Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Accurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysis.

In Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society

Damage to cartilage is an important indicator of osteoarthritis progression, but manual extraction of cartilage morphology is time-consuming and prone to error. To address this, we hypothesize that automatic labeling of cartilage can be achieved through the comparison of contrasted and non-contrasted Computer Tomography (CT). However, this is non-trivial as the pre-clinical volumes are at arbitrary starting poses due to the lack of standardized acquisition protocols. Thus, we propose an annotation-free deep learning method, D-net, for accurate and automatic alignment of pre- and post-contrasted cartilage CT volumes. D-Net is based on a novel mutual attention network structure to capture large-range translation and full-range rotation without the need for a prior pose template. CT volumes of mice tibiae are used for validation, with synthetic transformation for training and tested with real pre- and post-contrasted CT volumes. Analysis of Variance (ANOVA) was used to compare the different network structures. Our proposed method, D-net, achieves a Dice coefficient of 0.87, and significantly outperforms other state-of-the-art deep learning models, in the real-world alignment of 50 pairs of pre- and post-contrasted CT volumes when cascaded as a multi-stage network.

Zheng Jian-Qing, Lim Ngee Han, Papież Bartłomiej W

2023-Feb-24

Deep learning, Image registration, Mutual attention, Tibiae CT

General General

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks.

In Computers in biology and medicine

Artificial Intelligence (AI) techniques of deep learning have revolutionized the disease diagnosis with their outstanding image classification performance. In spite of the outstanding results, the widespread adoption of these techniques in clinical practice is still taking place at a moderate pace. One of the major hindrance is that a trained Deep Neural Networks (DNN) model provides a prediction, but questions about why and how that prediction was made remain unanswered. This linkage is of utmost importance for the regulated healthcare domain to increase the trust in the automated diagnosis system by the practitioners, patients and other stakeholders. The application of deep learning for medical imaging has to be interpreted with caution due to the health and safety concerns similar to blame attribution in the case of an accident involving autonomous cars. The consequences of both a false positive and false negative cases are far reaching for patients' welfare and cannot be ignored. This is exacerbated by the fact that the state-of-the-art deep learning algorithms comprise of complex interconnected structures, millions of parameters, and a 'black box' nature, offering little understanding of their inner working unlike the traditional machine learning algorithms. Explainable AI (XAI) techniques help to understand model predictions which help develop trust in the system, accelerate the disease diagnosis, and meet adherence to regulatory requirements. This survey provides a comprehensive review of the promising field of XAI for biomedical imaging diagnostics. We also provide a categorization of the XAI techniques, discuss the open challenges, and provide future directions for XAI which would be of interest to clinicians, regulators and model developers.

Nazir Sajid, Dickson Diane M, Akram Muhammad Usman

2023-Feb-18

Backpropagation, Blackbox, Diagnostic imaging, Features, Interpretable AI, Neural networks, Predictive models, Supervised learning

General General

EchoEFNet: Multi-task deep learning network for automatic calculation of left ventricular ejection fraction in 2D echocardiography.

In Computers in biology and medicine

Left ventricular ejection fraction (LVEF) is essential for evaluating left ventricular systolic function. However, its clinical calculation requires the physician to interactively segment the left ventricle and obtain the mitral annulus and apical landmarks. This process is poorly reproducible and error prone. In this study, we propose a multi-task deep learning network EchoEFNet. The network use ResNet50 with dilated convolution as the backbone to extract high-dimensional features while maintaining spatial features. The branching network used our designed multi-scale feature fusion decoder to segment the left ventricle and detect landmarks simultaneously. The LVEF was then calculated automatically and accurately using the biplane Simpson's method. The model was tested for performance on the public dataset CAMUS and private dataset CMUEcho. The experimental results showed that the geometrical metrics and percentage of correct keypoints of EchoEFNet outperformed other deep learning methods. The correlation between the predicted LVEF and true values on the CAMUS and CMUEcho datasets was 0.854 and 0.916, respectively.

Li Honghe, Wang Yonghuai, Qu Mingjun, Cao Peng, Feng Chaolu, Yang Jinzhu

2023-Feb-24

Deep learning, Echocardiogram, Ejection fraction, Multitasking

General General

Spectroscopic measurement of the two-dimensional flame temperature based on a perovskite single photodetector.

In Optics express

Existing non-contact flame temperature measuring methods depend on complex, bulky and expensive optical instruments, which make it difficult for portable applications and high-density distributed networking monitoring. Here, we demonstrate a flame temperature imaging method based on a perovskite single photodetector. High-quality perovskite film epitaxy grows on the SiO2/Si substrate to fabricate the photodetector. Duo to the Si/MAPbBr3 heterojunction, the light detection wavelength is extended from 400 nm to 900 nm. Then, a perovskite single photodetector spectrometer has been developed using the deep-learning method for spectroscopic measurement of flame temperature. In the temperature test experiment, the spectral line of doping element K+ has been selected to measure the flame temperature. The photoresponsivity function of the wavelength was learned based on a commercial standard blackbody source. The spectral line of element K+ has been reconstructed using the photocurrents matrix by the regression solving photoresponsivity function. As a validation experiment, the "NUC" pattern is realized by scanning the perovskite single-pixel photodetector. Finally, the flame temperature of adulterated element K+ has been imaged with the error of 5%. It provides a way to develop high precision, portable, low-cost flame temperature imaging technology.

Wang Jia, Hao Xiaojian, Pan Baowu, Huang Xiaodong, Sun Haoliang, Pei Pan

2023-Feb-27

General General

Longwave infrared multispectral image sensor system using aluminum-germanium plasmonic filter arrays

ArXiv Preprint

A multispectral camera records image data in various wavelengths across the electromagnetic spectrum to acquire additional information that a conventional camera fails to capture. With the advent of high-resolution image sensors and colour filter technologies, multispectral imagers in the visible wavelengths have become popular with increasing commercial viability in the last decade. However, multispectral imaging in longwave infrared (LWIR: 8 to 14 microns) is still an emerging area due to the limited availability of optical materials, filter technologies, and high-resolution sensors. Images from LWIR multispectral cameras can capture emission spectra of objects to extract additional information that a human eye fails to capture and thus have important applications in precision agriculture, forestry, medicine, and object identification. In this work, we experimentally demonstrate an LWIR multispectral image sensor with three wavelength bands using optical elements made of an aluminum-based plasmonic filter array sandwiched in germanium. To realize the multispectral sensor, the filter arrays are then integrated into a 3D printed wheel stacked on a low-resolution monochrome thermal sensor. Our prototype device is calibrated using a blackbody and its thermal output has been enhanced with computer vision methods. By applying a state-of-the-art deep learning method, we have also reconstructed multispectral images to a better spatial resolution. Scientifically, our work demonstrates a versatile spectral thermography technique for detecting target signatures in the LWIR range and other advanced spectral analyses.

Noor E Karishma Shaik, Bryce Widdicombe, Dechuan Sun, Sam E John, Dongryeol Ryu, Ampalavanapillai Nirmalathas, Ranjith R Unnithan

2023-03-03

Public Health Public Health

Full-length 16S rRNA gene sequencing and machine learning reveal the bacterial composition of inhalable particles from two different breeding stages in a piggery.

In Ecotoxicology and environmental safety ; h5-index 67.0

Bacterial loading aggravates the harm of particulate matter (PM) to public health and ecological systems, especially in operations of concentrated animal production. This study aimed to explore the characteristics and influencing factors of bacterial components of inhalable particles at a piggery. The morphology and elemental composition of coarse particles (PM10, aerodynamic diameter ≤ 10 µm) and fine particles (PM2.5, aerodynamic diameter ≤ 2.5 µm) were analyzed. Full-length 16 S rRNA sequencing technology was used to identify bacterial components according to breeding stage, particle size, and diurnal rhythm. Machine learning (ML) algorithms were used to further explore the relationship between bacteria and the environment. The results showed that the morphology of particles in the piggery differed, and the morphologies of the suspected bacterial components were elliptical deposited particles. Full-length 16 S rRNA indicated that most of the airborne bacteria in the fattening and gestation houses were bacilli. The analysis of beta diversity and difference between samples showed that the relative abundance of some bacteria in PM2.5 was significantly higher than that in PM10 at the same pig house (P < 0.01). There were significant differences in the bacterial composition of inhalable particles between the fattening and gestation houses (P < 0.01). The aggregated boosted tree (ABT) model showed that PM2.5 had a great influence on airborne bacteria among air pollutants. Fast expectation-maximization microbial source tracking (FEAST) showed that feces was a major potential source of airborne bacteria in pig houses (contribution 52.64-80.58 %). These results will provide a scientific basis for exploring the potential risks of airborne bacteria in a piggery to human and animal health.

Peng Siyi, Luo Min, Long Dingbiao, Liu Zuohua, Tan Qiong, Huang Ping, Shen Jie, Pu Shihua

2023-Feb-28

Bacteria morphology, Full-length 16 S rRNA, Inhalable particles, Piggery, Potential source