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

General General

SAN-Net: Learning generalization to unseen sites for stroke lesion segmentation with self-adaptive normalization.

In Computers in biology and medicine

There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as stroke is an important cerebrovascular disease. Although deep learning-based models have been proposed for this task, generalizing these models to unseen sites is difficult due to not only the large inter-site discrepancy among different scanners, imaging protocols, and populations, but also the variations in stroke lesion shape, size, and location. To tackle this issue, we introduce a self-adaptive normalization network, termed SAN-Net, to achieve adaptive generalization on unseen sites for stroke lesion segmentation. Motivated by traditional z-score normalization and dynamic network, we devise a masked adaptive instance normalization (MAIN) to minimize inter-site discrepancies, which standardizes input MR images from different sites into a site-unrelated style by dynamically learning affine parameters from the input; i.e., MAIN can affinely transform the intensity values. Then, we leverage a gradient reversal layer to force the U-net encoder to learn site-invariant representation with a site classifier, which further improves the model generalization in conjunction with MAIN. Finally, inspired by the "pseudosymmetry" of the human brain, we introduce a simple yet effective data augmentation technique, termed symmetry-inspired data augmentation (SIDA), that can be embedded within SAN-Net to double the sample size while halving memory consumption. Experimental results on the benchmark Anatomical Tracings of Lesions After Stroke (ATLAS) v1.2 dataset, which includes MR images from 9 different sites, demonstrate that under the "leave-one-site-out" setting, the proposed SAN-Net outperforms recently published methods in terms of quantitative metrics and qualitative comparisons.

Yu Weiyi, Huang Zhizhong, Zhang Junping, Shan Hongming

2023-Feb-28

Convolutional neural network, Domain generalization, Multi-site learning, Site generalization, Stroke lesion segmentation

General General

Establishment of extensive artificial intelligence models for kinase inhibitor prediction: Identification of novel PDGFRB inhibitors.

In Computers in biology and medicine

Identifying hit compounds is an important step in drug development. Unfortunately, this process continues to be a challenging task. Several machine learning models have been generated to aid in simplifying and improving the prediction of candidate compounds. Models tuned for predicting kinase inhibitors have been established. However, an effective model can be limited by the size of the chosen training dataset. In this study, we tested several machine learning models to predict potential kinase inhibitors. A dataset was curated from a number of publicly available repositories. This resulted in a comprehensive dataset covering more than half of the human kinome. More than 2,000 kinase models were established using different model approaches. The performances of the models were compared, and the Keras-MLP model was determined to be the best performing model. The model was then used to screen a chemical library for potential inhibitors targeting platelet-derived growth factor receptor-β (PDGFRB). Several PDGFRB candidates were selected, and in vitro assays confirmed four compounds with PDGFRB inhibitory activity and IC50 values in the nanomolar range. These results show the effectiveness of machine learning models trained on the reported dataset. This report would aid in the establishment of machine learning models as well as in the discovery of novel kinase inhibitors.

Lien Ssu-Ting, Lin Tony Eight, Hsieh Jui-Hua, Sung Tzu-Ying, Chen Jun-Hong, Hsu Kai-Cheng

2023-Mar-01

Artificial intelligence, Kinase, Machine learning, PDGFRB inhibitor, Small molecule

General General

Rough-set based learning: Assessing patterns and predictability of anxiety, depression, and sleep scores associated with the use of cannabinoid-based medicine during COVID-19.

In Frontiers in artificial intelligence

Recently, research is emerging highlighting the potential of cannabinoids' beneficial effects related to anxiety, mood, and sleep disorders as well as pointing to an increased use of cannabinoid-based medicines since COVID-19 was declared a pandemic. The objective of this research is 3 fold: i) to evaluate the relationship of the clinical delivery of cannabinoid-based medicine for anxiety, depression and sleep scores by utilizing machine learning specifically rough set methods; ii) to discover patterns based on patient features such as specific cannabinoid recommendations, diagnosis information, decreasing/increasing levels of clinical assessment tools (CAT) scores over a period of time; and iii) to predict whether new patients could potentially experience either an increase or decrease in CAT scores. The dataset for this study was derived from patient visits to Ekosi Health Centres, Canada over a 2 year period including the COVID timeline. Extensive pre-processing and feature engineering was performed. A class feature indicative of their progress or lack thereof due to the treatment received was introduced. Six Rough/Fuzzy-Rough classifiers as well as Random Forest and RIPPER classifiers were trained on the patient dataset using a 10-fold stratified CV method. The highest overall accuracy, sensitivity and specificity measures of over 99% was obtained using the rule-based rough-set learning model. In this study, we have identified rough-set based machine learning model with high accuracy that could be utilized for future studies regarding cannabinoids and precision medicine.

Ramanna Sheela, Ashrafi Negin, Loster Evan, Debroni Karen, Turner Shelley

2023

cannabinoid medicine, electronic health records, machine learning, mental health, rough sets, rough-fuzzy sets

Radiology Radiology

Integrative Scoring System for Survival Prediction in Patients With Locally Advanced Nasopharyngeal Carcinoma: A Retrospective Multicenter Study.

In JCO clinical cancer informatics

PURPOSE : Tumor stage is crucial for prognostic evaluation and therapeutic decisions in locally advanced nasopharyngeal carcinoma (NPC) but is imprecise. We aimed to propose a new prognostic system by integrating quantitative imaging features and clinical factors.

MATERIALS AND METHODS : This retrospective study included 1,319 patients with stage III-IVa NPC between April 1, 2010, and July 31, 2019, who underwent pretherapy magnetic resonance imaging (MRI) and received concurrent chemoradiotherapy with or without induction chemotherapy. The hand-crafted and deep-learned features were extracted from MRI for each patient. After feature selection, the clinical score, radiomic score, deep score, and integrative scores were constructed via Cox regression analysis. The scores were validated in two external cohorts. The predictive accuracy and discrimination were measured by the area under the curve (AUC) and risk group stratification. The end points were progression-free survival (PFS), overall survival (OS), and distant metastasis-free survival (DMFS).

RESULTS : Both radiomics and deep learning were complementary to clinical variables (age, T stage, and N stage; all P < .05). The clinical-deep score was superior or equivalent to clinical-radiomic score, whereas it was noninferior to clinical-radiomic-deep score (all P > .05). These findings were also verified in the evaluation of OS and DMFS. The clinical-deep score yielded an AUC of 0.713 (95% CI, 0.697 to 0.729) and 0.712 (95% CI, 0.693 to 0.731) in the two external validation cohorts for predicting PFS with good calibration. This scoring system could stratify patients into high- and low-risk groups with distinct survivals (all P < .05).

CONCLUSION : We established and validated a prognostic system integrating clinical data and deep learning to provide an individual prediction of survival for patients with locally advanced NPC, which might inform clinicians in treatment decision making.

Zhang Bin, Luo Chun, Zhang Xiao, Hou Jing, Liu Shuyi, Gao Mingyong, Zhang Lu, Jin Zhe, Chen Qiuying, Yu Xiaoping, Zhang Shuixing

2023-Feb

Public Health Public Health

Application of machine learning approach in emergency department to support clinical decision making for SARS-CoV-2 infected patients.

In Journal of integrative bioinformatics

To support physicians in clinical decision process on patients affected by Coronavirus Disease 2019 (COVID-19) in areas with a low vaccination rate, we devised and evaluated the performances of several machine learning (ML) classifiers fed with readily available clinical and laboratory data. Our observational retrospective study collected data from a cohort of 779 COVID-19 patients presenting to three hospitals of the Lazio-Abruzzo area (Italy). Based on a different selection of clinical and respiratory (ROX index and PaO2/FiO2 ratio) variables, we devised an AI-driven tool to predict safe discharge from ED, disease severity and mortality during hospitalization. To predict safe discharge our best classifier is an RF integrated with ROX index that reached AUC of 0.96. To predict disease severity the best classifier was an RF integrated with ROX index that reached an AUC of 0.91. For mortality prediction the best classifier was an RF integrated with ROX index, that reached an AUC of 0.91. The results obtained thanks to our algorithms are consistent with the scientific literature an accomplish significant performances to forecast safe discharge from ED and severe clinical course of COVID-19.

Casano Nicolò, Santini Silvano Junior, Vittorini Pierpaolo, Sinatti Gaia, Carducci Paolo, Mastroianni Claudio Maria, Ciardi Maria Rosa, Pasculli Patrizia, Petrucci Emiliano, Marinangeli Franco, Balsano Clara

2023-Mar-07

COVID-19, ROX index, SARS-CoV-2, emergency medicine, machine learning

General General

Social copying drives a tipping point for nonlinear population collapse.

In Proceedings of the National Academy of Sciences of the United States of America

Sudden changes in populations are ubiquitous in ecological systems, especially under perturbations. The agents of global change may increase the frequency and severity of anthropogenic perturbations, but complex populations' responses hamper our understanding of their dynamics and resilience. Furthermore, the long-term environmental and demographic data required to study those sudden changes are rare. Fitting dynamical models with an artificial intelligence algorithm to population fluctuations over 40 y in a social bird reveals that feedback in dispersal after a cumulative perturbation drives a population collapse. The collapse is well described by a nonlinear function mimicking social copying, whereby dispersal made by a few individuals induces others to leave the patch in a behavioral cascade for decision-making to disperse. Once a threshold for deterioration of the quality of the patch is crossed, there is a tipping point for a social response of runaway dispersal corresponding to social copying feedback. Finally, dispersal decreases at low population densities, which is likely due to the unwillingness of the more philopatric individuals to disperse. In providing the evidence of copying for the emergence of feedback in dispersal in a social organism, our results suggest a broader impact of self-organized collective dispersal in complex population dynamics. This has implications for the theoretical study of population and metapopulation nonlinear dynamics, including population extinction, and managing of endangered and harvested populations of social animals subjected to behavioral feedback loops.

Oro Daniel, Alsedà Lluís, Hastings Alan, Genovart Meritxell, Sardanyés Josep

2023-Mar-14

feedback, nonlinear population dynamics, runaway dispersal, social behavior, tipping points