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

General General

An experimental study of animating-based facial image manipulation in online class environments.

In Scientific reports ; h5-index 158.0

Recent advances in artificial intelligence technology have significantly improved facial image manipulation, which is known as Deepfake. Facial image manipulation synthesizes or replaces a region of the face in an image with that of another face. The techniques for facial image manipulation are classified into four categories: (1) entire face synthesis, (2) identity swap, (3) attribute manipulation, and (4) expression swap. Out of them, we focus on expression swap because it effectively manipulates only the expression of the face in the images or videos without creating or replacing the entire face, having advantages for the real-time application. In this study, we propose an evaluation framework of the expression swap models targeting the real-time online class environments. For this, we define three kinds of scenarios according to the portion of the face in the entire image considering actual online class situations: (1) attendance check (Scenario 1), (2) presentation (Scenario 2), and (3) examination (Scenario 3). Considering the manipulation on the online class environments, the framework receives a single source image and a target video and generates the video that manipulates a face of the target video to that in the source image. To this end, we select two models that satisfy the conditions required by the framework: (1) first order model and (2) GANimation. We implement these models in the framework and evaluate their performance for the defined scenarios. Through the quantitative and qualitative evaluation, we observe distinguishing properties of the used two models. Specifically, both models show acceptable results in Scenario 1, where the face occupies a large portion of the image. However, their performances are significantly degraded in Scenarios 2 and 3, where the face occupies less portion of the image; the first order model causes relatively less loss of image quality than GANimation in the result of the quantitative evaluation. In contrast, GANimation has the advantages of representing facial expression changes compared to the first order model. Finally, we devise an architecture for applying the expression swap model to the online video conferencing application in real-time. In particular, by applying the expression swap model to widely used online meeting platforms such as Zoom, Google Meet, and Microsoft Teams, we demonstrate its feasibility for real-time online classes.

Park Jeong-Ha, Lim Chae-Yun, Kwon Hyuk-Yoon


Dermatology Dermatology

Role of the Microbiome in Immunotherapy of Melanoma.

In Cancer journal (Sudbury, Mass.)

Novel immunotherapeutics for advanced melanoma have drastically changed survival rates and management strategies in recent years. Immune checkpoint inhibitors have emerged as efficacious agents for some patients but have not been proven to be as beneficial in other patient cohorts. Recent investigation into this observation has implicated the gut microbiome as a potential immunomodulator in regulating patient response to therapy. Numerous studies have provided evidence for this link. Bacterial colonization patterns have been associated with therapeutic outcomes, under the notion that favorable commensal organisms improve host immune response. This review aims to report the most recent and pertinent findings related to the relationship between gut microbial communities and melanoma therapy efficacy. This article also highlights the emerging frontier of artificial intelligence in its application regarding patient microbial composition evaluation, predictive models for therapy response, and recommendations for the future of probiotics and dietary interventions to optimize melanoma survival and outcomes.

Jiminez Victoria, Yusuf Nabiha

Radiology Radiology

Transformer Performance for Chemical Reactions: Analysis of Different Predictive and Evaluation Scenarios.

In Journal of chemical information and modeling

The prediction of chemical reaction pathways has been accelerated by the development of novel machine learning architectures based on the deep learning paradigm. In this context, deep neural networks initially designed for language translation have been used to accurately predict a wide range of chemical reactions. Among models suited for the task of language translation, the recently introduced molecular transformer reached impressive performance in terms of forward-synthesis and retrosynthesis predictions. In this study, we first present an analysis of the performance of transformer models for product, reactant, and reagent prediction tasks under different scenarios of data availability and data augmentation. We find that the impact of data augmentation depends on the prediction task and on the metric used to evaluate the model performance. Second, we probe the contribution of different combinations of input formats, tokenization schemes, and embedding strategies to model performance. We find that less stable input settings generally lead to better performance. Lastly, we validate the superiority of round-trip accuracy over simpler evaluation metrics, such as top-k accuracy, using a committee of human experts and show a strong agreement for predictions that pass the round-trip test. This demonstrates the usefulness of more elaborate metrics in complex predictive scenarios and highlights the limitations of direct comparisons to a predefined database, which may include a limited number of chemical reaction pathways.

Jaume-Santero Fernando, Bornet Alban, Valery Alain, Naderi Nona, Vicente Alvarez David, Proios Dimitrios, Yazdani Anthony, Bournez Colin, Fessard Thomas, Teodoro Douglas


Pathology Pathology

Learning to predict RNA sequence expressions from whole slide images with applications for search and classification.

In Communications biology

Deep learning methods are widely applied in digital pathology to address clinical challenges such as prognosis and diagnosis. As one of the most recent applications, deep models have also been used to extract molecular features from whole slide images. Although molecular tests carry rich information, they are often expensive, time-consuming, and require additional tissue to sample. In this paper, we propose tRNAsformer, an attention-based topology that can learn both to predict the bulk RNA-seq from an image and represent the whole slide image of a glass slide simultaneously. The tRNAsformer uses multiple instance learning to solve a weakly supervised problem while the pixel-level annotation is not available for an image. We conducted several experiments and achieved better performance and faster convergence in comparison to the state-of-the-art algorithms. The proposed tRNAsformer can assist as a computational pathology tool to facilitate a new generation of search and classification methods by combining the tissue morphology and the molecular fingerprint of the biopsy samples.

Alsaafin Areej, Safarpoor Amir, Sikaroudi Milad, Hipp Jason D, Tizhoosh H R


Pathology Pathology

A systematic evaluation of deep learning methods for the prediction of drug synergy in cancer.

In PLoS computational biology

One of the main obstacles to the successful treatment of cancer is the phenomenon of drug resistance. A common strategy to overcome resistance is the use of combination therapies. However, the space of possibilities is huge and efficient search strategies are required. Machine Learning (ML) can be a useful tool for the discovery of novel, clinically relevant anti-cancer drug combinations. In particular, deep learning (DL) has become a popular choice for modeling drug combination effects. Here, we set out to examine the impact of different methodological choices on the performance of multimodal DL-based drug synergy prediction methods, including the use of different input data types, preprocessing steps and model architectures. Focusing on the NCI ALMANAC dataset, we found that feature selection based on prior biological knowledge has a positive impact-limiting gene expression data to cancer or drug response-specific genes improved performance. Drug features appeared to be more predictive of drug response, with a 41% increase in coefficient of determination (R2) and 26% increase in Spearman correlation relative to a baseline model that used only cell line and drug identifiers. Molecular fingerprint-based drug representations performed slightly better than learned representations-ECFP4 fingerprints increased R2 by 5.3% and Spearman correlation by 2.8% w.r.t the best learned representations. In general, fully connected feature-encoding subnetworks outperformed other architectures. DL outperformed other ML methods by more than 35% (R2) and 14% (Spearman). Additionally, an ensemble combining the top DL and ML models improved performance by about 6.5% (R2) and 4% (Spearman). Using a state-of-the-art interpretability method, we showed that DL models can learn to associate drug and cell line features with drug response in a biologically meaningful way. The strategies explored in this study will help to improve the development of computational methods for the rational design of effective drug combinations for cancer therapy.

Baptista Delora, Ferreira Pedro G, Rocha Miguel


Pathology Pathology

The value of artificial intelligence in the diagnosis of lung cancer: A systematic review and meta-analysis.

In PloS one ; h5-index 176.0

Lung cancer is a common malignant tumor disease with high clinical disability and death rates. Currently, lung cancer diagnosis mainly relies on manual pathology section analysis, but the low efficiency and subjective nature of manual film reading can lead to certain misdiagnoses and omissions. With the continuous development of science and technology, artificial intelligence (AI) has been gradually applied to imaging diagnosis. Although there are reports on AI-assisted lung cancer diagnosis, there are still problems such as small sample size and untimely data updates. Therefore, in this study, a large amount of recent data was included, and meta-analysis was used to evaluate the value of AI for lung cancer diagnosis. With the help of STATA16.0, the value of AI-assisted lung cancer diagnosis was assessed by specificity, sensitivity, negative likelihood ratio, positive likelihood ratio, diagnostic ratio, and plotting the working characteristic curves of subjects. Meta-regression and subgroup analysis were used to investigate the value of AI-assisted lung cancer diagnosis. The results of the meta-analysis showed that the combined sensitivity of the AI-aided diagnosis system for lung cancer diagnosis was 0.87 [95% CI (0.82, 0.90)], specificity was 0.87 [95% CI (0.82, 0.91)] (CI stands for confidence interval.), the missed diagnosis rate was 13%, the misdiagnosis rate was 13%, the positive likelihood ratio was 6.5 [95% CI (4.6, 9.3)], the negative likelihood ratio was 0.15 [95% CI (0.11, 0.21)], a diagnostic ratio of 43 [95% CI (24, 76)] and a sum of area under the combined subject operating characteristic (SROC) curve of 0.93 [95% CI (0.91, 0.95)]. Based on the results, the AI-assisted diagnostic system for CT (Computerized Tomography), imaging has considerable diagnostic accuracy for lung cancer diagnosis, which is of significant value for lung cancer diagnosis and has greater feasibility of realizing the extension application in the field of clinical diagnosis.

Liu Mingsi, Wu Jinghui, Wang Nian, Zhang Xianqin, Bai Yujiao, Guo Jinlin, Zhang Lin, Liu Shulin, Tao Ke