Non-linear modifications enhance prediction of pathological response to pre-operative PD-1 blockade in lung cancer: A longitudinal hybrid radiological model.

Major pathologic remission (MPR, residual tumor <10%) is a promising clinical endpoint for prognosis analysis in patients with lung cancer receiving pre-operative PD-1 blockade therapy. Most of the current biomarkers for predicting MPR such as PD-L1 and tumor mutation burden (TMB) need to be obtained invasively. They cannot overcome the spatiotemporal heterogeneity or provide dynamic monitoring solutions. Radiomics and artificial intelligence (AI) models provide a practical tool enabling non-invasive follow-up observation of tumor structural information through high-throughput data analysis. Currently, AI-based models mainly focus on the single baseline scan or pipeline, namely sole radiomics or deep learning (DL). This work merged the delta-radiomics based on the slope of classic radiomics indexes within a time interval and the features extracted by deep networks from the subtraction between the baseline and follow-up images. The subtracted images describing the tumor changes were based on the transformation generated by registration. Stepwise optimization of components was performed by repeating experiments among various combinations of DL networks, registration methods, feature selection algorithms, and classifiers. The optimized model could predict MPR with a cross-validation AUC of 0.91 and an external validation AUC of 0.85. A core set of 27 features (eight classic radiomics, 15 delta-radiomics, one classic DL features, and three delta-DL features) was identified. The changes in delta-radiomics indexes during the treatment were fitted with mathematic models. The fitting results revealed that over half of the features were of non-linear dynamics. Therefore, non-linear modifications were made on eight features by replacing the original features with non-linear fitting parameters, and the modified model achieved an improved power. The dynamic hybrid model serves as a novel and promising tool to predict the response of lesions to PD-1 blockade, which implies the importance of introducing the non-linear dynamic effects and DL approaches to the original delta-radiomics in the future.

Improving the prediction of Spreading Through Air Spaces (STAS) in primary lung cancer with a dynamic dual-delta hybrid machine learning model: a multicenter cohort study.

BACKGROUND: Reliable pre-surgical prediction of spreading through air spaces (STAS) in primary lung cancer is essential for precision treatment and surgical decision-making. We aimed to develop and validate a dual-delta deep-learning and radiomics model based on pretreatment computed tomography (CT) image series to predict the STAS in patients with lung cancer. METHOD: Six hundred seventy-four patients with pre-surgery CT follow-up scans (with a minimum interval of two weeks) and primary lung cancer diagnosed by surgery were retrospectively recruited from three Chinese hospitals. The training cohort and internal validation cohort, comprising 509 and 76 patients respectively, were selected from Shanghai Chest Hospital; the external validation cohorts comprised 36 and 53 patients from two other centers, respectively. Four imaging signatures (classic radiomics features and deep learning [DL] features, delta-radiomics and delta-DL features) reflecting the STAS status were constructed from the pretreatment CT images by comprehensive methods including handcrafting, 3D views extraction, image registration and subtraction. A stepwise optimized three-step procedure, including feature extraction (by DL and time-base radiomics slope), feature selection (by reproducibility check and 45 selection algorithms), and classification (32 classifiers considered), was applied for signature building and methodology optimization. The interpretability of the proposed model was further assessed with Grad-CAM for DL-features and feature ranking for radiomics features. RESULTS: The dual-delta model showed satisfactory discrimination between STAS and non-STAS and yielded the areas under the receiver operating curve (AUCs) of 0.94 (95% CI, 0.92-0.96), 0.84 (95% CI, 0.82-0.86), and 0.84 (95% CI, 0.83-0.85) in the internal and two external validation cohorts, respectively, with interpretable core feature sets and feature maps. CONCLUSION: The coupling of delta-DL model with delta-radiomics features enriches information such as anisotropy of tumor growth and heterogeneous changes within the tumor during the radiological follow-up, which could provide valuable information for STAS prediction in primary lung cancer.

The multifaceted role of MUC1 in tumor therapy resistance.

Tumor therapeutic resistances are frequently linked to the recurrence and poor prognosis of cancers and have been a key bottleneck in clinical tumor treatment. Mucin1 (MUC1), a heterodimeric transmembrane glycoprotein, exhibits abnormally overexpression in a variety of human tumors and has been confirmed to be related to the formation of therapeutic resistance. In this review, the multifaceted roles of MUC1 in tumor therapy resistance are summarized from aspects of pan-cancer principles shared among therapies and individual mechanisms dependent on different therapies. Concretely, the common mechanisms of therapy resistance across cancers include interfering with gene expression, promoting genome instability, modifying tumor microenvironment, enhancing cancer heterogeneity and stemness, and activating evasion and metastasis. Moreover, the individual mechanisms of therapy resistance in chemotherapy, radiotherapy, and biotherapy are introduced. Last but not least, MUC1-involved therapy resistance in different types of cancers and MUC1-related clinical trials are summarized.

Hybrid ensemble model for differential diagnosis between COVID-19 and common viral pneumonia by chest X-ray radiograph.

BACKGROUND: Chest X-ray radiography (CXR) has been widely considered as an accessible, feasible, and convenient method to evaluate suspected patients' lung involvement during the COVID-19 pandemic. However, with the escalating number of suspected cases, traditional diagnosis via CXR fails to deliver results within a short period of time. Therefore, it is crucial to employ artificial intelligence (AI) to enhance CXRs for obtaining quick and accurate diagnoses. Previous studies have reported the feasibility of utilizing deep learning methods to screen for COVID-19 using CXR and CT results. However, these models only use a single deep learning network for chest radiograph detection; the accuracy of this approach required further improvement. METHODS: In this study, we propose a three-step hybrid ensemble model, including a feature extractor, a feature selector, and a classifier. First, a pre-trained AlexNet with an improved structure extracts the original image features. Then, the ReliefF algorithm is adopted to sort the extracted features, and a trial-and-error approach is used to select the n most important features to reduce the feature dimension. Finally, an SVM classifier provides classification results based on the n selected features. RESULTS: Compared to five existing models (InceptionV3: 97.916 ± 0.408%; SqueezeNet: 97.189 ± 0.526%; VGG19: 96.520 ± 1.220%; ResNet50: 97.476 ± 0.513%; ResNet101: 98.241 ± 0.209%), the proposed model demonstrated the best performance in terms of overall accuracy rate (98.642 ± 0.398%). Additionally, compared to the existing models, the proposed model demonstrates a considerable improvement in classification time efficiency (SqueezeNet: 6.602 ± 0.001s; InceptionV3: 12.376 ± 0.002s; ResNet50: 10.952 ± 0.001s; ResNet101: 18.040 ± 0.002s; VGG19: 16.632 ± 0.002s; proposed model: 5.917 ± 0.001s). CONCLUSION: The model proposed in this article is practical and effective, and can provide high-precision COVID-19 CXR detection. We demonstrated its suitability to aid medical professionals in distinguishing normal CXRs, viral pneumonia CXRs and COVID-19 CXRs efficiently on small sample sizes.

Nano-Carriers of Combination Tumor Physical Stimuli-Responsive Therapies.

With the development of nanotechnology, Tumor Physical Stimuli-Responsive Therapies (TPSRTs) have reached a new stage because of the remarkable characteristics of nanocarriers. The nanocarriers enable such therapies to overcome the drawbacks of traditional therapies, such as radiotherapy or chemotherapy. To further explore the possibility of the nanocarrier-assisted TPSRTs, scientists have combined different TPSRTs via; the platform of nanocarriers into combination TPSRTs, which include Photothermal Therapy (PTT) with Magnetic Hyperthermia Therapy (MHT), PTT with Sonodynamic Therapy (SDT), MHT with Photodynamic Therapy (PDT), and PDT with PTT. To achieve such therapies, it requires to fully utilize the versatile functions of a specific nanocarrier, which depend on a pellucid understanding of the traits of those nanocarriers. This review covers the principles of different TPSRTs and their combinations, summarizes various types of combination TPSRTs nanocarriers and their therapeutic effects on tumors, and discusses the current disadvantages and future developments of these nanocarriers in the application of combination TPSRTs.

A simple MWCNTs@paper biosensor for CA19-9 detection and its long-term preservation by vacuum freeze drying.

This paper introduces a cheap simple MWCNTs@paper biosensor for the detection of CA19-9, which is a biomarker of pancreatic cancer. By adding the CA19-9 antibody to the surface of MWCNTs which are deposited on the microporous filter paper, the correlation between the concentration of CA19-9 and resistance of biosensor element was linear due to the site-specific binding of antigen and antibody. The detection range is wide (0 U/mL-at least 1000 U/mL), and even in the low concentration of CA19-9, the linearity remains satisfying. Based on this property, it could be used for the detection of early-stage pancreatic cancer. Besides, this research originally introduces a vacuum freeze-drying method for the long-term preservation of biosensor, prolonging its storage time from 3 h to at least 7 days, which signifcantly promoted its value in practical application. One piece of the MWCNTs@paper biosensor only cost $2 (about 30 times cheaper than ELISA) approximately, and the detection speed is satisfying (2 h, 12 times faster than ELISA), which will possibly increase its opportunity of mass production and clinical practice.