1
|
Tian L, Wu J, Song W, Hong Q, Liu D, Ye F, Gao F, Hu Y, Wu M, Lan Y, Chen L. Precise and automated lung cancer cell classification using deep neural network with multiscale features and model distillation. Sci Rep 2024; 14:10471. [PMID: 38714840 PMCID: PMC11076475 DOI: 10.1038/s41598-024-61101-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2023] [Accepted: 05/02/2024] [Indexed: 05/12/2024] Open
Abstract
Lung diseases globally impose a significant pathological burden and mortality rate, particularly the differential diagnosis between adenocarcinoma, squamous cell carcinoma, and small cell lung carcinoma, which is paramount in determining optimal treatment strategies and improving clinical prognoses. Faced with the challenge of improving diagnostic precision and stability, this study has developed an innovative deep learning-based model. This model employs a Feature Pyramid Network (FPN) and Squeeze-and-Excitation (SE) modules combined with a Residual Network (ResNet18), to enhance the processing capabilities for complex images and conduct multi-scale analysis of each channel's importance in classifying lung cancer. Moreover, the performance of the model is further enhanced by employing knowledge distillation from larger teacher models to more compact student models. Subjected to rigorous five-fold cross-validation, our model outperforms existing models on all performance metrics, exhibiting exceptional diagnostic accuracy. Ablation studies on various model components have verified that each addition effectively improves model performance, achieving an average accuracy of 98.84% and a Matthews Correlation Coefficient (MCC) of 98.83%. Collectively, the results indicate that our model significantly improves the accuracy of disease diagnosis, providing physicians with more precise clinical decision-making support.
Collapse
Affiliation(s)
- Lan Tian
- Department of Pulmonary and Critical Care Medicine, Fujian Medical University Union Hospital, Fuzhou, 350001, Fujian, China
| | - Jiabao Wu
- Department of Pulmonary and Critical Care Medicine, Fujian Medical University Union Hospital, Fuzhou, 350001, Fujian, China
| | - Wanting Song
- Department of Pulmonary and Critical Care Medicine, Fujian Medical University Union Hospital, Fuzhou, 350001, Fujian, China
| | - Qinghuai Hong
- Department of Pulmonary and Critical Care Medicine, Fujian Medical University Union Hospital, Fuzhou, 350001, Fujian, China
| | - Di Liu
- Department of Pulmonary and Critical Care Medicine, Fujian Medical University Union Hospital, Fuzhou, 350001, Fujian, China
| | - Fei Ye
- Department of Pulmonary and Critical Care Medicine, Fujian Medical University Union Hospital, Fuzhou, 350001, Fujian, China
| | - Feng Gao
- Department of Pathology, The First Affiliated Hospital of Fujian Medical University, Fuzhou, 350005, Fujian, China
| | - Yue Hu
- Department of Oncology, Guang'anmen Hospital, China Academy of Chinese Medical Sciences, Beijing, 100053, China
| | - Meijuan Wu
- Department of Pulmonary and Critical Care Medicine, The Second Hospital of Sanming, Sanming, 366000, Fujian, China
| | - Yi Lan
- Department of General Medicine, Nanping First Hospital Affiliated to Fujian Medical University, Nanping, 353000, Fujian, China.
| | - Limin Chen
- Department of Pulmonary and Critical Care Medicine, Fujian Medical University Union Hospital, Fuzhou, 350001, Fujian, China.
| |
Collapse
|
2
|
Shanmugam K, Rajaguru H. Exploration and Enhancement of Classifiers in the Detection of Lung Cancer from Histopathological Images. Diagnostics (Basel) 2023; 13:3289. [PMID: 37892110 PMCID: PMC10606104 DOI: 10.3390/diagnostics13203289] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2023] [Revised: 10/20/2023] [Accepted: 10/21/2023] [Indexed: 10/29/2023] Open
Abstract
Lung cancer is a prevalent malignancy that impacts individuals of all genders and is often diagnosed late due to delayed symptoms. To catch it early, researchers are developing algorithms to study lung cancer images. The primary objective of this work is to propose a novel approach for the detection of lung cancer using histopathological images. In this work, the histopathological images underwent preprocessing, followed by segmentation using a modified approach of KFCM-based segmentation and the segmented image intensity values were dimensionally reduced using Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO). Algorithms such as KL Divergence and Invasive Weed Optimization (IWO) are used for feature selection. Seven different classifiers such as SVM, KNN, Random Forest, Decision Tree, Softmax Discriminant, Multilayer Perceptron, and BLDC were used to analyze and classify the images as benign or malignant. Results were compared using standard metrics, and kappa analysis assessed classifier agreement. The Decision Tree Classifier with GWO feature extraction achieved good accuracy of 85.01% without feature selection and hyperparameter tuning approaches. Furthermore, we present a methodology to enhance the accuracy of the classifiers by employing hyperparameter tuning algorithms based on Adam and RAdam. By combining features from GWO and IWO, and using the RAdam algorithm, the Decision Tree classifier achieves the commendable accuracy of 91.57%.
Collapse
Affiliation(s)
| | - Harikumar Rajaguru
- Department of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam 638401, India;
| |
Collapse
|
3
|
Anjum S, Ahmed I, Asif M, Aljuaid H, Alturise F, Ghadi YY, Elhabob R. Lung Cancer Classification in Histopathology Images Using Multiresolution Efficient Nets. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2023; 2023:7282944. [PMID: 37876944 PMCID: PMC10593544 DOI: 10.1155/2023/7282944] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/19/2022] [Revised: 11/07/2022] [Accepted: 11/29/2022] [Indexed: 10/26/2023]
Abstract
Histopathological images are very effective for investigating the status of various biological structures and diagnosing diseases like cancer. In addition, digital histopathology increases diagnosis precision and provides better image quality and more detail for the pathologist with multiple viewing options and team annotations. As a result of the benefits above, faster treatment is available, increasing therapy success rates and patient recovery and survival chances. However, the present manual examination of these images is tedious and time-consuming for pathologists. Therefore, reliable automated techniques are needed to effectively classify normal and malignant cancer images. This paper applied a deep learning approach, namely, EfficientNet and its variants from B0 to B7. We used different image resolutions for each model, from 224 × 224 pixels to 600 × 600 pixels. We also applied transfer learning and parameter tuning techniques to improve the results and overcome the overfitting problem. We collected the dataset from the Lung and Colon Cancer Histopathological Image LC25000 image dataset. The dataset acquisition consists of 25,000 histopathology images of five classes (lung adenocarcinoma, lung squamous cell carcinoma, benign lung tissue, colon adenocarcinoma, and colon benign tissue). Then, we performed preprocessing on the dataset to remove the noisy images and bring them into a standard format. The model's performance was evaluated in terms of classification accuracy and loss. We have achieved good accuracy results for all variants; however, the results of EfficientNetB2 stand excellent, with an accuracy of 97% for 260 × 260 pixels resolution images.
Collapse
Affiliation(s)
- Sunila Anjum
- Center of Excellence in Information Technology, Institute of Management Sciences, Hayatabad, Peshawar 25000, Pakistan
| | - Imran Ahmed
- School of Computing and Information Science, Anglia Ruskin University, Cambridge, UK
| | - Muhammad Asif
- Department of Computer Science, National Textile University, Faisalabad, Pakistan
| | - Hanan Aljuaid
- Computer Sciences Department, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University (PNU), P.O. Box 84428, Riyadh 11671, Saudi Arabia
| | - Fahad Alturise
- Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass, Qassim, Saudi Arabia
| | - Yazeed Yasin Ghadi
- Department of Software Engineering/Computer Science, Al Ain University, Al Ain, UAE
| | - Rashad Elhabob
- College of Computer Science and Information Technology, Karary University, Omdurman, Sudan
| |
Collapse
|
4
|
Das M, Dash R, Mishra SK. Automatic Detection of Oral Squamous Cell Carcinoma from Histopathological Images of Oral Mucosa Using Deep Convolutional Neural Network. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2023; 20:2131. [PMID: 36767498 PMCID: PMC9915186 DOI: 10.3390/ijerph20032131] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/08/2022] [Revised: 01/19/2023] [Accepted: 01/20/2023] [Indexed: 06/18/2023]
Abstract
Worldwide, oral cancer is the sixth most common type of cancer. India is in 2nd position, with the highest number of oral cancer patients. To the population of oral cancer patients, India contributes to almost one-third of the total count. Among several types of oral cancer, the most common and dominant one is oral squamous cell carcinoma (OSCC). The major reason for oral cancer is tobacco consumption, excessive alcohol consumption, unhygienic mouth condition, betel quid eating, viral infection (namely human papillomavirus), etc. The early detection of oral cancer type OSCC, in its preliminary stage, gives more chances for better treatment and proper therapy. In this paper, author proposes a convolutional neural network model, for the automatic and early detection of OSCC, and for experimental purposes, histopathological oral cancer images are considered. The proposed model is compared and analyzed with state-of-the-art deep learning models like VGG16, VGG19, Alexnet, ResNet50, ResNet101, Mobile Net and Inception Net. The proposed model achieved a cross-validation accuracy of 97.82%, which indicates the suitability of the proposed approach for the automatic classification of oral cancer data.
Collapse
Affiliation(s)
- Madhusmita Das
- Department of Computer Application, Siksha ‘O’ Anusandhan Deemed to be University, Bhubaneswar 751030, India
| | - Rasmita Dash
- Department of Computer Science and Engineering, Siksha ‘O’ Anusandhan Deemed to be University, Bhubaneswar 751030, India
| | - Sambit Kumar Mishra
- Department of Computer Science and Engineering, SRM University-AP, Guntur 522240, India
| |
Collapse
|
5
|
Das A, Nair MS, Peter SD. Computer-Aided Histopathological Image Analysis Techniques for Automated Nuclear Atypia Scoring of Breast Cancer: a Review. J Digit Imaging 2021; 33:1091-1121. [PMID: 31989390 DOI: 10.1007/s10278-019-00295-z] [Citation(s) in RCA: 33] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022] Open
Abstract
Breast cancer is the most common type of malignancy diagnosed in women. Through early detection and diagnosis, there is a great chance of recovery and thereby reduce the mortality rate. Many preliminary tests like non-invasive radiological diagnosis using ultrasound, mammography, and MRI are widely used for the diagnosis of breast cancer. However, histopathological analysis of breast biopsy specimen is inevitable and is considered to be the golden standard for the affirmation of cancer. With the advancements in the digital computing capabilities, memory capacity, and imaging modalities, the development of computer-aided powerful analytical techniques for histopathological data has increased dramatically. These automated techniques help to alleviate the laborious work of the pathologist and to improve the reproducibility and reliability of the interpretation. This paper reviews and summarizes digital image computational algorithms applied on histopathological breast cancer images for nuclear atypia scoring and explores the future possibilities. The algorithms for nuclear pleomorphism scoring of breast cancer can be widely grouped into two categories: handcrafted feature-based and learned feature-based. Handcrafted feature-based algorithms mainly include the computational steps like pre-processing the images, segmenting the nuclei, extracting unique features, feature selection, and machine learning-based classification. However, most of the recent algorithms are based on learned features, that extract high-level abstractions directly from the histopathological images utilizing deep learning techniques. In this paper, we discuss the various algorithms applied for the nuclear pleomorphism scoring of breast cancer, discourse the challenges to be dealt with, and outline the importance of benchmark datasets. A comparative analysis of some prominent works on breast cancer nuclear atypia scoring is done using a benchmark dataset which enables to quantitatively measure and compare the different features and algorithms used for breast cancer grading. Results show that improvements are still required, to have an automated cancer grading system suitable for clinical applications.
Collapse
Affiliation(s)
- Asha Das
- Artificial Intelligence & Computer Vision Lab, Department of Computer Science, Cochin University of Science and Technology, Kochi, Kerala, 682022, India.
| | - Madhu S Nair
- Artificial Intelligence & Computer Vision Lab, Department of Computer Science, Cochin University of Science and Technology, Kochi, Kerala, 682022, India
| | - S David Peter
- Artificial Intelligence & Computer Vision Lab, Department of Computer Science, Cochin University of Science and Technology, Kochi, Kerala, 682022, India
| |
Collapse
|
6
|
Batch Mode Active Learning on the Riemannian Manifold for Automated Scoring of Nuclear Pleomorphism in Breast Cancer. Artif Intell Med 2020; 103:101805. [PMID: 32143801 DOI: 10.1016/j.artmed.2020.101805] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2019] [Revised: 01/12/2020] [Accepted: 01/13/2020] [Indexed: 11/22/2022]
Abstract
Breast cancer is the most prevalent invasive type of cancer among women. The mortality rate of the disease can be reduced considerably through timely prognosis and felicitous treatment planning, by utilizing the computer aided detection and diagnosis techniques. With the advent of whole slide image (WSI) scanners for digitizing the histopathological tissue samples, there is a drastic increase in the availability of digital histopathological images. However, these samples are often unlabeled and hence they need labeling to be done through manual annotations by domain experts and experienced pathologists. But this annotation process required for acquiring high quality large labeled training set for nuclear atypia scoring is a tedious, expensive and time consuming job. Active learning techniques have achieved widespread acceptance in reducing this human effort in annotating the data samples. In this paper, we explore the possibilities of active learning on nuclear pleomorphism scoring over a non-Euclidean framework, the Riemannian manifold. Active learning technique adopted for the cancer grading is in the batch-mode framework, that adaptively identifies the apt batch size along with the batch of instances to be queried, following a submodular optimization framework. Samples for annotation are selected considering the diversity and redundancy between the pair of samples, based on the kernelized Riemannian distance measures such as log-Euclidean metrics and the two Bregman divergences - Stein and Jeffrey divergences. Results of the adaptive Batch Mode Active Learning on the Riemannian metric show a superior performance when compared with the state-of-the-art techniques for breast cancer nuclear pleomorphism scoring, as it makes use of the information from the unlabeled samples.
Collapse
|
7
|
Decision Support System for Lung Cancer Using PET/CT and Microscopic Images. ADVANCES IN EXPERIMENTAL MEDICINE AND BIOLOGY 2020; 1213:73-94. [DOI: 10.1007/978-3-030-33128-3_5] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/03/2022]
|
8
|
Das A, Nair MS, Peter D. Kernel-based Fisher discriminant analysis on the Riemannian manifold for nuclear atypia scoring of breast cancer. Biocybern Biomed Eng 2019. [DOI: 10.1016/j.bbe.2019.06.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
|
9
|
Das A, Nair MS, Peter SD. Sparse Representation Over Learned Dictionaries on the Riemannian Manifold for Automated Grading of Nuclear Pleomorphism in Breast Cancer. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2019; 28:1248-1260. [PMID: 30346284 DOI: 10.1109/tip.2018.2877337] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
Breast cancer is found to be the most pervasive type of cancer among women. Computer aided detection and diagnosis of cancer at the initial stages can increase the chances of recovery and thus reduce the mortality rate through timely prognosis and adequate treatment planning. The nuclear atypia scoring or histopathological breast tumor grading remains to be a challenging problem due to the various artifacts and variabilities introduced during slide preparation and also because of the complexity in the structure of the underlying tissue patterns. Inspired by the success of symmetric positive definite (SPD) matrices in many of the challenging tasks in machine learning and computer vision, a sparse coding and dictionary learning on SPD matrices is proposed in this paper for the breast tumor grading. The proposed covariance-based SPD matrices form a Riemannian manifold and are represented as the sparse combination of Riemannian dictionary atoms. Non-linearity of the SPD manifold is tackled by embedding into the reproducing kernel Hilbert space using kernels derived from log-Euclidean metric, Jeffrey and Stein divergences and compared with the non-kernel-based affine invariant Riemannian metric. The novelty of the work lies in exploiting the kernel approach for the Hilbert space embedding of the Riemannian manifold, that can achieve a better discrimination of the breast cancer tissues, following a sparse representation over learned dictionaries and henceforth it outperforms many of the state-of-the-art algorithms in breast cancer grading in terms of quantitative and qualitative analysis.
Collapse
|
10
|
Teramoto A, Yamada A, Kiriyama Y, Tsukamoto T, Yan K, Zhang L, Imaizumi K, Saito K, Fujita H. Automated classification of benign and malignant cells from lung cytological images using deep convolutional neural network. INFORMATICS IN MEDICINE UNLOCKED 2019. [DOI: 10.1016/j.imu.2019.100205] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022] Open
|
11
|
Suárez-Nájera LE, Chanona-Pérez JJ, Valdivia-Flores A, Marrero-Rodríguez D, Salcedo-Vargas M, García-Ruiz DI, Castro-Reyes MA. Morphometric study of adipocytes on breast cancer by means of photonic microscopy and image analysis. Microsc Res Tech 2017; 81:240-249. [PMID: 29193620 DOI: 10.1002/jemt.22972] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2017] [Revised: 10/11/2017] [Accepted: 11/11/2017] [Indexed: 01/10/2023]
Abstract
Worldwide, breast cancer (BrCa) is currently the leading cause of deaths associated to malignant lesions in adult women. Given that some studies have mentioned that peritumoral adipocytes may contribute to breast carcinogenesis, present work sought to quantitative evaluate the morphometry of these cells in a group of adult women. Three thousand six hundred sixty four breast adipocytes, that came from biopsies of a group of adult females with different types of breast carcinomas (ductal, lobular, and mixed) and one with normal tissues, were evaluated through an image analysis (IA) process regarding six morphometric descriptors: area (A), perimeter (P), Feret diameter (FD ), aspect ratio (AR), roundness factor (RF), and fractal dimension of cellular contour (FDC ). Data showed that the adipocytes of the normal tissues group were bigger (A: 3398 ± 2331 µm2 , P: 239 ± 83 µm, and FD : 79.9 ± 24.5 µm) than those from BrCa samples (A: 2860 ± 1933 µm2 , P: 214 ± 66 µm, and FD : 73.2 ± 22.5 µm), and presented a more irregular contour (FDC of 1.370 ± 0.037 for normal group and of 1.335 ± 0.049 for the oncologic one). Moreover, it could be accounted that adipocytes of mixed carcinomas were largest (FD : 75.1 ± 22.4 µm) than those of lobular lesions (FD : 61.6 ± 22.6 µm), while the adipocytes of ductal carcinomas were the most oval (AR: 1.421 ± 0.524) and roughest (FDC : 1.324 ± 0.050) cells. IA results suggest that BrCa lesions can be categorized through a quantitative morphometric evaluation of peritumoral adipocytes. These findings could let the development of an analytical tool to help the Pathologist to enhance the accuracy of the oncologic diagnose.
Collapse
Affiliation(s)
- Luis Eduardo Suárez-Nájera
- Departamento de Ingeniería Bioquímica, Escuela Nacional de Ciencias Biológicas, Instituto Politécnico Nacional, Unidad Profesional Adolfo López Mateos, Ciudad de México, México
| | - José Jorge Chanona-Pérez
- Departamento de Ingeniería Bioquímica, Escuela Nacional de Ciencias Biológicas, Instituto Politécnico Nacional, Unidad Profesional Adolfo López Mateos, Ciudad de México, México
| | - Alejandra Valdivia-Flores
- Dirección de Investigación, Secretaria de Investigación y Posgrado, Instituto Politécnico Nacional, Ciudad de México, México
| | - Daniel Marrero-Rodríguez
- Laboratorio de Oncología Genómica, Hospital de Oncología del Centro Médico Nacional Siglo XXI, Instituto Mexicano del Seguro Social, Ciudad de México, México
| | - Mauricio Salcedo-Vargas
- Laboratorio de Oncología Genómica, Hospital de Oncología del Centro Médico Nacional Siglo XXI, Instituto Mexicano del Seguro Social, Ciudad de México, México
| | - David Israel García-Ruiz
- Servicio de Cirugía Oncológica, Hospital de Oncología del Centro Médico Nacional Siglo XXI, Instituto Mexicano del Seguro Social, Ciudad de México, México
| | - Marco Antonio Castro-Reyes
- Departamento de Posgrado, Centro Interdisciplinario de Ciencias de la Salud, Unidad Milpa Alta, Instituto Politécnico Nacional, Ciudad de México, México
| |
Collapse
|
12
|
Wen S, Kurc TM, Gao Y, Zhao T, Saltz JH, Zhu W. A Methodology for Texture Feature-based Quality Assessment in Nucleus Segmentation of Histopathology Image. J Pathol Inform 2017; 8:38. [PMID: 28966837 PMCID: PMC5609357 DOI: 10.4103/jpi.jpi_43_17] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2017] [Accepted: 07/11/2017] [Indexed: 12/31/2022] Open
Abstract
CONTEXT Image segmentation pipelines often are sensitive to algorithm input parameters. Algorithm parameters optimized for a set of images do not necessarily produce good-quality-segmentation results for other images. Even within an image, some regions may not be well segmented due to a number of factors, including multiple pieces of tissue with distinct characteristics, differences in staining of the tissue, normal versus tumor regions, and tumor heterogeneity. Evaluation of quality of segmentation results is an important step in image analysis. It is very labor intensive to do quality assessment manually with large image datasets because a whole-slide tissue image may have hundreds of thousands of nuclei. Semi-automatic mechanisms are needed to assist researchers and application developers to detect image regions with bad segmentations efficiently. AIMS Our goal is to develop and evaluate a machine-learning-based semi-automated workflow to assess quality of nucleus segmentation results in a large set of whole-slide tissue images. METHODS We propose a quality control methodology, in which machine-learning algorithms are trained with image intensity and texture features to produce a classification model. This model is applied to image patches in a whole-slide tissue image to predict the quality of nucleus segmentation in each patch. The training step of our methodology involves the selection and labeling of regions by a pathologist in a set of images to create the training dataset. The image regions are partitioned into patches. A set of intensity and texture features is computed for each patch. A classifier is trained with the features and the labels assigned by the pathologist. At the end of this process, a classification model is generated. The classification step applies the classification model to unlabeled test images. Each test image is partitioned into patches. The classification model is applied to each patch to predict the patch's label. RESULTS The proposed methodology has been evaluated by assessing the segmentation quality of a segmentation method applied to images from two cancer types in The Cancer Genome Atlas; WHO Grade II lower grade glioma (LGG) and lung adenocarcinoma (LUAD). The results show that our method performs well in predicting patches with good-quality segmentations and achieves F1 scores 84.7% for LGG and 75.43% for LUAD. CONCLUSIONS As image scanning technologies advance, large volumes of whole-slide tissue images will be available for research and clinical use. Efficient approaches for the assessment of quality and robustness of output from computerized image analysis workflows will become increasingly critical to extracting useful quantitative information from tissue images. Our work demonstrates the feasibility of machine-learning-based semi-automated techniques to assist researchers and algorithm developers in this process.
Collapse
Affiliation(s)
- Si Wen
- Department of Applied Mathematics and Statistics, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Tahsin M. Kurc
- Department of Biomedical Informatics, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Yi Gao
- Department of Biomedical Informatics, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Tianhao Zhao
- Department of Biomedical Informatics, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Joel H. Saltz
- Department of Biomedical Informatics, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Wei Zhu
- Department of Applied Mathematics and Statistics, State University of New York at Stony Brook, Stony Brook, NY, USA
| |
Collapse
|
13
|
Mazo C, Alegre E, Trujillo M. Classification of cardiovascular tissues using LBP based descriptors and a cascade SVM. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2017; 147:1-10. [PMID: 28734525 DOI: 10.1016/j.cmpb.2017.06.003] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/07/2016] [Revised: 05/09/2017] [Accepted: 06/02/2017] [Indexed: 06/07/2023]
Abstract
BACKGROUND AND OBJECTIVE Histological images have characteristics, such as texture, shape, colour and spatial structure, that permit the differentiation of each fundamental tissue and organ. Texture is one of the most discriminative features. The automatic classification of tissues and organs based on histology images is an open problem, due to the lack of automatic solutions when treating tissues without pathologies. METHOD In this paper, we demonstrate that it is possible to automatically classify cardiovascular tissues using texture information and Support Vector Machines (SVM). Additionally, we realised that it is feasible to recognise several cardiovascular organs following the same process. The texture of histological images was described using Local Binary Patterns (LBP), LBP Rotation Invariant (LBPri), Haralick features and different concatenations between them, representing in this way its content. Using a SVM with linear kernel, we selected the more appropriate descriptor that, for this problem, was a concatenation of LBP and LBPri. Due to the small number of the images available, we could not follow an approach based on deep learning, but we selected the classifier who yielded the higher performance by comparing SVM with Random Forest and Linear Discriminant Analysis. Once SVM was selected as the classifier with a higher area under the curve that represents both higher recall and precision, we tuned it evaluating different kernels, finding that a linear SVM allowed us to accurately separate four classes of tissues: (i) cardiac muscle of the heart, (ii) smooth muscle of the muscular artery, (iii) loose connective tissue, and (iv) smooth muscle of the large vein and the elastic artery. The experimental validation was conducted using 3000 blocks of 100 × 100 sized pixels, with 600 blocks per class and the classification was assessed using a 10-fold cross-validation. RESULTS using LBP as the descriptor, concatenated with LBPri and a SVM with linear kernel, the main four classes of tissues were recognised with an AUC higher than 0.98. A polynomial kernel was then used to separate the elastic artery and vein, yielding an AUC in both cases superior to 0.98. CONCLUSION Following the proposed approach, it is possible to separate with very high precision (AUC greater than 0.98) the fundamental tissues of the cardiovascular system along with some organs, such as the heart, arteries and veins.
Collapse
Affiliation(s)
- Claudia Mazo
- University of Valle, Computer and Systems Engineering School, Cali, Colombia.
| | - Enrique Alegre
- University of León, Industrial and Informatics Engineering School, León, Spain
| | - Maria Trujillo
- University of Valle, Computer and Systems Engineering School, Cali, Colombia
| |
Collapse
|
14
|
Wan T, Cao J, Chen J, Qin Z. Automated grading of breast cancer histopathology using cascaded ensemble with combination of multi-level image features. Neurocomputing 2017. [DOI: 10.1016/j.neucom.2016.05.084] [Citation(s) in RCA: 72] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
|
15
|
Aziz MA, Kanazawa H, Murakami Y, Kimura F, Yamaguchi M, Kiyuna T, Yamashita Y, Saito A, Ishikawa M, Kobayashi N, Abe T, Hashiguchi A, Sakamoto M. Enhancing automatic classification of hepatocellular carcinoma images through image masking, tissue changes and trabecular features. J Pathol Inform 2015; 6:26. [PMID: 26110093 PMCID: PMC4470016 DOI: 10.4103/2153-3539.158044] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2015] [Accepted: 04/24/2015] [Indexed: 11/18/2022] Open
Abstract
Background: Recent breakthroughs in computer vision and digital microscopy have prompted the application of such technologies in cancer diagnosis, especially in histopathological image analysis. Earlier, an attempt to classify hepatocellular carcinoma images based on nuclear and structural features has been carried out on a set of surgical resected samples. Here, we proposed methods to enhance the process and improve the classification performance. Methods: First, we segmented the histological components of the liver tissues and generated several masked images. By utilizing the masked images, some set of new features were introduced, producing three sets of features consisting nuclei, trabecular and tissue changes features. Furthermore, we extended the classification process by using biopsy resected samples in addition to the surgical samples. Results: Experiments by using support vector machine (SVM) classifier with combinations of features and sample types showed that the proposed methods improve the classification rate in HCC detection for about 1-3%. Moreover, detection rate of low-grades cancer increased when the new features were appended in the classification process, although the rate was worsen in the case of undifferentiated tumors. Conclusions: The masking process increased the reliability of extracted nuclei features. The additional of new features improved the system especially for early HCC detection. Likewise, the combination of surgical and biopsy samples as training data could also improve the classification rates. Therefore, the methods will extend the support for pathologists in the HCC diagnosis.
Collapse
Affiliation(s)
- Maulana Abdul Aziz
- Department of Information Processing, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, 4259-S1-17 Nagatsuta, Midori, Yokohama, Kanagawa 226-8503, Japan
| | - Hiroshi Kanazawa
- Global Scientific Information and Computing Center, Tokyo Institute of Technology, 2-12-1-I7-6 Ookayama, Meguro-ku, Tokyo 152-8550, Japan
| | - Yuri Murakami
- Global Scientific Information and Computing Center, Tokyo Institute of Technology, 2-12-1-I7-6 Ookayama, Meguro-ku, Tokyo 152-8550, Japan
| | - Fumikazu Kimura
- Global Scientific Information and Computing Center, Tokyo Institute of Technology, 2-12-1-I7-6 Ookayama, Meguro-ku, Tokyo 152-8550, Japan
| | - Masahiro Yamaguchi
- Department of Information Processing, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, 4259-S1-17 Nagatsuta, Midori, Yokohama, Kanagawa 226-8503, Japan ; Global Scientific Information and Computing Center, Tokyo Institute of Technology, 2-12-1-I7-6 Ookayama, Meguro-ku, Tokyo 152-8550, Japan
| | - Tomoharu Kiyuna
- Medical Solutions Division, NEC Corporation, 5-7-1 Shiba Minato-ku, Tokyo 108-8001, Japan
| | - Yoshiko Yamashita
- Department of Information Processing, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, 4259-S1-17 Nagatsuta, Midori, Yokohama, Kanagawa 226-8503, Japan ; Medical Solutions Division, NEC Corporation, 5-7-1 Shiba Minato-ku, Tokyo 108-8001, Japan
| | - Akira Saito
- Medical Solutions Division, NEC Corporation, 5-7-1 Shiba Minato-ku, Tokyo 108-8001, Japan
| | - Masahiro Ishikawa
- Faculty of Health and Medical Care, Saitama Medical University, 1397-1 Yamane, Hidaka-shi, Saitama 350-1241, Japan
| | - Naoki Kobayashi
- Faculty of Health and Medical Care, Saitama Medical University, 1397-1 Yamane, Hidaka-shi, Saitama 350-1241, Japan
| | - Tokiya Abe
- Department of Pathology, School of Medicine, Keio University, 35 Shinanomachi, Shinjuku-ku, Tokyo 160-8582, Japan
| | - Akinori Hashiguchi
- Department of Pathology, School of Medicine, Keio University, 35 Shinanomachi, Shinjuku-ku, Tokyo 160-8582, Japan
| | - Michiie Sakamoto
- Department of Pathology, School of Medicine, Keio University, 35 Shinanomachi, Shinjuku-ku, Tokyo 160-8582, Japan
| |
Collapse
|
16
|
Su H, Shen Y, Xing F, Qi X, Hirshfield KM, Yang L, Foran DJ. Robust automatic breast cancer staging using a combination of functional genomics and image-omics. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2015; 2015:7226-9. [PMID: 26737959 PMCID: PMC4918467 DOI: 10.1109/embc.2015.7320059] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/12/2023]
Abstract
Breast cancer is one of the leading cancers worldwide. Precision medicine is a new trend that systematically examines molecular and functional genomic information within each patient's cancer to identify the patterns that may affect treatment decisions and potential outcomes. As a part of precision medicine, computer-aided diagnosis enables joint analysis of functional genomic information and image from pathological images. In this paper we propose an integrated framework for breast cancer staging using image-omics and functional genomic information. The entire biomedical imaging informatics framework consists of image-omics extraction, feature combination, and classification. First, a robust automatic nuclei detection and segmentation is presented to identify tumor regions, delineate nuclei boundaries and calculate a set of image-based morphological features; next, the low dimensional image-omics is obtained through principal component analysis and is concatenated with the functional genomic features identified by a linear model. A support vector machine for differentiating stage I breast cancer from other stages are learned. We experimentally demonstrate that compared with a single type of representation (image-omics), the combination of image-omics and functional genomic feature can improve the classification accuracy by 3%.
Collapse
Affiliation(s)
- Hai Su
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL 32611, USA
| | - Yong Shen
- Genetics Institute, University of Florida, Gainesville, FL 32611, USA
| | - Fuyong Xing
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL 32611, USA
| | - Xin Qi
- Rutgers Cancer Institute of New Jersey, New Brunswick, NJ 08901, USA
| | - Kim M. Hirshfield
- Rutgers Cancer Institute of New Jersey, New Brunswick, NJ 08901, USA
| | - Lin Yang
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL 32611, USA
| | - David J. Foran
- Rutgers Cancer Institute of New Jersey, New Brunswick, NJ 08901, USA
| |
Collapse
|