Explainable cancer factors discovery: Shapley additive explanation for machine learning models demonstrates the best practices in the case of pancreatic cancer

Pancreatic cancer is one of digestive tract cancers with high mortality rate. Despite the wide range of available treatments and improvements in surgery, chemotherapy, and radiation therapy, the five-year prognosis for individuals diagnosed pancreatic cancer remains poor. There is still research to be done to see if immunotherapy may be used to treat pancreatic cancer. The goals of our research were to comprehend the tumor microenvironment of pancreatic cancer, found a useful biomarker to assess the prognosis of patients, and investigated its biological relevance. In this paper, machine learning methods such as random forest were fused with weighted gene co-expression networks for screening hub immune-related genes (hub-IRGs). LASSO regression model was used to further work. Thus, we got eight hub-IRGs. Based on hub-IRGs, we created a prognosis risk prediction model for PAAD that can stratify accurately and produce a prognostic risk score (IRG_Score) for each patient. In the raw data set and the validation data set, the five-year area under the curve (AUC) for this model was 0.9 and 0.7, respectively. And shapley additive explanation (SHAP) portrayed the importance of prognostic risk prediction influencing factors from a machine learning perspective to obtain the most influential certain gene (or clinical factor). The five most important factors were TRIM67, CORT, PSPN, SCAMP5, RFXAP, all of which are genes. In summary, the eight hub-IRGs had accurate risk prediction performance and biological significance, which was validated in other cancers. The result of SHAP helped to understand the molecular mechanism of pancreatic cancer.

Lightweight Attentive Graph Neural Network with Conditional Random Field for Diagnosis of Anterior Cruciate Ligament Tear

Anterior cruciate ligament (ACL) tears are prevalent orthopedic sports injuries and are difficult to precisely classify. Previous works have demonstrated the ability of deep learning (DL) to provide support for clinicians in ACL tear classification scenarios, but it requires a large quantity of labeled samples and incurs a high computational expense. This study aims to overcome the challenges brought by small and imbalanced data and achieve fast and accurate ACL tear classification based on magnetic resonance imaging (MRI) of the knee. We propose a lightweight attentive graph neural network (GNN) with a conditional random field (CRF), named the ACGNN, to classify ACL ruptures in knee MR images. A metric-based meta-learning strategy is introduced to conduct independent testing through multiple node classification tasks. We design a lightweight feature embedding network using a feature-based knowledge distillation method to extract features from the given images. Then, GNN layers are used to find the dependencies between samples and complete the classification process. The CRF is incorporated into each GNN layer to refine the affinities. To mitigate oversmoothing and overfitting issues, we apply self-boosting attention, node attention, and memory attention for graph initialization, node updating, and correlation across graph layers, respectively. Experiments demonstrated that our model provided excellent performance on both oblique coronal data and sagittal data with accuracies of 92.94% and 91.92%, respectively. Notably, our proposed method exhibited comparable performance to that of orthopedic surgeons during an internal clinical validation. This work shows the potential of our method to advance ACL diagnosis and facilitates the development of computer-aided diagnosis methods for use in clinical practice.

A Digital Mask-Voiceprint System for Postpandemic Surveillance and Tracing Based on the STRONG Strategy

Lockdowns and border closures due to COVID-19 imposed mental, social, and financial hardships in many societies. Living with the virus and resuming normal life are increasingly being advocated due to decreasing virus severity and widespread vaccine coverage. However, current trends indicate a continued absence of effective contingency plans to stop the next more virulent variant of the pandemic. The COVID-19-related mask waste crisis has also caused serious environmental problems and virus spreads. It is timely and important to consider how to precisely implement surveillance for the dynamic clearance of COVID-19 and how to efficiently manage discarded masks to minimize disease transmission and environmental hazards. In this viewpoint, we sought to address this issue by proposing an appropriate strategy for intelligent surveillance of infected cases and centralized management of mask waste. Such an intelligent strategy against COVID-19, consisting of wearable mask sample collectors (masklect) and voiceprints and based on the STRONG (Spatiotemporal Reporting Over Network and GPS) strategy, could enable the resumption of social activities and economic recovery and ensure a safe public health environment sustainably.

Evaluation of drug sensitivity, immunological characteristics, and prognosis in melanoma patients using an endoplasmic reticulum stress-associated signature based on bioinformatics and pan-cancer analysis

We aimed to develop endoplasmic reticulum (ER) stress-related risk signature to predict the prognosis of melanoma and elucidate the immune characteristics and benefit of immunotherapy in ER-related risk score-defined subgroups of melanoma based on a machine learning algorithm. Based on The Cancer Genome Atlas (TCGA) melanoma dataset (n = 471) and GTEx database (n = 813), 365 differentially expressed ER-associated genes were selected using the univariate Cox model and LASSO penalty Cox model. Ten genes impacting OS were identified to construct an ER-related signature by using the multivariate Cox regression method and validated with the Gene Expression Omnibus (GEO) dataset. Thereafter, the immune features, CNV, methylation, drug sensitivity, and the clinical benefit of anticancer immune checkpoint inhibitor (ICI) therapy in risk score subgroups, were analyzed. We further validated the gene signature using pan-cancer analysis by comparing it to other tumor types. The ER-related risk score was constructed based on the ARNTL, AGO1, TXN, SORL1, CHD7, EGFR, KIT, HLA-DRB1 KCNA2, and EDNRB genes. The high ER stress-related risk score group patients had a poorer overall survival (OS) than the low-risk score group patients, consistent with the results in the GEO cohort. The combined results suggested that a high ER stress-related risk score was associated with cell adhesion, gamma phagocytosis, cation transport, cell surface cell adhesion, KRAS signalling, CD4 T cells, M1 macrophages, naive B cells, natural killer (NK) cells, and eosinophils and less benefitted from ICI therapy. Based on the expression patterns of ER stress-related genes, we created an appropriate predictive model, which can also help distinguish the immune characteristics, CNV, methylation, and the clinical benefit of ICI therapy. KEY MESSAGES: Melanoma is the cutaneous tumor with a high degree of malignancy, the highest fatality rate, and extremely poor prognosis. Model usefulness should be considered when using models that contained more features. We constructed the Endoplasmic Reticulum stress-associated signature using TCGA and GEO database based on machine learning algorithm. ER stress-associated signature has excellent ability for predicting prognosis for melanoma.

Development and validation of ferroptosis-related lncRNA signature and immune-related gene signature for predicting the prognosis of cutaneous melanoma patients

Ferroptosis, a form of cell death caused by iron-dependent peroxidation of lipids, plays an important role in cancer. Recent studies have shown that long noncoding RNAs (lncRNAs) are involved in the regulation of ferroptosis in tumor cells and are also closely related to tumor immunity. Immune cell infiltration in the tumor microenvironment affects the prognosis and clinical outcome of immunotherapy in melanoma patients, and immune cell classification may be able to accurately predict the prognosis of melanoma patients. However, the prognostic value of ferroptosis-related lncRNAs (FRLs) in melanoma has not been thoroughly explored, and it is difficult to define the immune characteristics of melanoma. We used The Cancer Genome Atlas (TCGA), the Genotype-Tissue Expression (GTEx) database, and the FerrDb database to identify FRLs. FRLs with prognostic value were evaluated in an experimental cohort utilizing univariate, LASSO (least absolute shrinkage and selection operator) and multivariate Cox regression, followed by in vitro assays evaluating the expression levels and the biological functions of three candidate FRLs. Kaplan-Meier (K-M) and receiver operating characteristic (ROC) curve analyses were used to assess the validity of the risk model, and the drug sensitivity of FRLs was examined by drug sensitivity analysis. The differentially expressed genes between the high- and low-risk groups in the risk model were enriched in the immune pathway, and we further found immune gene signatures (IRGs) that could predict the prognosis of melanoma patients through a series of methods including single-sample Gene Set Enrichment Analysis (ssGSEA). Finally, two GEO cohorts were used to validate the predictive accuracy and reliability of these two signature models. Our findings suggest that FRLs and IRGs have the potential to predict the prognosis of patients with cutaneous melanoma.

A novel Cuprotosis-related signature predicts the prognosis and selects personal treatments for melanoma based on bioinformatics analysis

Background

Melanoma is a common and aggressive cutaneous malignancy characterized by poor prognosis and a high fatality rate. Recently, due to the application of Immune-checkpoint inhibitors (ICI) in melanoma treatment, melanoma patients' prognosis has been tremendously improved. However, the treatment effect varies quite differently from patient to patient. In this study, we aim to construct and validate a Cuproptosis-related risk model to improve outcome prediction of ICIs in melanoma and divide patients into subtypes with different Cuproptosis-related genes.

Methods

Here, according to differentially expressed genes from four melanoma datasets in GEO (Gene Expression Omnibus), and one in TCGA (The Cancer Genome Atlas) database, a novel signature was developed through LASSO and Cox regression analysis. We used 781 melanoma samples to examine the molecular subtypes associated with Cuproptosis-related genes and studied the related gene mutation and TME cell infiltration. Patients with melanoma can be divided into at least three subtypes based on gene expression profile. Survival pan-cancer analysis was also conducted for melanoma patients.

Results

The Cuproptosis risk score can predict tumor immunity, subtype, survival, and drug sensitivity for melanoma. And Cuproptosis-associated subtypes can help predict therapeutic outcomes.

Conclusion

Cuproptosis risk score is a promising potential biomarker in cancer diagnosis, molecular subtypes determination, TME cell infiltration characteristics, and therapy response prediction in melanoma patients.

A cell phone app for facial acne severity assessment

Acne vulgaris, the most common skin disease, can cause substantial economic and psychological impacts to the people it affects, and its accurate grading plays a crucial role in the treatment of patients. In this paper, we firstly proposed an acne grading criterion that considers lesion classifications and a metric for producing accurate severity ratings. Due to similar appearance of acne lesions with comparable severities and difficult-to-count lesions, severity assessment is a challenging task. We cropped facial skin images of several lesion patches and then addressed the acne lesion with a lightweight acne regular network (Acne-RegNet). Acne-RegNet was built by using a median filter and histogram equalization to improve image quality, a channel attention mechanism to boost the representational power of network, a region-based focal loss to handle classification imbalances and a model pruning and feature-based knowledge distillation to reduce model size. After the application of Acne-RegNet, the severity score is calculated, and the acne grading is further optimized by the metadata of the patients. The entire acne assessment procedure was deployed to a mobile device, and a phone app was designed. Compared with state-of-the-art lightweight models, the proposed Acne-RegNet significantly improves the accuracy of lesion classifications. The acne app demonstrated promising results in severity assessments (accuracy: 94.56%) and showed a dermatologist-level diagnosis on the internal clinical dataset.The proposed acne app could be a useful adjunct to assess acne severity in clinical practice and it enables anyone with a smartphone to immediately assess acne, anywhere and anytime.

Identification and Validation of Three Autophagy-Related Long Noncoding RNAs as Prognostic Signature in Cholangiocarcinoma

Cholangiocarcinoma (CCA) is featured by common occurrence and poor prognosis. Autophagy is a biological process that has been extensively involved in the progression of tumors. Long noncoding RNAs (lncRNAs) have been discovered to be critical in diagnosing and predicting various tumors. It may be valuable to elaborate autophagy-related lncRNAs (ARlncRNAs) in CCA, and indeed, there are still few studies concerning the role of ARlncRNAs in CCA. Here, a prognostic ARlncRNA signature was constructed to predict the survival outcome of CCA patients. Through identification, three differentially expressed ARlncRNAs (DEARlncRNAs), including CHRM3.AS2, MIR205HG, and LINC00661, were screened and were considered predictive signatures. Furthermore, the overall survival (OS) of patients with high-risk scores was significantly lower than that of patients with low scores. Interestingly, the risk score was an independent factor for the OS of patients with CCA. Moreover, receiver operating characteristic (ROC) curve analysis showed that the screened and constructed prognosis signature for 1 year (AUC = 0.884), 3 years (AUC =0.759), and 5 years (AUC = 0.788) presented a high score of accuracy in predicting OS of CCA patients. Gene set enrichment analysis (GSEA) revealed that the three DEARlncRNAs were significantly enriched in CCA-related signaling pathways, including “pathways of basal cell carcinoma”, “glycerolipid metabolism”, etc. Quantitative real-time PCR (qRT-PCR) showed that expressions of CHRM3.AS2, MIR205HG, and LINC00661 were higher in CCA tissues than those in normal tissues, similar to the trends detected in the CCA dataset. Furthermore, Pearson’s analysis reported an intimate correlation of the risk score with immune cell infiltration, indicating a predictive value of the signature for the efficacy of immunotherapy. In addition, the screened lncRNAs were found to have the ability to modulate the expression of mRNAs by interacting with miRNAs based on the established lncRNA-miRNA-mRNA network. In conclusion, our study develops a novel nomogram with good reliability and accuracy to predict the OS of CCA patients, providing a significant guiding value for developing tailored therapy for CCA patients.

Deep learning for abdominal adipose tissue segmentation with few labelled samples

PURPOSE

Fully automated abdominal adipose tissue segmentation from computed tomography (CT) scans plays an important role in biomedical diagnoses and prognoses. However, to identify and segment subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT) in the abdominal region, the traditional routine process used in clinical practise is unattractive, expensive, time-consuming and leads to false segmentation. To address this challenge, this paper introduces and develops an effective global-anatomy-level convolutional neural network (ConvNet) automated segmentation of abdominal adipose tissue from CT scans termed EFNet to accommodate multistage semantic segmentation and high similarity intensity characteristics of the two classes (VAT and SAT) in the abdominal region.

METHODS

EFNet consists of three pathways: (1) The first pathway is the max unpooling operator, which was used to reduce computational consumption. (2) The second pathway is concatenation, which was applied to recover the shape segmentation results. (3) The third pathway is anatomy pyramid pooling, which was adopted to obtain fine-grained features. The usable anatomical information was encoded in the output of EFNet and allowed for the control of the density of the fine-grained features.

RESULTS

We formulated an end-to-end manner for the learning process of EFNet, where the representation features can be jointly learned through a mixed feature fusion layer. We immensely evaluated our model on different datasets and compared it to existing deep learning networks. Our proposed model called EFNet outperformed other state-of-the-art models on the segmentation results and demonstrated tremendous performances for abdominal adipose tissue segmentation.

CONCLUSION

EFNet is extremely fast with remarkable performance for fully automated segmentation of the VAT and SAT in abdominal adipose tissue from CT scans. The proposed method demonstrates a strength ability for automated detection and segmentation of abdominal adipose tissue in clinical practise.