NDG-CAM: Nuclei Detection in Histopathology Images with Semantic Segmentation Networks and Grad-CAM
Nuclei identification is a fundamental task in many areas of biomedical image analysis related to computational pathology applications. Nowadays, deep learning is the primary approach by which to segment the nuclei, but accuracy is closely linked to the amount of histological ground truth data for t...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/9/9/475 |
| _version_ | 1797491091255066624 |
|---|---|
| author | Nicola Altini Antonio Brunetti Emilia Puro Maria Giovanna Taccogna Concetta Saponaro Francesco Alfredo Zito Simona De Summa Vitoantonio Bevilacqua |
| author_facet | Nicola Altini Antonio Brunetti Emilia Puro Maria Giovanna Taccogna Concetta Saponaro Francesco Alfredo Zito Simona De Summa Vitoantonio Bevilacqua |
| author_sort | Nicola Altini |
| collection | DOAJ |
| description | Nuclei identification is a fundamental task in many areas of biomedical image analysis related to computational pathology applications. Nowadays, deep learning is the primary approach by which to segment the nuclei, but accuracy is closely linked to the amount of histological ground truth data for training. In addition, it is known that most of the hematoxylin and eosin (H&E)-stained microscopy nuclei images contain complex and irregular visual characteristics. Moreover, conventional semantic segmentation architectures grounded on convolutional neural networks (CNNs) are unable to recognize distinct overlapping and clustered nuclei. To overcome these problems, we present an innovative method based on gradient-weighted class activation mapping (Grad-CAM) saliency maps for image segmentation. The proposed solution is comprised of two steps. The first is the semantic segmentation obtained by the use of a CNN; then, the detection step is based on the calculation of local maxima of the Grad-CAM analysis evaluated on the nucleus class, allowing us to determine the positions of the nuclei centroids. This approach, which we denote as NDG-CAM, has performance in line with state-of-the-art methods, especially in isolating the different nuclei instances, and can be generalized for different organs and tissues. Experimental results demonstrated a precision of 0.833, recall of 0.815 and a Dice coefficient of 0.824 on the publicly available validation set. When used in combined mode with instance segmentation architectures such as Mask R-CNN, the method manages to surpass state-of-the-art approaches, with precision of 0.838, recall of 0.934 and a Dice coefficient of 0.884. Furthermore, performance on the external, locally collected validation set, with a Dice coefficient of 0.914 for the combined model, shows the generalization capability of the implemented pipeline, which has the ability to detect nuclei not only related to tumor or normal epithelium but also to other cytotypes. |
| first_indexed | 2024-03-10T00:42:14Z |
| format | Article |
| id | doaj.art-a98f1b273da14ef0845b7839f300f72f |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-10T00:42:14Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-a98f1b273da14ef0845b7839f300f72f2023-11-23T15:06:12ZengMDPI AGBioengineering2306-53542022-09-019947510.3390/bioengineering9090475NDG-CAM: Nuclei Detection in Histopathology Images with Semantic Segmentation Networks and Grad-CAMNicola Altini0Antonio Brunetti1Emilia Puro2Maria Giovanna Taccogna3Concetta Saponaro4Francesco Alfredo Zito5Simona De Summa6Vitoantonio Bevilacqua7Department of Electrical and Information Engineering (DEI), Polytechnic University of Bari, Via Edoardo Orabona n.4, 70126 Bari, BA, ItalyDepartment of Electrical and Information Engineering (DEI), Polytechnic University of Bari, Via Edoardo Orabona n.4, 70126 Bari, BA, ItalyDepartment of Electrical and Information Engineering (DEI), Polytechnic University of Bari, Via Edoardo Orabona n.4, 70126 Bari, BA, ItalyDepartment of Electrical and Information Engineering (DEI), Polytechnic University of Bari, Via Edoardo Orabona n.4, 70126 Bari, BA, ItalyLaboratory of Preclinical and Translational Research, Centro di Riferimento Oncologico della Basilicata (IRCCS-CROB), Via Padre Pio n.1, 85028 Rionero in Vulture, PZ, ItalyPathology Department, IRCCS Istituto Tumori “Giovanni Paolo II”, Via O. Flacco n.65, 70124 Bari, BA, ItalyMolecular Diagnostics and Pharmacogenetics Unit, IRCCS Istituto Tumori “Giovanni Paolo II”, Via O. Flacco n.65, 70124 Bari, BA, ItalyDepartment of Electrical and Information Engineering (DEI), Polytechnic University of Bari, Via Edoardo Orabona n.4, 70126 Bari, BA, ItalyNuclei identification is a fundamental task in many areas of biomedical image analysis related to computational pathology applications. Nowadays, deep learning is the primary approach by which to segment the nuclei, but accuracy is closely linked to the amount of histological ground truth data for training. In addition, it is known that most of the hematoxylin and eosin (H&E)-stained microscopy nuclei images contain complex and irregular visual characteristics. Moreover, conventional semantic segmentation architectures grounded on convolutional neural networks (CNNs) are unable to recognize distinct overlapping and clustered nuclei. To overcome these problems, we present an innovative method based on gradient-weighted class activation mapping (Grad-CAM) saliency maps for image segmentation. The proposed solution is comprised of two steps. The first is the semantic segmentation obtained by the use of a CNN; then, the detection step is based on the calculation of local maxima of the Grad-CAM analysis evaluated on the nucleus class, allowing us to determine the positions of the nuclei centroids. This approach, which we denote as NDG-CAM, has performance in line with state-of-the-art methods, especially in isolating the different nuclei instances, and can be generalized for different organs and tissues. Experimental results demonstrated a precision of 0.833, recall of 0.815 and a Dice coefficient of 0.824 on the publicly available validation set. When used in combined mode with instance segmentation architectures such as Mask R-CNN, the method manages to surpass state-of-the-art approaches, with precision of 0.838, recall of 0.934 and a Dice coefficient of 0.884. Furthermore, performance on the external, locally collected validation set, with a Dice coefficient of 0.914 for the combined model, shows the generalization capability of the implemented pipeline, which has the ability to detect nuclei not only related to tumor or normal epithelium but also to other cytotypes.https://www.mdpi.com/2306-5354/9/9/475nuclei segmentationhistopathologydeep learningGrad-CAMsemantic segmentationinstance segmentation |
| spellingShingle | Nicola Altini Antonio Brunetti Emilia Puro Maria Giovanna Taccogna Concetta Saponaro Francesco Alfredo Zito Simona De Summa Vitoantonio Bevilacqua NDG-CAM: Nuclei Detection in Histopathology Images with Semantic Segmentation Networks and Grad-CAM Bioengineering nuclei segmentation histopathology deep learning Grad-CAM semantic segmentation instance segmentation |
| title | NDG-CAM: Nuclei Detection in Histopathology Images with Semantic Segmentation Networks and Grad-CAM |
| title_full | NDG-CAM: Nuclei Detection in Histopathology Images with Semantic Segmentation Networks and Grad-CAM |
| title_fullStr | NDG-CAM: Nuclei Detection in Histopathology Images with Semantic Segmentation Networks and Grad-CAM |
| title_full_unstemmed | NDG-CAM: Nuclei Detection in Histopathology Images with Semantic Segmentation Networks and Grad-CAM |
| title_short | NDG-CAM: Nuclei Detection in Histopathology Images with Semantic Segmentation Networks and Grad-CAM |
| title_sort | ndg cam nuclei detection in histopathology images with semantic segmentation networks and grad cam |
| topic | nuclei segmentation histopathology deep learning Grad-CAM semantic segmentation instance segmentation |
| url | https://www.mdpi.com/2306-5354/9/9/475 |
| work_keys_str_mv | AT nicolaaltini ndgcamnucleidetectioninhistopathologyimageswithsemanticsegmentationnetworksandgradcam AT antoniobrunetti ndgcamnucleidetectioninhistopathologyimageswithsemanticsegmentationnetworksandgradcam AT emiliapuro ndgcamnucleidetectioninhistopathologyimageswithsemanticsegmentationnetworksandgradcam AT mariagiovannataccogna ndgcamnucleidetectioninhistopathologyimageswithsemanticsegmentationnetworksandgradcam AT concettasaponaro ndgcamnucleidetectioninhistopathologyimageswithsemanticsegmentationnetworksandgradcam AT francescoalfredozito ndgcamnucleidetectioninhistopathologyimageswithsemanticsegmentationnetworksandgradcam AT simonadesumma ndgcamnucleidetectioninhistopathologyimageswithsemanticsegmentationnetworksandgradcam AT vitoantoniobevilacqua ndgcamnucleidetectioninhistopathologyimageswithsemanticsegmentationnetworksandgradcam |