Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug) - Info and Reading Options
By Amina Mamuda Damo, Hashim Ibrahim Bisallah, Fatimah Binta Abdullahi and Benjamin Okike
“Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)” Metadata:
- Title: ➤ Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)
- Author: ➤ Amina Mamuda Damo, Hashim Ibrahim Bisallah, Fatimah Binta Abdullahi and Benjamin Okike
“Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)” Subjects and Themes:
- Subjects: Deep Learning - Grad-CAM - Model Interpretability - Brain Tumor Classification - Medical Imaging.
Edition Identifiers:
- Internet Archive ID: ➤ httpsdoi.org10.59298iaajsr20251221728.00
AI-generated Review of “Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)”:
"Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)" Description:
The Internet Archive:
The application of deep learning in radiology has markedly improved diagnostic performance; however, widespread clinical adoption is hindered by the opaque, black-box nature of these models, which limits interpretability and undermines trust among healthcare professionals. This study introduces an explainable deep learning framework for brain tumor classification using magnetic resonance imaging (MRI). A convolutional neural network (CNN) was trained and validated on a curated dataset comprising four diagnostic categories: glioma, meningioma, pituitary tumor, and normal brain scans. To address the interpretability challenge, Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to generate visual explanations highlighting the regions most influential to the model’s predictions. The framework achieved high quantitative performance across key metrics, including accuracy, precision, recall, and F1-score. In addition, qualitative assessments by radiologists confirmed that the Grad-CAM visualizations provided clinically meaningful insights, aligning with known diagnostic landmarks and improving trust in the model’s outputs. These findings underscore the value of integrating explainability into deep learning systems for medical imaging, paving the way for safer, more transparent, and clinically acceptable AI assisted diagnostics.
Read “Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)”:
Read “Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)” by choosing from the options below.
Available Downloads for “Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)”:
"Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)" is available for download from The Internet Archive in "texts" format, the size of the file-s is: 8.76 Mbs, and the file-s went public at Fri Jul 04 2025.
Legal and Safety Notes
Copyright Disclaimer and Liability Limitation:
A. Automated Content Display
The creation of this page is fully automated. All data, including text, images, and links, is displayed exactly as received from its original source, without any modification, alteration, or verification. We do not claim ownership of, nor assume any responsibility for, the accuracy or legality of this content.
B. Liability Disclaimer for External Content
The files provided below are solely the responsibility of their respective originators. We disclaim any and all liability, whether direct or indirect, for the content, accuracy, legality, or any other aspect of these files. By using this website, you acknowledge that we have no control over, nor endorse, the content hosted by external sources.
C. Inquiries and Disputes
For any inquiries, concerns, or issues related to the content displayed, including potential copyright claims, please contact the original source or provider of the files directly. We are not responsible for resolving any content-related disputes or claims of intellectual property infringement.
D. No Copyright Ownership
We do not claim ownership of any intellectual property contained in the files or data displayed on this website. All copyrights, trademarks, and other intellectual property rights remain the sole property of their respective owners. If you believe that content displayed on this website infringes upon your intellectual property rights, please contact the original content provider directly.
E. Fair Use Notice
Some content displayed on this website may fall under the "fair use" provisions of copyright law for purposes such as commentary, criticism, news reporting, research, or educational purposes. If you believe any content violates fair use guidelines, please reach out directly to the original source of the content for resolution.
Virus Scanning for Your Peace of Mind:
The files provided below have already been scanned for viruses by their original source. However, if you’d like to double-check before downloading, you can easily scan them yourself using the following steps:
How to scan a direct download link for viruses:
- 1- Copy the direct link to the file you want to download (don’t open it yet). (a free online tool) and paste the direct link into the provided field to start the scan.
- 2- Visit VirusTotal (a free online tool) and paste the direct link into the provided field to start the scan.
- 3- VirusTotal will scan the file using multiple antivirus vendors to detect any potential threats.
- 4- Once the scan confirms the file is safe, you can proceed to download it with confidence and enjoy your content.
Available Downloads
- Source: Internet Archive
- Internet Archive Link: Archive.org page
- All Files are Available: Yes
- Number of Files: 15
- Number of Available Files: 15
- Added Date: 2025-07-04 08:13:21
- Scanner: Internet Archive HTML5 Uploader 1.7.0
- PPI (Pixels Per Inch): 300
- OCR: tesseract 5.3.0-6-g76ae
- OCR Detected Language: en
Available Files:
1- Text PDF
- File origin: original
- File Format: Text PDF
- File Size: 0.00 Mbs
- File Name: B. 12. IAA JSR P3.pdf
- Direct Link: Click here
2- Item Tile
- File origin: original
- File Format: Item Tile
- File Size: 0.00 Mbs
- File Name: __ia_thumb.jpg
- Direct Link: Click here
3- Metadata
- File origin: original
- File Format: Metadata
- File Size: 0.00 Mbs
- File Name: httpsdoi.org10.59298iaajsr20251221728.00_files.xml
- Direct Link: Click here
4- Metadata
- File origin: original
- File Format: Metadata
- File Size: 0.00 Mbs
- File Name: httpsdoi.org10.59298iaajsr20251221728.00_meta.sqlite
- Direct Link: Click here
5- Metadata
- File origin: original
- File Format: Metadata
- File Size: 0.00 Mbs
- File Name: httpsdoi.org10.59298iaajsr20251221728.00_meta.xml
- Direct Link: Click here
6- chOCR
- File origin: derivative
- File Format: chOCR
- File Size: 0.00 Mbs
- File Name: B. 12. IAA JSR P3_chocr.html.gz
- Direct Link: Click here
7- DjVuTXT
- File origin: derivative
- File Format: DjVuTXT
- File Size: 0.00 Mbs
- File Name: B. 12. IAA JSR P3_djvu.txt
- Direct Link: Click here
8- Djvu XML
- File origin: derivative
- File Format: Djvu XML
- File Size: 0.00 Mbs
- File Name: B. 12. IAA JSR P3_djvu.xml
- Direct Link: Click here
9- hOCR
- File origin: derivative
- File Format: hOCR
- File Size: 0.00 Mbs
- File Name: B. 12. IAA JSR P3_hocr.html
- Direct Link: Click here
10- OCR Page Index
- File origin: derivative
- File Format: OCR Page Index
- File Size: 0.00 Mbs
- File Name: B. 12. IAA JSR P3_hocr_pageindex.json.gz
- Direct Link: Click here
11- OCR Search Text
- File origin: derivative
- File Format: OCR Search Text
- File Size: 0.00 Mbs
- File Name: B. 12. IAA JSR P3_hocr_searchtext.txt.gz
- Direct Link: Click here
12- Single Page Processed JP2 ZIP
- File origin: derivative
- File Format: Single Page Processed JP2 ZIP
- File Size: 0.01 Mbs
- File Name: B. 12. IAA JSR P3_jp2.zip
- Direct Link: Click here
13- Page Numbers JSON
- File origin: derivative
- File Format: Page Numbers JSON
- File Size: 0.00 Mbs
- File Name: B. 12. IAA JSR P3_page_numbers.json
- Direct Link: Click here
14- Scandata
- File origin: derivative
- File Format: Scandata
- File Size: 0.00 Mbs
- File Name: B. 12. IAA JSR P3_scandata.xml
- Direct Link: Click here
15- Archive BitTorrent
- File origin: metadata
- File Format: Archive BitTorrent
- File Size: 0.00 Mbs
- File Name: httpsdoi.org10.59298iaajsr20251221728.00_archive.torrent
- Direct Link: Click here
Search for “Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)” downloads:
Visit our Downloads Search page to see if downloads are available.
Find “Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)” in Libraries Near You:
Read or borrow “Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)” from your local library.
Buy “Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)” online:
Shop for “Improving Trust And Usability Of Deep Learning Predictions In Radiology By Making Medical Diagnostics More Explainable (www.kiu.ac.ug)” on popular online marketplaces.
- Ebay: New and used books.