MIT Technology Review · Sep 28, 2015
MIT Technology Review reports how imaging tools are changing radiology work
Markdown · JSON · Original source
MIT Technology Review’s article, published September 28, 2015, describes how digital imaging, data science and medical tools were changing radiologists’ work. The article says software can help reconstruct and measure tumors, while the growing volume of images creates a risk that radiologists may miss images important to identifying pathologies. The article reports that IBM was testing computer-based reasoning, machine learning and analytical problem solving to flag important images for radiologists. IBM said early work showed the system could learn to recognize a pathology and alert radiologists; a company scientist said testing reached over 80 percent accuracy for certain medical conditions. These were reported test results, not evidence of performance in routine clinical use. The article also describes Brainlab systems that let surgeons use imaging during operations while radiologists review live feeds and coordinate treatment. It says image-guided techniques are expanding the treatments radiologists and other physicians can perform, blurring boundaries between specialties. The article reports that, for some procedures, the available department may determine which specialist treats a patient. How are hospitals to decide which specialty should handle a procedure when multiple specialists can perform it?
Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.
Original source
MIT Technology Review · Article
Source details
Original source date: Sep 28, 2015 (2015-09-28T04:00:00Z).
Date basis: Date from the publisher’s own records, through its API.
Added to Escape Meridian: 2026-10-29T15:22:13.084Z. First observed: 2026-10-26T18:46:28.340Z. Retrieved: 2026-10-26T18:47:36.413Z.
Referenced by
Recorded citations and public file attachments. A reference alone does not establish agreement or influence.
No public references recorded here yet.
Limits
Text as retrieved on October 26, 2026; originally published September 28, 2015. The page was edited after publication, and the retrieved text does not establish whether every passage reflects the original article as published. The IBM accuracy figure is attributed to a company scientist and concerns testing; the text does not establish real-world clinical performance.
Open question
How are hospitals to decide which specialty should handle a procedure when multiple specialists can perform it?
Source-stated
The article says digital tools and growing image volumes are changing radiologists’ work and creating a risk of missing diagnostically important images.
With all this data—images for one patient might account for 250 gigabytes, says Syeda-Mahmood—a radiologist is at risk of missing the small percentage of images crucial to identifying pathologies.
Source-stated
IBM was testing computer-based tools to identify important images for radiologists; the reported accuracy was a test result for certain conditions.
in testing it has achieved over 80 percent accuracy with certain medical conditions—in the range of a good radiologist.
Source-stated
The article describes image-guided tools as enabling more kinds of treatment and blurring boundaries between medical specialties.
These technological advances enable radiologists and other physicians to perform more kinds of treatments, including minimally invasive techniques like recanalization of blocked blood vessels and targeted tumor therapies carried out under image guidance.
Source-stated
The article says that which department is available may determine who performs some procedures.
Today the answer, surprisingly, may come down to which department is available when you walk in.
Source and contributor context
MIT Technology Review · Publisher
The publisher is identified here. No individual author has been inferred.
Source media
Media retrieval status: unchecked.
Terms and references
Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.
Machine learning
Methods that let computers learn patterns from examples instead of following rules written by hand.
Figure
Figure develops humanoid robots and publishes its own tests of how they perform physical tasks.
Editorial provenance
Version 1. Publication ID: 71cf2f77-8061-ecff-e9c5-c6eea21bf937.
Prepared by openai/gpt-6-luna; grounding review by anthropic/claude-opus-5.5.
Source check: passed by anthropic/claude-opus-5.5 on 2026-10-29T15:22:11.816Z. This checks fidelity to the source, not whether its claims are independently true.
Editorial selection: accept; reasons: bridge_screen.
Observation: bf2b2aa99dff8c7fc3b3fcd5d0a46cb388109d5bd067a8d6bc6e404cda6ce67c. Source text hash: 7a018c02b8ec6c6a68826acf915f8d92f2625caa5644fa41124d06a266d1816b.
Revision and source-check history
Version 1 · 2026-10-29T15:22:13.084Z
MIT Technology Review reports how imaging tools are changing radiology work
MIT Technology Review’s article, published September 28, 2015, describes how digital imaging, data science and medical tools were changing radiologists’ work. The article says software can help reconstruct and measure tumors, while the growing volume of images creates a risk that radiologists may miss images important to identifying pathologies. The article reports that IBM was testing computer-based reasoning, machine learning and analytical problem solving to flag important images for radiologists. IBM said early work showed the system could learn to recognize a pathology and alert radiologists; a company scientist said testing reached over 80 percent accuracy for certain medical conditions. These were reported test results, not evidence of performance in routine clinical use. The article also describes Brainlab systems that let surgeons use imaging during operations while radiologists review live feeds and coordinate treatment. It says image-guided techniques are expanding the treatments radiologists and other physicians can perform, blurring boundaries between specialties. The article reports that, for some procedures, the available department may determine which specialist treats a patient. How are hospitals to decide which specialty should handle a procedure when multiple specialists can perform it?
Original source
MIT Technology Review · Article
Source details
Original source date: Sep 28, 2015 (2015-09-28T04:00:00Z).
Date basis: Date from the publisher’s own records, through its API.
Added to Escape Meridian: 2026-10-29T15:22:13.084Z. First observed: 2026-10-26T18:46:28.340Z. Retrieved: 2026-10-26T18:47:36.413Z.
Limits
Text as retrieved on October 26, 2026; originally published September 28, 2015. The page was edited after publication, and the retrieved text does not establish whether every passage reflects the original article as published. The IBM accuracy figure is attributed to a company scientist and concerns testing; the text does not establish real-world clinical performance.
Open question
How are hospitals to decide which specialty should handle a procedure when multiple specialists can perform it?
Source-stated
The article says digital tools and growing image volumes are changing radiologists’ work and creating a risk of missing diagnostically important images.
With all this data—images for one patient might account for 250 gigabytes, says Syeda-Mahmood—a radiologist is at risk of missing the small percentage of images crucial to identifying pathologies.
Source-stated
IBM was testing computer-based tools to identify important images for radiologists; the reported accuracy was a test result for certain conditions.
in testing it has achieved over 80 percent accuracy with certain medical conditions—in the range of a good radiologist.
Source-stated
The article describes image-guided tools as enabling more kinds of treatment and blurring boundaries between medical specialties.
These technological advances enable radiologists and other physicians to perform more kinds of treatments, including minimally invasive techniques like recanalization of blocked blood vessels and targeted tumor therapies carried out under image guidance.
Source-stated
The article says that which department is available may determine who performs some procedures.
Today the answer, surprisingly, may come down to which department is available when you walk in.
Source and contributor context
MIT Technology Review · Publisher
The publisher is identified here. No individual author has been inferred.
Source media
Media retrieval status: unchecked.
Terms and references
Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.
Machine learning
Methods that let computers learn patterns from examples instead of following rules written by hand.
Figure
Figure develops humanoid robots and publishes its own tests of how they perform physical tasks.
Editorial provenance
Version 1. Publication ID: 71cf2f77-8061-ecff-e9c5-c6eea21bf937.
Prepared by openai/gpt-6-luna; grounding review by anthropic/claude-opus-5.5.
Source check: passed by anthropic/claude-opus-5.5 on 2026-10-29T15:22:11.816Z. This checks fidelity to the source, not whether its claims are independently true.
Editorial selection: accept; reasons: bridge_screen.
Observation: bf2b2aa99dff8c7fc3b3fcd5d0a46cb388109d5bd067a8d6bc6e404cda6ce67c. Source text hash: 7a018c02b8ec6c6a68826acf915f8d92f2625caa5644fa41124d06a266d1816b.
passed · 2026-10-29T15:22:11.816Z · anthropic/claude-opus-5.5
Publication: 71cf2f77-8061-ecff-e9c5-c6eea21bf937
attribution — pass: The reading attributes the article to MIT Technology Review. It attributes IBM's early-work claims to the company and the 80 percent figure to a company scientist (Syeda-Mahmood), matching the source. The Brainlab descriptions are reported as the article's own account.
According to the company, early work has demonstrated that the system can autonomously learn what a pathology looks like
summary — pass: The title, summary and question accurately reflect the article's themes: growing image volume, software tools, IBM's image-flagging system, Brainlab's intraoperative imaging and the blurring of specialties. A general reader can follow the actors and terms. The question follows from the article's closing point about which department treats a patient.
This blurring of medical portfolios has begun to create conflicts between once-distinct medical specialties.
date — pass: The stated date, September 28, 2015, matches the UTC day of originalPublished. The 'Most Popular' sidebar items, such as the AlphaGo ten-year piece, are later additions, but the reading does not use them. The kind is publisher-page, so no archive disclosure is needed. The page was edited after publication; the cited passages are plainly part of the article body, and the limitations disclose the edit.
support — pass: Each claim is directly supported by its excerpt. The reading frames the accuracy figure as a test result for certain conditions and adds an appropriate caveat against reading it as clinical reliability. No unsupported benefits or costs are implied. The page was edited after publication, but the cited text is plainly from the original article body.
The system is still learning, but Syeda-Mahmood says that in testing it has achieved over 80 percent accuracy with certain medical conditions
media — pass: No media is selected, and no verified media candidates were supplied, so no media identity or relevance issue arises.
Challenge or correct this reading
Send a correction or an opposing source with this reading’s URL. Disagreement and uncertainty can remain unresolved.