Application of quantitative histomorphometric features in computational pathology
Abstract Computer vision has facilitated the execution of various computer‐aided diagnostic tasks. From a methodological perspective, these tasks are primarily implemented using two dominant strategies: end‐to‐end Deep learning (DL)‐based methods and traditional feature engineering‐based methods. DL...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2025-01-01
|
| Series: | Interdisciplinary Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/INMD.20240037 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586452801683456 |
|---|---|
| author | Yujie Shi Bo Hu Mingyan Xu Yunhan Yao Shuaiqiang Gao Xiang Xia Xikai Deng Jianfeng Liu Jia Gu Shifu Chen |
| author_facet | Yujie Shi Bo Hu Mingyan Xu Yunhan Yao Shuaiqiang Gao Xiang Xia Xikai Deng Jianfeng Liu Jia Gu Shifu Chen |
| author_sort | Yujie Shi |
| collection | DOAJ |
| description | Abstract Computer vision has facilitated the execution of various computer‐aided diagnostic tasks. From a methodological perspective, these tasks are primarily implemented using two dominant strategies: end‐to‐end Deep learning (DL)‐based methods and traditional feature engineering‐based methods. DL methods are capable of automatically extracting, analyzing, and filtering features, leading to final decision‐making from whole slide images. However, these methods are often criticized for the “black box” issue, a significant limitation of DL. In contrast, traditional feature engineering‐based methods involve well‐defined quantitative input features. But it was considered as less potent than DL methods. Advances in segmentation technology and the development of quantitative histomorphometric (QH) feature representation have propelled the evolution of feature engineering‐based methods. This review contrasts the performance differences between the two methods and traces the development of QH feature representation. The conclusion is that, with the ongoing progress in QH feature representation and segmentation technology, methods based on QH features will leverage their advantages—such as explainability, reduced reliance on large training datasets, and lower computational resource requirements—to play a more significant role in some clinical tasks. They may even replace DL methods somewhat or be used in conjunction with them to achieve accurate and understandable results. |
| format | Article |
| id | doaj-art-f469db7737a84e7d972479219c8cd1c7 |
| institution | Kabale University |
| issn | 2832-6245 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Interdisciplinary Medicine |
| spelling | doaj-art-f469db7737a84e7d972479219c8cd1c72025-01-25T17:57:32ZengWiley-VCHInterdisciplinary Medicine2832-62452025-01-0131n/an/a10.1002/INMD.20240037Application of quantitative histomorphometric features in computational pathologyYujie Shi0Bo Hu1Mingyan Xu2Yunhan Yao3Shuaiqiang Gao4Xiang Xia5Xikai Deng6Jianfeng Liu7Jia Gu8Shifu Chen9Department of Pathology Henan Provincial People's Hospital Zhengzhou University Zhengzhou Henan ChinaHaploX Biotechnology Shenzhen Guangdong ChinaHaploX Biotechnology Shenzhen Guangdong ChinaHaploX Biotechnology Shenzhen Guangdong ChinaHaploX Biotechnology Shenzhen Guangdong ChinaHaploX Biotechnology Shenzhen Guangdong ChinaHaploX Biotechnology Shenzhen Guangdong ChinaInstitute of Medical Psychology and Behavioural Neurobiology University of Tübingen Tübingen GermanyFaculty of Data Science City University of Macau Taipa Macau ChinaHaploX Biotechnology Shenzhen Guangdong ChinaAbstract Computer vision has facilitated the execution of various computer‐aided diagnostic tasks. From a methodological perspective, these tasks are primarily implemented using two dominant strategies: end‐to‐end Deep learning (DL)‐based methods and traditional feature engineering‐based methods. DL methods are capable of automatically extracting, analyzing, and filtering features, leading to final decision‐making from whole slide images. However, these methods are often criticized for the “black box” issue, a significant limitation of DL. In contrast, traditional feature engineering‐based methods involve well‐defined quantitative input features. But it was considered as less potent than DL methods. Advances in segmentation technology and the development of quantitative histomorphometric (QH) feature representation have propelled the evolution of feature engineering‐based methods. This review contrasts the performance differences between the two methods and traces the development of QH feature representation. The conclusion is that, with the ongoing progress in QH feature representation and segmentation technology, methods based on QH features will leverage their advantages—such as explainability, reduced reliance on large training datasets, and lower computational resource requirements—to play a more significant role in some clinical tasks. They may even replace DL methods somewhat or be used in conjunction with them to achieve accurate and understandable results.https://doi.org/10.1002/INMD.20240037deep learningpathological imagequantitative histomorphometric featuresegmentation |
| spellingShingle | Yujie Shi Bo Hu Mingyan Xu Yunhan Yao Shuaiqiang Gao Xiang Xia Xikai Deng Jianfeng Liu Jia Gu Shifu Chen Application of quantitative histomorphometric features in computational pathology Interdisciplinary Medicine deep learning pathological image quantitative histomorphometric feature segmentation |
| title | Application of quantitative histomorphometric features in computational pathology |
| title_full | Application of quantitative histomorphometric features in computational pathology |
| title_fullStr | Application of quantitative histomorphometric features in computational pathology |
| title_full_unstemmed | Application of quantitative histomorphometric features in computational pathology |
| title_short | Application of quantitative histomorphometric features in computational pathology |
| title_sort | application of quantitative histomorphometric features in computational pathology |
| topic | deep learning pathological image quantitative histomorphometric feature segmentation |
| url | https://doi.org/10.1002/INMD.20240037 |
| work_keys_str_mv | AT yujieshi applicationofquantitativehistomorphometricfeaturesincomputationalpathology AT bohu applicationofquantitativehistomorphometricfeaturesincomputationalpathology AT mingyanxu applicationofquantitativehistomorphometricfeaturesincomputationalpathology AT yunhanyao applicationofquantitativehistomorphometricfeaturesincomputationalpathology AT shuaiqianggao applicationofquantitativehistomorphometricfeaturesincomputationalpathology AT xiangxia applicationofquantitativehistomorphometricfeaturesincomputationalpathology AT xikaideng applicationofquantitativehistomorphometricfeaturesincomputationalpathology AT jianfengliu applicationofquantitativehistomorphometricfeaturesincomputationalpathology AT jiagu applicationofquantitativehistomorphometricfeaturesincomputationalpathology AT shifuchen applicationofquantitativehistomorphometricfeaturesincomputationalpathology |