Revolutionizing diagnosis of pulmonary Mycobacterium tuberculosis based on CT: a systematic review of imaging analysis through deep learning
IntroductionThe mortality rate associated with Mycobacterium tuberculosis (MTB) has seen a significant rise in regions heavily affected by the disease over the past few decades. The traditional methods for diagnosing and differentiating tuberculosis (TB) remain thorny issues, particularly in areas w...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2024.1510026/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555158125772800 |
|---|---|
| author | Fei Zhang Hui Han Minglin Li Tian Tian Guilei Zhang Zhenrong Yang Feng Guo Maomao Li Yuting Wang Jiahe Wang Ying Liu |
| author_facet | Fei Zhang Hui Han Minglin Li Tian Tian Guilei Zhang Zhenrong Yang Feng Guo Maomao Li Yuting Wang Jiahe Wang Ying Liu |
| author_sort | Fei Zhang |
| collection | DOAJ |
| description | IntroductionThe mortality rate associated with Mycobacterium tuberculosis (MTB) has seen a significant rise in regions heavily affected by the disease over the past few decades. The traditional methods for diagnosing and differentiating tuberculosis (TB) remain thorny issues, particularly in areas with a high TB epidemic and inadequate resources. Processing numerous images can be time-consuming and tedious. Therefore, there is a need for automatic segmentation and classification technologies based on lung computed tomography (CT) scans to expedite and enhance the diagnosis of TB, enabling the rapid and secure identification of the condition. Deep learning (DL) offers a promising solution for automatically segmenting and classifying lung CT scans, expediting and enhancing TB diagnosis.MethodsThis review evaluates the diagnostic accuracy of DL modalities for diagnosing pulmonary tuberculosis (PTB) after searching the PubMed and Web of Science databases using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines.ResultsSeven articles were found and included in the review. While DL has been widely used and achieved great success in CT-based PTB diagnosis, there are still challenges to be addressed and opportunities to be explored, including data scarcity, model generalization, interpretability, and ethical concerns. Addressing these challenges requires data augmentation, interpretable models, moral frameworks, and clinical validation.ConclusionFurther research should focus on developing robust and generalizable DL models, enhancing model interpretability, establishing ethical guidelines, and conducting clinical validation studies. DL holds great promise for transforming PTB diagnosis and improving patient outcomes. |
| format | Article |
| id | doaj-art-4625cf37a66d4fa6a51423048ed6c012 |
| institution | Kabale University |
| issn | 1664-302X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj-art-4625cf37a66d4fa6a51423048ed6c0122025-01-08T06:11:48ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2025-01-011510.3389/fmicb.2024.15100261510026Revolutionizing diagnosis of pulmonary Mycobacterium tuberculosis based on CT: a systematic review of imaging analysis through deep learningFei Zhang0Hui Han1Minglin Li2Tian Tian3Guilei Zhang4Zhenrong Yang5Feng Guo6Maomao Li7Yuting Wang8Jiahe Wang9Ying Liu10Department of Family Medicine, Shengjing Hospital of China Medical University, Shenyang, Liaoning, ChinaScience and Technology Research Center of China Customs, Beijing, ChinaDepartment of Family Medicine, Shengjing Hospital of China Medical University, Shenyang, Liaoning, ChinaDepartment of Family Medicine, Shengjing Hospital of China Medical University, Shenyang, Liaoning, ChinaDepartment of Family Medicine, Shengjing Hospital of China Medical University, Shenyang, Liaoning, ChinaDepartment of Pulmonary and Critical Care Medicine, Anshan Central Hospital, Anshan, Liaoning, ChinaDepartment of Emergency Medicine, Shengjing Hospital of China Medical University, Shenyang, Liaoning, ChinaDepartment of General Practice, First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, ChinaDepartment of Cardiology, Shengjing Hospital of China Medical University, Shenyang, Liaoning, ChinaDepartment of Family Medicine, Shengjing Hospital of China Medical University, Shenyang, Liaoning, ChinaDepartment of Nephrology, Shengjing Hospital of China Medical University, Shenyang, ChinaIntroductionThe mortality rate associated with Mycobacterium tuberculosis (MTB) has seen a significant rise in regions heavily affected by the disease over the past few decades. The traditional methods for diagnosing and differentiating tuberculosis (TB) remain thorny issues, particularly in areas with a high TB epidemic and inadequate resources. Processing numerous images can be time-consuming and tedious. Therefore, there is a need for automatic segmentation and classification technologies based on lung computed tomography (CT) scans to expedite and enhance the diagnosis of TB, enabling the rapid and secure identification of the condition. Deep learning (DL) offers a promising solution for automatically segmenting and classifying lung CT scans, expediting and enhancing TB diagnosis.MethodsThis review evaluates the diagnostic accuracy of DL modalities for diagnosing pulmonary tuberculosis (PTB) after searching the PubMed and Web of Science databases using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines.ResultsSeven articles were found and included in the review. While DL has been widely used and achieved great success in CT-based PTB diagnosis, there are still challenges to be addressed and opportunities to be explored, including data scarcity, model generalization, interpretability, and ethical concerns. Addressing these challenges requires data augmentation, interpretable models, moral frameworks, and clinical validation.ConclusionFurther research should focus on developing robust and generalizable DL models, enhancing model interpretability, establishing ethical guidelines, and conducting clinical validation studies. DL holds great promise for transforming PTB diagnosis and improving patient outcomes.https://www.frontiersin.org/articles/10.3389/fmicb.2024.1510026/fulldeep learningpneumoniatuberculosisdiagnosisreview |
| spellingShingle | Fei Zhang Hui Han Minglin Li Tian Tian Guilei Zhang Zhenrong Yang Feng Guo Maomao Li Yuting Wang Jiahe Wang Ying Liu Revolutionizing diagnosis of pulmonary Mycobacterium tuberculosis based on CT: a systematic review of imaging analysis through deep learning Frontiers in Microbiology deep learning pneumonia tuberculosis diagnosis review |
| title | Revolutionizing diagnosis of pulmonary Mycobacterium tuberculosis based on CT: a systematic review of imaging analysis through deep learning |
| title_full | Revolutionizing diagnosis of pulmonary Mycobacterium tuberculosis based on CT: a systematic review of imaging analysis through deep learning |
| title_fullStr | Revolutionizing diagnosis of pulmonary Mycobacterium tuberculosis based on CT: a systematic review of imaging analysis through deep learning |
| title_full_unstemmed | Revolutionizing diagnosis of pulmonary Mycobacterium tuberculosis based on CT: a systematic review of imaging analysis through deep learning |
| title_short | Revolutionizing diagnosis of pulmonary Mycobacterium tuberculosis based on CT: a systematic review of imaging analysis through deep learning |
| title_sort | revolutionizing diagnosis of pulmonary mycobacterium tuberculosis based on ct a systematic review of imaging analysis through deep learning |
| topic | deep learning pneumonia tuberculosis diagnosis review |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2024.1510026/full |
| work_keys_str_mv | AT feizhang revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT huihan revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT minglinli revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT tiantian revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT guileizhang revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT zhenrongyang revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT fengguo revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT maomaoli revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT yutingwang revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT jiahewang revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning AT yingliu revolutionizingdiagnosisofpulmonarymycobacteriumtuberculosisbasedonctasystematicreviewofimaginganalysisthroughdeeplearning |