A Review of Explainable Deep Learning Cancer Detection Models in Medical Imaging
Deep learning has demonstrated remarkable accuracy analyzing images for cancer detection tasks in recent years. The accuracy that has been achieved rivals radiologists and is suitable for implementation as a clinical tool. However, a significant problem is that these models are black-box algorithms...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/10/4573 |
| _version_ | 1797533740377833472 |
|---|---|
| author | Mehmet A. Gulum Christopher M. Trombley Mehmed Kantardzic |
| author_facet | Mehmet A. Gulum Christopher M. Trombley Mehmed Kantardzic |
| author_sort | Mehmet A. Gulum |
| collection | DOAJ |
| description | Deep learning has demonstrated remarkable accuracy analyzing images for cancer detection tasks in recent years. The accuracy that has been achieved rivals radiologists and is suitable for implementation as a clinical tool. However, a significant problem is that these models are black-box algorithms therefore they are intrinsically unexplainable. This creates a barrier for clinical implementation due to lack of trust and transparency that is a characteristic of black box algorithms. Additionally, recent regulations prevent the implementation of unexplainable models in clinical settings which further demonstrates a need for explainability. To mitigate these concerns, there have been recent studies that attempt to overcome these issues by modifying deep learning architectures or providing after-the-fact explanations. A review of the deep learning explanation literature focused on cancer detection using MR images is presented here. The gap between what clinicians deem explainable and what current methods provide is discussed and future suggestions to close this gap are provided. |
| first_indexed | 2024-03-10T11:19:51Z |
| format | Article |
| id | doaj.art-3c2bb870137d4e758ad3bd37cf5b5a7e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T11:19:51Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-3c2bb870137d4e758ad3bd37cf5b5a7e2023-11-21T20:06:36ZengMDPI AGApplied Sciences2076-34172021-05-011110457310.3390/app11104573A Review of Explainable Deep Learning Cancer Detection Models in Medical ImagingMehmet A. Gulum0Christopher M. Trombley1Mehmed Kantardzic2Computer Science & Engineering Department, J.B. Speed School of Engineering, University of Louisville, Louisville, KT 40292, USAComputer Science & Engineering Department, J.B. Speed School of Engineering, University of Louisville, Louisville, KT 40292, USAComputer Science & Engineering Department, J.B. Speed School of Engineering, University of Louisville, Louisville, KT 40292, USADeep learning has demonstrated remarkable accuracy analyzing images for cancer detection tasks in recent years. The accuracy that has been achieved rivals radiologists and is suitable for implementation as a clinical tool. However, a significant problem is that these models are black-box algorithms therefore they are intrinsically unexplainable. This creates a barrier for clinical implementation due to lack of trust and transparency that is a characteristic of black box algorithms. Additionally, recent regulations prevent the implementation of unexplainable models in clinical settings which further demonstrates a need for explainability. To mitigate these concerns, there have been recent studies that attempt to overcome these issues by modifying deep learning architectures or providing after-the-fact explanations. A review of the deep learning explanation literature focused on cancer detection using MR images is presented here. The gap between what clinicians deem explainable and what current methods provide is discussed and future suggestions to close this gap are provided.https://www.mdpi.com/2076-3417/11/10/4573deep learningexplanabilityexplainabilitycancer detectonMRIXAI |
| spellingShingle | Mehmet A. Gulum Christopher M. Trombley Mehmed Kantardzic A Review of Explainable Deep Learning Cancer Detection Models in Medical Imaging Applied Sciences deep learning explanability explainability cancer detecton MRI XAI |
| title | A Review of Explainable Deep Learning Cancer Detection Models in Medical Imaging |
| title_full | A Review of Explainable Deep Learning Cancer Detection Models in Medical Imaging |
| title_fullStr | A Review of Explainable Deep Learning Cancer Detection Models in Medical Imaging |
| title_full_unstemmed | A Review of Explainable Deep Learning Cancer Detection Models in Medical Imaging |
| title_short | A Review of Explainable Deep Learning Cancer Detection Models in Medical Imaging |
| title_sort | review of explainable deep learning cancer detection models in medical imaging |
| topic | deep learning explanability explainability cancer detecton MRI XAI |
| url | https://www.mdpi.com/2076-3417/11/10/4573 |
| work_keys_str_mv | AT mehmetagulum areviewofexplainabledeeplearningcancerdetectionmodelsinmedicalimaging AT christophermtrombley areviewofexplainabledeeplearningcancerdetectionmodelsinmedicalimaging AT mehmedkantardzic areviewofexplainabledeeplearningcancerdetectionmodelsinmedicalimaging AT mehmetagulum reviewofexplainabledeeplearningcancerdetectionmodelsinmedicalimaging AT christophermtrombley reviewofexplainabledeeplearningcancerdetectionmodelsinmedicalimaging AT mehmedkantardzic reviewofexplainabledeeplearningcancerdetectionmodelsinmedicalimaging |