scholarly journals Leveraging Multi-Task Learning to Cope With Poor and Missing Labels of Mammograms

2022 ◽  
Vol 1 ◽  
Author(s):  
Mickael Tardy ◽  
Diana Mateus

In breast cancer screening, binary classification of mammograms is a common task aiming to determine whether a case is malignant or benign. A Computer-Aided Diagnosis (CADx) system based on a trainable classifier requires clean data and labels coming from a confirmed diagnosis. Unfortunately, such labels are not easy to obtain in clinical practice, since the histopathological reports of biopsy may not be available alongside mammograms, while normal cases may not have an explicit follow-up confirmation. Such ambiguities result either in reducing the number of samples eligible for training or in a label uncertainty that may decrease the performances. In this work, we maximize the number of samples for training relying on multi-task learning. We design a deep-neural-network-based classifier yielding multiple outputs in one forward pass. The predicted classes include binary malignancy, cancer probability estimation, breast density, and image laterality. Since few samples have all classes available and confirmed, we propose to introduce the uncertainty related to the classes as a per-sample weight during training. Such weighting prevents updating the network's parameters when training on uncertain or missing labels. We evaluate our approach on the public INBreast and private datasets, showing statistically significant improvements compared to baseline and independent state-of-the-art approaches. Moreover, we use mammograms from Susan G. Komen Tissue Bank for fine-tuning, further demonstrating the ability to improve the performances in our multi-task learning setup from raw clinical data. We achieved the binary classification performance of AUC = 80.46 on our private dataset and AUC = 85.23 on the INBreast dataset.

Geomatics ◽  
2021 ◽  
Vol 1 (1) ◽  
pp. 34-49
Author(s):  
Mael Moreni ◽  
Jerome Theau ◽  
Samuel Foucher

The combination of unmanned aerial vehicles (UAV) with deep learning models has the capacity to replace manned aircrafts for wildlife surveys. However, the scarcity of animals in the wild often leads to highly unbalanced, large datasets for which even a good detection method can return a large amount of false detections. Our objectives in this paper were to design a training method that would reduce training time, decrease the number of false positives and alleviate the fine-tuning effort of an image classifier in a context of animal surveys. We acquired two highly unbalanced datasets of deer images with a UAV and trained a Resnet-18 classifier using hard-negative mining and a series of recent techniques. Our method achieved sub-decimal false positive rates on two test sets (1 false positive per 19,162 and 213,312 negatives respectively), while training on small but relevant fractions of the data. The resulting training times were therefore significantly shorter than they would have been using the whole datasets. This high level of efficiency was achieved with little tuning effort and using simple techniques. We believe this parsimonious approach to dealing with highly unbalanced, large datasets could be particularly useful to projects with either limited resources or extremely large datasets.


2019 ◽  
Vol 44 (2) ◽  
pp. 62-67
Author(s):  
Dijana Alic

On 6 april 1992, the european union (eu) recognised bosnia and hercegovina as a new independent state, no longer a part of the socialist federal republic of Yugoslavia. The event marked the start of the siege of sarajevo, which lasted nearly four years, until late february 1996. It became the longest siege in the history of modern warfare, outlasting the leningrad enclosure by a year. During its 1425 days, more than 11,500 people were killed. The attacks left a trail of destruction across the city, which began to transform it in ways not experienced before. This paper explores how the physical transformation of sarajevo affected the ways in which meaning and significance were assigned to its built fabric. I argue that the changes imposed by war and the daily destruction of the city challenged long-established relationships between the built fabric and those who inhabited the city, introducing new modes of thinking and interpreting the city. Loosely placing the discussion within the framework of ‘Thirdspace', established by urban theorist and cultural geographer edward soja, i discuss the relationship that emerged between the historicality, sociality and spatiality of war-torn sarajevo. Whether responding to the impacts of physical destruction or dramatic social change, the nexus of time, space and being shows that the concept of spatiality is essential to comprehending the world and to adjusting to and resisting the impact of extraordinary circumstances. Recognising the continuation of daily life as essential to survival sheds light on processes of renewal and change in a war-affected landscape. These shattered urban spaces also show the ways in which people make a sense of place in relation to specific socio-historical environments and political contexts.


2017 ◽  
Vol 13 (1) ◽  
pp. 155014771668368 ◽  
Author(s):  
Charissa Ann Ronao ◽  
Sung-Bae Cho

Human activity recognition has been gaining more and more attention from researchers in recent years, particularly with the use of widespread and commercially available devices such as smartphones. However, most of the existing works focus on discriminative classifiers while neglecting the inherent time-series and continuous characteristics of sensor data. To address this, we propose a two-stage continuous hidden Markov model framework, which also takes advantage of the innate hierarchical structure of basic activities. This kind of system architecture not only enables the use of different feature subsets on different subclasses, which effectively reduces feature computation overhead, but also allows for varying number of states and iterations. Experiments show that the hierarchical structure dramatically increases classification performance. We analyze the behavior of the accelerometer and gyroscope signals for each activity through graphs, and with added fine tuning of states and training iterations, the proposed method is able to achieve an overall accuracy of up to 93.18%, which is the best performance among the state-of-the-art classifiers for the problem at hand.


Author(s):  
P. Zhong ◽  
Z. Q. Gong ◽  
C. Schönlieb

In recent years, researches in remote sensing demonstrated that deep architectures with multiple layers can potentially extract abstract and invariant features for better hyperspectral image classification. Since the usual real-world hyperspectral image classification task cannot provide enough training samples for a supervised deep model, such as convolutional neural networks (CNNs), this work turns to investigate the deep belief networks (DBNs), which allow unsupervised training. The DBN trained over limited training samples usually has many “dead” (never responding) or “potential over-tolerant” (always responding) latent factors (neurons), which decrease the DBN’s description ability and thus finally decrease the hyperspectral image classification performance. This work proposes a new diversified DBN through introducing a diversity promoting prior over the latent factors during the DBN pre-training and fine-tuning procedures. The diversity promoting prior in the training procedures will encourage the latent factors to be uncorrelated, such that each latent factor focuses on modelling unique information, and all factors will be summed up to capture a large proportion of information and thus increase description ability and classification performance of the diversified DBNs. The proposed method was evaluated over the well-known real-world hyperspectral image dataset. The experiments demonstrate that the diversified DBNs can obtain much better results than original DBNs and comparable or even better performances compared with other recent hyperspectral image classification methods.


Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7417
Author(s):  
Alex J. Hope ◽  
Utkarsh Vashisth ◽  
Matthew J. Parker ◽  
Andreas B. Ralston ◽  
Joshua M. Roper ◽  
...  

Concussion injuries remain a significant public health challenge. A significant unmet clinical need remains for tools that allow related physiological impairments and longer-term health risks to be identified earlier, better quantified, and more easily monitored over time. We address this challenge by combining a head-mounted wearable inertial motion unit (IMU)-based physiological vibration acceleration (“phybrata”) sensor and several candidate machine learning (ML) models. The performance of this solution is assessed for both binary classification of concussion patients and multiclass predictions of specific concussion-related neurophysiological impairments. Results are compared with previously reported approaches to ML-based concussion diagnostics. Using phybrata data from a previously reported concussion study population, four different machine learning models (Support Vector Machine, Random Forest Classifier, Extreme Gradient Boost, and Convolutional Neural Network) are first investigated for binary classification of the test population as healthy vs. concussion (Use Case 1). Results are compared for two different data preprocessing pipelines, Time-Series Averaging (TSA) and Non-Time-Series Feature Extraction (NTS). Next, the three best-performing NTS models are compared in terms of their multiclass prediction performance for specific concussion-related impairments: vestibular, neurological, both (Use Case 2). For Use Case 1, the NTS model approach outperformed the TSA approach, with the two best algorithms achieving an F1 score of 0.94. For Use Case 2, the NTS Random Forest model achieved the best performance in the testing set, with an F1 score of 0.90, and identified a wider range of relevant phybrata signal features that contributed to impairment classification compared with manual feature inspection and statistical data analysis. The overall classification performance achieved in the present work exceeds previously reported approaches to ML-based concussion diagnostics using other data sources and ML models. This study also demonstrates the first combination of a wearable IMU-based sensor and ML model that enables both binary classification of concussion patients and multiclass predictions of specific concussion-related neurophysiological impairments.


2022 ◽  
Author(s):  
Maede Maftouni ◽  
Bo Shen ◽  
Andrew Chung Chee Law ◽  
Niloofar Ayoobi Yazdi ◽  
Zhenyu Kong

<p>The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images.</p><p>The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task baseline and state-of-the-art models, as measured by various popular metrics. In our experiment with different percentages of data from our curated dataset, the classification performance gain from this multi-task learning approach is more significant for the smaller training sizes. Furthermore, experimental results demonstrate that our method enhances the focus on the lesions, as witnessed by both</p><p>attention and attribution maps, resulting in a more interpretable model.</p>


2012 ◽  
Vol 9 (3) ◽  
pp. 33-43 ◽  
Author(s):  
Paulo Gaspar ◽  
Jaime Carbonell ◽  
José Luís Oliveira

Summary Classifying biological data is a common task in the biomedical context. Predicting the class of new, unknown information allows researchers to gain insight and make decisions based on the available data. Also, using classification methods often implies choosing the best parameters to obtain optimal class separation, and the number of parameters might be large in biological datasets.Support Vector Machines provide a well-established and powerful classification method to analyse data and find the minimal-risk separation between different classes. Finding that separation strongly depends on the available feature set and the tuning of hyper-parameters. Techniques for feature selection and SVM parameters optimization are known to improve classification accuracy, and its literature is extensive.In this paper we review the strategies that are used to improve the classification performance of SVMs and perform our own experimentation to study the influence of features and hyper-parameters in the optimization process, using several known kernels.


2021 ◽  
pp. 20201263
Author(s):  
Mohammad Salehi ◽  
Reza Mohammadi ◽  
Hamed Ghaffari ◽  
Nahid Sadighi ◽  
Reza Reiazi

Objective: Pneumonia is a lung infection and causes the inflammation of the small air sacs (Alveoli) in one or both lungs. Proper and faster diagnosis of pneumonia at an early stage is imperative for optimal patient care. Currently, chest X-ray is considered as the best imaging modality for diagnosing pneumonia. However, the interpretation of chest X-ray images is challenging. To this end, we aimed to use an automated convolutional neural network-based transfer-learning approach to detect pneumonia in paediatric chest radiographs. Methods: Herein, an automated convolutional neural network-based transfer-learning approach using four different pre-trained models (i.e. VGG19, DenseNet121, Xception, and ResNet50) was applied to detect pneumonia in children (1–5 years) chest X-ray images. The performance of different proposed models for testing data set was evaluated using five performances metrics, including accuracy, sensitivity/recall, Precision, area under curve, and F1 score. Results: All proposed models provide accuracy greater than 83.0% for binary classification. The pre-trained DenseNet121 model provides the highest classification performance of automated pneumonia classification with 86.8% accuracy, followed by Xception model with an accuracy of 86.0%. The sensitivity of the proposed models was greater than 91.0%. The Xception and DenseNet121 models achieve the highest classification performance with F1-score greater than 89.0%. The plotted area under curve of receiver operating characteristics of VGG19, Xception, ResNet50, and DenseNet121 models are 0.78, 0.81, 0.81, and 0.86, respectively. Conclusion: Our data showed that the proposed models achieve a high accuracy for binary classification. Transfer learning was used to accelerate training of the proposed models and resolve the problem associated with insufficient data. We hope that these proposed models can help radiologists for a quick diagnosis of pneumonia at radiology departments. Moreover, our proposed models may be useful to detect other chest-related diseases such as novel Coronavirus 2019. Advances in knowledge: Herein, we used transfer learning as a machine learning approach to accelerate training of the proposed models and resolve the problem associated with insufficient data. Our proposed models achieved accuracy greater than 83.0% for binary classification.


Author(s):  
Aigerim MANAKBAYEVA ◽  
Serik SEIDUMANOV

Cinematography is one of the least studied and emerging areas of research in public administration. The main principles of state policy in the field of cinema are support for domestic cinema and providing access to Kazakhstani film products. The purpose of the article is to analyze the topical problems of domestic cinematography, taking into account the principles of state policy in the field of cinematography. The methodological basis of the research is based on scientific works on the issues under consideration, regulatory legal acts. The work used the official statistics of services in the field of cinema. A factorial analysis of the current state of the film industry was carried out using the analytical tool PEST-analysis. In addition, a discursive analysis of the representation of ideas of state policy in modern Kazakhstani cinema was carried out. Modern Kazakhstani films of the last 10 years were considered as additional materials. The study showed that the support of national films is an important direction in the public administration in the field of cinematography. Socially significant films have non-commercial, spiritual and artistic value. Financial profit belongs to commercial films of private companies. The sharp decline in industry statistics confirms that the global pandemic in 2020 was a tough time for the film industry. Further development of the industry should be a common task not only of the state, but also of all interested parties.


Sign in / Sign up

Export Citation Format

Share Document