Automated Hybrid Model for Detecting Perineural Invasion in the Histology of Colorectal Cancer
Perineural invasion (PNI) is a well-established independent prognostic factor for poor outcomes in colorectal cancer (CRC). However, PNI detection in CRC is a cumbersome and time-consuming process, with low inter-and intra-rater agreement. In this study, a deep-learning-based approach was proposed f...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/18/9159 |
| _version_ | 1797491466635837440 |
|---|---|
| author | Jiyoon Jung Eunsu Kim Hyeseong Lee Sung Hak Lee Sangjeong Ahn |
| author_facet | Jiyoon Jung Eunsu Kim Hyeseong Lee Sung Hak Lee Sangjeong Ahn |
| author_sort | Jiyoon Jung |
| collection | DOAJ |
| description | Perineural invasion (PNI) is a well-established independent prognostic factor for poor outcomes in colorectal cancer (CRC). However, PNI detection in CRC is a cumbersome and time-consuming process, with low inter-and intra-rater agreement. In this study, a deep-learning-based approach was proposed for detecting PNI using histopathological images. We collected 530 regions of histology from 77 whole-slide images (PNI, 100 regions; non-PNI, 430 regions) for training. The proposed hybrid model consists of two components: a segmentation network for tumor and nerve tissues, and a PNI classifier. Unlike a “black-box” model that is unable to account for errors, the proposed approach enables false predictions to be explained and addressed. We presented a high performance, automated PNI detector, with the area under the curve (AUC) for the receiver operating characteristic (ROC) curve of 0.92. Thus, the potential for the use of deep neural networks in PNI screening was proved, and a possible alternative to conventional methods for the pathologic diagnosis of CRC was provided. |
| first_indexed | 2024-03-10T00:48:54Z |
| format | Article |
| id | doaj.art-519e8c74dec04c50869e573fd6647399 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T00:48:54Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-519e8c74dec04c50869e573fd66473992023-11-23T14:53:56ZengMDPI AGApplied Sciences2076-34172022-09-011218915910.3390/app12189159Automated Hybrid Model for Detecting Perineural Invasion in the Histology of Colorectal CancerJiyoon Jung0Eunsu Kim1Hyeseong Lee2Sung Hak Lee3Sangjeong Ahn4Department of Pathology, Kangnam Sacred Heart Hospital, College of Medicine, Hallym University, 1, Singil-ro, Yeongdeungpo-gu, Seoul 07441, KoreaDepartment of Hospital Pathology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 222 Banpodae-ro, Seocho-gu, Seoul 06591, KoreaDepartment of Hospital Pathology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 222 Banpodae-ro, Seocho-gu, Seoul 06591, KoreaDepartment of Hospital Pathology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 222 Banpodae-ro, Seocho-gu, Seoul 06591, KoreaDepartment of Pathology, Korea University Anam Hospital, College of Medicine, Korea University, 73 Inchon-ro, Seonbuk-gu, Seoul 02841, KoreaPerineural invasion (PNI) is a well-established independent prognostic factor for poor outcomes in colorectal cancer (CRC). However, PNI detection in CRC is a cumbersome and time-consuming process, with low inter-and intra-rater agreement. In this study, a deep-learning-based approach was proposed for detecting PNI using histopathological images. We collected 530 regions of histology from 77 whole-slide images (PNI, 100 regions; non-PNI, 430 regions) for training. The proposed hybrid model consists of two components: a segmentation network for tumor and nerve tissues, and a PNI classifier. Unlike a “black-box” model that is unable to account for errors, the proposed approach enables false predictions to be explained and addressed. We presented a high performance, automated PNI detector, with the area under the curve (AUC) for the receiver operating characteristic (ROC) curve of 0.92. Thus, the potential for the use of deep neural networks in PNI screening was proved, and a possible alternative to conventional methods for the pathologic diagnosis of CRC was provided.https://www.mdpi.com/2076-3417/12/18/9159colorectal cancerperineural invasionsemantic segmentationdeep learningcomputational pathology |
| spellingShingle | Jiyoon Jung Eunsu Kim Hyeseong Lee Sung Hak Lee Sangjeong Ahn Automated Hybrid Model for Detecting Perineural Invasion in the Histology of Colorectal Cancer Applied Sciences colorectal cancer perineural invasion semantic segmentation deep learning computational pathology |
| title | Automated Hybrid Model for Detecting Perineural Invasion in the Histology of Colorectal Cancer |
| title_full | Automated Hybrid Model for Detecting Perineural Invasion in the Histology of Colorectal Cancer |
| title_fullStr | Automated Hybrid Model for Detecting Perineural Invasion in the Histology of Colorectal Cancer |
| title_full_unstemmed | Automated Hybrid Model for Detecting Perineural Invasion in the Histology of Colorectal Cancer |
| title_short | Automated Hybrid Model for Detecting Perineural Invasion in the Histology of Colorectal Cancer |
| title_sort | automated hybrid model for detecting perineural invasion in the histology of colorectal cancer |
| topic | colorectal cancer perineural invasion semantic segmentation deep learning computational pathology |
| url | https://www.mdpi.com/2076-3417/12/18/9159 |
| work_keys_str_mv | AT jiyoonjung automatedhybridmodelfordetectingperineuralinvasioninthehistologyofcolorectalcancer AT eunsukim automatedhybridmodelfordetectingperineuralinvasioninthehistologyofcolorectalcancer AT hyeseonglee automatedhybridmodelfordetectingperineuralinvasioninthehistologyofcolorectalcancer AT sunghaklee automatedhybridmodelfordetectingperineuralinvasioninthehistologyofcolorectalcancer AT sangjeongahn automatedhybridmodelfordetectingperineuralinvasioninthehistologyofcolorectalcancer |