Goto

Collaborating Authors

Innovative AI Breath Analyzer Diagnoses Diseases by "Smell"

#artificialintelligence

Imagine being able to know if you have Parkinson's disease, multiple sclerosis, liver failure, Crohn's diseases, pulmonary hypertension, chronic kidney disease, or any number of cancers based on a simple, non-invasive test of your breath. Breath analyzers to detect alcohol have been around for well over half a century--why not apply the same concept to detect diseases? A global team of scientists from universities in Israel, France, Latvia, China and the United States have developed an artificial intelligence (AI) system to detect 17 diseases from exhaled breath with 86 percent accuracy. The research team led by Professor Hassam Haick of the Technion-Israel Institute of Technology collected breath samples from 1404 subjects with either no disease (healthy control) or one of 17 different diseases. The disease conditions include lung cancer, colorectal cancer, head and neck cancer, ovarian cancer, bladder cancer, prostate cancer, kidney cancer, gastric cancer, Crohn's disease, ulcerative colitis, irritable bowel syndrome, idiopathic Parkinson's, atypical Parkinson ISM, multiple sclerosis, pulmonary hypertension, pre-eclampsia toxemia, and chronic kidney disease.


Intel and Penn Medicine are developing an AI to spot brain tumors

Engadget

We've seen AI outperform doctors in spotting breast cancer, lung cancer and skin cancer. Now, researchers from Intel and the University of Pennsylvania are turning their attention to brain tumors. Using Intel's AI hardware and software, Penn Medicine will lead 29 international healthcare and research institutions in creating an AI model trained on the largest brain tumor dataset ever -- and will do so without sharing sensitive patient data. The project is based on a technique called federated learning, which trains an algorithm across decentralized servers, so that hospitals can work together without actually sharing patient data. This will allow the institutions -- from the US, Canada, the UK, Germany, the Netherlands, Switzerland and India -- to create a much larger data set than any one institution would be able to on its own.


AI cancer detectors

The Guardian

An AI system developed by a team from Germany, France and the US can diagnose skin cancer more accurately than dermatologists. In the study, the software was able to accurately detect cancer in 95% of images of cancerous moles and benign spots, whereas a team of 58 dermatologists was accurate 87% of the time. Chinese researchers have developed an algorithm that can diagnose prostate cancer as accurately as a pathologist. Research leader Hongqian Guo of Nanjing University said: "[This] will help pathologists make better, faster diagnoses, as well as eliminating the day-to-day variation in judgment that can creep into human evaluations." Researchers at the University of Texas, Houston, have developed software to accurately contour the shape of head and neck cancer tumours.


Advance articles Annals of Oncology

#artificialintelligence

Accepted Manuscript Editorial 28 May 2018 Artificial intelligence for melanoma diagnosis: How can we deliver on the promise? Published: 28 May 2018 Section: Editorial Melanoma Corrected Proof Research Article 28 May 2018 Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists H A Haenssle; C Fink; R Schneiderbauer; F Toberer; T Buhl ... Annals of Oncology, mdy166, https://doi.org/10.1093/annonc/mdy166 Published: 28 May 2018 Section: Original Article Corrected Proof Review Article 28 May 2018 Gastrointestinal stromal tumours: ESMO–EURACAN Clinical Practice Guidelines for diagnosis, treatment and follow-up P G Casali; N Abecassis; S Bauer; R Biagini; S Bielack ... Annals of Oncology, mdy095, https://doi.org/10.1093/annonc/mdy095 Published: 28 May 2018 Section: clinical practice guidelines Corrected Proof Review Article 28 May 2018 Soft tissue and visceral sarcomas: ESMO–EURACAN Clinical Practice Guidelines for diagnosis, treatment and follow-up P G Casali; N Abecassis; S Bauer; R Biagini; S Bielack ... Annals of Oncology, mdy096, https://doi.org/10.1093/annonc/mdy096 Published: 28 May 2018 Section: clinical practice guidelines Corrected Proof Review Article 23 May 2018 Hodgkin lymphoma: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up D A Eichenauer; B M P Aleman; M André; M Federico; M Hutchings ... Annals of Oncology, mdy080, https://doi.org/10.1093/annonc/mdy080 Published: 23 May 2018 Section: clinical practice guidelines Accepted Manuscript Review Article 22 May 2018 Advances in the systemic treatment of melanoma brain metastases I C Glitza Oliva; G Schvartsman; H Tawbi Annals of Oncology, mdy185, https://doi.org/10.1093/annonc/mdy185


Detecting cutaneous basal cell carcinomas in ultra-high resolution and weakly labelled histopathological images

arXiv.org Machine Learning

Diagnosing basal cell carcinomas (BCC), one of the most common cutaneous malignancies in humans, is a task regularly performed by pathologists and dermato-pathologists. Improving histological diagnosis by providing diagnosis suggestions, i.e. computer-assisted diagnoses is actively researched to improve safety, quality and efficiency. Increasingly, machine learning methods are applied due to their superior performance. However, typical images obtained by scanning histological sections often have a resolution that is prohibitive for processing with current state-of-the-art neural networks. Furthermore, the data pose a problem of weak labels, since only a tiny fraction of the image is indicative of the disease class, whereas a large fraction of the image is highly similar to the non-disease class. The aim of this study is to evaluate whether it is possible to detect basal cell carcinomas in histological sections using attention-based deep learning models and to overcome the ultra-high resolution and the weak labels of whole slide images. We demonstrate that attention-based models can indeed yield almost perfect classification performance with an AUC of 0.95.