AI-Provided Instant Differential Diagnosis of Pemphigus Vulgaris and Bullous Pemphigoid: Qualitative Study (Preprint)

2020 ◽  
Author(s):  
Xiaoyu He ◽  
Juan Su ◽  
Guangyu Wang ◽  
Kang Zhang ◽  
Navarini Alexander ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Early Diagnosis ◽  
Image Classification ◽  
Bullous Pemphigoid ◽  
Skin Diseases ◽  
Pemphigus Vulgaris ◽  
Classification Model ◽  
Clinical Image ◽  
Clinical Images ◽  
Multimodal Classification

BACKGROUND Pemphigus vulgaris (PV) and bullous pemphigoid (BP) are two rare but severe inflammatory dermatoses. Due to the regional lack of trained dermatologists, many patients with these two diseases are misdiagnosed and therefore incorrectly treated. An artificial intelligence diagnosis framework would be highly adaptable for the early diagnosis of these two diseases. OBJECTIVE Design and evaluate an artificial intelligence diagnosis framework for PV and BP. METHODS The work was conducted on a dermatological dataset consisting of 17,735 clinical images and 346 patient metadata of bullous dermatoses. A two-stage diagnosis framework was designed, where the first stage trained a clinical image classification model to classify bullous dermatoses from five common skin diseases and normal skin and the second stage developed a multimodal classification model of clinical images and patient metadata to further differentiate PV and BP. RESULTS The clinical image classification model and the multimodal classification model achieved an area under the receiver operating characteristic curve (AUROC) of 0.998 and 0.942, respectively. On the independent test set of 20 PV and 20 BP cases, our multimodal classification model (sensitivity: 0.85, specificity: 0.95) performed better than the average of 27 junior dermatologists (sensitivity: 0.68, specificity: 0.78) and comparable to the average of 69 senior dermatologists (sensitivity: 0.80, specificity: 0.87). CONCLUSIONS Our diagnosis framework based on clinical images and patient metadata achieved expert-level identification of PV and BP, and is potential to be an effective tool for dermatologists in remote areas in the early diagnosis of these two diseases.

scholarly journals Applying Artificial Intelligence for the Diagnosis and Classification of Rosacea (Preprint)

2020 ◽  
Author(s):  
Zhixiang Zhao ◽  
CheMing Wu ◽  
Shuping Zhang ◽  
Fanping He ◽  
Fangfen Liu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Skin Diseases ◽  
Seborrheic Dermatitis ◽  
Characteristic Curve ◽  
Clinical Manifestations ◽  
Accurate Identification ◽  
Clinical Images ◽  
Convolution Neural Networks ◽  
Accuracy And Precision

BACKGROUND Rosacea is a chronic inflammatory disease with variable clinical presentations including transient flushing, fixed erythema, papules, pustules and phymatous changes on the central face. Owing to the diversity of clinical manifestations, the lack of objective biochemical examinations and non-specificity of histopathology, accurate identification of rosacea is a big challenge. Artificial intelligence has emerged as a potential tool in the identification and evaluation of some skin diseases such as melanoma, basal cell carcinoma and psoriasis. OBJECTIVE In this work, we utilized convolution neural networks (CNN) to identify the clinical photos (from three different angles) of patients with rosacea and other diseases that would be easily confused with rosacea (such as acne, seborrheic dermatitis and eczema). METHODS In this work, we utilized convolution neural networks (CNN) to identify the clinical photos (from three different angles) of patients with rosacea and other diseases that would be easily confused with rosacea (such as acne, seborrheic dermatitis and eczema). RESULTS The CNN in our study achieved an overall accuracy and precision of 0.914 and 0.898, with an area under the receiver operating characteristic curve (AUROC) of 0.972 for the detection of rosacea. The accuracy of classifying the three subtypes of rosacea, ETR, PPR, PhR was 83.9%, 74.3% and 80.0%, respectively. Moreover, the accuracy and precision of our CNN to distinguish rosacea from acne reached 0.931 and 0.893, respectively. For the identificaiton between rosacea, seborrheic dermatitis and eczema, the overall accuracy was 0.757 and the precision was 0.667. Finally, by comparing the CNN with different levels of dermatologists, we showed that our CNN system is capable of identifying rosacea with a performance superior to resident doctors or attending physicians and comparable to experienced specialists. CONCLUSIONS In conclusion, by assessing clinical images, the CNN system in our study performed at dermatologist-level in the identification of rosacea. CLINICALTRIAL None

scholarly journals Bullous Skin Diseases: Classical Types of Autoimmune Diseases

Scientifica ◽  
2013 ◽  
Vol 2013 ◽  
pp. 1-5 ◽  
Author(s):  
Jan Damoiseaux
Keyword(s):  
Autoimmune Diseases ◽  
Bullous Pemphigoid ◽  
Oral Mucosa ◽  
Skin Diseases ◽  
Pemphigus Vulgaris ◽  
Pemphigus Foliaceus ◽  
Blister Formation ◽  
Koch’S Postulates ◽  
Bullous Skin Diseases ◽  
Koch's Postulates

The prototypic bullous skin diseases, pemphigus vulgaris, pemphigus foliaceus, and bullous pemphigoid, are characterized by the blister formation in the skin and/or oral mucosa in combination with circulating and deposited autoantibodies reactive with (hemi)desmosomes. Koch’s postulates, adapted for autoimmune diseases, were applied on these skin diseases. It appears that all adapted Koch’s postulates are fulfilled, and, therefore, these bullous skin diseases are to be considered classical autoimmune diseases within the wide and expanding spectrum of autoimmune diseases.

Penetration of mouse and human skin by cercariae of Schistosoma mansoni; immunological and histological observations

1980 ◽  
Vol 79 (1-3) ◽  
pp. 173-182
Author(s):  
H. V. Smith ◽  
A. McQueen ◽  
J. R. Kusel
Keyword(s):  
Schistosoma Mansoni ◽  
Human Skin ◽  
Bullous Pemphigoid ◽  
Skin Diseases ◽  
Mouse Skin ◽  
Pemphigus Vulgaris ◽  
Intercellular Substance ◽  
Human Cadaver Skin ◽  
Cadaver Skin

SynopsisSera from patients suffering from the autoimmune skin diseases pemphigus vulgaris and bullous pemphigoid were used to demonstrate the presence of intercellular substance (ICS) or bullous pemphigoid antigen (BPA) on the surface of the schistosomula of Schistosoma mansoni which had penetrated mouse and human cadaver skin, and mouse skin percutaneously. Both ICS and BPA were absent from mechanically transformed schistosomula or those formed in the peritoneal cavity of mice. Schistosomula which penetrated slowly through mouse or human skin in vitro, acquired more ICS or BPA than those which penetrated rapidly.During percutaneous infections of mice, schistosomula recovered from skin after 2h and 24h had acquired large quantities of these materials whereas those which were recovered from skin after 10min had no detectable ICS or BPA. These materials must be shed during subsequent migration since schistosomula from lungs and liver, and 7-week old adults do not possess them.Histological examination of both mouse and human skin revealed that the schistosomula remained in the epidermis for varying lengths of time. Schistosomula which remained there for more than 2h became vacuolated, whereas schistosomula which were present in the dermis at 2h appeared undamaged.On cercarial penetration of human skin, the granular layer of the epidermis became disrupted or condensed. The implications of these findings are discussed.

scholarly journals Automatic skin disease diagnosis using deep learning from clinical image and patient information

2021 ◽  
Author(s):  
Kedir Ali Muhaba ◽  
Kokeb Dese ◽  
Tadele Mola Aga ◽  
Feleke Tilahun Zewdu ◽  
Gizeaddis Lamesgin Simegn
Keyword(s):  
Deep Learning ◽  
Patient Information ◽  
Skin Disease ◽  
Skin Diseases ◽  
Disease Diagnosis ◽  
Automated System ◽  
Clinical Image ◽  
Clinical Images ◽  
Common Diagnosis ◽  
The Common

Abstract Background Skin diseases are the fourth most common cause of human illness which results enormous non-fatal burden in daily life activities. They are caused by chemical, physical and biological factors. Visual assessment in combination with clinical information is the common diagnosis procedure for the diseases. However, these procedures are manual, time consuming, and require experience and excellent visual perception. Methods In this study, an automated system is proposed for diagnosis of five common skin diseases by using data from clinical images and patient information using deep learning pretrained mobilenet-v2 model. Clinical images were acquired using different smartphone cameras and patient’s information were collected during patient registration. Different data preprocessing and augmentation techniques were applied to boost the performance of the model prior to training. Results A multiclass classification accuracy of 97.5%, sensitivity of 97.7% and precision of 97.7% has been achieved using the proposed technique for the common five skin disease. The results demonstrate that, the developed system provides excellent diagnosis performance for the five skin diseases. Conclusion The system has been designed as a smartphone application and it has a potential to be used as a decision support system in low resource settings, where both the expert dermatologist and the means is limited.

Xiangya-Derm, A Chinese Database For Artificial Intelligence and Research on Classification of Six Common Skin Diseases (Preprint)

2021 ◽  
Author(s):  
Shuang Zhao ◽  
Xianggui Wang ◽  
Zixi Jiang ◽  
Yixin Li ◽  
Zhe Wu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Rural Areas ◽  
Chinese Population ◽  
Skin Diseases ◽  
Initial Study ◽  
Input Image ◽  
Clinical Images ◽  
Short Supply ◽  
Common Skin

BACKGROUND Skin and subcutaneous disease is the fourth leading cause of nonfatal disease burden globally and also one of the most common chief complaints in primary care. However, dermatologists are consistently in short supply, particularly in Chinese rural areas. Artificial intelligence tools can assist in diagnosing skin disorders from images, however the database for Chinese population is very limited, and it’s also non-trivial to directly apply the datasets built upon the US or EU population. OBJECTIVE To establish a dataset for artificial intelligence based on Chinese population, and present an initial study on six common skin diseases. METHODS Each image is captured with digital cameras or smartphones and verified by at least 3 experienced dermatologists and corresponding pathology information, and finally formed the Xiangya-Derm database. Based on this database, we conducted artificial intelligence-assisted classification research on 6 common skin diseases and then proposed a network called SkinNet. SkinNet applied a two-step strategy to identify skin diseases. Firstly, given an input image, we segment the regions of the skin lesion; Secondly, we introduce an information fusion block to combine the output of all segmented regions. We compare the performance with 31 dermatologists of varied experiences. RESULTS Xiangya-Derm, as a new database which consists of over 150,000 clinical images of 571 different skin diseases from Chinese population. It is known to be the largest and most abundant dermatological dataset of the Chinese. The artificial intelligence–based six-classification achieves the top-3 accuracy of 84.77%, which outperforms the average accuracy of dermatologists (78.15%). CONCLUSIONS Xiangya-Derm, a new and the largest database for the Chinese population was formed and the accuracy of classification of six common skin conditions based on Xiangya-Derm is comparable to that of dermatologists.

scholarly journals Study of Various Vesiculobullous Lesions Using Tzanck Smear

2020 ◽  
Vol 7 (6) ◽  
pp. A301-305
Author(s):  
Sanchit Singhal ◽  
Hemalata M
Keyword(s):  
Early Diagnosis ◽  
Bullous Pemphigoid ◽  
Viral Infections ◽  
Pemphigus Vulgaris ◽  
Giant Cells ◽  
Pemphigus Foliaceus ◽  
Dermoepidermal Junction ◽  
Non Invasive ◽  
Histopathological Correlation ◽  
Invasive Method

Background: The vesiculobullous reaction pattern is characterized by the presence of vesicles or bullae within the epidermis or at the dermoepidermal junction. Despite some having characteristic presentations, it’s difficult to make a definite diagnosis clinically. Hence, cytological evaluation is required for reliable and early diagnosis. Objectives of the study are to determine the incidence of various vesiculobullous lesions and evaluate cytology as a tool for early diagnosis of vesiculobullous lesions. Methods: For Tzanck smears fresh vesicle or bulla was selected and incised with scalpel, reflecting the roof of bulla. Base of the blister scraped gently and material spread on a glass slide. These smears were stained with MGG (air dried), Pap and H&E stains (fixed).Skin punch biopsies from the bullae were subjected to routine fixation, processing, sectioning and staining. Results: A total of 62 Tzanck smears were done for vesiculobullous lesions of skin of which 29 had histopathological correlation. Herpes constituted the most common vesiculobullous disorder (42%) followed by bullous pemphigoid (27.4%) and pemphigus vulgaris (19.3%). Most patients were in the age group 61- 70 years. The M:F ratio of 1:1.38 showing female preponderance. Tzanck smears showed acantholytic cells in pemphigus group, eosinophils in bullous pemphigoid and multinucleate giant cells in viral blisters. Histopathology showed intraepidermal acantholysis in pemphigus vulgaris, subcorneal blister in pemphigus foliaceus and subepidermal in bullous pemphigoid. Conclusion: Cytohistopathological correlation showed an overall sensitivity of 79%. Tzanck smear showed 96% sensitivity for viral infections. Tzanck smear is a quick, non-invasive method for the early diagnosis of vesiculobullous disorders.

scholarly journals A retrospective study on clinical and demographic features of autoimmune vesiculobullous disorders from a rural tertiary care institute in Tamil Nadu

2019 ◽  
Vol 5 (3) ◽  
pp. 486
Author(s):  
Rajalakshmi Ramalingam ◽  
Vikram Kumar Adaikalam Ganapathy ◽  
Seethalakshmi Rajanga Chandrasekar ◽  
Balasubramanian Narasiman ◽  
Deivam Subbaraya Gounder
Keyword(s):  
Retrospective Study ◽  
Bullous Pemphigoid ◽  
Medical Records ◽  
Tamil Nadu ◽  
Skin Diseases ◽  
Tertiary Care ◽  
Pemphigus Vulgaris ◽  
Age Group ◽  
Care Institute ◽  
Heterogenous Group

<p class="abstract"><strong>Background:</strong> Autoimmune vesiculobullous disorders are a heterogenous group of skin diseases in which autoantibodies are directed against cell adhesion molecules which are essential for the integrity of skin and oral mucosa. They are clinically characterized by the presence of vesicles, bullae or erosions over the skin and/ or mucosa depending on the antibodies involved. They are divided into intraepidermal and subepidermal based on the location of the bulla. Among intraepidermal bullous disorders, pemphigus vulgaris (PV) is most common. Bullous pemphigoid (BP) is the most common among the subepidermal bullous disorders. Although they occur worldwide, the incidence shows geographical variation. A retrospective study was carried out with the objective to analyse the clinical and demographic profile of patients with autoimmune vesiculobullous disorders among patients attending a tertiary care teaching hospital in a rural setup.</p><p class="abstract"><strong>Methods:</strong> A total of 137 case sheets were audited from the Medical Records Department of our institute. Details were collected and tabulated, compiled and analysed.<strong></strong></p><p class="abstract"><strong>Results:</strong> Out of the 137 cases studied, intraepidermal autoimmune vesiculobullous disorders accounted for 63.4% of cases, and subepidermal autoimmune vesiculobullous disorders accounted for 36.6% of cases. Out of the 137 cases, 74 patients (54%) were females, and 63 patients (46%) were males. Majority of the patients were in the age group of 51-60 years (29.9%), followed by 41-50 years (24.1%) and 61-70 years (17.5%).</p><p class="abstract"><strong>Conclusions:</strong> Pemphigus vulgaris was the most common among the intraepidermal autoimmune vesiculobullous disorders, and bullous pemphigoid was the most common among the subepidermal autoimmune vesiculobullous disorders.</p>

scholarly journals Quantum Enhanced Filter: QFilter

2021 ◽  
Author(s):  
Parfait Atchade ◽  
Guillermo Alonso-Linaje
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Classification Model ◽  
Classification Methods ◽  
Convolutional Networks ◽  
Classical Computing

Abstract Convolutional Neural Networks (CNN) are used mainly to treat problems with many images characteristic of Deep Learning. In this work, we propose a hybrid image classification model to take advantage of quantum and classical computing. The method will use the potential that convolutional networks have shown in artificial intelligence by replacing classical filters with variational quantum filters. Similarly, this work will compare with other classification methods and the system's execution on different servers. The algorithm's quantum feasibility is modelled and tested on Amazon Braket Notebook instances and experimented on the Pennylane's philosophy and framework.

Statistical Study of Patients with pemphigus Vulgaris and Bullous Pemphigoid at Saga Medical School Hospital.

1993 ◽  
Vol 55 (6) ◽  
pp. 1092-1095 ◽  
Author(s):  
Tatsurou TANAKA ◽  
Kiyohisa MOTOKI ◽  
Takahisa NISHI ◽  
Yutaka NARISAWA ◽  
Hiromu KOHDA
Keyword(s):  
Medical School ◽  
Bullous Pemphigoid ◽  
Statistical Study ◽  
Pemphigus Vulgaris

PROSPECTS OF ARTIFICIAL INTELLIGENCE IN CARRYING OUT THE ONCOLOGICAL COMPONENT OF MEDICAL EXAMINATION OF THE POPULATION

2019 ◽  
Vol 65 (2) ◽  
pp. 234-237
Author(s):  
Vyacheslav Cherenkov ◽  
A. Petrov ◽  
I. Gulkov ◽  
A. Kostyukov
Keyword(s):  
Artificial Intelligence ◽  
Early Diagnosis ◽  
Mass Screening ◽  
Malignant Tumors ◽  
Risk Groups ◽  
Modern World ◽  
Pilot Program ◽  
Urgent Problem ◽  
Gender And Age ◽  
Group Version

Diagnosis of malignant tumors is an urgent problem of the modern world. Early diagnosis depends on General practitioners. The doctor should conduct a systematic examination of the patient regularly, taking into account the risk groups, gender and age. With mass screening, signs of dysplasia or an early focus, developing cancer can «slip away» [1]. Optimization of analysis and examination algorithms is required, which is not always possible for one person. Positive application of the digital program with elements of imaging in Oncology, we were able to create such a class of tasks for the preliminary subjective-objective survey of patients in three versions: with a widescreen screen and consoles for patients (group version up to 15 or more patients), interactive (touch) and tablet. The results of the survey are sent through the accepted channels to the doctor with recommendations for further examination, and the patient is given a coupon. The pilot program showed that the system of such robotic technologies in the future can replace the oncologist in its development to artificial intelligence at the stage of the primary link.

Sign in / Sign up

Export Citation Format

Share Document