Deep Convolutional Neural Networks Detect no Morphological Differences Between Culture-Positive and Culture-Negative Infectious Keratitis Images
Purpose: To determine whether convolutional neural networks can detect morphological differences between images of microbiologically positive and negative corneal ulcers.
Methods: A cross-sectional comparison of prospectively collected data consisting of bacterial and fungal cultures and smears from eyes with acute infectious keratitis at Aravind Eye Hospital. Two convolutional neural network architectures (DenseNet and MobileNet) were trained using images obtained from handheld cameras collected from culture-positive and negative images and smear-positive and -negative images. Each architecture was trained on two image sets: (1) one with labels assigned using only culture results and (2) one using culture and smear results. The outcome measure was area under the receiver operating characteristic curve for predicting whether an ulcer would be microbiologically positive or negative.
Results: There were 1970 images from 886 patients were included. None of the models were better than random chance at predicting positive microbiologic results (area under the receiver operating characteristic curve ranged from 0.49 to 0.56; all confidence intervals included 0.5).
Conclusions: These two state-of-the-art deep convolutional neural network architectures could not reliably predict whether a corneal ulcer would be microbiologically positive or negative based on clinical photographs. This absence of detectable morphological differences informs the future development of computer vision models trained to predict the causative agent in infectious keratitis using corneal photography.
Translational Relevance: These deep learning models were not able to identify morphological differences between microbiologically positive and negative corneal ulcers. This finding suggests that similar artificial intelligence models trained to identify the causative pathogen using only microbiologically positive cases may have potential to generalize well, including to cases with falsely negative microbiologic testing.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:12 |
---|---|
Enthalten in: |
Translational vision science & technology - 12(2023), 1 vom: 03. Jan., Seite 12 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Kogachi, Kaitlin [VerfasserIn] |
---|
Links: |
---|
Themen: |
Comparative Study |
---|
Anmerkungen: |
Date Completed 11.01.2023 Date Revised 02.08.2023 published: Print Citation Status MEDLINE |
---|
doi: |
10.1167/tvst.12.1.12 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM351187677 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM351187677 | ||
003 | DE-627 | ||
005 | 20231226050742.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1167/tvst.12.1.12 |2 doi | |
028 | 5 | 2 | |a pubmed24n1170.xml |
035 | |a (DE-627)NLM351187677 | ||
035 | |a (NLM)36607623 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Kogachi, Kaitlin |e verfasserin |4 aut | |
245 | 1 | 0 | |a Deep Convolutional Neural Networks Detect no Morphological Differences Between Culture-Positive and Culture-Negative Infectious Keratitis Images |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 11.01.2023 | ||
500 | |a Date Revised 02.08.2023 | ||
500 | |a published: Print | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Purpose: To determine whether convolutional neural networks can detect morphological differences between images of microbiologically positive and negative corneal ulcers | ||
520 | |a Methods: A cross-sectional comparison of prospectively collected data consisting of bacterial and fungal cultures and smears from eyes with acute infectious keratitis at Aravind Eye Hospital. Two convolutional neural network architectures (DenseNet and MobileNet) were trained using images obtained from handheld cameras collected from culture-positive and negative images and smear-positive and -negative images. Each architecture was trained on two image sets: (1) one with labels assigned using only culture results and (2) one using culture and smear results. The outcome measure was area under the receiver operating characteristic curve for predicting whether an ulcer would be microbiologically positive or negative | ||
520 | |a Results: There were 1970 images from 886 patients were included. None of the models were better than random chance at predicting positive microbiologic results (area under the receiver operating characteristic curve ranged from 0.49 to 0.56; all confidence intervals included 0.5) | ||
520 | |a Conclusions: These two state-of-the-art deep convolutional neural network architectures could not reliably predict whether a corneal ulcer would be microbiologically positive or negative based on clinical photographs. This absence of detectable morphological differences informs the future development of computer vision models trained to predict the causative agent in infectious keratitis using corneal photography | ||
520 | |a Translational Relevance: These deep learning models were not able to identify morphological differences between microbiologically positive and negative corneal ulcers. This finding suggests that similar artificial intelligence models trained to identify the causative pathogen using only microbiologically positive cases may have potential to generalize well, including to cases with falsely negative microbiologic testing | ||
650 | 4 | |a Comparative Study | |
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, N.I.H., Extramural | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
700 | 1 | |a Lalitha, Prajna |e verfasserin |4 aut | |
700 | 1 | |a Prajna, N Venkatesh |e verfasserin |4 aut | |
700 | 1 | |a Gunasekaran, Rameshkumar |e verfasserin |4 aut | |
700 | 1 | |a Keenan, Jeremy D |e verfasserin |4 aut | |
700 | 1 | |a Campbell, J Peter |e verfasserin |4 aut | |
700 | 1 | |a Song, Xubo |e verfasserin |4 aut | |
700 | 1 | |a Redd, Travis K |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Translational vision science & technology |d 2012 |g 12(2023), 1 vom: 03. Jan., Seite 12 |w (DE-627)NLM227066596 |x 2164-2591 |7 nnns |
773 | 1 | 8 | |g volume:12 |g year:2023 |g number:1 |g day:03 |g month:01 |g pages:12 |
856 | 4 | 0 | |u http://dx.doi.org/10.1167/tvst.12.1.12 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 12 |j 2023 |e 1 |b 03 |c 01 |h 12 |