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

Ophthalmology Ophthalmology

A quantitative study of the effect of ICL orientation selection on post-operative vault and model-assisted vault prediction.

In Frontiers in neurology

BACKGROUND : Appropriate vault height of implantable collamer lens (ICL) implantation matters for it has risks of corneal endothelial cell loss, cataract formation and intraocular pressure elevation, which could lead to irreversible damage to optic nerve. Therefore, pre-operative prediction for an ideal vault height is a hotspot. However, few data exist regarding quantitative effect of ICL orientation on vault height. This study is aimed to quantitatively investigate the effect of ICL implantation orientation on vault height, and built a machine-learning (ML)-based vault prediction model taking implantation orientation into account.

METHODS : 473 consecutive case series treated with ICL implantation were retrospectively analyzed (408 were horizontally implanted, and 65 were vertically implanted). Multivariable logistic regression analysis was performed to determine the association between ICL orientation and achieved vault. ML was performed to develop a new vault height prediction model taking ICL orientation into account. Receiver operating characteristic curve (ROC) and net reclassification index (NRI) were obtained to assess the prediction ability.

RESULTS : 95% of all the patients achieved 20/20 uncorrected distance visual acuity (UDVA) or better. No complications including cataract formation, dispersion or optic nerve injury were observed in any cases. Sex, sphere power, cylinder power, axis, ICL size and ICL orientation were all significant risk factors associated to vault height, and age was positively co-related. Of note, ICL size and ICL orientation were the top-ranking risk factors. Comparing to conventional horizontal implantation, vertical implantation could reduce the achieved vault by 81.187 μm (p < 0.001). In regarding to different ICL sizes, vertical implantation had no good to vault reduction when using ICL of 12.1 mm. However, it could reduce the vault by 59.351 μm and 160.992 μm respectively when ICL of 12.6mm and 13.2 mm were implanted (p = 0.0097 and p = 0.0124). For prediction of vault height, ML based model significantly outperformed traditional multivariable regression model.

CONCLUSION : We provide quantitative evidence that vertical implantation of ICL could effectively reduce the achieved vault height, especially when large size ICL was implanted, comparing to traditional horizontal implantation. ML is extremely applicable in development of vault prediction model.

Zhang Weijie, Li Fang, Li Lin, Zhang Jing

2023

ICL implantation orientation, machine-learning, myopia, optic nerve, vault height

oncology Oncology

Feasibility of a deep-learning based anatomical region labeling tool for Cone-Beam Computed Tomography scans in radiotherapy.

In Physics and imaging in radiation oncology

BACKGROUND AND PURPOSE : Currently, there is no robust indicator within the Cone-Beam Computed Tomography (CBCT) DICOM headers as to which anatomical region is present on the scan. This can be a predicament to CBCT-based algorithms trained on specific body regions, such as auto-segmentation and radiomics tools used in the radiotherapy workflow. We propose an anatomical region labeling (ARL) algorithm to classify CBCT scans into four distinct regions: head & neck, thoracic-abdominal, pelvis, and extremity.

MATERIALS AND METHODS : Algorithm training and testing was performed on 3,802 CBCT scans from 596 patients treated at our radiotherapy center. The ARL model, which consists of a convolutional neural network, makes use of a single CBCT coronal slice to output a probability of occurrence for each of the four classes. ARL was evaluated on the test dataset composed of 1,090 scans and compared to a support vector machine (SVM) model. ARL was also used to label CBCT treatment scans for 22 consecutive days as part of a proof-of-concept implementation. A validation study was performed on the first 100 unique patient scans to evaluate the functionality of the tool in the clinical setting.

RESULTS : ARL achieved an overall accuracy of 99.2% on the test dataset, outperforming the SVM (91.5% accuracy). Our validation study has shown strong agreement between the human annotations and ARL predictions, with accuracies of 99.0% for all four regions.

CONCLUSION : The high classification accuracy demonstrated by ARL suggests that it may be employed as a pre-processing step for site-specific, CBCT-based radiotherapy tools.

Luximon Dishane C, Neylon John, Lamb James M

2023-Jan

Anatomy labeling, Cone-beam computed tomography, Deep learning, Radiotherapy

Public Health Public Health

Mechanisms influencing the factors of urban built environments and coronavirus disease 2019 at macroscopic and microscopic scales: The role of cities.

In Frontiers in public health

In late 2019, the coronavirus disease 2019 (COVID-19) pandemic soundlessly slinked in and swept the world, exerting a tremendous impact on lifestyles. This study investigated changes in the infection rates of COVID-19 and the urban built environment in 45 areas in Manhattan, New York, and the relationship between the factors of the urban built environment and COVID-19. COVID-19 was used as the outcome variable, which represents the situation under normal conditions vs. non-pharmacological intervention (NPI), to analyze the macroscopic (macro) and microscopic (micro) factors of the urban built environment. Computer vision was introduced to quantify the material space of urban places from street-level panoramic images of the urban streetscape. The study then extracted the microscopic factors of the urban built environment. The micro factors were composed of two parts. The first was the urban level, which was composed of urban buildings, Panoramic View Green View Index, roads, the sky, and buildings (walls). The second was the streets' green structure, which consisted of macrophanerophyte, bush, and grass. The macro factors comprised population density, traffic, and points of interest. This study analyzed correlations from multiple levels using linear regression models. It also effectively explored the relationship between the urban built environment and COVID-19 transmission and the mechanism of its influence from multiple perspectives.

Zhang Longhao, Han Xin, Wu Jun, Wang Lei

2023

COVID-19, computer vision, deep learning, relevance, street view images, urban built environment

Radiology Radiology

Computed tomography-based COVID-19 triage through a deep neural network using mask-weighted global average pooling.

In Frontiers in cellular and infection microbiology ; h5-index 53.0

BACKGROUND : There is an urgent need to find an effective and accurate method for triaging coronavirus disease 2019 (COVID-19) patients from millions or billions of people. Therefore, this study aimed to develop a novel deep-learning approach for COVID-19 triage based on chest computed tomography (CT) images, including normal, pneumonia, and COVID-19 cases.

METHODS : A total of 2,809 chest CT scans (1,105 COVID-19, 854 normal, and 850 non-3COVID-19 pneumonia cases) were acquired for this study and classified into the training set (n = 2,329) and test set (n = 480). A U-net-based convolutional neural network was used for lung segmentation, and a mask-weighted global average pooling (GAP) method was proposed for the deep neural network to improve the performance of COVID-19 classification between COVID-19 and normal or common pneumonia cases.

RESULTS : The results for lung segmentation reached a dice value of 96.5% on 30 independent CT scans. The performance of the mask-weighted GAP method achieved the COVID-19 triage with a sensitivity of 96.5% and specificity of 87.8% using the testing dataset. The mask-weighted GAP method demonstrated 0.9% and 2% improvements in sensitivity and specificity, respectively, compared with the normal GAP. In addition, fusion images between the CT images and the highlighted area from the deep learning model using the Grad-CAM method, indicating the lesion region detected using the deep learning method, were drawn and could also be confirmed by radiologists.

CONCLUSIONS : This study proposed a mask-weighted GAP-based deep learning method and obtained promising results for COVID-19 triage based on chest CT images. Furthermore, it can be considered a convenient tool to assist doctors in diagnosing COVID-19.

Zhang Hong-Tao, Sun Ze-Yu, Zhou Juan, Gao Shen, Dong Jing-Hui, Liu Yuan, Bai Xu, Ma Jin-Lin, Li Ming, Li Guang, Cai Jian-Ming, Sheng Fu-Geng

2023

artificial intelligence, computed tomography (CT), coronavirus disease 2019 (COVID-19), deep learning, global average pooling (GAP)

General General

Dynamic Healthcare Embeddings for Improving Patient Care

ArXiv Preprint

As hospitals move towards automating and integrating their computing systems, more fine-grained hospital operations data are becoming available. These data include hospital architectural drawings, logs of interactions between patients and healthcare professionals, prescription data, procedures data, and data on patient admission, discharge, and transfers. This has opened up many fascinating avenues for healthcare-related prediction tasks for improving patient care. However, in order to leverage off-the-shelf machine learning software for these tasks, one needs to learn structured representations of entities involved from heterogeneous, dynamic data streams. Here, we propose DECENT, an auto-encoding heterogeneous co-evolving dynamic neural network, for learning heterogeneous dynamic embeddings of patients, doctors, rooms, and medications from diverse data streams. These embeddings capture similarities among doctors, rooms, patients, and medications based on static attributes and dynamic interactions. DECENT enables several applications in healthcare prediction, such as predicting mortality risk and case severity of patients, adverse events (e.g., transfer back into an intensive care unit), and future healthcare-associated infections. The results of using the learned patient embeddings in predictive modeling show that DECENT has a gain of up to 48.1% on the mortality risk prediction task, 12.6% on the case severity prediction task, 6.4% on the medical intensive care unit transfer task, and 3.8% on the Clostridioides difficile (C.diff) Infection (CDI) prediction task over the state-of-the-art baselines. In addition, case studies on the learned doctor, medication, and room embeddings show that our approach learns meaningful and interpretable embeddings.

Hankyu Jang, Sulyun Lee, D. M. Hasibul Hasan, Philip M. Polgreen, Sriram V. Pemmaraju, Bijaya Adhikari

2023-03-21

General General

Diagnosis and prognosis prediction model for digestive system tumors based on immunologic gene sets.

In Frontiers in oncology

According to 2020 global cancer statistics, digestive system tumors (DST) are ranked first in both incidence and mortality. This study systematically investigated the immunologic gene set (IGS) to discover effective diagnostic and prognostic biomarkers. Gene set variation (GSVA) analysis was used to calculate enrichment scores for 4,872 IGSs in patients with digestive system tumors. Using the machine learning algorithm XGBoost to build a classifier that distinguishes between normal samples and cancer samples, it shows high specificity and sensitivity on both the validation set and the overall dataset (area under the receptor operating characteristic curve [AUC]: validation set = 0.993, overall dataset = 0.999). IGS-based digestive system tumor subtypes (IGTS) were constructed using a consistent clustering approach. A risk prediction model was developed using the Least Absolute Shrinkage and Selection Operator (LASSO) method. DST is divided into three subtypes: subtype 1 has the best prognosis, subtype 3 is the second, and subtype 2 is the worst. The prognosis model constructed using nine gene sets can effectively predict prognosis. Prognostic models were significantly associated with tumor mutational burden (TMB), tumor immune microenvironment (TIME), immune checkpoints, and somatic mutations. A composite nomogram was constructed based on the risk score and the patient's clinical information, with a well-fitted calibration curve (AUC = 0.762). We further confirmed the reliability and validity of the diagnostic and prognostic models using other cohorts from the Gene Expression Omnibus database. We identified diagnostic and prognostic models based on IGS that provide a strong basis for early diagnosis and effective treatment of digestive system tumors.

Zhou Lin, Wang Chunyu

2023

XGBoost, diagnostic, digestive system tumors, immunologic gene set, prognostic