/
Source: TG-Derma Topic Driver Source: TG-Derma Topic Driver

Source: TG-Derma Topic Driver - PowerPoint Presentation

cecilia
cecilia . @cecilia
Follow
66 views
Uploaded On 2023-05-21

Source: TG-Derma Topic Driver - PPT Presentation

Title Att3 Presentation TGDerma Purpose Discussion Contact Sharad Kumar Email sharadkumarsloanmitedu Abstract This PPT summarizes the status of work within TGDerma for presentation and discussion during the meeting ID: 998795

patient cancer disease skin cancer patient skin disease phone data image oral diseases forum history group derma datasets server

Share:

Link:

Embed:

Download Presentation from below link

Download Presentation The PPT/PDF document "Source: TG-Derma Topic Driver" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.


Presentation Transcript

1. Source:TG-Derma Topic DriverTitle:Att.3 - Presentation (TG-Derma)Purpose:DiscussionContact:Sharad KumarE-mail: sharad.kumar@sloan.mit.eduAbstract:This PPT summarizes the status of work within TG-Derma, for presentation and discussion during the meeting.FGAI4H-O-007-A03Berlin, 31 May – 2 June 2022

2. SKIN CANCERS‣‣‣One in every three cancers diagnosed is a skin cancerEvery year approximately 3 million new cases of skin cancer are detected worldwide, more than breast cancer, prostate cancer, lung cancer and colon cancer combinedAccording to Skin Cancer Foundation Statistics, one in every five Americans will develop skin cancer in their lifetimeThe Global Burden of Disease project has shown that skin diseases continue to be the 4th leading cause of nonfatal disease burden world-wide

3. GROWING DISEASES LIST: 100 DISEASES IN 18 MONTHS!1Acanthosis nigricans2Acne3Actinic keratosis4Alopecia5Anogenital warts6Basal cell carcinoma7Bowens disease8Bullous pemphigoid9Candidiasis10Chicken pox11Eczema12Fixed drug eruption13Genital herpes14Hemangioma15Herpes zoster16Hidradenitis suppurativa17Ichthyosis18Impetigo and Pyodermas19Keloids/ Hypertrophic scar20Keratoacanthoma21Lichen planus22Lichen sclerosus et atrophicus23Melanocytic nevi/Mole24Melanoma25Melasma26Milia27Molluscum contagiosum28Morphea29Normal skin30Paronychia31Pemphigus32Pityriasis alba33Pityriasis rosea34Pityriasis versicolor35Psoriasis36Rosacea37Scabies38Seborrheic keratosis39Secondary syphilis40Squamous cell carcinoma41Striae42Tinea capitis43Tinea cruris, corporis or faciei44Tinea manuum45Tinea pedis46Tinea unguium47Urticaria48Viral warts49Vitiligo/Leucoderma50Xanthelasma palpebrarumAverage▸ Next Stage๏ Expand data set: Africa and West๏ Master Disease Lists

4. MARKET IN NEED: ORAL DISEASES‣‣In India 6 people die every hour everyday because of oral cancer.About 60-80% Indian patients present with advanced disease versus 40% in developed countriesEarly-stage detection offers the best chance for long-term survival and lower treatment cost

5. THE PHONE APP: SEE VIDEO & DOWNLOAD PROTOTYPE APP▸ Download app on Google or Apple▸ No additional hardware except phone camera

6. SOLUTION; PROVIDE MACHINE LEARNING DRIVEN SOLUTION▸ Augment Doctors & Healthcare Workers๏ Mobile phone based decision support using AI1. Non Specialist takes pictures of patient with oral disease via mobile phone and fills in interactive questionnaire3. Server returns diagnosed diseased class. No images or private information stored on server without consentDisease: SCC 95%Treatment::QUESTIONS AGE: SYMPTOMS: HISTORY:2. Patient images andother history information sent to secure cloud serverfor diagnosis4. Correct diagnoses received by doctor with no wait-timeNew Patient

7. OPERATIONAL VALIDATION: 5,500 PATIENT STUDY AT AIIMSLargest peer reviewed AI- driven study in dermatology

8. DERMASub Group Objective: The initial objectives of this subtopic group community forum include:Providing a forum to discuss NEEDS for input image standardisation along with needed data structures for patient data. For example, JPEG, DICOM etc. for image plus additional fields for patient history. This could also include audio and video data if the need is established.Providing a forum to discuss APIs for image pre-processing for quality adherenceDeveloping an anonymized dataset that adheres to the guidelines that are developed. There might be opportunity to embellish existing datasets.A related charter of this group can be development of possible exploration of methods for developing artificial datasets and standardization of protocol around these