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

General General

Development of maize plant dataset for intelligent recognition and weed control.

In Data in brief

This paper focuses on the development of maize plant datasets for the purposes of recognizing maize plants and weed species, as well as the precise automated application of herbicides to the weeds. The dataset includes 36,374 images captured with a high-resolution digital camera during the weed survey and 500 images annotated with the Labelmg suite. Images of the eighteen farmland locations in North Central Nigeria, containing the maize plants and their associated weeds were captured using a high-resolution camera in each location. This dataset will serve as a benchmark for computer vision and machine learning tasks in the intelligent maize and weed recognition research.

Olaniyi Olayemi Mikail, Salaudeen Muhammadu Tajudeen, Daniya Emmanuel, Abdullahi Ibrahim Mohammed, Folorunso Taliha Abiodun, Bala Jibril Abdullahi, Nuhu Bello Kontagora, Adedigba Adeyinka Peace, Oluwole Blessing Israel, Bankole Abdullah Oreoluwa, Macarthy Odunayo Moses

2023-Apr

Autonomous robot, Herbicides, Maize images, Precision agriculture

Surgery Surgery

Real-time administration of indocyanine green in combination with computer vision and artificial intelligence for the identification and delineation of colorectal liver metastases.

In Surgery open science

INTRODUCTION : Fluorescence guided surgery for the identification of colorectal liver metastases (CRLM) can be better with low specificity and antecedent dosing impracticalities limiting indocyanine green (ICG) usefulness currently. We investigated the application of artificial intelligence methods (AIM) to demonstrate and characterise CLRMs based on dynamic signalling immediately following intraoperative ICG administration.

METHODS : Twenty-five patients with liver surface lesions (24 CRLM and 1 benign cyst) undergoing open/laparoscopic/robotic procedures were studied. ICG (0.05 mg/kg) was administered with near-infrared recording of fluorescence perfusion. User-selected region-of-interest (ROI) perfusion profiles were generated, milestones relating to ICG inflow/outflow extracted and used to train a machine learning (ML) classifier. 2D heatmaps were constructed in a subset using AIM to depict whole screen imaging based on dynamic tissue-ICG interaction. Fluorescence appearances were also assessed microscopically (using H&E and fresh-frozen preparations) to provide tissue-level explainability of such methods.

RESULTS : The ML algorithm correctly classified 97.2 % of CRLM ROIs (n = 132) and all benign lesion ROIs (n = 6) within 90-s of ICG administration following initial mathematical curve analysis identifying ICG inflow/outflow differentials between healthy liver and CRLMs. Time-fluorescence plots extracted for each pixel in 10 lesions enabled creation of 2D characterising heatmaps using flow parameters and through unsupervised ML. Microscopy confirmed statistically less CLRM fluorescence vs adjacent liver (mean ± std deviation signal/area 2.46 ± 9.56 vs 507.43 ± 160.82 respectively p < 0.001) with H&E diminishing ICG signal (n = 4).

CONCLUSION : ML accurately identifies CRLMs from surrounding liver tissue enabling representative 2D mapping of such lesions from their fluorescence perfusion patterns using AIM. This may assist in reducing positive margin rates at metastatectomy and in identifying unexpected/occult malignancies.

Hardy Niall P, Epperlein Jonathan P, Dalli Jeffrey, Robertson William, Liddy Richard, Aird John J, Mulligan Niall, Neary Peter M, McEntee Gerard P, Conneely John B, Cahill Ronan A

2023-Mar

Artificial intelligence, Colorectal liver metastases, Fluorescence guided surgery, Fluorescence quantification, Indocyanine green, Liver surgery

General General

Characterization of chromatin accessibility patterns in different mouse cell types using machine learning methods at single-cell resolution.

In Frontiers in genetics ; h5-index 62.0

Chromatin accessibility is a generic property of the eukaryotic genome, which refers to the degree of physical compaction of chromatin. Recent studies have shown that chromatin accessibility is cell type dependent, indicating chromatin heterogeneity across cell lines and tissues. The identification of markers used to distinguish cell types at the chromosome level is important to understand cell function and classify cell types. In the present study, we investigated transcriptionally active chromosome segments identified by sci-ATAC-seq at single-cell resolution, including 69,015 cells belonging to 77 different cell types. Each cell was represented by existence status on 20,783 genes that were obtained from 436,206 active chromosome segments. The gene features were deeply analyzed by Boruta, resulting in 3897 genes, which were ranked in a list by Monte Carlo feature selection. Such list was further analyzed by incremental feature selection (IFS) method, yielding essential genes, classification rules and an efficient random forest (RF) classifier. To improve the performance of the optimal RF classifier, its features were further processed by autoencoder, light gradient boosting machine and IFS method. The final RF classifier with MCC of 0.838 was constructed. Some marker genes such as H2-Dmb2, which are specifically expressed in antigen-presenting cells (e.g., dendritic cells or macrophages), and Tenm2, which are specifically expressed in T cells, were identified in this study. Our analysis revealed numerous potential epigenetic modification patterns that are unique to particular cell types, thereby advancing knowledge of the critical functions of chromatin accessibility in cell processes.

Xu Yaochen, Huang FeiMing, Guo Wei, Feng KaiYan, Zhu Lin, Zeng Zhenbing, Huang Tao, Cai Yu-Dong

2023

biomarker genes, chromatin accessibility, chromatin heterogeneity, machine learning, mouse cell type, single-cell resolution

Public Health Public Health

Identification of immune biomarkers associated with basement membranes in idiopathic pulmonary fibrosis and their pan-cancer analysis.

In Frontiers in genetics ; h5-index 62.0

Idiopathic pulmonary fibrosis (IPF) is a chronic progressive interstitial lung disease of unknown etiology, characterized by diffuse alveolitis and alveolar structural damage. Due to the short median survival time and poor prognosis of IPF, it is particularly urgent to find new IPF biomarkers. Previous studies have shown that basement membranes (BMs) are associated with the development of IPF and tumor metastasis. However, there is still a lack of research on BMs-related genes in IPF. Therefore, we investigated the expression level of BMs genes in IPF and control groups, and explored their potential as biomarkers for IPF diagnosis. In this study, the GSE32537 and GSE53845 datasets were used as training sets, while the GSE24206, GSE10667 and GSE101286 datasets were used as validation sets. In the training set, seven immune biomarkers related to BMs were selected by differential expression analysis, machine learning algorithm (LASSO, SVM-RFE, Randomforest) and ssGSEA analysis. Further ROC analysis confirmed that seven BMs-related genes played an important role in IPF. Finally, four immune-related Hub genes (COL14A1, COL17A1, ITGA10, MMP7) were screened out. Then we created a logistic regression model of immune-related hub genes (IHGs) and used a nomogram to predict IPF risk. The nomogram model was evaluated to have good reliability and validity, and ROC analysis showed that the AUC value of IHGs was 0.941 in the training set and 0.917 in the validation set. Pan-cancer analysis showed that IHGs were associated with prognosis, immune cell infiltration, TME, and drug sensitivity in 33 cancers, suggesting that IHGs may be potential targets for intervention in human diseases including IPF and cancer.

Fu Chenkun, Chen Lina, Cheng Yiju, Yang Wenting, Zhu Honglan, Wu Xiao, Cai Banruo

2023

basement membrane, idiopathic pulmonary fibrosis, immune, interstitial lung disease, pan-cancer

General General

Towards automated video-based assessment of dystonia in dyskinetic cerebral palsy: A novel approach using markerless motion tracking and machine learning.

In Frontiers in robotics and AI

Introduction: Video-based clinical rating plays an important role in assessing dystonia and monitoring the effect of treatment in dyskinetic cerebral palsy (CP). However, evaluation by clinicians is time-consuming, and the quality of rating is dependent on experience. The aim of the current study is to provide a proof-of-concept for a machine learning approach to automatically assess scoring of dystonia using 2D stick figures extracted from videos. Model performance was compared to human performance. Methods: A total of 187 video sequences of 34 individuals with dyskinetic CP (8-23 years, all non-ambulatory) were filmed at rest during lying and supported sitting. Videos were scored by three raters according to the Dyskinesia Impairment Scale (DIS) for arm and leg dystonia (normalized scores ranging from 0-1). Coordinates in pixels of the left and right wrist, elbow, shoulder, hip, knee and ankle were extracted using DeepLabCut, an open source toolbox that builds on a pose estimation algorithm. Within a subset, tracking accuracy was assessed for a pretrained human model and for models trained with an increasing number of manually labeled frames. The mean absolute error (MAE) between DeepLabCut's prediction of the position of body points and manual labels was calculated. Subsequently, movement and position features were calculated from extracted body point coordinates. These features were fed into a Random Forest Regressor to train a model to predict the clinical scores. The model performance trained with data from one rater evaluated by MAEs (model-rater) was compared to inter-rater accuracy. Results: A tracking accuracy of 4.5 pixels (approximately 1.5 cm) could be achieved by adding 15-20 manually labeled frames per video. The MAEs for the trained models ranged from 0.21 ± 0.15 for arm dystonia to 0.14 ± 0.10 for leg dystonia (normalized DIS scores). The inter-rater MAEs were 0.21 ± 0.22 and 0.16 ± 0.20, respectively. Conclusion: This proof-of-concept study shows the potential of using stick figures extracted from common videos in a machine learning approach to automatically assess dystonia. Sufficient tracking accuracy can be reached by manually adding labels within 15-20 frames per video. With a relatively small data set, it is possible to train a model that can automatically assess dystonia with a performance comparable to human scoring.

Haberfehlner Helga, van de Ven Shankara S, van der Burg Sven A, Huber Florian, Georgievska Sonja, Aleo Ignazio, Harlaar Jaap, Bonouvrié Laura A, van der Krogt Marjolein M, Buizer Annemieke I

2023

cerebral palsy, human pose estimation, machine learning, markerless skeleton tracking, motion capture, movement disorders

oncology Oncology

Multi-omics to predict acute radiation esophagitis in patients with lung cancer treated with intensity-modulated radiation therapy.

In European journal of medical research

PURPOSE : The study aimed to predict acute radiation esophagitis (ARE) with grade  ≥ 2 for patients with locally advanced lung cancer (LALC) treated with intensity-modulated radiation therapy (IMRT) using multi-omics features, including radiomics and dosiomics.

METHODS : 161 patients with stage IIIA-IIIB LALC who received chemoradiotherapy (CRT) or radiotherapy by IMRT with a prescribed dose from 45 to 70 Gy from 2015 to 2019 were enrolled retrospectively. All the toxicity gradings were given following the Common Terminology Criteria for Adverse Events V4.0. Multi-omics features, including radiomics, dosiomics (including dose-volume histogram dosimetric parameters), were extracted based on the planning CT image and three-dimensional dose distribution. All data were randomly divided into training cohorts (N = 107) and testing cohorts (N = 54). In the training cohorts, features with reliably high outcome relevance and low redundancy were selected under random patient subsampling. Four classification models (using clinical factors (CF) only, using radiomics features (RFs) only, dosiomics features (DFs) only, and the hybrid features (HFs) containing clinical factors, radiomics and dosiomics) were constructed employing the Ridge classifier using two-thirds of randomly selected patients as the training cohort. The remaining patient was treated as the testing cohort. A series of models were built with 30 times training-testing splits. Their performances were assessed using the area under the ROC curve (AUC) and accuracy.

RESULTS : Among all patients, 51 developed ARE grade  ≥ 2, with an incidence of 31.7%. Next, 8990 radiomics and 213 dosiomics features were extracted, and 3, 6, 12, and 13 features remained after feature selection in the CF, DF, RF and DF models, respectively. The RF and HF models achieved similar classification performance, with the training and testing AUCs of 0.796 ± 0.023 (95% confidence interval (CI [0.79, 0.80])/0.744 ± 0.044 (95% CI [0.73, 0.76]) and 0.801 ± 0.022 (95% CI [0.79, 0.81]) (p = 0.74), respectively. The model performances using CF and DF features were poorer, with training and testing AUCs of 0.573 ± 0.026 (95% CI [0.56, 0.58])/ 0.509 ± 0.072 (95% CI [0.48, 0.53]) and 0.679 ± 0.027 (95% CI [0.67, 0.69])/0.604 ± 0.041 (95% CI [0.53, 0.63]) compared with the above two models (p < 0.001), respectively.

CONCLUSIONS : In LALC patients treated with CRT IMRT, the ARE grade  ≥ 2 can be predicted using the pretreatment radiotherapy image features. To predict ARE, the multi-omics features had similar predictability with radiomics features; however, the dosiomics features and clinical factors had a limited classification performance.

Zheng Xiaoli, Guo Wei, Wang Yunhan, Zhang Jiang, Zhang Yuanpeng, Cheng Chen, Teng Xinzhi, Lam Saikit, Zhou Ta, Ma Zongrui, Liu Ruining, Wu Hui, Ge Hong, Cai Jing, Li Bing

2023-Mar-19

Acute radiation esophagitis, Dosiomics, Lung cancer, Machine learning, Radiomics, Radiotherapy