ABSTRACT
The deep neural network, based on the backpropagation learning algorithm, has achieved tremendous success. However, the backpropagation algorithm is consistently considered biologically implausible. Many efforts have recently been made to address these biological implausibility issues, nevertheless, these methods are tailored to discrete neural network structures. Continuous neural networks are crucial for investigating novel neural network models with more biologically dynamic characteristics and for interpretability of large language models. The neural memory ordinary differential equation (nmODE) is a recently proposed continuous neural network model that exhibits several intriguing properties. In this study, we present a forward-learning algorithm, called nmForwardLA, for nmODE. This algorithm boasts lower computational dimensions and greater efficiency. Compared with the other learning algorithms, experimental results on MNIST, CIFAR10, and CIFAR100 demonstrate its potency.
Subject(s)
Neural Networks, Computer , Algorithms , Humans , Deep Learning , Machine LearningABSTRACT
Thoracic computed tomography (CT) currently plays the primary role in pulmonary nodule detection, where the reconstruction kernel significantly impacts performance in computer-aided pulmonary nodule detectors. The issue of kernel selection affecting performance has been overlooked in pulmonary nodule detection. This paper first introduces a novel pulmonary nodule detection dataset named Reconstruction Kernel Imaging for Pulmonary Nodule Detection (RKPN) for quantifying algorithm differences between the two imaging types. The dataset contains pairs of images taken from the same patient on the same date, featuring both smooth (B31f) and sharp kernel (B60f) reconstructions. All other imaging parameters and pulmonary nodule labels remain entirely consistent across these pairs. Extensive quantification reveals mainstream detectors perform better on smooth kernel imaging than on sharp kernel imaging. To address suboptimal detection on the sharp kernel imaging, we further propose an image conversion-based pulmonary nodule detector called ICNoduleNet. A lightweight 3D slice-channel converter (LSCC) module is introduced to convert sharp kernel images into smooth kernel images, which can sufficiently learn inter-slice and inter-channel feature information while avoiding introducing excessive parameters. We conduct thorough experiments that validate the effectiveness of ICNoduleNet, it takes sharp kernel images as input and can achieve comparable or even superior detection performance to the baseline that uses the smooth kernel images. The evaluation shows promising results and proves the effectiveness of ICNoduleNet.
Subject(s)
Algorithms , Lung Neoplasms , Radiographic Image Interpretation, Computer-Assisted , Solitary Pulmonary Nodule , Tomography, X-Ray Computed , Humans , Solitary Pulmonary Nodule/diagnostic imaging , Tomography, X-Ray Computed/methods , Lung Neoplasms/diagnostic imaging , Radiographic Image Interpretation, Computer-Assisted/methods , Lung/diagnostic imaging , Databases, FactualABSTRACT
Deep learning, transforming input data into target prediction through intricate network structures, has inspired novel exploration in automated diagnosis based on medical images. The distinct morphological characteristics of chest abnormalities between drug-resistant tuberculosis (DR-TB) and drug-sensitive tuberculosis (DS-TB) on chest computed tomography (CT) are of potential value in differential diagnosis, which is challenging in the clinic. Hence, based on 1176 chest CT volumes from the equal number of patients with tuberculosis (TB), we presented a Deep learning-based system for TB drug resistance identification and subtype classification (DeepTB), which could automatically diagnose DR-TB and classify crucial subtypes, including rifampicin-resistant tuberculosis, multidrug-resistant tuberculosis, and extensively drug-resistant tuberculosis. Moreover, chest lesions were manually annotated to endow the model with robust power to assist radiologists in image interpretation and the Circos revealed the relationship between chest abnormalities and specific types of DR-TB. Finally, DeepTB achieved an area under the curve (AUC) up to 0.930 for thoracic abnormality detection and 0.943 for DR-TB diagnosis. Notably, the system demonstrated instructive value in DR-TB subtype classification with AUCs ranging from 0.880 to 0.928. Meanwhile, class activation maps were generated to express a human-understandable visual concept. Together, showing a prominent performance, DeepTB would be impactful in clinical decision-making for DR-TB.
ABSTRACT
BACKGROUND AND OBJECTIVES: There is a noticeable gap in diagnostic evidence strength between the thick and thin scans of Low-Dose CT (LDCT) for pulmonary nodule detection. When the thin scans are needed is unknown, especially when aided with an artificial intelligence nodule detection system. METHODS: A case study is conducted with a set of 1,000 pulmonary nodule screening LDCT scans with both thick (5.0mm), and thin (1.0mm) section scans available. Pulmonary nodule detection is performed by human and artificial intelligence models for nodule detection developed using 3D convolutional neural networks (CNNs). The intra-sample consistency is evaluated with thick and thin scans, for both clinical doctor and NN (neural network) models. Free receiver operating characteristic (FROC) is used to measure the accuracy of humans and NNs. RESULTS: Trained NNs outperform humans with small nodules < 6.0mm, which is a good complement to human ability. For nodules > 6.0mm, human and NNs perform similarly while human takes a fractional advantage. By allowing a few more FPs, a significant sensitivity improvement can be achieved with NNs. CONCLUSIONS: There is a performance gap between the thick and thin scans for pulmonary nodule detection regarding both false negatives and false positives. NNs can help reduce false negatives when the nodules are small and trade off the false negatives for sensitivity. A combination of human and trained NNs is a promising way to achieve a fast and accurate diagnosis.
Subject(s)
Lung Neoplasms , Solitary Pulmonary Nodule , Humans , Artificial Intelligence , Lung Neoplasms/diagnostic imaging , Solitary Pulmonary Nodule/diagnostic imaging , Neural Networks, Computer , Tomography, X-Ray Computed , Radiographic Image Interpretation, Computer-AssistedABSTRACT
Radiographic attributes of lung nodules remedy the shortcomings of lung cancer computer-assisted diagnosis systems, which provides interpretable diagnostic reference for doctors. However, current studies fail to dedicate multi-label classification of lung nodules using convolutional neural networks (CNNs) and are inferior in exploiting statistical dependency between the labels. In addition, data imbalance is an indispensable problem to be reckoned with when employing CNNs to perform lung nodule classification. It introduces greater challenges especially in the multi-label classification. In this paper, we propose a method called MLSL-Net to discriminate lung nodule characteristics and simultaneously address the challenges. Particularly, the proposal employs multi-label softmax loss (MLSL) as the performance index, aiming to reduce the ranking errors between the labels and within the labels during training, thereby optimizing ranking loss and AUC directly. Such criterions can better evaluate the classifier's performance on the multi-label imbalanced dataset. Furthermore, a scale factor is introduced based on the investigation of the max surrogate function. Different from preceding usages, the small factor is used so that to narrow the discrepancy of gradients produced by different labels. More interestingly, this factor also facilitates the exploit of label dependency. Experimental results on the LIDC-IDRI dataset as well as another akin dataset demonstrate that MLSL-Net can effectively perform multi-label classification despite the imbalance issue. Meanwhile, the results confirm the responsibility of the factor for capturing label correlations, accordingly leading to more accurate predictions.
Subject(s)
Lung Neoplasms , Solitary Pulmonary Nodule , Humans , Solitary Pulmonary Nodule/diagnostic imaging , Tomography, X-Ray Computed/methods , Radiographic Image Interpretation, Computer-Assisted/methods , Lung Neoplasms/diagnostic imaging , Neural Networks, Computer , LungABSTRACT
BACKGROUND: Existing challenges of lung cancer screening included non-accessibility of computed tomography (CT) scanners and inter-reader variability, especially in resource-limited areas. The combination of mobile CT and deep learning technique has inspired innovations in the routine clinical practice. METHODS: This study recruited participants prospectively in two rural sites of western China. A deep learning system was developed to assist clinicians to identify the nodules and evaluate the malignancy with state-of-the-art performance assessed by recall, free-response receiver operating characteristic curve (FROC), accuracy (ACC), area under the receiver operating characteristic curve (AUC). RESULTS: This study enrolled 12,360 participants scanned by mobile CT vehicle, and detected 9511 (76.95%) patients with pulmonary nodules. Majority of participants were female (8169, 66.09%), and never-smokers (9784, 79.16%). After 1-year follow-up, 86 patients were diagnosed with lung cancer, with 80 (93.03%) of adenocarcinoma, and 73 (84.88%) at stage I. This deep learning system was developed to detect nodules (recall of 0.9507; FROC of 0.6470) and stratify the risk (ACC of 0.8696; macro-AUC of 0.8516) automatically. CONCLUSIONS: A novel model for lung cancer screening, the integration mobile CT with deep learning, was proposed. It enabled specialists to increase the accuracy and consistency of workflow and has potential to assist clinicians in detecting early-stage lung cancer effectively.
Subject(s)
Deep Learning , Lung Neoplasms , Multiple Pulmonary Nodules , Early Detection of Cancer/methods , Female , Humans , Lung Neoplasms/pathology , Male , Multiple Pulmonary Nodules/pathology , Retrospective Studies , Tomography, X-Ray Computed/methodsABSTRACT
Objectives: Distinction of malignant pulmonary nodules from the benign ones based on computed tomography (CT) images can be time-consuming but significant in routine clinical management. The advent of artificial intelligence (AI) has provided an opportunity to improve the accuracy of cancer risk prediction. Methods: A total of 8950 detected pulmonary nodules with complete pathological results were retrospectively enrolled. The different radiological manifestations were identified mainly as various nodules densities and morphological features. Then, these nodules were classified into benign and malignant groups, both of which were subdivided into finer specific pathological types. Here, we proposed a deep convolutional neural network for the assessment of lung nodules named DeepLN to identify the radiological features and predict the pathologic subtypes of pulmonary nodules. Results: In terms of density, the area under the receiver operating characteristic curves (AUCs) of DeepLN were 0.9707 (95% confidence interval, CI: 0.9645-0.9765), 0.7789 (95%CI: 0.7569-0.7995), and 0.8950 (95%CI: 0.8822-0.9088) for the pure-ground glass opacity (pGGO), mixed-ground glass opacity (mGGO) and solid nodules. As for the morphological features, the AUCs were 0.8347 (95%CI: 0.8193-0.8499) and 0.9074 (95%CI: 0.8834-0.9314) for spiculation and lung cavity respectively. For the identification of malignant nodules, our DeepLN algorithm achieved an AUC of 0.8503 (95%CI: 0.8319-0.8681) in the test set. Pertaining to predicting the pathological subtypes in the test set, the multi-task AUCs were 0.8841 (95%CI: 0.8567-0.9083) for benign tumors, 0.8265 (95%CI: 0.8004-0.8499) for inflammation, and 0.8022 (95%CI: 0.7616-0.8445) for other benign ones, while AUCs were 0.8675 (95%CI: 0.8525-0.8813) for lung adenocarcinoma (LUAD), 0.8792 (95%CI: 0.8640-0.8950) for squamous cell carcinoma (LUSC), 0.7404 (95%CI: 0.7031-0.7782) for other malignant ones respectively in the malignant group. Conclusions: The DeepLN based on deep learning algorithm represented a competitive performance to predict the imaging characteristics, malignancy and pathologic subtypes on the basis of non-invasive CT images, and thus had great possibility to be utilized in the routine clinical workflow.
ABSTRACT
A simple, rapid and ultrasensitive visual sensing method for the detection of Cronobacter sakazakii (C. sakazakii) based on a biohybrid interface was established. During the entire sensing process, quadruple-cascade amplification showed its superior sensing performance. First, the prepared immunomagnetic beads (IMB) were used to isolate and enrich specific targets from the food matrix. After adding the fusion aptamer, the aptamer sequence specifically recognized the target and formed the immune sandwich structure of antibody-target-fusion aptamer. In addition, the fusion aptamer also included the template sequence of exponential amplification reaction (EXPAR), which contained the antisense sequence of the G-rich sequence. Therefore, a large number of G-rich sequences can be generated after EXPAR can be triggered in the presence of Bst. DNA polymerase, nicking endonuclease, cDNA, and dNTP. They were self-assembled into G-quadruplex structures and then combined with hemin to form G4/hemin DNAzyme, resulting in visible coloration and measuring absorbance at 450 nm for quantitative detection. The assay showed a limit of detection (LOD) of 2 CFU/mL in pure culture and 12 CFU/g in milk powder in optimal conditions. This method provides a promising strategy for rapid and point-of-care testing (POCT) since it does not require DNA extraction, medium culturing, and expensive instrumentation. KEY POINTS: â¢Single-cell level detection of C. sakazakii with ultrasensitive and rapidness â¢The fusion aptamer integrated recognition and amplification â¢Sensing analysis of C. sakazakii based on cascade amplification of biohybrid interface.
Subject(s)
Cronobacter sakazakii , Cronobacter sakazakii/genetics , DNA-Directed DNA Polymerase , Hemin/chemistry , Limit of DetectionABSTRACT
ß-lactoglobulin (ß-LG) is a nonnegligible allergenic protein found in cow milk. A label-free, enzyme-free, dual-functional aptameric sensor was constructed based on rational aptamer tailoring for ß-LG detection. Via an established three-step rational tailoring strategy, the original aptamer was transformed from an inflexible antiparallel topology into the flexible, antiparallel/parallel hybrid topology, enlg2-pl3. enlg2-pl3 displayed the dual-functionality of not only binding with ß-LG via the antiparallel conformation but also outputting signals via the parallel type. The dual-functionality depended on the conformational conversion of enlg2-pl3. The ß-LG-driven conformational conversion to antiparallel type was the detection basis of aptasensor. The detection conditions were optimized regarding ions, hemin, chromogenic substrate, pH levels, and detection time. Furthermore, the aptasensor offered advantages, such as cost-efficiency, simple operation, 40 min rapid detection, excellent specificity, and a sensitivity of a three-orders of magnitude linear range and an 8.23-fold linear curve slope, meeting the point-of-care testing (POCT) requirements for dairy analysis.
Subject(s)
Aptamers, Nucleotide , Biosensing Techniques , G-Quadruplexes , Aptamers, Nucleotide/chemistry , Colorimetry , Hemin/chemistry , Lactoglobulins , Limit of DetectionABSTRACT
The current-induced magnetization switching and damping-like field in Pt/(Co/Pt)/PtMn trilayer films prepared with and without an in situ in-plane field of 600 Oe have been studied systematically. In the presence of the in situ field, a small in-plane bias field (HEB) is observed for films with PtMn thickness ≥5 nm, while there is no observable HEB for PtMn thickness ≤3 nm. Nevertheless, a field-free switching of perpendicular magnetization of Co/Pt is observed for all the films with the PtMn thickness of 1-7 nm. On the other hand, without the presence of the in situ field, HEB and field-free switching are not seen. Furthermore, the damping-like fields (HDL) are much enhanced in the presence of the in situ field, and the increasement can be up to 47%. We further revealed that the spin current is mainly from the Pt layer, while the noncollinear spin configuration at the interface caused by the in situ in-plane field may play a role in the HDL enhancement. Micromagnetic simulations indicate that the canting of antiferromagnet PtMn spins plays an important role in the field-free switching. Our findings clarify the source of spin current in the trilayer films and provide an easier approach to field-free switching and HDL enhancement for future low-power spintronic devices.
ABSTRACT
PURPOSE: The robust and automatic segmentation of the pulmonary lobe is vital to surgical planning and regional image analysis of pulmonary related diseases in real-time Computer Aided Diagnosis systems. While a number of studies have examined this issue, the segmentation of unclear borders of the five lobes of the lung remains challenging because of incomplete fissures, the diversity of anatomical pulmonary information, and obstructive lesions caused by pulmonary diseases. This study proposes a model called Regularized Pulmonary Lobe Segmentation Network to accurately predict the lobes as well as the borders. METHODS: First, a 3D fully convolutional network is constructed to extract contextual features from computed tomography images. Second, multi-task learning is employed to learn the segmentations of the lobes and the borders between them to train the neural network to better predict the borders via shared representation. Third, a 3D depth-wise separable de-convolution block is proposed for deep supervision to efficiently train the network. We also propose a hybrid loss function by combining cross-entropy loss with focal loss using adaptive parameters to focus on the tissues and the borders of the lobes. RESULTS: Experiments are conducted on a dataset annotated by experienced clinical radiologists. A 4-fold cross-validation result demonstrates that the proposed approach can achieve a mean dice coefficient of 0.9421 and average symmetric surface distance of 1.3546 mm, which is comparable to state of the art methods. The proposed approach has the capability to accurately segment voxels that are near the lung wall and fissure. CONCLUSION: In this paper, a 3D fully convolutional networks framework is proposed to segment pulmonary lobes in chest CT images accurately. Experimental results show the effectiveness of the proposed approach in segmenting the tissues as well as the borders of the lobes.
Subject(s)
Image Processing, Computer-Assisted/methods , Imaging, Three-Dimensional/methods , Lung Diseases/diagnosis , Lung/diagnostic imaging , Neural Networks, Computer , Tomography, X-Ray Computed/methods , HumansABSTRACT
PURPOSE: Airway tree segmentation plays a pivotal role in chest computed tomography (CT) analysis tasks such as lesion localization, surgical planning, and intra-operative guidance. The remaining challenge is to identify small bronchi correctly, which facilitates further segmentation of the pulmonary anatomies. METHODS: A three-dimensional (3D) multi-scale feature aggregation network (MFA-Net) is proposed against the scale difference of substructures in airway tree segmentation. In this model, the multi-scale feature aggregation (MFA) block is used to capture the multi-scale context information, which improves the sensitivity of the small bronchi segmentation and addresses the local discontinuities. Meanwhile, the concept of airway tree partition is introduced to evaluate the segmentation performance at a more granular level. RESULTS: Experiments were conducted on a dataset of 250 CT scans, which were annotated by experienced clinical radiologists. Through the airway partition, we evaluated the segmentation results of the small bronchi compared with the state-of-the-art methods. Experiments show that MFA-Net achieves the best performance in the Dice similarity coefficient (DSC) in the intra-lobar airway and improves the true positive rate (TPR) by 7.59% on average. Besides, in the entire airway, the proposed method achieves the best results in DSC and TPR scores of 86.18% and 79.31%, respectively, with the consequence of higher false positives. CONCLUSION: The MFA-Net is competitive with the state-of-the-art methods. The experiment results indicate that the MFA block improves the performance of the network by utilizing multi-scale context information. More accurate segmentation results will be more helpful in further clinical analysis.
Subject(s)
Bronchi/diagnostic imaging , Lung/diagnostic imaging , Thorax/diagnostic imaging , Humans , Tomography, X-Ray Computed/methodsABSTRACT
OBJECTIVE: The detection of epidermal growth factor receptor (EGFR) mutation and programmed death ligand-1 (PD-L1) expression status is crucial to determine the treatment strategies for patients with non-small-cell lung cancer (NSCLC). Recently, the rapid development of radiomics including but not limited to deep learning techniques has indicated the potential role of medical images in the diagnosis and treatment of diseases. METHODS: Eligible patients diagnosed/treated at the West China Hospital of Sichuan University from January 2013 to April 2019 were identified retrospectively. The preoperative CT images were obtained, as well as the gene status regarding EGFR mutation and PD-L1 expression. Tumor region of interest (ROI) was delineated manually by experienced respiratory specialists. We used 3D convolutional neural network (CNN) with ROI information as input to construct a classification model and established a prognostic model combining deep learning features and clinical features to stratify survival risk of lung cancer patients. RESULTS: The whole cohort (N = 1262) was divided into a training set (N = 882, 70%), validation set (N = 125, 10%), and test set (N = 255, 20%). We used a 3D convolutional neural network (CNN) to construct a prediction model, with AUCs of 0.96 (95% CI: 0.94-0.98), 0.80 (95% CI: 0.72-0.88), and 0.73 (95% CI: 0.63-0.83) in the training, validation, and test cohorts, respectively. The combined prognostic model showed a good performance on survival prediction in NSCLC patients (C-index: 0.71). CONCLUSION: In this study, a noninvasive and effective model was proposed to predict EGFR mutation and PD-L1 expression status as a clinical decision support tool. Additionally, the combination of deep learning features with clinical features demonstrated great stratification capabilities in the prognostic model. Our team would continue to explore the application of imaging markers for treatment selection of lung cancer patients.
ABSTRACT
BACKGROUND: Lung cancer causes more deaths worldwide than any other cancer. For early-stage patients, low-dose computed tomography (LDCT) of the chest is considered to be an effective screening measure for reducing the risk of mortality. The accuracy and efficiency of cancer screening would be enhanced by an intelligent and automated system that meets or surpasses the diagnostic capabilities of human experts. METHODS: Based on the artificial intelligence (AI) technique, i.e., deep neural network (DNN), we designed a framework for lung cancer screening. First, a semi-automated annotation strategy was used to label the images for training. Then, the DNN-based models for the detection of lung nodules (LNs) and benign or malignancy classification were proposed to identify lung cancer from LDCT images. Finally, the constructed DNN-based LN detection and identification system was named as DeepLN and confirmed using a large-scale dataset. RESULTS: A dataset of multi-resolution LDCT images was constructed and annotated by a multidisciplinary group and used to train and evaluate the proposed models. The sensitivity of LN detection was 96.5% and 89.6% in a thin section subset [the free-response receiver operating characteristic (FROC) is 0.716] and a thick section subset (the FROC is 0.699), respectively. With an accuracy of 92.46%±0.20%, a specificity of 95.93%±0.47%, and a precision of 90.46%±0.93%, an ensemble result of benign or malignancy identification demonstrated a very good performance. Three retrospective clinical comparisons of the DeepLN system with human experts showed a high detection accuracy of 99.02%. CONCLUSIONS: In this study, we presented an AI-based system with the potential to improve the performance and work efficiency of radiologists in lung cancer screening. The effectiveness of the proposed system was verified through retrospective clinical evaluation. Thus, the future application of this system is expected to help patients and society.
ABSTRACT
The accurate identification of malignant lung nodules using computed tomography (CT) screening images is vital for the early detection of lung cancer. It also offers patients the best chance of cure, because non-invasive CT imaging has the ability to capture intra-tumoral heterogeneity. Deep learning methods have obtained promising results for the malignancy identification problem; however, two substantial challenges still remain. First, small datasets cannot insufficiently train the model and tend to overfit it. Second, category imbalance in the data is a problem. In this paper, we propose a method called MSCS-DeepLN that evaluates lung nodule malignancy and simultaneously solves these two problems. Three light models are trained and combined to evaluate the malignancy of a lung nodule. Three-dimensional convolutional neural networks (CNNs) are employed as the backbone of each light model to extract the lung nodule features from CT images and preserve lung nodule spatial heterogeneity. Multi-scale input cropped from CT images enables the sub-networks to learn the multi-level contextual features and preserve diverse. To tackle the imbalance problem, our proposed method employs an AUC approximation as the penalty term. During training, the error in this penalty term is generated from each major and minor class pair, so that negatives and positives can contribute equally to updating this model. Based on these methods, we obtain state-of-the-art results on the LIDC-IDRI dataset. Furthermore, we constructed a new dataset collected from a grade-A tertiary hospital and annotated using biopsy-based cytological analysis to verify the performance of our method in clinical practice.
Subject(s)
Lung Neoplasms , Solitary Pulmonary Nodule , Humans , Lung , Lung Neoplasms/diagnostic imaging , Neural Networks, Computer , Solitary Pulmonary Nodule/diagnostic imaging , Tomography, X-Ray ComputedABSTRACT
Lung cancer is one of the most leading causes of death throughout the world, and there is an urgent requirement for the precision medical management of it. Artificial intelligence (AI) consisting of numerous advanced techniques has been widely applied in the field of medical care. Meanwhile, radiomics based on traditional machine learning also does a great job in mining information through medical images. With the integration of AI and radiomics, great progress has been made in the early diagnosis, specific characterization, and prognosis of lung cancer, which has aroused attention all over the world. In this study, we give a brief review of the current application of AI and radiomics for precision medical management in lung cancer.
ABSTRACT
Survival analysis is important for guiding further treatment and improving lung cancer prognosis. It is a challenging task because of the poor distinguishability of features and the missing values in practice. A novel multi-task based neural network, SurvNet, is proposed in this paper. The proposed SurvNet model is trained in a multi-task learning framework to jointly learn across three related tasks: input reconstruction, survival classification, and Cox regression. It uses an input reconstruction mechanism cooperating with incomplete-aware reconstruction loss for latent feature learning of incomplete data with missing values. Besides, the SurvNet model introduces a context gating mechanism to bridge the gap between survival classification and Cox regression. A new real-world dataset of 1,137 patients with IB-IIA stage non-small cell lung cancer is collected to evaluate the performance of the SurvNet model. The proposed SurvNet achieves a higher concordance index than the traditional Cox model and Cox-Net. The difference between high-risk and low-risk groups obtained by SurvNet is more significant than that of high-risk and low-risk groups obtained by the other models. Moreover, the SurvNet outperforms the other models even though the input data is randomly cropped and it achieves better generalization performance on the Surveillance, Epidemiology, and End Results Program (SEER) dataset.
ABSTRACT
Lung cancer postoperative complication prediction (PCP) is significant for decreasing the perioperative mortality rate after lung cancer surgery. In this paper we concentrate on two PCP tasks: (1) the binary classification for predicting whether a patient will have postoperative complications; and (2) the three-class multi-label classification for predicting which postoperative complication a patient will experience. Furthermore, an important clinical requirement of PCP is the extraction of crucial variables from electronic medical records. We propose a novel multi-layer perceptron (MLP) model called medical MLP (MediMLP) together with the gradient-weighted class activation mapping (Grad-CAM) algorithm for lung cancer PCP. The proposed MediMLP, which involves one locally connected layer and fully connected layers with a shortcut connection, simultaneously extracts crucial variables and performs PCP tasks. The experimental results indicated that MediMLP outperformed normal MLP on two PCP tasks and had comparable performance with existing feature selection methods. Using MediMLP and further experimental analysis, we found that the variable of "time of indwelling drainage tube" was very relevant to lung cancer postoperative complications.
Subject(s)
Lung Neoplasms/surgery , Neural Networks, Computer , Postoperative Complications/diagnosis , Female , Humans , Male , Medical Informatics Applications , Models, Statistical , Postoperative Complications/prevention & controlABSTRACT
Lung cancer is one of the most common and fatal types of cancer, and pulmonary nodule detection plays a crucial role in the screening and diagnosis of this disease. A well-trained deep neural network model can help doctors to find nodules on computed tomography(CT) images while requiring lots of labeled data. However, currently available annotating systems are not suitable for annotating pulmonary nodules in CT images. We propose a web-based lung nodules annotating system named as DeepLNAnno. DeepLNAnno has a unique three-tier working process and loads of features like semi-automatic annotation, which not only make it much easier for doctors to annotate compared to some other annotating systems but also increase the accuracy of the labels. We invited a medical group from West China Hospital to annotate the CT images using our DeepLNAnno system, and collected a large number of labeled data. The results of our experiments demonstrated that a usable nodule-detection system is developed, and good benchmark scores on our evaluation data are obtained.
Subject(s)
Internet , Lung Neoplasms/diagnostic imaging , Software , Tomography, X-Ray Computed , Humans , Neural Networks, Computer , User-Computer InterfaceABSTRACT
In situ chemical oxidation (ISCO) applications using permanganate involve the injection or release of permanganate into the subsurface to destroy various target contaminants. Naturally occurring reduced components associated with aquifer materials can exert a significant oxidant demand thereby reducing the amount of permanganate available for the destruction of contaminants as well as reducing the overall rate of oxidation. Quantification of this natural oxidant demand (NOD) is a requirement for site-specific assessment and the design of cost-effective oxidant delivery systems. To further our understanding of the interaction between permanganate and aquifer materials, aerobic and anaerobic aquifer materials from eight representative sites throughout North America were tested in a series of systematic bench-scale experiments. Various permanganate to aquifer solids mass loading ratios at different initial permanganate concentrations in well-mixed batch reactors were monitored for >300 days. All NOD temporal profiles demonstrated an initial fast consumption rate followed by a persistent slower consumption rate. The data generated show that the mass loading ratio, the initial permanganate concentration, and the nature and quantity of reduced aquifer material species are the main factors controlling permanganate consumption rates. A higher initial permanganate concentration or a larger mass loading ratio produced a larger fast NOD consumption rate and generated a corresponding higher maximum NOD value. Hence, both the NOD temporal profile and the maximum NOD are not single-valued but are heavily dependent on the experimental conditions. Predictive relationships were developed to estimate the maximum NOD and the NOD at 7 days based on aquifer material properties. The concentration of manganese oxides deposited on the aquifer solids was highly correlated with the mass of permanganate consumed suggesting that passivation of NOD reaction sites occurred due to the formation of manganese oxide coating on the grains. A long-term NOD kinetic model was developed assuming a single fast and slow reacting oxidizable aquifer material species, passivation of NOD reaction sites, and the presence of an autocatalytic reaction. The developed model was able to successfully capture the observed NOD temporal profiles, and can be used to estimate in situ NOD behavior using batch reactor experimental data. The use of batch tests to provide data representative of in situ conditions should be used with caution.