Lung Nodule Sizes Are Encoded When Scaling CT Image for CNN's

Impact of intelligent convolutional neural network -based algorithms on head computed tomography evaluation and comprehensive rehabilitation acupuncture therapy for patients with cerebral infarction

This work was to evaluate the impacts of comprehensive rehabilitation acupuncture therapy on the recovery of neurological function in cerebral infarction (CI) patients and to utilize convolutional neural network (CNN) intelligent algorithms to optimize head computed tomography (CT) images and improve lesion localization accuracy. 98 CI patients were divided into a control group (Ctrl group) and an experimental group (Exp group), with 48 patients in each group. The patients in the Ctrl group received CT evaluation combined with comprehensive rehabilitation acupuncture therapy. While, those in the Exp group received CT evaluation with the use of CNN algorithms for optimization, along with comprehensive rehabilitation acupuncture therapy. Acupuncture therapy included selecting acupoints on the patient's head, selecting two horizontal needling needles from top to bottom at the acupoints on the front side of the lesion, and then horizontal needling along the top midline. The differences in treatment outcomes were compared between the two groups based on Fugl-Meyer upper limb assessment (FMA) scores, Barthel Index (BI) scores, National Institutes of Health Stroke Scale (NIHSS4) scores, Modified Edinburgh-Scandinavian Stroke Scale (MESSS) scores, and hemodynamics. Simultaneously, the CT images were optimized using CNN intelligent algorithms to improve image quality and lesion localization accuracy. The results showed that the CI CT images processed by the CNN-based intelligent algorithm showed significant improvements in clarity and contrast compared to conventional CT images. The CNN-based intelligent algorithm demonstrated higher sensitivity (97.5 %, 93.8 %), higher PSNR (30.14 dB, 24.72 dB), and lower missed detection rate (0.52 %, 1.88 %) in detecting CI lesions. The total effective rate in the Exp group was 95.83 %, which was significantly higher than the 85.42 % in the Ctrl group (P < 0.05). The Exp group showed significantly higher levels in FMA and BI scores (P < 0.05). After treatment, the NIHSS4 and MESSS scores in the Exp group were lower than those in the Ctrl group (P < 0.05). Additionally, post-treatment, the plasma concentrations and whole-blood viscosity (low shear and high shear) in the Exp group were lower than those in the Ctrl group, and the plasma concentration and whole-blood viscosity (high shear) were also lower than those in the Ctrl group (P < 0.05). In conclusion, comprehensive rehabilitation acupuncture therapy had a positive impact on the recovery of neurological function in CI patients. By applying CNN-based intelligent algorithms to optimize head CT images, lesion localization accuracy can be improved, thereby guiding rehabilitation treatment more effectively.

Discovery of a Generalization Gap of Convolutional Neural Networks on COVID-19 X-Rays Classification

A number of recent papers have shown experimental evidence that suggests it is possible to build highly accurate deep neural network models to detect COVID-19 from chest X-ray images. In this paper, we show that good generalization to unseen sources has not been achieved. Experiments with richer data sets than have previously been used show models have high accuracy on seen sources, but poor accuracy on unseen sources. The reason for the disparity is that the convolutional neural network model, which learns features, can focus on differences in X-ray machines or in positioning within the machines, for example. Any feature that a person would clearly rule out is called a confounding feature. Some of the models were trained on COVID-19 image data taken from publications, which may be different than raw images. Some data sets were of pediatric cases with pneumonia where COVID-19 chest X-rays are almost exclusively from adults, so lung size becomes a spurious feature that can be exploited. In this work, we have eliminated many confounding features by working with as close to raw data as possible. Still, deep learned models may leverage source specific confounders to differentiate COVID-19 from pneumonia preventing generalizing to new data sources (i.e. external sites). Our models have achieved an AUC of 1.00 on seen data sources but in the worst case only scored an AUC of 0.38 on unseen ones. This indicates that such models need further assessment/development before they can be broadly clinically deployed. An example of fine-tuning to improve performance at a new site is given.

Quantitative Imaging Enters the Clinical Arena: A Personal Viewpoint

The National Cancer Institute's Quantitative Imaging Network (QIN) has thrived over the past 12 years with an emphasis on the development of image-based decision support software tools for improving measurements of imaging metrics. An overarching goal has been to develop advanced tools that could be translated into clinical trials to provide for improved prediction of response to therapeutic interventions. This article provides an overview of the successes in development and translation of new algorithms into the clinical workflow by the many research teams of the Quantitative Imaging Network.