Artificial intelligence recognition of cutaneous chronic graft-versus-host disease by a deep learning neural network.
Ontology highlight
ABSTRACT:
SUBMITTER: McNeil A
PROVIDER: S-EPMC9197858 | biostudies-literature | 2022 Jun
REPOSITORIES: biostudies-literature
Publications
Artificial intelligence recognition of cutaneous chronic graft-versus-host disease by a deep learning neural network.
McNeil Andrew A Parks Kelsey K Liu Xiaoqi X Saknite Inga I Chen Fuyao F Reasat Tahsin T Cronin Austin A Wheless Lee L Dawant Benoit M BM Tkaczyk Eric R ER
British journal of haematology 20220324 6
Similar Datasets
Project description:Dermatologists are ideally suited to manage the various cutaneous sequelae of graft-versus-host disease (GVHD) outlined in part I of this review. However, the complexity of the patient with GVHD, including comorbidities, potential drug interactions related to polypharmacy, and the lack of evidence-based treatment guidelines, are significant challenges to optimizing patient care. In this section, we will provide an outline for the role of the dermatologist in a multispecialty approach to caring for patients with GVHD.
| S-EPMC7357210 | biostudies-literature
Project description:In order to explore the application of the image recognition model based on multi-stage convolutional neural network (MS-CNN) in the deep learning neural network in the intelligent recognition of commodity images and the recognition performance of the method, in the study, the features of color, shape, and texture of commodity images are first analyzed, and the basic structure of deep convolutional neural network (CNN) model is analyzed. Then, 50,000 pictures containing different commodities are constructed to verify the recognition effect of the model. Finally, the MS-CNN model is taken as the research object for improvement to explore the influence of label errors (p = 0.03, 0.05, 0.07, 0.09, 0.12) with different parameter settings and different probabilities (size of convolutional kernel, Dropout rate) on the recognition accuracy of MS-CNN model, at the same time, a CIR system platform based on MS-CNN model is built, and the recognition performance of salt and pepper noise images with different SNR (0, 0.03, 0.05, 0.07, 0.1) was compared, then the performance of the algorithm in the actual image recognition test was compared. The results show that the recognition accuracy is the highest (97.8%) when the convolution kernel size in the MS-CNN model is 2*2 and 3*3, and the average recognition accuracy is the highest (97.8%) when the dropout rate is 0.1; when the error probability of picture label is 12%, the recognition accuracy of the model constructed in this study is above 96%. Finally, the commodity image database constructed in this study is used to identify and verify the model. The recognition accuracy of the algorithm in this study is significantly higher than that of the Minitch stochastic gradient descent algorithm under different SNR conditions, and the recognition accuracy is the highest when SNR = 0 (99.3%). The test results show that the model proposed in this study has good recognition effect in the identification of commodity images in scenes of local occlusion, different perspectives, different backgrounds, and different light intensity, and the recognition accuracy is 97.1%. To sum up, the CIR platform based on MS-CNN model constructed in this study has high recognition accuracy and robustness, which can lay a foundation for the realization of subsequent intelligent commodity recognition technology.
| S-EPMC7340283 | biostudies-literature
Project description:Bone scintigraphy (BS) is one of the most frequently utilized diagnostic techniques in detecting cancer bone metastasis, and it occupies an enormous workload for nuclear medicine physicians. So, we aimed to architecture an automatic image interpreting system to assist physicians for diagnosis. We developed an artificial intelligence (AI) model based on a deep neural network with 12,222 cases of 99mTc-MDP bone scintigraphy and evaluated its diagnostic performance of bone metastasis. This AI model demonstrated considerable diagnostic performance, the areas under the curve (AUC) of receiver operating characteristic (ROC) was 0.988 for breast cancer, 0.955 for prostate cancer, 0.957 for lung cancer, and 0.971 for other cancers. Applying this AI model to a new dataset of 400 BS cases, it represented comparable performance to that of human physicians individually classifying bone metastasis. Further AI-consulted interpretation also improved human diagnostic sensitivity and accuracy. In total, this AI model performed a valuable benefit for nuclear medicine physicians in timely and accurate evaluation of cancer bone metastasis.
| S-EPMC7550561 | biostudies-literature
Project description:BackgroundSkin biopsies are often used in daily practice for the diagnosis of acute (aGvHD) or chronic graft versus host disease (cGvHD). With the latest understanding in pathogenesis and new National Institute of Health (NIH) classifications for aGvHD and cGvHD, there is a need to evaluate the current prognostic value of histological grading cutaneous GvHD and its correlation to the clinical grade.MethodsIn a retrospective study with 120 skin biopsies (all taken for suspected GvHD) from 110 patients (all classified according to the NIH), biopsies were revised and graded, blinded for clinical information, for either acute of chronic features. Morphological grades were compared for concordance with the clinical grade and survival analyses were done for clinical and histological grading.ResultsCorrelation for histologic vs. clinical grading was (very) poor for aGvHD and cGvHD (weighted κ - 0.038 and 0.0009, respectively). Patients with clinical aGvHD had worse prognosis compared to cGvHD. However, at time of biopsy neither clinical nor histological grading predicted the eventual survival for either aGvHD (p = 0.9739 and p = 0.0744, respectively) or cGvHD (p = 0.2149 and p = 0.4465, respectively).ConclusionsConfirming the diagnosis of GvHD is still a valuable reason for taking a skin biopsy, but this study shows that histologic grading of GvHD in the skin biopsy has no additional value for clinicians in current practice.
| S-EPMC6457000 | biostudies-literature
Project description:The polymorphism of cutaneous leishmaniasis (CL) complicates diagnosis in health care services because lesions may be confused with other dermatoses such as sporotrichosis, paracocidiocomycosis, and venous insufficiency. Automated identification of skin diseases based on deep learning (DL) has been applied to assist diagnosis. In this study, we evaluated the performance of AlexNet, a DL algorithm, to identify pictures of CL lesions in patients from Midwest Brazil. We used a set of 2458 pictures (up to 10 of each lesion) obtained from patients treated between 2015 and 2022 in the Leishmaniasis Clinic at the University Hospital of Brasilia. We divided the picture database into training (80%), internal validation (10%), and testing sets (10%), and trained and tested AlexNet to identify pictures of CL lesions. We performed three simulations and trained AlexNet to differentiate CL from 26 other dermatoses (e.g., chromomycosis, ecthyma, venous insufficiency). We obtained an average accuracy of 95.04% (Confidence Interval 95%: 93.81-96.04), indicating an excellent performance of AlexNet in identifying pictures of CL lesions. We conclude that automated CL identification using AlexNet has the potential to assist clinicians in diagnosing skin lesions. These results contribute to the development of a mobile application to assist in the diagnosis of CL in health care services.
| S-EPMC10813291 | biostudies-literature
Project description:Allogeneic hematopoietic stem cell transplantation is a curative treatment for numerous hematological malignancies. However, acute graft-versus-host disease (aGvHD) is a major complication affecting 40-70% of all transplant patients, whereby the earliest and most frequent presentation is in the skin. MicroRNAs play a role in varied biological process and have been reported as potential biomarkers for aGvHD. More recently, microRNAs have received added attention as circulatory biomarkers that can be detected in biofluids. In this study, we performed global microRNA expression profiling using a discovery cohort of diagnostic cutaneous aGvHD biopsies (n = 5, stages 1-3) and healthy volunteers (n = 4), in order to identify a signature list of microRNAs that could be used as diagnostic biomarkers for cutaneous aGvHD. Candidate microRNAs (n = 8) were then further investigated in a validation cohort of post-HSCT skin biopsies (n = 17), pre-HSCT skin biopsies (n = 6) and normal controls (n = 6) for their association with aGvHD. Expression of let-7c (p = 0.014), miR-503-5p (p = 0.003), miR-365a-3p (p = 0.02), miR-34a-5p (p < 0.001) and miR-34a-3p (p = 0.006) were significantly differentially expressed between groups and significantly associated with survival outcome in post-HSCT patients (miR-503-5p ROC AUC = 0.83 p = 0.021, Log Rank p = 0.003; miR-34a-3p ROC AUC = 0.93, p = 0.003, Log Rank p = 0.004). There was no association with relapse. A statistical interaction between miR-34a-3p and miR-503-5p (p = 0.016) was diagnostic for aGvHD. Expression levels of the miR-34a-5p protein target p53 were assessed in the epidermis of the skin, and an inverse correlation was identified (r2 = 0.44, p = 0.039). Expression of the validated candidate microRNAs was also assessed at day 28 post-HSCT in the sera of transplant recipients, in order to investigate their potential as circulatory microRNA biomarkers. Expression of miR-503-5p (p = 0.001), miR-34a-5p (p = 0.005), and miR-34a-3p (p = 0.004) was significantly elevated in the sera of patients who developed aGvHD versus no-aGvHD (n = 30) and miR-503-5p was associated with overall survival (OS) (ROC AUC = 0.80, p = 0.04, Log Rank p = 0.041). In conclusion, this investigation reports that microRNA expression levels in clinical skin biopsies, obtained at the time of cutaneous aGvHD onset, show potential as diagnostic biomarkers for aGvHD and as predictive biomarkers for OS. In addition, the same microRNAs can be detected in the circulation and show predictive association with post-HSCT outcomes.
| S-EPMC6048189 | biostudies-literature
Project description:The kinetics of gene expression associated with the development of cutaneous graft-versus-host disease (GVHD) were examined in a mouse model of MHC-matched allogeneic hematopoietic stem cell transplantation. Ear skin was obtained from recipient mice with or without GVHD between 7 and 40 days after transplantation for histopathological analysis and gene expression profiling. Gene expression patterns were consistent with early infiltration and activation of CD8(+) T and mast cells, followed by CD4(+) T, natural killer, and myeloid cells. The sequential infiltration and activation of effector cells correlated with the histopathological development of cutaneous GVHD and was accompanied by up-regulated expression of many chemokines and their receptors (CXCL-1, -2, -9, and -10; CCL-2, -5, -6, -7, -8, -9, -11, and -19; CCR-1 and CCR-5), adhesion molecules (ICAM-1, CD18, Ly69, PSGL-1, VCAM-1), molecules involved in antigen processing and presentation (TAP1 and TAP2, MHC class I and II, CD80), regulators of apoptosis (granzyme B, caspase 7, Bak1, Bax, and BclII), interferon-inducible genes (STAT1, IRF-1, IIGP, GTPI, IGTP, Ifi202A), stimulators of fibroblast proliferation and matrix synthesis (interleukin-1beta, transforming growth factor-beta1), and markers of keratinocyte proliferation (keratins 5 and 6), and differentiation (small proline-rich proteins 2E and 1B). Many acute-phase proteins were up-regulated early in murine cutaneous GVHD including serum amyloid A2 (SAA2), SAA3, serpins a3g and a3n, secretory leukocyte protease inhibitor, and metallothioneins 1 and 2. The kinetics of gene expression were consistent with the evolution of cutaneous pathology as well as with current models of disease progression during cutaneous GVHD.
| S-EPMC1615752 | biostudies-literature
Project description:In recent decades, preterm birth (PTB) has become a significant research focus in the healthcare field, as it is a leading cause of neonatal mortality worldwide. Using five independent study cohorts including 1290 vaginal samples from 561 pregnant women who delivered at term (n = 1029) or prematurely (n = 261), we analysed vaginal metagenomics data for precise microbiome structure characterization. Then, a deep neural network (DNN) was trained to predict term birth (TB) and PTB with an accuracy of 84.10% and an area under the receiver operating characteristic curve (AUROC) of 0.875 ± 0.11. During a benchmarking process, we demonstrated that our DL model outperformed seven currently used machine learning algorithms. Finally, our results indicate that overall diversity of the vaginal microbiota should be taken in account to predict PTB and not specific species. This artificial-intelligence based strategy should be highly helpful for clinicians in predicting preterm birth risk, allowing personalized assistance to address various health issues. DeepMPTB is open source and free for academic use. It is licensed under a GNU Affero General Public License 3.0 and is available at https://deepmptb.streamlit.app/ . Source code is available at https://github.com/oschakoory/DeepMPTB and can be easily installed using Docker ( https://www.docker.com/ ).
| S-EPMC10865581 | biostudies-literature
Project description:Tongue diagnosis plays a pivotal role in traditional Chinese medicine (TCM) for thousands of years. As one of the most important tongue characteristics, tooth-marked tongue is related to spleen deficiency and can greatly contribute to the symptoms differentiation and treatment selection. Yet, the tooth-marked tongue recognition for TCM practitioners is subjective and challenging. Most of the previous studies have concentrated on subjectively selected features of the tooth-marked region and gained accuracy under 80%. In the present study, we proposed an artificial intelligence framework using deep convolutional neural network (CNN) for the recognition of tooth-marked tongue. First, we constructed relatively large datasets with 1548 tongue images captured by different equipments. Then, we used ResNet34 CNN architecture to extract features and perform classifications. The overall accuracy of the models was over 90%. Interestingly, the models can be successfully generalized to images captured by other devices with different illuminations. The good effectiveness and generalization of our framework may provide objective and convenient computer-aided tongue diagnostic method on tracking disease progression and evaluating pharmacological effect from a informatics perspective.
| S-EPMC7186367 | biostudies-literature
Project description:Interventions: None
Primary outcome(s): The primary outcome of the study is the accuracy of the CAD-CNN system for predicting histology of diminutive colorectal polyps (1-5mm) compared with the accuracy of the prediction of the endoscopist. Both the CAD-CNN system and the endoscopist will use NBI for their predictions.
Accuracy is defined as the percentage of correctly predicted optical diagnoses of the CAD-CNN system and/or endoscopist compared to the gold standard pathology. For the calculation of the accuracy, adenomas and SSLs will be dichotomised as neoplastic polyps, while HPs and other non-neoplastic histology are considered non-neoplastic.
Study Design: N/A: single arm study, Open (masking not used), N/A , unknown, Other
| 2443187 | ecrin-mdr-crc