Deep learning enhances radiologists’ detection of potential spinal malignancies in CT scans

Incidental spinal bone lesions, potential indicators of malignancies, are frequently underreported in abdominal and thoracic CT imaging due to scan focus and diagnostic bias towards patient complaints. Here, we evaluate a deep-learning algorithm (DLA) designed to support radiologists’ reporting of i...

Full description

Saved in:
Bibliographic Details
Main Authors: Gilberg, Leonard (Author) , Teodorescu, Bianca (Author) , Maerkisch, Leander (Author) , Baumgart, André (Author) , Ramaesh, Rishi (Author) , Gomes Ataide, Elmer Jeto (Author) , Koç, Ali Murat (Author)
Format: Article (Journal)
Language:English
Published: 13 July 2023
In: Applied Sciences
Year: 2023, Volume: 13, Issue: 14, Pages: 1-11
ISSN:2076-3417
DOI:10.3390/app13148140
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.3390/app13148140
Verlag, kostenfrei, Volltext: https://www.mdpi.com/2076-3417/13/14/8140
Get full text
Author Notes:Leonard Gilberg, Bianca Teodorescu, Leander Maerkisch, Andre Baumgart, Rishi Ramaesh, Elmer Jeto Gomes Ataide and Ali Murat Koç

MARC

LEADER 00000caa a2200000 c 4500
001 1870249909
003 DE-627
005 20240307042140.0
007 cr uuu---uuuuu
008 231114s2023 xx |||||o 00| ||eng c
024 7 |a 10.3390/app13148140  |2 doi 
035 |a (DE-627)1870249909 
035 |a (DE-599)KXP1870249909 
035 |a (OCoLC)1425209419 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Gilberg, Leonard  |e VerfasserIn  |0 (DE-588)1309856338  |0 (DE-627)1870251148  |4 aut 
245 1 0 |a Deep learning enhances radiologists’ detection of potential spinal malignancies in CT scans  |c Leonard Gilberg, Bianca Teodorescu, Leander Maerkisch, Andre Baumgart, Rishi Ramaesh, Elmer Jeto Gomes Ataide and Ali Murat Koç 
264 1 |c 13 July 2023 
300 |a 11 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 14.11.2023 
520 |a Incidental spinal bone lesions, potential indicators of malignancies, are frequently underreported in abdominal and thoracic CT imaging due to scan focus and diagnostic bias towards patient complaints. Here, we evaluate a deep-learning algorithm (DLA) designed to support radiologists’ reporting of incidental lesions during routine clinical practice. The present study is structured into two phases: unaided and AI-assisted. A total of 32 scans from multiple radiology centers were selected randomly and independently annotated by two experts. The U-Net-like architecture-based DLA used for the AI-assisted phase showed a sensitivity of 75.0% in identifying potentially malignant spinal bone lesions. Six radiologists of varying experience levels participated in this observational study. During routine reporting, the DLA helped improve the radiologists’ sensitivity by 20.8 percentage points. Notably, DLA-generated false-positive predictions did not significantly bias radiologists in their final diagnosis. These observations clearly indicate that using a suitable DLA improves the detection of otherwise missed potentially malignant spinal cases. Our results further emphasize the potential of artificial intelligence as a second reader in the clinical setting. 
650 4 |a AI detection 
650 4 |a computed tomography 
650 4 |a deep learning 
650 4 |a malignancies 
650 4 |a second reader 
650 4 |a spine 
650 4 |a vertebral lesions 
700 1 |a Teodorescu, Bianca  |e VerfasserIn  |4 aut 
700 1 |a Maerkisch, Leander  |e VerfasserIn  |4 aut 
700 1 |a Baumgart, André  |d 1974-  |e VerfasserIn  |0 (DE-588)1012533514  |0 (DE-627)66183316X  |0 (DE-576)345550773  |4 aut 
700 1 |a Ramaesh, Rishi  |e VerfasserIn  |4 aut 
700 1 |a Gomes Ataide, Elmer Jeto  |e VerfasserIn  |4 aut 
700 1 |a Koç, Ali Murat  |e VerfasserIn  |4 aut 
773 0 8 |i Enthalten in  |t Applied Sciences  |d Basel : MDPI, 2011  |g 13(2023), 14, Artikel-ID 8140, Seite 1-11  |h Online-Ressource  |w (DE-627)737287640  |w (DE-600)2704225-X  |w (DE-576)379466716  |x 2076-3417  |7 nnas  |a Deep learning enhances radiologists’ detection of potential spinal malignancies in CT scans 
773 1 8 |g volume:13  |g year:2023  |g number:14  |g elocationid:8140  |g pages:1-11  |g extent:11  |a Deep learning enhances radiologists’ detection of potential spinal malignancies in CT scans 
856 4 0 |u https://doi.org/10.3390/app13148140  |x Verlag  |x Resolving-System  |z kostenfrei  |3 Volltext 
856 4 0 |u https://www.mdpi.com/2076-3417/13/14/8140  |x Verlag  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20231114 
993 |a Article 
994 |a 2023 
998 |g 1012533514  |a Baumgart, André  |m 1012533514:Baumgart, André  |d 60000  |d 65300  |e 60000PB1012533514  |e 65300PB1012533514  |k 0/60000/  |k 1/60000/65300/  |p 4 
999 |a KXP-PPN1870249909  |e 4406596895 
BIB |a Y 
SER |a journal 
JSO |a {"relHost":[{"id":{"zdb":["2704225-X"],"eki":["737287640"],"issn":["2076-3417"]},"origin":[{"dateIssuedDisp":"2011-","publisher":"MDPI","dateIssuedKey":"2011","publisherPlace":"Basel"}],"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title_sort":"Applied Sciences","title":"Applied Sciences","subtitle":"open access journal"}],"language":["eng"],"recId":"737287640","note":["Gesehen am 19.02.13"],"type":{"bibl":"periodical","media":"Online-Ressource"},"disp":"Deep learning enhances radiologists’ detection of potential spinal malignancies in CT scansApplied Sciences","part":{"year":"2023","pages":"1-11","issue":"14","volume":"13","text":"13(2023), 14, Artikel-ID 8140, Seite 1-11","extent":"11"},"pubHistory":["1.2011 -"]}],"physDesc":[{"extent":"11 S."}],"id":{"eki":["1870249909"],"doi":["10.3390/app13148140"]},"origin":[{"dateIssuedKey":"2023","dateIssuedDisp":"13 July 2023"}],"name":{"displayForm":["Leonard Gilberg, Bianca Teodorescu, Leander Maerkisch, Andre Baumgart, Rishi Ramaesh, Elmer Jeto Gomes Ataide and Ali Murat Koç"]},"language":["eng"],"recId":"1870249909","type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Gesehen am 14.11.2023"],"title":[{"title_sort":"Deep learning enhances radiologists’ detection of potential spinal malignancies in CT scans","title":"Deep learning enhances radiologists’ detection of potential spinal malignancies in CT scans"}],"person":[{"role":"aut","display":"Gilberg, Leonard","roleDisplay":"VerfasserIn","given":"Leonard","family":"Gilberg"},{"roleDisplay":"VerfasserIn","display":"Teodorescu, Bianca","role":"aut","family":"Teodorescu","given":"Bianca"},{"display":"Maerkisch, Leander","roleDisplay":"VerfasserIn","role":"aut","family":"Maerkisch","given":"Leander"},{"display":"Baumgart, André","roleDisplay":"VerfasserIn","role":"aut","family":"Baumgart","given":"André"},{"given":"Rishi","family":"Ramaesh","role":"aut","roleDisplay":"VerfasserIn","display":"Ramaesh, Rishi"},{"given":"Elmer Jeto","family":"Gomes Ataide","role":"aut","roleDisplay":"VerfasserIn","display":"Gomes Ataide, Elmer Jeto"},{"display":"Koç, Ali Murat","roleDisplay":"VerfasserIn","role":"aut","family":"Koç","given":"Ali Murat"}]} 
SRT |a GILBERGLEODEEPLEARNI1320