Kaggle Data Science Bowl Research Articles

An efficient combined intelligent system for segmentation and classification of lung cancer computed tomography images

Background and Objective One of the illnesses with most significant mortality and morbidity rates worldwide is lung cancer. From CT images, automatic lung tumor segmentation is significantly essential. However, segmentation has several difficulties, such as different sizes, variable shapes, and complex surrounding tissues. Therefore, a novel enhanced combined intelligent system is presented to predict lung cancer in this research. Methods Non-small cell lung cancer should be recognized for detecting lung cancer. In the pre-processing stage, the noise in the CT images is eliminated by using an average filter and adaptive median filter, and histogram equalization is used to enhance the filtered images to enhance the lung image quality in the proposed model. The adapted deep belief network (ADBN) is used to segment the affected region with the help of network layers from the noise-removed lung CT image. Two cascaded RBMs are used for the segmentation process in the structure of ADBN, including Bernoulli–Bernoulli (BB) and Gaussian-Bernoulli (GB), and then relevant significant features are extracted. The hybrid spiral optimization intelligent-generalized rough set (SOI-GRS) approach is used to select compelling features of the CT image. Then, an optimized light gradient boosting machine (LightGBM) model using the Ensemble Harris hawk optimization (EHHO) algorithm is used for lung cancer classification. Results LUNA 16, the Kaggle Data Science Bowl (KDSB), the Cancer Imaging Archive (CIA), and local datasets are used to train and test the proposed approach. Python and several well-known modules, including TensorFlow and Scikit-Learn, are used for the extensive experiment analysis. The proposed research accurately spot people with lung cancer according to the results. The method produced the least classification error possible while maintaining 99.87% accuracy. Conclusion The integrated intelligent system (ADBN-Optimized LightGBM) gives the best results among all input prediction models, taking performance criteria into account and boosting the system’s effectiveness, hence enabling better lung cancer patient diagnosis by physicians and radiologists.

Advanced lung tumor diagnosis using a 3D deep neural network based CAD system

In the realm of interdisciplinary research, Computer-Aided Diagnosis (CAD) emerges as a pivotal tool, aiding radiologists in comprehending lung computer tomography scans (both 2D and 3D) for enhanced prediction of lung malignancy and benign cases with heightened accuracy. The objective of clinical examination is to furnish medical experts with more effective scientific insights and treatment strategies. As conventional computer-aided design frameworks prove to be increasingly challenging and time-consuming, this study delves into the contemporary landscape of clinical image analysis in computer-aided diagnosis, with a specific focus on the architecture of the Convolutional Neural Network (CNN). Employing the Kaggle Data Science Bowl dataset, encompassing CT scan images of lung tumors, our proposed CNN architecture has exhibited remarkable performance. Notably, the CNN Net deep learning algorithm achieved a peak classification accuracy of 94%, coupled with a substantial sensitivity and specificity of 90.2%. The extensive 15-fold cross-validation procedure further highlighted the robustness of the CNN network, reporting a minimal log loss of 0.54. This outcome underscores the superior diagnostic capabilities of the CNN architecture in the context of lung tumor diagnosis. In essence, this paper not only contributes to advancements in radio diagnosis and precision medication but also provides a valuable addition to the field by presenting a meticulous figure for computer-aided design utilization.

A new lung cancer detection method based on the chest CT images using Federated Learning and blockchain systems

With an estimated five million fatal cases each year, lung cancer is one of the significant causes of death worldwide. Lung diseases can be diagnosed with a Computed Tomography (CT) scan. The scarcity and trustworthiness of human eyes is the fundamental issue in diagnosing lung cancer patients. The main goal of this study is to detect malignant lung nodules in a CT scan of the lungs and categorize lung cancer according to severity. In this work, cutting-edge Deep Learning (DL) algorithms were used to detect the location of cancerous nodules. Also, the real-life issue is sharing data with hospitals around the world while bearing in mind the organizations' privacy issues. Besides, the main problems for training a global DL model are creating a collaborative model and maintaining privacy. This study presented an approach that takes a modest amount of data from multiple hospitals and uses blockchain-based Federated Learning (FL) to train a global DL model. The data were authenticated using blockchain technology, and FL trained the model internationally while maintaining the organization's anonymity. First, we presented a data normalization approach that addresses the variability of data obtained from various institutions using various CT scanners. Furthermore, using a CapsNets method, we classified lung cancer patients in local mode. Finally, we devised a way to train a global model cooperatively utilizing blockchain technology and FL while maintaining anonymity. We also gathered data from real-life lung cancer patients for testing purposes. The suggested method was trained and tested on the Cancer Imaging Archive (CIA) dataset, Kaggle Data Science Bowl (KDSB), LUNA 16, and the local dataset. Finally, we performed extensive experiments with Python and its well-known libraries, such as Scikit-Learn and TensorFlow, to evaluate the suggested method. The findings showed that the method effectively detects lung cancer patients. The technique delivered 99.69 % accuracy with the smallest possible categorization error.

Active Semi-Supervised Learning via Bayesian Experimental Design for Lung Cancer Classification Using Low Dose Computed Tomography Scans

We introduce an active, semisupervised algorithm that utilizes Bayesian experimental design to address the shortage of annotated images required to train and validate Artificial Intelligence (AI) models for lung cancer screening with computed tomography (CT) scans. Our approach incorporates active learning with semisupervised expectation maximization to emulate the human in the loop for additional ground truth labels to train, evaluate, and update the neural network models. Bayesian experimental design is used to intelligently identify which unlabeled samples need ground truth labels to enhance the model’s performance. We evaluate the proposed Active Semi-supervised Expectation Maximization for Computer aided diagnosis (CAD) tasks (ASEM-CAD) using three public CT scans datasets: the National Lung Screening Trial (NLST), the Lung Image Database Consortium (LIDC), and Kaggle Data Science Bowl 2017 for lung cancer classification using CT scans. ASEM-CAD can accurately classify suspicious lung nodules and lung cancer cases with an area under the curve (AUC) of 0.94 (Kaggle), 0.95 (NLST), and 0.88 (LIDC) with significantly fewer labeled images compared to a fully supervised model. This study addresses one of the significant challenges in early lung cancer screenings using low-dose computed tomography (LDCT) scans and is a valuable contribution towards the development and validation of deep learning algorithms for lung cancer screening and other diagnostic radiology examinations.

Deep Learning for Lung Cancer Detection on Screening CT Scans: Results of a Large-Scale Public Competition and an Observer Study with 11 Radiologists.

To determine whether deep learning algorithms developed in a public competition could identify lung cancer on low-dose CT scans with a performance similar to that of radiologists. In this retrospective study, a dataset consisting of 300 patient scans was used for model assessment; 150 patient scans were from the competition set and 150 were from an independent dataset. Both test datasets contained 50 cancer-positive scans and 100 cancer-negative scans. The reference standard was set by histopathologic examination for cancer-positive scans and imaging follow-up for at least 2 years for cancer-negative scans. The test datasets were applied to the three top-performing algorithms from the Kaggle Data Science Bowl 2017 public competition: grt123, Julian de Wit and Daniel Hammack (JWDH), and Aidence. Model outputs were compared with an observer study of 11 radiologists that assessed the same test datasets. Each scan was scored on a continuous scale by both the deep learning algorithms and the radiologists. Performance was measured using multireader, multicase receiver operating characteristic analysis. The area under the receiver operating characteristic curve (AUC) was 0.877 (95% CI: 0.842, 0.910) for grt123, 0.902 (95% CI: 0.871, 0.932) for JWDH, and 0.900 (95% CI: 0.870, 0.928) for Aidence. The average AUC of the radiologists was 0.917 (95% CI: 0.889, 0.945), which was significantly higher than grt123 (P = .02); however, no significant difference was found between the radiologists and JWDH (P = .29) or Aidence (P = .26). Deep learning algorithms developed in a public competition for lung cancer detection in low-dose CT scans reached performance close to that of radiologists.Keywords: Lung, CT, Thorax, Screening, Oncology Supplemental material is available for this article. © RSNA, 2021.

R2AU-Net: Attention Recurrent Residual Convolutional Neural Network for Multimodal Medical Image Segmentation

In recent years, semantic segmentation method based on deep learning provides advanced performance in medical image segmentation. As one of the typical segmentation networks, U-Net is successfully applied to multimodal medical image segmentation. A recurrent residual convolutional neural network with attention gate connection (R2AU-Net) based on U-Net is proposed in this paper. It enhances the capability of integrating contextual information by replacing basic convolutional units in U-Net by recurrent residual convolutional units. Furthermore, R2AU-Net adopts attention gates instead of the original skip connection. In this paper, the experiments are performed on three multimodal datasets: ISIC 2018, DRIVE, and public dataset used in LUNA and the Kaggle Data Science Bowl 2017. Experimental results show that R2AU-Net achieves much better performance than other improved U-Net algorithms for multimodal medical image segmentation.

Reproducible Machine Learning Methods for Lung Cancer Detection Using Computed Tomography Images: Algorithm Development and Validation.

BackgroundChest computed tomography (CT) is crucial for the detection of lung cancer, and many automated CT evaluation methods have been proposed. Due to the divergent software dependencies of the reported approaches, the developed methods are rarely compared or reproduced.ObjectiveThe goal of the research was to generate reproducible machine learning modules for lung cancer detection and compare the approaches and performances of the award-winning algorithms developed in the Kaggle Data Science Bowl.MethodsWe obtained the source codes of all award-winning solutions of the Kaggle Data Science Bowl Challenge, where participants developed automated CT evaluation methods to detect lung cancer (training set n=1397, public test set n=198, final test set n=506). The performance of the algorithms was evaluated by the log-loss function, and the Spearman correlation coefficient of the performance in the public and final test sets was computed.ResultsMost solutions implemented distinct image preprocessing, segmentation, and classification modules. Variants of U-Net, VGGNet, and residual net were commonly used in nodule segmentation, and transfer learning was used in most of the classification algorithms. Substantial performance variations in the public and final test sets were observed (Spearman correlation coefficient = .39 among the top 10 teams). To ensure the reproducibility of results, we generated a Docker container for each of the top solutions.ConclusionsWe compared the award-winning algorithms for lung cancer detection and generated reproducible Docker images for the top solutions. Although convolutional neural networks achieved decent accuracy, there is plenty of room for improvement regarding model generalizability.

Demonstrative of cancer in lungs utilizing CT scan in DL

As of late, such a large number of Computer Aided Diagnosis (CAD) frameworks are intended for determination of a few maladies. Lung malignant growth discovery at beginning phase has gotten significant and furthermore extremely simple with picture handling and profound learning procedures. In this examination lung understanding Computer Tomography (CT) check pictures are utilized to identify and characterize the lung knobs and to recognize the harm level of that knobs. The CT examine pictures are divided utilizing U-Net engineering. This paper proposes 3D multipath VGG-like system, which is assessed on 3D shapes, extricated from Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), Lung Nodule Analysis fio16 (LUNA16) and Kaggle Data Science Bowl fio17 datasets. Expectation from U-Net and 3D multipath VGG-like system are joined for conclusive outcomes. The lung knobs are characterized and threat level is distinguished utilizing this design with 100% of Accuracy and o.38773fi of log loss.

Inception U-Net Architecture for Semantic Segmentation to Identify Nuclei in Microscopy Cell Images

With the increasing applications of deep learning in biomedical image analysis, in this article we introduce an inception U-Net architecture for automating nuclei detection in microscopy cell images of varying size and modality to help unlock faster cures, inspired from Kaggle Data Science Bowl Challenge 2018 (KDSB18). This study follows from the fact that most of the analysis requires nuclei detection as the starting phase for getting an insight into the underlying biological process and further diagnosis. The proposed architecture consists of a switch normalization layer, convolution layers, and inception layers (concatenated 1x1, 3x3, and 5x5 convolution and the hybrid of a max and Hartley spectral pooling layer) connected in the U-Net fashion for generating the image masks. This article also illustrates the model perception of image masks using activation maximization and filter map visualization techniques. A novel objective function segmentation loss is proposed based on the binary cross entropy, dice coefficient, and intersection over union loss functions. The intersection over union score, loss value, and pixel accuracy metrics evaluate the model over the KDSB18 dataset. The proposed inception U-Net architecture exhibits quite significant results as compared to the original U-Net and recent U-Net++ architecture.

Microscopy cell nuclei segmentation with enhanced U-Net

BackgroundCell nuclei segmentation is a fundamental task in microscopy image analysis, based on which multiple biological related analysis can be performed. Although deep learning (DL) based techniques have achieved state-of-the-art performances in image segmentation tasks, these methods are usually complex and require support of powerful computing resources. In addition, it is impractical to allocate advanced computing resources to each dark- or bright-field microscopy, which is widely employed in vast clinical institutions, considering the cost of medical exams. Thus, it is essential to develop accurate DL based segmentation algorithms working with resources-constraint computing.ResultsAn enhanced, light-weighted U-Net (called U-Net+) with modified encoded branch is proposed to potentially work with low-resources computing. Through strictly controlled experiments, the average IOU and precision of U-Net+ predictions are confirmed to outperform other prevalent competing methods with 1.0% to 3.0% gain on the first stage test set of 2018 Kaggle Data Science Bowl cell nuclei segmentation contest with shorter inference time.ConclusionsOur results preliminarily demonstrate the potential of proposed U-Net+ in correctly spotting microscopy cell nuclei with resources-constraint computing.

A Deep Convolutional Neural Network Framework for Lung Cancer Detection

Exact identification of pulmonary nodules with high sensitivity and specificity is basic for programmed lung malignancy analysis from CT scans. In fact, many deep learning-based algorithms gain incredible ground for improving the exactness of nodule recognition; the high false positive rate is yet a difficult issue which restricted the programmed determination. We propose a novel customized Deep Convolutional Neural Network (DCNN) architecture for learning high-level image representation to achieve high classification accuracy with low variance in medical image binary classification tasks. Moreover, a High Sensitivity and Specificity system is introduced to eliminate the erroneously recognized nodule competitors by following the appearance changes in consistent CT slices of every nodule. The proposed structure is assessed on the open Kaggle Data Science Bowl (KDSB17) challenge dataset. Our strategy can precisely distinguish lung nodules at high sensitivity and specificity and accomplishes 95 % sensitivity.

A 3D Probabilistic Deep Learning System for Detection and Diagnosis of Lung Cancer Using Low-Dose CT Scans.

We introduce a new computer aided detection and diagnosis system for lung cancer screening with low-dose CT scans that produces meaningful probability assessments. Our system is based entirely on 3D convolutional neural networks and achieves state-of-the-art performance for both lung nodule detection and malignancy classification tasks on the publicly available LUNA16 and Kaggle Data Science Bowl challenges. While nodule detection systems are typically designed and optimized on their own, we find that it is important to consider the coupling between detection and diagnosis components. Exploiting this coupling allows us to develop an end-to-end system that has higher and more robust performance and eliminates the need for a nodule detection false positive reduction stage. Furthermore, we characterize model uncertainty in our deep learning systems, a first for lung CT analysis, and show that we can use this to provide well-calibrated classification probabilities for both nodule detection and patient malignancy diagnosis. These calibrated probabilities informed by model uncertainty can be used for subsequent risk-based decision making towards diagnostic interventions or disease treatments, as we demonstrate using a probability-based patient referral strategy to further improve our results.

Multi-path convolutional neural network for lung cancer detection

Lung cancer is the leading cause of death among cancer-related death. Like other cancers, the finest solution for lung cancer diagnosis and treatment is early screening. Automatic CAD system of lung cancer screening from Computed Tomography scan mainly involves two steps: detect all suspicious pulmonary nodules and evaluate the malignancy of the nodules. Recently, there are many works about the first step, but rare about the second step. Since the presence of pulmonary nodules does not absolutely specify cancer, the morphology of nodules such as shape, size, and contextual information has a sophisticated relationship with cancer, the screening of lung cancer needs a careful investigation on each suspicious nodule and integration of information of all nodules. We propose deep CNN architecture which differs from those traditionally used in computer vision to solve this problem. First, the suspicious nodules are generated with the modified version of U-Net and then the generated nodules become an input data for our model. The proposed model is a multi-path CNN which exploits both local features as well as more global contextual features simultaneously to automatically detect lung cancer. To this end, the model used three paths, each path employed different receptive field size which helps to model distant dependencies (short and long-range dependencies of the neighboring pixels). Then, to further upgrade our model performance, we concatenate features from the three paths. This balance the receptive field size effect and makes our model more adaptable to the variability of shape, size, and contextual information among nodules. Finally, we also introduce a retraining phase system that permits us to tackle difficulties related to the imbalance of image labels. Experimental results on Kaggle Data Science Bowl 2017 challenge shows that our model is better adaptable to the described inconsistency among nodules size and shape, and also obtained better detection results compared to the recently published state of the art methods.

Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers.

Deep fully convolutional neural network (FCN) based architectures have shown great potential in medical image segmentation. However, such architectures usually have millions of parameters and inadequate number of training samples leading to over-fitting and poor generalization. In this paper, we present a novel DenseNet based FCN architecture for cardiac segmentation which is parameter and memory efficient. We propose a novel up-sampling path which incorporates long skip and short-cut connections to overcome the feature map explosion in conventional FCN based architectures. In order to process the input images at multiple scales and view points simultaneously, we propose to incorporate Inception module's parallel structures. We propose a novel dual loss function whose weighting scheme allows to combine advantages of cross-entropy and Dice loss leading to qualitative improvements in segmentation. We demonstrate computational efficacy of incorporating conventional computer vision techniques for region of interest detection in an end-to-end deep learning based segmentation framework. From the segmentation maps we extract clinically relevant cardiac parameters and hand-craft features which reflect the clinical diagnostic analysis and train an ensemble system for cardiac disease classification. We validate our proposed network architecture on three publicly available datasets, namely: (i) Automated Cardiac Diagnosis Challenge (ACDC-2017), (ii) Left Ventricular segmentation challenge (LV-2011), (iii) 2015 Kaggle Data Science Bowl cardiac challenge data. Our approach in ACDC-2017 challenge stood second place for segmentation and first place in automated cardiac disease diagnosis tasks with an accuracy of 100% on a limited testing set (n=50). In the LV-2011 challenge our approach attained 0.74 Jaccard index, which is so far the highest published result in fully automated algorithms. In the Kaggle challenge our approach for LV volume gave a Continuous Ranked Probability Score (CRPS) of 0.0127, which would have placed us tenth in the original challenge. Our approach combined both cardiac segmentation and disease diagnosis into a fully automated framework which is computationally efficient and hence has the potential to be incorporated in computer-aided diagnosis (CAD) tools for clinical application.

ES01.03 Deep Machine Learning for Screening LDCT

The first computer algorithms to automatically detect pulmonary nodules in CT scans, based on classical machine learning approaches, were developed almost two decades ago. These systems appeared in commercially available computer-aided detection packages. However, a recent study concluded that such older software systems fail to flag a substantial number of cancerous lesions and have a fairly high false positive rate. Recently, algorithms based on deep learning, in particular, convolutional neural networks, have been developed that report high sensitivity with low false positive rates. Similar deep learning algorithms have been successful in classifying nodules as solid, subsolid or part-solid with accuracy comparable to radiologists, and in estimating the probability of malignancy of nodules. The 2017 Kaggle Data Science Bowl combined these tasks into a single challenge where 2000 teams developed methods to predict, on the basis of a single screening CT scan, whether a patient would be diagnosed with lung cancer within one year of the date of the scan. The 10 best performing solutions are now available under an open source license and form the basis of commercial solutions that show, in recent validation studies, a performance comparable to radiologists. Thorough validation studies are now needed to investigate if the good performance of these deep learning systems can be replicated, independent of CT parameters, and how such systems can be implemented in a lung cancer screening setting. Possibilities include the use of AI software as a second reader, as a concurrent reader, or even a stand-alone reader for a fraction of the cases, when widespread implementation of screening will put a too large burden on scarce radiological resources. In this lecture, I will review the currently available computer solutions and discuss their validation and integration into CT lung screening workflows. artificial intelligence, deep learning, chest ct

Lung Cancer Detection and Classification with 3D Convolutional Neural Network (3D-CNN)

This paper demonstrates a computer-aided diagnosis (CAD) system for lung cancer classification of CT scans with unmarked nodules, a dataset from the Kaggle Data Science Bowl, 2017. Thresholding was used as an initial segmentation approach to segment out lung tissue from the rest of the CT scan. Thresholding produced the next best lung segmentation. The initial approach was to directly feed the segmented CT scans into 3D CNNs for classification, but this proved to be inadequate. Instead, a modified U-Net trained on LUNA16 data (CT scans with labeled nodules) was used to first detect nodule candidates in the Kaggle CT scans. The U-Net nodule detection produced many false positives, so regions of CTs with segmented lungs where the most likely nodule candidates were located as determined by the U-Net output were fed into 3D Convolutional Neural Networks (CNNs) to ultimately classify the CT scan as positive or negative for lung cancer. The 3D CNNs produced a test set Accuracy of 86.6%. The performance of our CAD system outperforms the current CAD systems in literature which have several training and testing phases that each requires a lot of labeled data, while our CAD system has only three major phases (segmentation, nodule candidate detection, and malignancy classification), allowing more efficient training and detection and more generalizability to other cancers.