Optimizing TB Bacteria Detection Efficiency: Utilizing RetinaNet‐Based Preprocessing Techniques for Small Image Patch Classification.
Saved in:
| Title: | Optimizing TB Bacteria Detection Efficiency: Utilizing RetinaNet‐Based Preprocessing Techniques for Small Image Patch Classification. |
|---|---|
| Authors: | V., Shwetha1 (AUTHOR) shwetha.v@manipal.edu, Banerjee, Barnini2 (AUTHOR), Laxmi, Vijaya1 (AUTHOR), Kamath, Priya3 (AUTHOR), Ahmad, Irfan (AUTHOR) iahmad@wiley.com |
| Source: | International Journal of Biomedical Imaging. 10/5/2025, Vol. 2025, p1-14. 14p. |
| Subjects: | Tuberculosis diagnosis, Predictive tests, Prediction models, Computer-assisted image analysis (Medicine), Microbial sensitivity tests, Convolutional neural networks, Detection algorithms, Medical screening, Stains & staining (Microscopy), Automation, Microscopy, Comparative studies, Machine learning, Tuberculosis, Sensitivity & specificity (Statistics), Skin tests |
| Abstract: | Tuberculosis (TB), caused by Mycobacterium tuberculosis, is a re‐emerging disease that necessitates early and accurate detection. While Ziehl–Neelsen (ZN) staining is effective in highlighting bacterial morphology, automation significantly accelerates the diagnostic workflow. However, detecting TB bacilli—which are typically much smaller than white blood cells (WBCs)—in stained images remains a considerable challenge. This study leverages the ZNSM‐iDB dataset, which comprises approximately 2000 publicly available images captured using different staining methods. Notably, 800 images are fully stained with the ZN technique. We propose a novel two‐stage pipeline where a RetinaNet‐based object detection model functions as a preprocessing step to localize and isolate TB bacilli and WBCs from ZN‐stained images. To address the challenges posed by low spatial resolution and background interference, the RetinaNet model is enhanced with dilated convolutional layers to improve fine‐grained feature extraction. This approach not only facilitates accurate detection of small objects but also achieves an average precision (AP) of 0.94 for WBCs and 0.97 for TB bacilli. Following detection, a patch‐based convolutional neural network (CNN) classifier is employed to classify the extracted regions. The proposed CNN model achieves a remarkable classification accuracy of 93%, outperforming other traditional CNN architectures. This framework demonstrates a robust and scalable solution for automated TB screening using ZN‐stained microscopy images. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Biomedical Imaging is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 188442765 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Optimizing TB Bacteria Detection Efficiency: Utilizing RetinaNet‐Based Preprocessing Techniques for Small Image Patch Classification. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22V%2E%2C+Shwetha%22">V., Shwetha</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> shwetha.v@manipal.edu</i><br /><searchLink fieldCode="AR" term="%22Banerjee%2C+Barnini%22">Banerjee, Barnini</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Laxmi%2C+Vijaya%22">Laxmi, Vijaya</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kamath%2C+Priya%22">Kamath, Priya</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ahmad%2C+Irfan%22">Ahmad, Irfan</searchLink> (AUTHOR)<i> iahmad@wiley.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Biomedical+Imaging%22">International Journal of Biomedical Imaging</searchLink>. 10/5/2025, Vol. 2025, p1-14. 14p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Tuberculosis+diagnosis%22">Tuberculosis diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22Predictive+tests%22">Predictive tests</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br /><searchLink fieldCode="DE" term="%22Computer-assisted+image+analysis+%28Medicine%29%22">Computer-assisted image analysis (Medicine)</searchLink><br /><searchLink fieldCode="DE" term="%22Microbial+sensitivity+tests%22">Microbial sensitivity tests</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Detection+algorithms%22">Detection algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Medical+screening%22">Medical screening</searchLink><br /><searchLink fieldCode="DE" term="%22Stains+%26+staining+%28Microscopy%29%22">Stains & staining (Microscopy)</searchLink><br /><searchLink fieldCode="DE" term="%22Automation%22">Automation</searchLink><br /><searchLink fieldCode="DE" term="%22Microscopy%22">Microscopy</searchLink><br /><searchLink fieldCode="DE" term="%22Comparative+studies%22">Comparative studies</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Tuberculosis%22">Tuberculosis</searchLink><br /><searchLink fieldCode="DE" term="%22Sensitivity+%26+specificity+%28Statistics%29%22">Sensitivity & specificity (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Skin+tests%22">Skin tests</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Tuberculosis (TB), caused by Mycobacterium tuberculosis, is a re‐emerging disease that necessitates early and accurate detection. While Ziehl–Neelsen (ZN) staining is effective in highlighting bacterial morphology, automation significantly accelerates the diagnostic workflow. However, detecting TB bacilli—which are typically much smaller than white blood cells (WBCs)—in stained images remains a considerable challenge. This study leverages the ZNSM‐iDB dataset, which comprises approximately 2000 publicly available images captured using different staining methods. Notably, 800 images are fully stained with the ZN technique. We propose a novel two‐stage pipeline where a RetinaNet‐based object detection model functions as a preprocessing step to localize and isolate TB bacilli and WBCs from ZN‐stained images. To address the challenges posed by low spatial resolution and background interference, the RetinaNet model is enhanced with dilated convolutional layers to improve fine‐grained feature extraction. This approach not only facilitates accurate detection of small objects but also achieves an average precision (AP) of 0.94 for WBCs and 0.97 for TB bacilli. Following detection, a patch‐based convolutional neural network (CNN) classifier is employed to classify the extracted regions. The proposed CNN model achieves a remarkable classification accuracy of 93%, outperforming other traditional CNN architectures. This framework demonstrates a robust and scalable solution for automated TB screening using ZN‐stained microscopy images. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Biomedical Imaging is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=188442765 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1155/ijbi/3559598 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 14 StartPage: 1 Subjects: – SubjectFull: Tuberculosis diagnosis Type: general – SubjectFull: Predictive tests Type: general – SubjectFull: Prediction models Type: general – SubjectFull: Computer-assisted image analysis (Medicine) Type: general – SubjectFull: Microbial sensitivity tests Type: general – SubjectFull: Convolutional neural networks Type: general – SubjectFull: Detection algorithms Type: general – SubjectFull: Medical screening Type: general – SubjectFull: Stains & staining (Microscopy) Type: general – SubjectFull: Automation Type: general – SubjectFull: Microscopy Type: general – SubjectFull: Comparative studies Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Tuberculosis Type: general – SubjectFull: Sensitivity & specificity (Statistics) Type: general – SubjectFull: Skin tests Type: general Titles: – TitleFull: Optimizing TB Bacteria Detection Efficiency: Utilizing RetinaNet‐Based Preprocessing Techniques for Small Image Patch Classification. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: V., Shwetha – PersonEntity: Name: NameFull: Banerjee, Barnini – PersonEntity: Name: NameFull: Laxmi, Vijaya – PersonEntity: Name: NameFull: Kamath, Priya – PersonEntity: Name: NameFull: Ahmad, Irfan IsPartOfRelationships: – BibEntity: Dates: – D: 05 M: 10 Text: 10/5/2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 16874188 Numbering: – Type: volume Value: 2025 Titles: – TitleFull: International Journal of Biomedical Imaging Type: main |
| ResultId | 1 |
