Dataset Information

Learning to learn by yourself: Unsupervised meta‐learning with self‐knowledge distillation for COVID‐19 diagnosis from pneumonia cases

ABSTRACT: Abstract The goal of diagnosing the coronavirus disease 2019 (COVID‐19) from suspected pneumonia cases, that is, recognizing COVID‐19 from chest X‐ray or computed tomography (CT) images, is to improve diagnostic accuracy, leading to faster intervention. The most important and challenging problem here is to design an effective and robust diagnosis model. To this end, there are three challenges to overcome: (1) The lack of training samples limits the success of existing deep‐learning‐based methods. (2) Many public COVID‐19 data sets contain only a few images without fine‐grained labels. (3) Due to the explosive growth of suspected cases, it is urgent and important to diagnose not only COVID‐19 cases but also the cases of other types of pneumonia that are similar to the symptoms of COVID‐19. To address these issues, we propose a novel framework called Unsupervised Meta‐Learning with Self‐Knowledge Distillation to address the problem of differentiating COVID‐19 from pneumonia cases. During training, our model cannot use any true labels and aims to gain the ability of learning to learn by itself. In particular, we first present a deep diagnosis model based on a relation network to capture and memorize the relation among different images. Second, to enhance the performance of our model, we design a self‐knowledge distillation mechanism that distills knowledge within our model itself. Our network is divided into several parts, and the knowledge in the deeper parts is squeezed into the shallow ones. The final results are derived from our model by learning to compare the features of images. Experimental results demonstrate that our approach achieves significantly higher performance than other state‐of‐the‐art methods. Moreover, we construct a new COVID‐19 pneumonia data set based on text mining, consisting of 2696 COVID‐19 images (347 X‐ray + 2349 CT), 10,155 images (9661 X‐ray + 494 CT) about other types of pneumonia, and the fine‐grained labels of all. Our data set considers not only a bacterial infection or viral infection which causes pneumonia but also a viral infection derived from the influenza virus or coronavirus.

SUBMITTER: Zheng W

PROVIDER: S-EPMC8242586 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Purpose: To construct a deep learning knowledge distillation framework exploring the utilization of MRI alone or combing with distilled Arthroscopy information for meniscus tear detection. Methods: A database of 199 paired knee Arthroscopy-MRI exams was used to develop a multimodal teacher network and an MRI-based student network, which used residual neural networks architectures. A knowledge distillation framework comprising the multimodal teacher network T and the monomodal student network S was proposed. We optimized the loss functions of mean squared error (MSE) and cross-entropy (CE) to enable the student network S to learn arthroscopic information from the teacher network T through our deep learning knowledge distillation framework, ultimately resulting in a distilled student network S T. A coronal proton density (PD)-weighted fat-suppressed MRI sequence was used in this study. Fivefold cross-validation was employed, and the accuracy, sensitivity, specificity, F1-score, receiver operating characteristic (ROC) curves and area under the receiver operating characteristic curve (AUC) were used to evaluate the medial and lateral meniscal tears detection performance of the models, including the undistilled student model S, the distilled student model S T and the teacher model T. Results: The AUCs of the undistilled student model S, the distilled student model S T, the teacher model T for medial meniscus (MM) tear detection and lateral meniscus (LM) tear detection are 0.773/0.672, 0.792/0.751 and 0.834/0.746, respectively. The distilled student model S T had higher AUCs than the undistilled model S. After undergoing knowledge distillation processing, the distilled student model demonstrated promising results, with accuracy (0.764/0.734), sensitivity (0.838/0.661), and F1-score (0.680/0.754) for both medial and lateral tear detection better than the undistilled one with accuracy (0.734/0.648), sensitivity (0.733/0.607), and F1-score (0.620/0.673). Conclusion: Through the knowledge distillation framework, the student model S based on MRI benefited from the multimodal teacher model T and achieved an improved meniscus tear detection performance.

Project description:BackgroundAcquiring medical knowledge is a key competency for medical students and a lifelong requirement for physicians. Learning techniques can improve academic success and help students cope with stressors. To support students' learning process medical faculties should know about learning techniques. The purpose of this study is to analyse the preferred learning techniques of female and male as well as junior and senior medical students and how these learning techniques are related to perceived learning difficulties.MethodsIn 2019, we conducted an online survey with students of the undergraduate, competency-based curriculum of medicine at Charité - Universitätsmedizin Berlin. We chose ten learning techniques of high, moderate and low utility according to Dunlosky et al. (2013) and we asked medical students to rate their preferred usage of those techniques using a 5-point Likert scale. We applied t-tests to show differences in usage between female and male as well as junior and senior learners. Additionally, we conducted a multiple regression analysis to explore the predictive power of learning techniques regarding perceived difficulties.ResultsA total of 730 medical students (488 women, 242 men, Mage = 24.85, SD = 4.49) use three techniques the most: 'highlighting' (low utility), 'self-explanation' (moderate utility) and 'practice testing' (high utility). Female students showed a significantly higher usage of low-utility learning techniques (t(404.24) = -7.13, p < .001) and a higher usage of high-utility learning techniques (t(728) = -2.50, p < .05) than male students (M = 3.55, SD = .95). Compared to junior students (second to sixth semester; M = 3.65, SD = .71), senior students (seventh semester to final clerkship year; M = 3.52, SD = .73) showed a lower use of low-utility learning techniques (t(603) = 2.15, p < .05). Usage of low-utility techniques is related to more difficulties (β = .08, t(724) = 2.13, p < .05). Usage of moderate-utility techniques is related to less learning difficulties (β = -.13, t(599) = -3.21, p < .01).ConclusionsStudents use a wide range of low-, moderate- and high-utility learning techniques. The use of learning techniques has an influence on the difficulties perceived by students. Therefore, they could benefit from knowing about and using high-utility learning techniques to facilitate their learning. Faculties should inform their students about effective learning and introduce them to useful learning techniques.

Dataset Information

Learning to learn by yourself: Unsupervised meta‐learning with self‐knowledge distillation for COVID‐19 diagnosis from pneumonia cases

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets