Artificial intelligence for human gunshot wound classification
© 2023 The Authors..
Certain features are helpful in the identification of gunshot entrance and exit wounds, such as the presence of muzzle imprints, peripheral tears, stippling, bone beveling, and wound border irregularity. Some cases are less straightforward and wounds can thus pose challenges to an emergency room doctor or forensic pathologist. In recent years, deep learning has shown promise in various automated medical image classification tasks. This study explores the feasibility of using a deep learning model to classify entry and exit gunshot wounds in digital color images. A collection of 2418 images of entrance and exit gunshot wounds were procured. Of these, 2028 entrance and 1314 exit wounds were cropped, focusing on the area around each gunshot wound. A ConvNext Tiny deep learning model was trained using the Fastai deep learning library, with a train/validation split ratio of 70/30, until a maximum validation accuracy of 92.6% was achieved. An additional 415 entrance and 293 exit wound images were collected for the test (holdout) set. The model achieved an accuracy of 87.99%, precision of 83.99%, recall of 87.71%, and F1-score 85.81% on the holdout set. Correctly classified were 88.19% of entrance wounds and 87.71% of exit wounds. The results are comparable to what a forensic pathologist can achieve without other morphologic cues. This study represents one of the first applications of artificial intelligence to the field of forensic pathology. This work demonstrates that deep learning models can discern entrance and exit gunshot wounds in digital images with high accuracy.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:15 |
|---|---|
| Enthalten in: |
Journal of pathology informatics - 15(2024) vom: 30. Jan., Seite 100361 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Cheng, Jerome [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Artificial intelligence |
|---|
| Anmerkungen: |
Date Revised 19.01.2024 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1016/j.jpi.2023.100361 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM367250969 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM367250969 | ||
| 003 | DE-627 | ||
| 005 | 20240119232049.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240118s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.jpi.2023.100361 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1264.xml |
| 035 | |a (DE-627)NLM367250969 | ||
| 035 | |a (NLM)38234590 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Cheng, Jerome |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Artificial intelligence for human gunshot wound classification |
| 264 | 1 | |c 2024 | |
| 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 Revised 19.01.2024 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © 2023 The Authors. | ||
| 520 | |a Certain features are helpful in the identification of gunshot entrance and exit wounds, such as the presence of muzzle imprints, peripheral tears, stippling, bone beveling, and wound border irregularity. Some cases are less straightforward and wounds can thus pose challenges to an emergency room doctor or forensic pathologist. In recent years, deep learning has shown promise in various automated medical image classification tasks. This study explores the feasibility of using a deep learning model to classify entry and exit gunshot wounds in digital color images. A collection of 2418 images of entrance and exit gunshot wounds were procured. Of these, 2028 entrance and 1314 exit wounds were cropped, focusing on the area around each gunshot wound. A ConvNext Tiny deep learning model was trained using the Fastai deep learning library, with a train/validation split ratio of 70/30, until a maximum validation accuracy of 92.6% was achieved. An additional 415 entrance and 293 exit wound images were collected for the test (holdout) set. The model achieved an accuracy of 87.99%, precision of 83.99%, recall of 87.71%, and F1-score 85.81% on the holdout set. Correctly classified were 88.19% of entrance wounds and 87.71% of exit wounds. The results are comparable to what a forensic pathologist can achieve without other morphologic cues. This study represents one of the first applications of artificial intelligence to the field of forensic pathology. This work demonstrates that deep learning models can discern entrance and exit gunshot wounds in digital images with high accuracy | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Artificial intelligence | |
| 650 | 4 | |a Convolutional neural network | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Human gunshot wound | |
| 700 | 1 | |a Schmidt, Carl |e verfasserin |4 aut | |
| 700 | 1 | |a Wilson, Allecia |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Zixi |e verfasserin |4 aut | |
| 700 | 1 | |a Hao, Wei |e verfasserin |4 aut | |
| 700 | 1 | |a Pantanowitz, Joshua |e verfasserin |4 aut | |
| 700 | 1 | |a Morris, Catherine |e verfasserin |4 aut | |
| 700 | 1 | |a Tashjian, Randy |e verfasserin |4 aut | |
| 700 | 1 | |a Pantanowitz, Liron |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of pathology informatics |d 2010 |g 15(2024) vom: 30. Jan., Seite 100361 |w (DE-627)NLM201240041 |x 2229-5089 |7 nnns |
| 773 | 1 | 8 | |g volume:15 |g year:2024 |g day:30 |g month:01 |g pages:100361 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.jpi.2023.100361 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 15 |j 2024 |b 30 |c 01 |h 100361 | ||