AUC) of EIC prediction of 0.758 and 0.775 at the image and breast (patient) levels, respectively. Mass was the most accurately classified imaging finding (AUC = 0.915), followed by calcifications and mass with calcifications (AUC = 0.878 and 0.824, respectively). Cell receptor status prediction was less accurate (AUC = 0.625-0.653). The multitask approach improves the model training compared to the single-task model, but without significant effects. A mammography-based multitask DL model can perform simultaneous imaging finding classification and EIC prediction. The study results demonstrated the potential of deep learning to extract more information from mammography for clinical decision-making. • Extensive intraductal component (EIC) is an independent risk factor of local tumor recurrence after breast-conserving surgery. • A mammography-based deep learning model was trained to predict extensive intraductal component close to radiologists' reading. • The developed multitask deep learning model could perform simultaneous imaging finding classification and extensive intraductal component prediction.

A multi-task deep learning model integrating ship trajectory and collision risk prediction

Trajectory prediction can provide position information for ship navigation behavior perception. This is very important for intelligent navigation. However, potential collision risk caused by other ships’ navigation behaviors will directly affect the navigation behavior of own ship. In order to incorporate the potential collision risk caused by the navigation behavior of other ships, this study proposes a Multi-Task Deep Learning Model to exploit the interaction between ships and predict the ship trajectory and potential collision risk simultaneously. Trajectory prediction task can exploit the knowledge contained in collision risk prediction task and the prediction of collision risk can utilize the navigational situation in the future. In the trajectory prediction task, we construct virtual channel center points in a data-driven way to capture the ship behavior in ship traffic flow and use them as constraints in our designed loss function. Furthermore, we design the soft collision risk classification label and the knowledge distillation module to improve the accuracy of the multi-task model. At last, we demonstrate that our method can not only improve the accuracy of trajectory prediction, but also gain reliable potential collision risk results. Our method improves the prediction time scale by an order of magnitude compared with other methods.

Uncertainty quantification of a deep learning fuel property prediction model

Deep learning models are being widely used in the field of combustion. Given the black-box nature of typical neural network based models, uncertainty quantification (UQ) is critical to ensure the reliability of predictions as well as the training datasets, and for a principled quantification of noise and its various sources. Deep learning surrogate models for predicting properties of chemical compounds and mixtures have been recently shown to be promising for enabling data-driven fuel design and optimization, with the ultimate goal of improving efficiency and lowering emissions from combustion engines. In this study, UQ is performed for a multi-task deep learning model that simultaneously predicts the research octane number (RON), Motor Octane Number (MON), and Yield Sooting Index (YSI) of pure components and multicomponent blends. The deep learning model is comprised of three smaller networks: Extractor 1, Extractor 2, and Predictor, and a mixing operator. The molecular fingerprints of individual components are encoded via Extractor 1 and Extractor 2, the mixing operator generates fingerprints for mixtures/blends based on linear mixing operation, and the predictor maps the fingerprint to the target properties. Two different classes of UQ methods, Monte Carlo ensemble methods and Bayesian neural networks (BNNs), are employed for quantifying the epistemic uncertainty. Combinations of Bernoulli and Gaussian distributions with DropConnect and DropOut techniques are explored as ensemble methods. All the DropConnect, DropOut and Bayesian layers are applied to the predictor network. Aleatoric uncertainty is modeled by assuming that each data point has an independent uncertainty associated with it. The results of the UQ study are further analyzed to compare the performance of BNN and ensemble methods. Although this study is confined to UQ of fuel property prediction, the methodologies are applicable to other deep learning frameworks that are being widely used in the combustion community.