Better knowledge of the dose-toxicity relationship is essential for safe dose escalation to improve local control in cervical cancer radiotherapy. The conventional dose-toxicity model is based on the dose volume histogram, which is the parameter lacking spatial dose information. To overcome this limit, we explore a comprehensive rectal dose-toxicity model based on both dose volume histogram and dose map features for accurate radiation toxicity prediction. Forty-two cervical cancer patients treated with combined external beam radiotherapy (EBRT) and brachytherapy (BT) were retrospectively studied, including 12 with Grade ≥ 2 rectum toxicity and 30 patients with Grade 0–1 toxicity (non-toxicity patients). The cumulative equivalent 2-Gy rectal surface dose was deformably summed using the deformation vector fields obtained through a recent developed local topology preserved non-rigid point matching algorithm. The cumulative three-dimensional (3D) dose was flattened and mapped to a two-dimensional (2D) plane to obtain the rectum surface dose map (RSDM). The dose volume parameters (DVPs) were calculated from the 3D rectum surface, while the texture features and the dose geometric parameters (DGPs) were extracted from the 2D RSDM. Representative features further computed from DVPs, textures and DGPs by principle component analysis (PCA) and statistical analysis were respectively fed into a support vector machine equipped with a sequential feature selection procedure. The predictive powers of the representative features were compared with the GEC-ESTRO dosimetric parameters D0.1/1/2cm3. Satisfactory predictive accuracy of sensitivity 74.75 and 84.75%, specificity 72.67 and 79.87%, and area under the receiver operating characteristic curve (AUC) 0.82 and 0.91 were respectively achieved by the PCA features and statistical significant features, which were superior to the D0.1/1/2cm3 (AUC 0.71). The relative area in dose levels of 64Gy, 67Gy, 68Gy, 87Gy, 88Gy and 89Gy, perimeters in dose levels of 89Gy, as well as two texture features were ranked as the important factors that were closely correlated with rectal toxicity. Our extensive experimental results have demonstrated the feasibility of the proposed scheme. A future large patient cohort study is still needed for model validation.

The aim of this work is to develop a novel recursive ensemble OARs segmentation (REOS) framework for accurate organs-at-risk (OARs) automatic segmentation. The REOS recursively segment individual OARs by ensembling images features extracted from an organ localization module and a contour detection module. Both modules are based on a 3D U-Net architecture. The organ localization module is trained for rough segmentation to localize a region of interest (ROI) that encompasses the to-be-delineated OAR, while the contour detection module is trained to segment the OAR within the identified ROI. In this study, the developed REOS framework is applied for brain radiotherapy on segmenting six OARs including the eyes, the brainstem (BS), the optical nerves and the chiasm. Eighty T1-weighted magnetic resonance images (MRI) from 80 brain cancer patients’ cases with OARs’ gold standard contours were collected for training and testing REOS. On 20 testing cases, the REOS achieve a high segmentation accuracy with Dice similarity coefficient (DSC) mean and standard deviation of 93.9% ± 1.4%, 94.5% ± 2.0%, 90.6% ± 2.7%, on the left and right eyes and the BS, respectively. On small and segmentation-challenging organs, the left and right optical nerves and the chiasm, the REOS achieves DSC of 78.0% ± 10.5%, 82.2% ± 5.9% and 71.1% ± 9.1%. The satisfactory performances demonstrated the effectiveness of the REOS in OARs segmentation.

Background: Diagnostics for pulmonary tuberculosis (PTB) are usually inaccurate, expensive, or complicated. The breathomics-based method may be an attractive option for fast and noninvasive PTB detection. Method: Exhaled breath samples were collected from 518 PTB patients and 887 controls and tested on the real-time high-pressure photon ionization time-of-flight mass spectrometer. Machine learning algorithms were employed for breathomics analysis and PTB detection mode, whose performance was evaluated in 430 blinded clinical patients. Results: The breathomics-based PTB detection model achieved an accuracy of 92.6%, a sensitivity of 91.7%, a specificity of 93.0%, and an AUC of 0.975 in the blinded test set (n = 430). Age, sex, and anti-tuberculosis treatment does not significantly impact PTB detection performance. In distinguishing PTB from other pulmonary diseases (n = 182), the VOC modes also achieve good performance with an accuracy of 91.2%, a sensitivity of 91.7%, a specificity of 88.0%, and an AUC of 0.961. Conclusions: The simple and noninvasive breathomics-based PTB detection method was demonstrated with high sensitivity and specificity, potentially valuable for clinical PTB screening and diagnosis.

Chronic obstructive pulmonary disease (COPD) and asthma are the most common chronic respiratory diseases. In middle-aged and elderly patients, it is difficult to distinguish between COPD and asthma based on clinical symptoms and pulmonary function examinations in clinical practice. Thus, an accurate and reliable inspection method is required. In this study, we aimed to identify breath biomarkers and evaluate the accuracy of breathomics-based methods for discriminating between COPD and asthma. In this multi-center cross-sectional study, exhaled breath samples were collected from 89 patients with COPD and 73 with asthma and detected on a high-pressure photon ionization time-of-flight mass spectrometry (HPPI-TOFMS) platform from 20 October 2022, to 20 May 2023, in four hospitals. Data analysis was performed from 15 June 2023 to 16 August 2023. The sensitivity, specificity, and accuracy were calculated to assess the overall performance of the volatile organic component (VOC)-based COPD and asthma discrimination models. Potential VOC markers related to COPD and asthma were also analyzed. The age of all participants ranged from to 18–86 years, and 54 (33.3%) were men. The age [median (minimum, maximum)] of COPD and asthma participants were 66.0 (46.0, 86.0), and 44.0 (17.0, 80.0). The male and female ratio of COPD and asthma participants were 14/75 and 40/33, respectively. Based on breathomics feature selection, ten VOCs were identified as COPD and asthma discrimination biomarkers via breath testing. The joint panel of these ten VOCs achieved an area under the curve of 0.843, sensitivity of 75.9%, specificity of 87.5%, and accuracy of 80.0% in COPD and asthma discrimination. Furthermore, the VOCs detected in the breath samples were closely related to the clinical characteristics of COPD and asthma. The VOC-based COPD and asthma discrimination model showed good accuracy, providing a new strategy for clinical diagnosis. Breathomics-based methods may play an important role in the diagnosis of COPD and asthma.

Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has caused a tremendous threat to global health. polymerase chain reaction (PCR) and antigen testing have played a prominent role in the detection of SARS-CoV-2-infected individuals and disease control. An efficient, reliable detection tool is still urgently needed to halt the global COVID-19 pandemic. Recently, the food and drug administration (FDA) emergency approved volatile organic component (VOC) as an alternative test for COVID-19 detection. In this case-control study, we prospectively and consecutively recruited 95 confirmed COVID-19 patients and 106 healthy controls in the designated hospital for treatment of COVID-19 patients in Shenzhen, China. Exhaled breath samples were collected and stored in customized bags and then detected by high-pressure photon ionization time-of-flight mass spectrometry for VOCs. Machine learning algorithms were employed for COVID-19 detection model construction. Participants were randomly assigned in a 5:2:3 ratio to the training, validation, and blinded test sets. The sensitivity (SEN), specificity (SPE), and other general metrics were employed for the VOCs based COVID-19 detection model performance evaluation. The VOCs based COVID-19 detection model achieved good performance, with a SEN of 92.2% (95% CI: 83.8%, 95.6%), a SPE of 86.1% (95% CI: 74.8%, 97.4%) on blinded test set. Five potential VOC ions related to COVID-19 infection were discovered, which are significantly different between COVID-19 infected patients and controls. This study evaluated a simple, fast, non-invasive VOCs-based COVID-19 detection method and demonstrated that it has good sensitivity and specificity in distinguishing COVID-19 infected patients from controls. It has great potential for fast and accurate COVID-19 detection.

Through a nested cohort study, we evaluated the diagnostic performance of breath-omics in differentiating between benign and malignant breast lesions, and assessed the diagnostic performance of a multi-omics approach that combines breath-omics, ultrasound radiomics, and clinic-omics in distinguishing between benign and malignant breast lesions. We recruited 1,723 consecutive patients who underwent an automated breast volume scanner (ABVS) examination. Breath samples were collected and analyzed by high-pressure photon ionization time-of-flight mass spectrometry (HPPI-TOF-MS) to obtain breath-omics features. 238 of 1,723 enrolled participants have received pathological confirmation of breast nodules finally. The breast lesions of the 238 participants were contoured manually based on ABVS images for ultrasound radiomics feature calculation. Then, single- and multi-omics models were constructed and evaluated for breast nodules diagnosis via five-fold cross-validation. The area under the curve (AUC) of the breath-omics model was 0.855. In comparison, the multi-omics model demonstrated superior diagnostic performance for breast cancer, with sensitivity, specificity, and AUC of 84.1 %, 89.9 %, and 0.946, respectively. The multi-omics performance was comparable to that of the Breast Imaging Reporting and Data System (BI-RADS) classification via senior ultrasound physician evaluation. The multi-omics approach combining metabolites in exhaled breath, ultrasound imaging, and basic clinical information exhibits superior diagnostic performance and promises to be a non-invasive and reliable tool for breast cancer diagnosis.