Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic study
Abstract Objectives This retrospective single-center analysis aimed to evaluate whether artificial intelligence can detect type 2 diabetes mellitus by evaluating the pectoral muscle on digital breast tomosynthesis (DBT). Material method An analysis of 11,594 DBT images of 287 consecutive female pati...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-03-01
|
| Series: | Insights into Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13244-024-01661-4 |
| _version_ | 1797233524213809152 |
|---|---|
| author | Meltem M. Yashar Ilayda Begum Izci Fatma Zeynep Gungoren Abdulkadir A. Eren Ali A. Mert Irmak I. Durur-Subasi |
| author_facet | Meltem M. Yashar Ilayda Begum Izci Fatma Zeynep Gungoren Abdulkadir A. Eren Ali A. Mert Irmak I. Durur-Subasi |
| author_sort | Meltem M. Yashar |
| collection | DOAJ |
| description | Abstract Objectives This retrospective single-center analysis aimed to evaluate whether artificial intelligence can detect type 2 diabetes mellitus by evaluating the pectoral muscle on digital breast tomosynthesis (DBT). Material method An analysis of 11,594 DBT images of 287 consecutive female patients (mean age 60, range 40–77 years) was conducted using convolutional neural networks (EfficientNetB5). The inclusion criterion was left-sided screening images with unsuspicious interpretation who also had a current glycosylated hemoglobin A1c (HBA1c) % value. The exclusion criteria were inadequate imaging, history of breast cancer, and/or diabetes mellitus. HbA1c values between 5.6 and 6.4% were categorized as prediabetic, and those with values ≥ 6.5% were categorized as diabetic. A recorded HbA1c ≤ 5.5% served as the control group. Each group was divided into 3 subgroups according to age. Images were subjected to pattern analysis parameters then cropped and resized in a format to contain only pectoral muscle. The dataset was split into 85% for training and 15% for testing the model’s performance. The accuracy rate and F1-score were selected as performance indicators. Results The training process was concluded in the 15th epoch, each comprising 1000 steps, with an accuracy rate of 92% and a loss of only 0.22. The average specificity and sensitivity for all 3 groups were 95%. The F1-score was 0.95. AUC-ROC was 0.995. PPV was 94%, and NPV was 98%. Conclusion Our study presented a pioneering approach, applying deep learning for the detection of diabetes mellitus status in women using pectoral muscle images and was found to function with an accuracy rate of 92%. Critical relevance statement AI can differentiate pathological changes within pectoral muscle tissue by assessing radiological images and maybe a potential diagnostic tool for detecting diabetes mellitus and other diseases that affect muscle tissues. Key points • AI may have an opportunistic use as a screening exam for diabetes during digital breast tomosynthesis. • This technique allows for early and non-invasive detection of diabetes mellitus by AI. • AI may have broad applications in detecting pathological changes within muscle tissue. Graphical Abstract |
| first_indexed | 2024-04-24T16:17:32Z |
| format | Article |
| id | doaj.art-601bbb60d56b4e60948bf94a26a6da69 |
| institution | Directory Open Access Journal |
| issn | 1869-4101 |
| language | English |
| last_indexed | 2024-04-24T16:17:32Z |
| publishDate | 2024-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Insights into Imaging |
| spelling | doaj.art-601bbb60d56b4e60948bf94a26a6da692024-03-31T11:22:46ZengSpringerOpenInsights into Imaging1869-41012024-03-0115111010.1186/s13244-024-01661-4Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic studyMeltem M. Yashar0Ilayda Begum Izci1Fatma Zeynep Gungoren2Abdulkadir A. Eren3Ali A. Mert4Irmak I. Durur-Subasi5Faculty of Medicine, Istanbul Medipol UniversityDeloitteDepartment of Radiology, Florence Nightingale HospitalFaculty of Medicine, Department of Radiology, Istanbul Medipol UniversityFaculty of Medicine, Department of Internal Medicine, Istanbul Medipol UniversityInternational Faculty of Medicine, Department of Radiology, Istanbul Medipol UniversityAbstract Objectives This retrospective single-center analysis aimed to evaluate whether artificial intelligence can detect type 2 diabetes mellitus by evaluating the pectoral muscle on digital breast tomosynthesis (DBT). Material method An analysis of 11,594 DBT images of 287 consecutive female patients (mean age 60, range 40–77 years) was conducted using convolutional neural networks (EfficientNetB5). The inclusion criterion was left-sided screening images with unsuspicious interpretation who also had a current glycosylated hemoglobin A1c (HBA1c) % value. The exclusion criteria were inadequate imaging, history of breast cancer, and/or diabetes mellitus. HbA1c values between 5.6 and 6.4% were categorized as prediabetic, and those with values ≥ 6.5% were categorized as diabetic. A recorded HbA1c ≤ 5.5% served as the control group. Each group was divided into 3 subgroups according to age. Images were subjected to pattern analysis parameters then cropped and resized in a format to contain only pectoral muscle. The dataset was split into 85% for training and 15% for testing the model’s performance. The accuracy rate and F1-score were selected as performance indicators. Results The training process was concluded in the 15th epoch, each comprising 1000 steps, with an accuracy rate of 92% and a loss of only 0.22. The average specificity and sensitivity for all 3 groups were 95%. The F1-score was 0.95. AUC-ROC was 0.995. PPV was 94%, and NPV was 98%. Conclusion Our study presented a pioneering approach, applying deep learning for the detection of diabetes mellitus status in women using pectoral muscle images and was found to function with an accuracy rate of 92%. Critical relevance statement AI can differentiate pathological changes within pectoral muscle tissue by assessing radiological images and maybe a potential diagnostic tool for detecting diabetes mellitus and other diseases that affect muscle tissues. Key points • AI may have an opportunistic use as a screening exam for diabetes during digital breast tomosynthesis. • This technique allows for early and non-invasive detection of diabetes mellitus by AI. • AI may have broad applications in detecting pathological changes within muscle tissue. Graphical Abstracthttps://doi.org/10.1186/s13244-024-01661-4Artificial intelligenceDiabetes mellitusDigital breast tomosynthesisGlycosylated hemoglobin A1cPectoral muscle |
| spellingShingle | Meltem M. Yashar Ilayda Begum Izci Fatma Zeynep Gungoren Abdulkadir A. Eren Ali A. Mert Irmak I. Durur-Subasi Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic study Insights into Imaging Artificial intelligence Diabetes mellitus Digital breast tomosynthesis Glycosylated hemoglobin A1c Pectoral muscle |
| title | Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic study |
| title_full | Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic study |
| title_fullStr | Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic study |
| title_full_unstemmed | Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic study |
| title_short | Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic study |
| title_sort | can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis diagnostic study |
| topic | Artificial intelligence Diabetes mellitus Digital breast tomosynthesis Glycosylated hemoglobin A1c Pectoral muscle |
| url | https://doi.org/10.1186/s13244-024-01661-4 |
| work_keys_str_mv | AT meltemmyashar canartificialintelligencedetecttype2diabetesinwomenbyevaluatingthepectoralmuscleontomosynthesisdiagnosticstudy AT ilaydabegumizci canartificialintelligencedetecttype2diabetesinwomenbyevaluatingthepectoralmuscleontomosynthesisdiagnosticstudy AT fatmazeynepgungoren canartificialintelligencedetecttype2diabetesinwomenbyevaluatingthepectoralmuscleontomosynthesisdiagnosticstudy AT abdulkadiraeren canartificialintelligencedetecttype2diabetesinwomenbyevaluatingthepectoralmuscleontomosynthesisdiagnosticstudy AT aliamert canartificialintelligencedetecttype2diabetesinwomenbyevaluatingthepectoralmuscleontomosynthesisdiagnosticstudy AT irmakidurursubasi canartificialintelligencedetecttype2diabetesinwomenbyevaluatingthepectoralmuscleontomosynthesisdiagnosticstudy |