High-throughput quantitative histology in systemic sclerosis skin disease using computer vision

Abstract Background Maize (Zea mays L.) is one of the most important food sources in the world and has been one of the main targets of plant genetics and phenotypic research for centuries. Observation and analysis of various morphological phenotypic traits during maize growth are essential for genetic and breeding study. The generally huge number of samples produce an enormous amount of high-resolution image data. While high throughput plant phenotyping platforms are increasingly used in maize breeding trials, there is a reasonable need for software tools that can automatically identify visual phenotypic features of maize plants and implement batch processing on image datasets. Results On the boundary between computer vision and plant science, we utilize advanced deep learning methods based on convolutional neural networks to empower the workflow of maize phenotyping analysis. This paper presents Maize-IAS (Maize Image Analysis Software), an integrated application supporting one-click analysis of maize phenotype, embedding multiple functions: (I) Projection, (II) Color Analysis, (III) Internode length, (IV) Height, (V) Stem Diameter and (VI) Leaves Counting. Taking the RGB image of maize as input, the software provides a user-friendly graphical interaction interface and rapid calculation of multiple important phenotypic characteristics, including leaf sheath points detection and leaves segmentation. In function Leaves Counting, the mean and standard deviation of difference between prediction and ground truth are 1.60 and 1.625. Conclusion The Maize-IAS is easy-to-use and demands neither professional knowledge of computer vision nor deep learning. All functions for batch processing are incorporated, enabling automated and labor-reduced tasks of recording, measurement and quantitative analysis of maize growth traits on a large dataset. We prove the efficiency and potential capability of our techniques and software to image-based plant research, which also demonstrates the feasibility and capability of AI technology implemented in agriculture and plant science.

Download Full-text

Computer vision approach to characterize size and shape phenotypes of horticultural crops using high-throughput imagery

Computers and Electronics in Agriculture ◽

10.1016/j.compag.2021.106011 ◽

2021 ◽

Vol 182 ◽

pp. 106011

Author(s):

Samiul Haque ◽

Edgar Lobaton ◽

Natalie Nelson ◽

G. Craig Yencho ◽

Kenneth V. Pecota ◽

...

Keyword(s):

Computer Vision ◽

High Throughput ◽

Size And Shape ◽

Horticultural Crops

Download Full-text

Exploring Web Images to Enhance Skin Disease Analysis Under A Computer Vision Framework

IEEE Transactions on Cybernetics ◽

10.1109/tcyb.2017.2765665 ◽

2018 ◽

Vol 48 (11) ◽

pp. 3080-3091

Author(s):

Yingjie Xia ◽

Luming Zhang ◽

Lei Meng ◽

Yan Yan ◽

Liqiang Nie ◽

...

Keyword(s):

Computer Vision ◽

Skin Disease ◽

Web Images ◽

Disease Analysis

Download Full-text

P162 Cross-validation and complementary value of optical coherence tomography and high frequency ultrasound for the assessment of skin disease in systemic sclerosis

Rheumatology ◽

10.1093/rheumatology/keaa111.157 ◽

2020 ◽

Vol 59 (Supplement_2) ◽

Author(s):

Duygu Temiz Karadag ◽

Giovanni Lettieri ◽

Valentina Picerno ◽

Ozcan Gundogdu ◽

Maria Carmela Padula ◽

...

Keyword(s):

Optical Coherence Tomography ◽

Systemic Sclerosis ◽

Skin Disease ◽

High Frequency ◽

Skin Thickness ◽

Optical Coherence ◽

Skin Involvement ◽

High Frequency Ultrasound ◽

Complementary Value ◽

Frequency Ultrasound

Abstract Background The modified Rodnan skin score (mRSS) is the current gold standard for skin assessment in systemic sclerosis (SSc) both in clinical trials and practice. Several studies have reported that skin high frequency ultrasound (HFUS) and, more recently, optical coherence tomography (OCT) are able to reflect the severity of the skin disease in SSc. Aim of the study was to compare OCT and HFUS in the assessment of skin involvement in SSc. Methods Dorsal forearm skin of consecutive diffuse cutaneous SSc (dcSSc) patients and matched-healthy controls (HC) were scanned using OCT and HFUS by investigators blinded to the clinical details using Vivosight scanner (1 assessor) and Esaote MyLab70 equipped with a 22 MHZ probe (2 assessors) respectively. Minimum Optical Density (MinOD), Maximum OD (MaxOD) and OD at 300 micron-depth (OD300) (OCT) and skin thickness (HFUS) were measured. Clinical involvement was assessed by a blinded operator using the mRSS and results were cross matched with imaging data. Statistical analysis was performed using GraphPad Prism software V.7.0. Results A total of 88 OCT images and 176 HFUS images were obtained from 22 dcSSc patients [20 Female, mean age 49 (±11) years, 12 with < 5 years disease duration) and 22 HC (20 Female, mean age 50.7 (±6.7) years]. All OCT measures (MinOD, MaxOD and OD300) were significantly lower in SSc patients than in HC (p = 0.011, p < 0.0001, p < 0.0001 respectively). HFUS showed a lower performance in discriminating SSc skin vs HC compared to OCT (overall AUC 0.6 vs 0.72, 0.8 and 0.89 for MinOD, MaxOD and OD300 respectively). Nevertheless, mean HFUS skin thickness significantly correlated with mRSS at site of analysis (r = 0.47, p = 0.0013) and showed overall excellent interobserver reliability between assessors (ICC >0.8). Importantly, MaxOD and OD300 negatively correlated with HFUS skin thickness (r=-0.32, p = 0.035; r=-0.31, p = 0.039). Conclusion OCT of the skin has been previously validated against skin biopsy in SSc. Our results validate HFUS against OCT and indicate that HFUS of the skin is a reliable measure of skin involvement. Further, here we show that HFUS and OCT outperform each other in measuring different aspects of skin involvement in SSc and they offer complementary surrogate outcome measures of disease. Disclosures D. Temiz Karadag None. G. Lettieri None. V. Picerno None. O. Gundogdu None. M. Padula None. G.A. Mennillo None. A.A. Padula None. F. Del Galdo None. S. D'Angelo None. G. Abignano None.

Download Full-text

Myofibroblasts and hyalinized collagen as markers of skin disease in systemic sclerosis

Arthritis & Rheumatism ◽

10.1002/art.22186 ◽

2006 ◽

Vol 54 (11) ◽

pp. 3655-3660 ◽

Cited By ~ 65

Author(s):

Eugene Y. Kissin ◽

Peter A. Merkel ◽

Robert Lafyatis

Keyword(s):

Systemic Sclerosis ◽

Skin Disease

Download Full-text

High serum sCD163/sTWEAK ratio is associated with lower risk of digital ulcers but more severe skin disease in patients with systemic sclerosis

Arthritis Research & Therapy ◽

10.1186/ar4246 ◽

2013 ◽

Vol 15 (3) ◽

pp. R69 ◽

Cited By ~ 19

Author(s):

Otylia Kowal-Bielecka ◽

Marek Bielecki ◽

Serena Guiducci ◽

Beata Trzcinska-Butkiewicz ◽

Małgorzata Michalska-Jakubus ◽

...

Keyword(s):

Systemic Sclerosis ◽

Skin Disease ◽

Lower Risk ◽

High Serum ◽

Digital Ulcers

Download Full-text

An analysis of abnormalities in the B cell receptor repertoire in patients with systemic sclerosis using high-throughput sequencing

PeerJ ◽

10.7717/peerj.8370 ◽

2020 ◽

Vol 8 ◽

pp. e8370

Author(s):

Xiaodong Shi ◽

Tihong Shao ◽

Feifei Huo ◽

Chenqing Zheng ◽

Wanyu Li ◽

...

Keyword(s):

Systemic Sclerosis ◽

B Cell ◽

High Throughput ◽

High Throughput Sequencing ◽

Cell Receptor ◽

Receptor Repertoire ◽

Skin Sclerosis ◽

Cdr3 Length ◽

Gene Usage ◽

Cell Receptor Repertoire

Systemic sclerosis is a chronic multisystem autoimmune disease that is associated with polyclonal B cell hyperreactivity. The CDR3 of BCRs is the major site of antigen recognition. Therefore, we analyzed the BCR repertoire of patients with SSc. The BCR repertoires in 12 subjects including eight SSc patients and four healthy controls were characterized by high-throughput sequencing, and bioinformatics analysis were studied. The average CDR3 length in the SSc group was significantly shorter. The SSc patient displayed more diverse BCR. Moreover, SSc patients with mild skin sclerosis, anti-Scl70, interstitial lung disease or female sex were more diversified. B cells from the SSc patients showed a differential V and J gene usage. SSc patients had distinct BCR repertoires.These findings reflected the differences of BCR repertoires between SSc patients and controls. The higher-usage genes for the BCR sequence might be potential biomarkers of B cell-targeted therapies or diagnosis for SSc.

Download Full-text