Search

Tuberculosis (TB) drug resistance is a worldwide public health problem. It decreases the likelihood of a positive outcome for the individual patient and increases the likelihood of disease spread. Therefore, early detection of TB drug resistance is crucial for improving outcomes and controlling disease transmission. While drug-sensitive tuberculosis cases are declining worldwide because of effective treatment, the threat of drug-resistant tuberculosis is growing, and the success rate of drug-resistant tuberculosis treatment is only around 60%. The TB Portals program provides a publicly accessible repository of TB case data with an emphasis on collecting drug-resistant cases. The dataset includes multi-modal information such as socioeconomic/geographic data, clinical characteristics, pathogen genomics, and radiological features. The program is an international collaboration whose participants are typically under a substantial burden of drug-resistant tuberculosis, with data collected from standard clinical care provided to the patients. Consequentially, the TB Portals dataset is heterogenous in nature, with data representing multiple treatment centers in different countries and containing cross-domain information. This study presents the challenges and methods used to address them when working with this real-world dataset. Our goal was to evaluate whether combining radiological features derived from a chest X-ray of the host and genomic features from the pathogen can potentially improve the identification of the drug susceptibility type, drug-sensitive (DS-TB) or drug-resistant (DR-TB), and the length of the first successful drug regimen. To perform these studies, significantly imbalanced data needed to be processed, which included a much larger number of DR-TB cases than DS-TB, many more cases with radiological findings than genomic ones, and the sparse high dimensional nature of the genomic information. Three evaluation studies were carried out. First, the DR-TB/DS-TB classification model achieved an average accuracy of 92.4% when using genomic features alone or when combining radiological and genomic features. Second, the regression model for the length of the first successful treatment had a relative error of 53.5% using radiological features, 25.6% using genomic features, and 22.0% using both radiological and genomic features. Finally, the relative error of the third regression model predicting the length of the first treatment using the most common drug combination varied depending on the feature type used. When using radiological features alone, the relative error was 17.8%. For geno- mic features alone, the relative error increased to 19.9%. The model had a relative error of 19.0% when both radiological and genomic features were combined. Although combining radiological and genomic features did not improve upon the use of genomic features when classifying DR-TB/DS-TB, the combination of the two feature types improved the relative error of the predictive model for the length of the first successful treatment. Furthermore, the regression model trained on radiological features achieved the best performance when predicting the treatment length of the most common drug combination.

Artificial Intelligence (AI)-based medical computer vision algorithm training and evaluations depend on annotations and labeling. However, variability between expert annotators introduces noise in training data that can adversely impact the performance of AI algorithms. This study aims to assess, illustrate and interpret the inter-annotator agreement among multiple expert annotators when segmenting the same lesion(s)/abnormalities on medical images. We propose the use of three metrics for the qualitative and quantitative assessment of inter-annotator agreement: 1) use of a common agreement heatmap and a ranking agreement heatmap; 2) use of the extended Cohen’s kappa and Fleiss’ kappa coefficients for a quantitative evaluation and interpretation of inter-annotator reliability; and 3) use of the Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm, as a parallel step, to generate ground truth for training AI models and compute Intersection over Union (IoU), sensitivity, and specificity to assess the inter-annotator reliability and variability. Experiments are performed on two datasets, namely cervical colposcopy images from 30 patients and chest X-ray images from 336 tuberculosis (TB) patients, to demonstrate the consistency of inter-annotator reliability assessment and the importance of combining different metrics to avoid bias assessment.

Abstract Background Microscopic examination is commonly used for malaria diagnosis in the field. However, the lack of well-trained microscopists in malaria-endemic areas impacted the most by the disease is a severe problem. Besides, the examination process is time-consuming and prone to human error. Automated diagnostic systems based on machine learning offer great potential to overcome these problems. This study aims to evaluate Malaria Screener, a smartphone-based application for malaria diagnosis. Methods A total of 190 patients were recruited at two sites in rural areas near Khartoum, Sudan. The Malaria Screener mobile application was deployed to screen Giemsa-stained blood smears. Both expert microscopy and nested PCR were performed to use as reference standards. First, Malaria Screener was evaluated using the two reference standards. Then, during post-study experiments, the evaluation was repeated for a newly developed algorithm, PlasmodiumVF-Net. Results Malaria Screener reached 74.1% (95% CI 63.5–83.0) accuracy in detecting Plasmodium falciparum malaria using expert microscopy as the reference after a threshold calibration. It reached 71.8% (95% CI 61.0–81.0) accuracy when compared with PCR. The achieved accuracies meet the WHO Level 3 requirement for parasite detection. The processing time for each smear varies from 5 to 15 min, depending on the concentration of white blood cells (WBCs). In the post-study experiment, Malaria Screener reached 91.8% (95% CI 83.8–96.6) accuracy when patient-level results were calculated with a different method. This accuracy meets the WHO Level 1 requirement for parasite detection. In addition, PlasmodiumVF-Net, a newly developed algorithm, reached 83.1% (95% CI 77.0–88.1) accuracy when compared with expert microscopy and 81.0% (95% CI 74.6–86.3) accuracy when compared with PCR, reaching the WHO Level 2 requirement for detecting both Plasmodium falciparum and Plasmodium vivax malaria, without using the testing sites data for training or calibration. Results reported for both Malaria Screener and PlasmodiumVF-Net used thick smears for diagnosis. In this paper, both systems were not assessed in species identification and parasite counting, which are still under development. Conclusion Malaria Screener showed the potential to be deployed in resource-limited areas to facilitate routine malaria screening. It is the first smartphone-based system for malaria diagnosis evaluated on the patient-level in a natural field environment. Thus, the results in the field reported here can serve as a reference for future studies.

Abstract Background Light microscopy is often used for malaria diagnosis in the field. However, it is time-consuming and quality of the results depends heavily on the skill of microscopists. Automating malaria light microscopy is a promising solution, but it still remains a challenge and an active area of research. Current tools are often expensive and involve sophisticated hardware components, which makes it hard to deploy them in resource-limited areas. Results We designed an Android mobile application called Malaria Screener, which makes smartphones an affordable yet effective solution for automated malaria light microscopy. The mobile app utilizes high-resolution cameras and computing power of modern smartphones to screen both thin and thick blood smear images for P. falciparum parasites. Malaria Screener combines image acquisition, smear image analysis, and result visualization in its slide screening process, and is equipped with a database to provide easy access to the acquired data. Conclusion Malaria Screener makes the screening process faster, more consistent, and less dependent on human expertise. The app is modular, allowing other research groups to integrate their methods and models for image processing and machine learning, while acquiring and analyzing their data.

Developments in deep learning techniques have led to significant advances in automated abnormality detection in radiological images and paved the way for their potential use in computer-aided diagnosis (CAD) systems. However, the development of CAD systems for pulmonary tuberculosis (TB) diagnosis is hampered by the lack of training data that is of good visual and diagnostic quality, of sufficient size, variety, and, where relevant, containing fine-region annotations. This study presents a collection of annotations/segmentations of pulmonary radiological manifestations that are consistent with TB in the publicly available and widely used Shenzhen chest X-ray (CXR) dataset made available by the U.S. National Library of Medicine and obtained via a research collaboration with No. 3. People’s Hospital Shenzhen, China. The goal of releasing these annotations is to advance the state of the art for image segmentation methods toward improving the performance of the fine-grained segmentation of TB-consistent findings in digital chest X-ray images. The annotation collection comprises the following: (1) annotation files in JavaScript Object Notation (JSON) format that indicate locations and shapes of 19 lung pattern abnormalities for 336 TB patients; (2) mask files saved in PNG format for each abnormality per TB patient; and (3) a comma-separated values (CSV) file that summarizes lung abnormality types and numbers per TB patient. To the best of our knowledge, this is the first collection of pixel-level annotations of TB-consistent findings in CXRs.

Deep learning (DL) methods have demonstrated superior performance in medical image segmentation tasks. However, selecting a loss function that conforms to the data characteristics is critical for optimal performance. Further, the direct use of traditional DL models does not provide a measure of uncertainty in predictions. Even high-quality automated predictions for medical diagnostic applications demand uncertainty quantification to gain user trust. In this study, we aim to investigate the benefits of (i) selecting an appropriate loss function and (ii) quantifying uncertainty in predictions using a VGG16-based-U-Net model with the Monto–Carlo (MCD) Dropout method for segmenting Tuberculosis (TB)-consistent findings in frontal chest X-rays (CXRs). We determine an optimal uncertainty threshold based on several uncertainty-related metrics. This threshold is used to select and refer highly uncertain cases to an expert. Experimental results demonstrate that (i) the model trained with a modified Focal Tversky loss function delivered superior segmentation performance (mean average precision (mAP): 0.5710, 95% confidence interval (CI): (0.4021,0.7399)), (ii) the model with 30 MC forward passes during inference further improved and stabilized performance (mAP: 0.5721, 95% CI: (0.4032,0.7410), and (iii) an uncertainty threshold of 0.7 is observed to be optimal to refer highly uncertain cases.

Classification of drug-resistant tuberculosis (DR-TB) and drug-sensitive tuberculosis (DS-TB) from chest radiographs remains an open problem. Our previous cross validation performance on publicly available chest X-ray (CXR) data combined with image augmentation, the addition of synthetically generated and publicly available images achieved a performance of 85% AUC with a deep convolutional neural network (CNN). However, when we evaluated the CNN model trained to classify DR-TB and DS-TB on unseen data, significant performance degradation was observed (65% AUC). Hence, in this paper, we investigate the generalizability of our models on images from a held out country’s dataset. We explore the extent of the problem and the possible reasons behind the lack of good generalization. A comparison of radiologist-annotated lesion locations in the lung and the trained model’s localization of areas of interest, using GradCAM, did not show much overlap. Using the same network architecture, a multi-country classifier was able to identify the country of origin of the X-ray with high accuracy (86%), suggesting that image acquisition differences and the distribution of non-pathological and non-anatomical aspects of the images are affecting the generalization and localization of the drug resistance classification model as well. When CXR images were severely corrupted, the performance on the validation set was still better than 60% AUC. The model overfitted to the data from countries in the cross validation set but did not generalize to the held out country. Finally, we applied a multi-task based approach that uses prior TB lesions location information to guide the classifier network to focus its attention on improving the generalization performance on the held out set from another country to 68% AUC.

We propose a new framework, PlasmodiumVF-Net, to analyze thick smear microscopy images for a malaria diagnosis on both image and patient-level. Our framework detects whether a patient is infected, and in case of a malarial infection, reports whether the patient is infected by Plasmodium falciparum or Plasmodium vivax. PlasmodiumVF-Net first detects candidates for Plasmodium parasites using a Mask Regional-Convolutional Neural Network (Mask R-CNN), filters out false positives using a ResNet50 classifier, and then follows a new approach to recognize parasite species based on a score obtained from the number of detected patches and their aggregated probabilities for all of the patient images. Reporting a patient-level decision is highly challenging, and therefore reported less often in the literature, due to the small size of detected parasites, the similarity to staining artifacts, the similarity of species in different development stages, and illumination or color variations on patient-level. We use a manually annotated dataset consisting of 350 patients, with about 6000 images, which we make publicly available together with this manuscript. Our framework achieves an overall accuracy above 90% on image and patient-level.

Background Malaria is a life-threatening disease caused by Plasmodium parasites that infect the red blood cells (RBCs). Manual identification and counting of parasitized cells in microscopic thick/thin-film blood examination remains the common, but burdensome method for disease diagnosis. Its diagnostic accuracy is adversely impacted by inter/intra-observer variability, particularly in large-scale screening under resource-constrained settings. Introduction State-of-the-art computer-aided diagnostic tools based on data-driven deep learning algorithms like convolutional neural network (CNN) has become the architecture of choice for image recognition tasks. However, CNNs suffer from high variance and may overfit due to their sensitivity to training data fluctuations. Objective The primary aim of this study is to reduce model variance, improve robustness and generalization through constructing model ensembles toward detecting parasitized cells in thin-blood smear images. Methods We evaluate the performance of custom and pretrained CNNs and construct an optimal model ensemble toward the challenge of classifying parasitized and normal cells in thin-blood smear images. Cross-validation studies are performed at the patient level to ensure preventing data leakage into the validation and reduce generalization errors. The models are evaluated in terms of the following performance metrics: (a) Accuracy; (b) Area under the receiver operating characteristic (ROC) curve (AUC); (c) Mean squared error (MSE); (d) Precision; (e) F-score; and (f) Matthews Correlation Coefficient (MCC). Results It is observed that the ensemble model constructed with VGG-19 and SqueezeNet outperformed the state-of-the-art in several performance metrics toward classifying the parasitized and uninfected cells to aid in improved disease screening. Conclusions Ensemble learning reduces the model variance by optimally combining the predictions of multiple models and decreases the sensitivity to the specifics of training data and selection of training algorithms. The performance of the model ensemble simulates real-world conditions with reduced variance, overfitting and leads to improved generalization.

Local implementation projects for sector coupling play an important role in the transformation to a more sustainable energy system. Despite various technical possibilities, there are various barriers to the realisation of local projects. Against this backdrop, we introduce an inter- and transdisciplinary approach to identifying and evaluating different power-to-X paths as well as setting up robust local implementation projects, which account for existing drivers and potential hurdles early on. After developing the approach conceptually, we exemplify our elaborations by applying them to a use case in the German city of Wuppertal. It can be shown that a mix of several interlinked interdisciplinary methods as well as several participatory elements is suitable for triggering a collective, local innovation process. However, the timing and extent of end-user integration remain a balancing act. The paper does not focus on a detailed description of power-to-X (PtX) as a central pillar of the sustainable transformation of the energy system. Rather, it focuses on the innovative methodological approach used to select a suitable use path and design a corresponding business model. The research approach was successfully implemented in the specific case study. However, it also becomes clear that the local-specific consideration entails limitations with regard to the transferability of the research design to other spatial contexts.

Malaria is a blood disease caused by the Plasmodium parasites transmitted through the bite of female Anopheles mosquito. Microscopists commonly examine thick and thin blood smears to diagnose disease and compute parasitemia. However, their accuracy depends on smear quality and expertise in classifying and counting parasitized and uninfected cells. Such an examination could be arduous for large-scale diagnoses resulting in poor quality. State-of-the-art image-analysis based computer-aided diagnosis (CADx) methods using machine learning (ML) techniques, applied to microscopic images of the smears using hand-engineered features demand expertise in analyzing morphological, textural, and positional variations of the region of interest (ROI). In contrast, Convolutional Neural Networks (CNN), a class of deep learning (DL) models promise highly scalable and superior results with end-to-end feature extraction and classification. Automated malaria screening using DL techniques could, therefore, serve as an effective diagnostic aid. In this study, we evaluate the performance of pre-trained CNN based DL models as feature extractors toward classifying parasitized and uninfected cells to aid in improved disease screening. We experimentally determine the optimal model layers for feature extraction from the underlying data. Statistical validation of the results demonstrates the use of pre-trained CNNs as a promising tool for feature extraction for this purpose.

This paper argues in favor of a specific type of confidence for use in computer-aided diagnosis and disease classification, namely, sine/cosine values of angles represented by points on the unit circle. The paper shows how this confidence is motivated by Chinese medicine and how sine/cosine values are directly related with the two forces Yin and Yang. The angle for which sine and cosine are equal (45°) represents the state of equilibrium between Yin and Yang, which is a state of nonduality that indicates neither normality nor abnormality in terms of disease classification. The paper claims that the proposed confidence is intuitive and can be readily understood by physicians. The paper underpins this thesis with theoretical results in neural signal processing, stating that a sine/cosine relationship between the actual input signal and the perceived (learned) input is key to neural learning processes. As a practical example, the paper shows how to use the proposed confidence values to highlight manifestations of tuberculosis in frontal chest X-rays.