Technical feasibility of automated blur detection in digital mammography using convolutional neural network
S. Nowakowska, V. Vescoli, T. Schnitzler, C. Ruppert, K. Borkowski, A. Boss, C. Rossi, B. Wein, A. Ciritsis · 2024
Read Technical feasibility of automated blur detection in digital mammography using convolutional neural network by S. Nowakowska, V. Vescoli, T. Schnitzler, C. Ruppert, K. Borkowski, A. Boss, C. Rossi, B. Wein, A. Ciritsis (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11574226.txt.
Description
Nowakowska and co-authors teach a neural network to spot blur in mammograms where it matters. Their twenty twenty-four study uses one hundred fifty-two exams from machines of three makers. A blurred patch can hide a mass or fake one, cutting diagnostic accuracy.
Expert radiologists outlined the blurred zones by hand. A sliding window pulled frequency spectra from each image as network input. The network scored each patch for blur, and a threshold turned the map into a sharp or blurred call per exam. Auto flagging at scan time could trigger a retake while the patient is still present, the moment when a fix is cheapest.
Catalog record
| CREATOR | S. Nowakowska, V. Vescoli, T. Schnitzler, C. Ruppert, K. Borkowski, A. Boss, C. Rossi, B. Wein, A. Ciritsis |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |