Artificial Intelligence and the Future of Cancer Detection

#artificialintelligence

At the International Symposium on Biomedical Imaging in Prague this past April, a Harvard-based artificial intelligence system won the Camelyon16 challenge, a competition comprised of participants introducing their individual AI system and its ability to facilitate automated lymph node metastasis diagnosis. Referred to as PathAl, the computing system identifies cancerous cells through deep learning--an algorithmic technique that accumulates copious amounts of unstructured data and organizes it into clusters before analyzing it for patterns. Deep learning is predominately used in speech recognition systems like Apple's Siri and Microsoft's Cortana. According to one of the challenge's organizers, Jeroen van der Laak of Radboud University Medical Center in Netherlands, the technology featured in the competition went "way beyond" his expectations, as the AI's accuracy proved strikingly close to that of human beings. In addition, van der Laak said AI technology has the propensity to intrinsically redefine the way histopathological images are handled in the medical community.


Artificial intelligence promising for CA, retinopathy diagnoses

#artificialintelligence

Babak Ehteshami Bejnordi, from the Radboud University Medical Center in Nijmegen, Netherlands, and colleagues compared the performance of automated deep learning algorithms for detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer with pathologists' diagnoses in a diagnostic setting. The researchers found that the area under the receiver operating characteristic curve (AUC) ranged from 0.556 to 0.994 for the algorithms. The lesion-level, true-positive fraction achieved for the top-performing algorithm was comparable to that of the pathologist without a time constraint at a mean of 0.0125 false-positives per normal whole-slide image. Daniel Shu Wei Ting, M.D., Ph.D., from the Singapore National Eye Center, and colleagues assessed the performance of a DLS for detecting referable diabetic retinopathy and related eye diseases using 494,661 retinal images. The researchers found that the AUC of the DLS for referable diabetic retinopathy was 0.936, and sensitivity and specificity were 90.5 and 91.6 percent, respectively.


Causal Inference through a Witness Protection Program

arXiv.org Machine Learning

One of the most fundamental problems in causal inference is the estimation of a causal effect when variables are confounded. This is difficult in an observational study, because one has no direct evidence that all confounders have been adjusted for. We introduce a novel approach for estimating causal effects that exploits observational conditional independencies to suggest "weak" paths in a unknown causal graph. The widely used faithfulness condition of Spirtes et al. is relaxed to allow for varying degrees of "path cancellations" that imply conditional independencies but do not rule out the existence of confounding causal paths. The outcome is a posterior distribution over bounds on the average causal effect via a linear programming approach and Bayesian inference. We claim this approach should be used in regular practice along with other default tools in observational studies.


Stephen Hawking - Wikipedia

@machinelearnbot

Stephen William Hawking CH CBE FRS FRSA (8 January 1942 – 14 March 2018)[14][15] was an English theoretical physicist, cosmologist, author and Director of Research at the Centre for Theoretical Cosmology within the University of Cambridge.[16][17] His scientific works included a collaboration with Roger Penrose on gravitational singularity theorems in the framework of general relativity and the theoretical prediction that black holes emit radiation, often called Hawking radiation. Hawking was the first to set out a theory of cosmology explained by a union of the general theory of relativity and quantum mechanics. He was a vigorous supporter of the many-worlds interpretation of quantum mechanics.[18][19] Hawking was an Honorary Fellow of the Royal Society of Arts (FRSA), a lifetime member of the Pontifical Academy of Sciences, and a recipient of the Presidential Medal of Freedom, the highest civilian award in the United States. In 2002, Hawking was ranked number 25 in the BBC's poll of the 100 Greatest Britons. He was the Lucasian Professor of Mathematics at the University of Cambridge between 1979 and 2009 and achieved commercial success with works of popular science in which he discusses his own theories and cosmology in general. His book, A Brief History of Time, appeared on the British Sunday Times best-seller list for a record-breaking 237 weeks. Hawking had a rare early-onset slow-progressing form of motor neurone disease (also known as amyotrophic lateral sclerosis and Lou Gehrig's disease), that gradually paralysed him over the decades.[20][21] Even after the loss of his speech, he was still able to communicate through a speech-generating device, initially through use of a hand-held switch, and eventually by using a single cheek muscle. Hawking was born on 8 January 1942[22] in Oxford to Frank (1905–1986) and Isobel Hawking (née Walker; 1915–2013).[23][24] Despite their families' financial constraints, both parents attended the University of Oxford, where Frank read medicine and Isobel read Philosophy, Politics and Economics.[24] The two met shortly after the beginning of the Second World War at a medical research institute where Isobel was working as a secretary and Frank was working as a medical researcher.[24][26] They lived in Highgate; but, as London was being bombed in those years, Isobel went to Oxford to give birth in greater safety.[27] Hawking had two younger sisters, Philippa and Mary, and an adopted brother, Edward.[28] In 1950, when Hawking's father became head of the division of parasitology at the National Institute for Medical Research, Hawking and his family moved to St Albans, Hertfordshire.[29][30]


Genome Classification Systematics: Application to Human and Simian Immunodeficiency Viruses

AAAI Conferences

Alexander A. Filyukov Keldysh Institute of Applied Mathematics Russian Academy of Sciences Moscow 125047, Russia Abstract My contribution to the AAAI 1995 Spring Symposium on Systematic Methods of Scientific Discovery starts with the brief sketch of consequences which followed the discovery that genomic molecules are existing and operating in nonequilibrium excited steady state. The proof of the latter statement was obtained through computer assisted investigations of genomic sequence of a particular virus. The strategy used for investigation was based on the general definition of any individual organism as a Gibbsian ensemble of identical personal DNA molecules. This approach provides application of methods of statistical thermodynamics of irreversible steady processes to genome informatics. The random processes theory and its Markov chains approximation lead in this approach directly to the definition of the generalized concept of evolution entropy and to the genuine measure of text information content in the sequences.