Google AI Claims 99 Percent Accuracy In Metastatic Breast Cancer Detection 34
Researchers at the Naval Medical Center San Diego and Google AI, a division within Google dedicated to artificial intelligence research, are using cancer-detecting algorithms to detect metastatic tumors by autonomously evaluating lymph node biopsies. VentureBeat reports: Their AI system -- dubbed Lymph Node Assistant, or LYNA -- is described in a paper titled "Artificial Intelligence-Based Breast Cancer Nodal Metastasis Detection," published in The American Journal of Surgical Pathology. In tests, it achieved an area under the receiver operating characteristic (AUC) -- a measure of detection accuracy -- of 99 percent. That's superior to human pathologists, who according to one recent assessment miss small metastases on individual slides as much as 62 percent of the time when under time constraints. LYNA is based on Inception-v3, an open source image recognition deep learning model that's been shown to achieve greater than 78.1 percent accuracy on Stanford's ImageNet dataset. As the researchers explained, it takes as input a 299-pixel image (Inception-v3's default input size), outlines tumors at the pixel level, and, in the course of training, extracts labels -- i.e., predictions -- of the tissue patch ("benign" or "tumor") and adjusts the model's algorithmic weights to reduce error.
In tests, LYNA achieved 99.3 percent slide-level accuracy. When the model's sensitivity threshold was adjusted to detect all tumors on every slide, it exhibited 69 percent sensitivity, accurately identifying all 40 metastases in the evaluation dataset without any false positives. Moreover, it was unaffected by artifacts in the slides such as air bubbles, poor processing, hemorrhage, and overstaining. LYNA wasn't perfect -- it occasionally misidentified giant cells, germinal cancers, and bone marrow-derived white blood cells known as histiocytes -- but managed to perform better than a practicing pathologist tasked with evaluating the same slides. And in a second paper published by Google AI and Verily, Google parent company Alphabet's life sciences subsidiary, the model halved the amount of time it took for a six-person team of board-certified pathologists to detect metastases in lymph nodes.
In tests, LYNA achieved 99.3 percent slide-level accuracy. When the model's sensitivity threshold was adjusted to detect all tumors on every slide, it exhibited 69 percent sensitivity, accurately identifying all 40 metastases in the evaluation dataset without any false positives. Moreover, it was unaffected by artifacts in the slides such as air bubbles, poor processing, hemorrhage, and overstaining. LYNA wasn't perfect -- it occasionally misidentified giant cells, germinal cancers, and bone marrow-derived white blood cells known as histiocytes -- but managed to perform better than a practicing pathologist tasked with evaluating the same slides. And in a second paper published by Google AI and Verily, Google parent company Alphabet's life sciences subsidiary, the model halved the amount of time it took for a six-person team of board-certified pathologists to detect metastases in lymph nodes.
Re: (Score:2)
That's somewhere between 17x17 and 17x18, which makes it even more impressive.
The default image for Inception-V3 is 299x299 RGB = 89401 pixels.
The journalist is a moron. All he had to do was cut-and-paste, and he screwed it up.
Re: (Score:3)
Very large training data set available on line.
Re: (Score:2)
Re: (Score:2)
If you'd even attempt to make a real argument I could provided some (layman level) reasons however...
Endgame (Score:2)
This will allow Google to properly target ads to breast cancer patients.
I'm better. (Score:2)
I just tell everyone I meet they have cancer. I haven't missed someone with cancer yet.
I never met ... (Score:2)
... a static I didn't like.
TLDR takeaway (Score:2)
If Google is starting to feel everyone up "looking for cancer" I'd say it's more than time to go use DuckDuckGo!
statistics (Score:3, Informative)
1 in 99 is really bad
1000 women, about 120 will get breast cancer, if we miss-diagnose 10 cases, that could be as bad as 8% failure
fuck statistics
Re:statistics (Score:5, Insightful)
99% is pretty good for a notoriously difficult problem.
Yeah, sucks if you're part of the 1%, but you'd be part of the 100% if there wasn't any test.
Re: (Score:2, Insightful)
I wanted to comment on a few things about medical statistics that are easy to misunderstand. Unfortunately, the summary of the article misuses some terminology which further obfuscates the issue.
Some basic measures of a test are its sensitivity and specificity.
1. Sensitivity is a measure of false negatives. It means that if you have 100 people with the disease, the test catches this percentage. So a test with a sensitivity of 99% would be positive on 99/100 patients with the disease.
2. Specificity is a m
Re: (Score:1)
Yeah. Fuck facts. #MAGA.
Re: (Score:2)
My understanding is that this is about the screening detecting metastatic spread of the breast cancer. Detect tumors, treat tumors (operation, radiation, chemotherapy), take biopsy samples of lymph nodes, analyze samples to detect cancer cells - if there are any further treatment is needed (chemo). Something like that.
So the missed case is one of the people (men can get breast cancer too) that have cancer spreading through the lymphatic system.