Article
Computer Science, Software Engineering
Xiaorong Li, Jiande Pi, Meng Lou, Yunliang Qi, Sizheng Li, Jie Meng, Yide Ma
Summary: The purpose of this research is to propose an automatic histopathological images nuclei segmentation method to accurately predict the boundaries of overlapping and multi-size nuclei. The proposed method, which includes iterative attention feature fusion (iAFF) and residual modules, outperforms other deep learning models in the task of nuclei segmentation.
Article
Computer Science, Information Systems
Loay Hassan, Mohamed Abdel-Nasser, Adel Saleh, Osama A. Omer, Domenec Puig
Summary: An efficient stain-aware nuclei segmentation method based on deep learning is proposed, utilizing stain clustering and an aggregation function for multi-center WSIs. Experimental results show that the method outperforms existing approaches in performance and parameter efficiency.
Article
Engineering, Electrical & Electronic
Hui Huang, Xi'an Feng, Jionghui Jiang, Peiyu Chen, Suying Zhou
Summary: The article introduced the application of the Mask RCNN algorithm in automatic nuclei detection in high-resolution histopathological images of breast cancer, with experimental results showing its superior performance.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Zhi Wang, Xiaoya Zhu, Ao Li, Yuan Wang, Gang Meng, Minghui Wang
Summary: This paper proposes an adversarial feature alignment method for domain adaptive nuclei detection. The method transfers knowledge from the source domain to the target domain through both global alignment and local attentional alignment components, and introduces a location-aware self-attention module to refine local features. Experimental results demonstrate the favorable performance of the proposed method in domain adaptive nuclei detection.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2022)
Article
Biology
Abdul Rahim Shihabuddin, K. Sabeena Beevi
Summary: In breast cancer diagnosis, the number of mitotic cells is important for determining the aggressiveness of cancer. Computer-aided mitosis detection technologies can assist in screening and labeling mitotic cells, making the process easier. This study explored the usefulness of a multi CNN framework with pre-trained VGG16, ResNet50, and DenseNet201 models for mitosis detection, achieving a precision of 93.81% and F1-score of 92.41%.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Information Systems
Hasnain Ali Shah, Jae-Mo Kang
Summary: In digital pathology, accurate cell nuclei segmentation is crucial for medical image analysis. This paper proposes a novel DL architecture, CBAM-Residual U-Net, to improve accuracy and robustness. It utilizes special modules to learn shallow and deep features and uses attention mechanism to focus on important features of cell nuclei for accurate segmentation.
Article
Computer Science, Information Systems
Haijun Lei, Shaomin Liu, Ahmed Elazab, Xuehao Gong, Baiying Lei
Summary: The text discusses a method using deep convolutional neural networks to automatically detect mitosis, identifying mitotic candidates for screening and achieving the best detection results on the dataset of the International Pattern Recognition Conference (ICPR) 2012 Mitosis Detection Competition.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2021)
Article
Multidisciplinary Sciences
Anabia Sohail, Asifullah Khan, Noorul Wahab, Aneela Zameer, Saranjam Khan
Summary: The research proposes a deep learning based multi-phase mitosis detection framework for identifying mitotic nuclei in breast cancer tissue, achieving good discrimination ability and generalization on challenging datasets.
SCIENTIFIC REPORTS
(2021)
Article
Geochemistry & Geophysics
Jinsong Zhang, Mengdao Xing, Guang-Cai Sun, Xin Shi
Summary: This article presents a method for vehicle trace detection using synthetic aperture radar (SAR) by enhancing the Unet model and employing an adaptive data augmentation strategy.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Mathematical & Computational Biology
Rik Das, Kanwalpreet Kaur, Ekta Walia
Summary: This study investigates transfer learning in computer-aided diagnosis of breast cancer and finds that using feature engineering and representation learning achieves high accuracy in classifying breast cancer images. Additionally, fusion-based techniques show superior feature learning capacity in breast cancer image classification.
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Zainab Hussein Arif, Moamin A. Mahmoud, Karrar Hameed Abdulkareem, Seifedine Kadry, Mazin Abed Mohammed, Mohammed Nasser Al-Mhiqani, Alaa S. Al-Waisy, Jan Nedoma
Summary: Fog has different effects and features in different environments. It is challenging to detect fog in images, and knowing the type of fog has an enlightening effect on image defogging. Machine learning techniques have contributed significantly to detecting foggy scenes. However, most existing detection models are based on traditional machine learning, and only a few studies have used deep learning models. This study proposes an adaptive deep learning model for detecting images with multiple types of fog and provides a dataset for multi-fog scenes.
INTERNATIONAL JOURNAL OF INTERACTIVE MULTIMEDIA AND ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Thomas Wollmann, Karl Rohr
Summary: The article presents a novel deep neural network for object detection in microscopy images, which includes a feature extractor, a centroid proposal network, and a layer for ensembling detection hypotheses over all image scales and anchors. Utilizing anchor regularization and a new loss function to address class imbalance, along with an improved non-maximum suppression algorithm, experiments demonstrate the method's outstanding performance on challenging data.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Engineering, Biomedical
Hao Liang, Zhiming Cheng, Haiqin Zhong, Aiping Qu, Lingna Chen
Summary: This paper proposes a region-based convolutional network for nuclei detection and segmentation, which can better locate adhered and clustered nuclei, and demonstrates better performance than existing methods in experiments.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Environmental Sciences
Fengcheng Ji, Dongping Ming, Beichen Zeng, Jiawei Yu, Yuanzhao Qing, Tongyao Du, Xinyi Zhang
Summary: Proposed a target detection model based on Faster R-CNN, combining multi-angle feature extraction and majority voting strategy, effectively addressing the challenges of aircraft detection. Achieved higher average precision on public and private datasets by 6.81% and 8.98% respectively.
Article
Mathematics
Mohammed Al-Jabbar, Mohammed Alshahrani, Ebrahim Mohammed Senan, Ibrahim Abdulrab Ahmed
Summary: Breast cancer is a global health concern for adult females, and early diagnosis is crucial for saving lives. This study proposes two approaches, one combining CNN and SVM, and the other combining CNN features with handcrafted features and using ANN for classification. The latter method has demonstrated superior accuracy in diagnosing breast cancer.
Article
Oncology
Can F. Koyuncu, Reetoja Nag, Cheng Lu, German Corredor, Vidya S. Viswanathan, Vlad C. Sandulache, Pingfu Fu, Kailin Yang, Quintin Pan, Zelin Zhang, Jun Xu, Deborah J. Chute, Wade L. Thorstad, Farhoud Faraji, Justin A. Bishop, Mitra Mehrad, Patricia D. Castro, Andrew G. Sikora, Lester D. R. Thompson, Rebecca D. Chernock, Krystle A. Lang Kuhs, Jay K. Wasman, Jingqin R. Luo, David J. Adelstein, Shlomo A. Koyfman, James S. Lewis, Anant Madabhushi
Summary: There are histological differences in terms of multinucleated tumor cells between Black and White patients with HPV-associated OPSCC, suggesting the importance of considering population-specific prognostic biomarkers for personalized risk stratification in these patients.
Article
Gastroenterology & Hepatology
Prathyush Chirra, Anamay Sharma, Kaustav Bera, H. Matthew Cohn, Jacob A. Kurowski, Katelin Amann, Marco-Jose Rivero, Anant Madabhushi, Cheng Lu, Rajmohan Paspulati, Sharon L. Stein, Jeffrey A. Katz, Satish E. Viswanath, Maneesh Dave
Summary: Radiomic features extracted from magnetic resonance enterography are associated with the need for surgery in Crohn's disease patients at risk of complications, and when combined with clinical variables and radiological assessment, they can accurately predict the time to surgery.
INFLAMMATORY BOWEL DISEASES
(2023)
Article
Oncology
Shayan Monabbati, Patrick Leo, Kaustav Bera, Claire W. Michael, Behtash G. Nezami, Aparna Harbhajanka, Anant Madabhushi
Summary: This study used computational image analysis to predict the presence of pancreatic and biliary tract adenocarcinoma on digitized brush cytology specimens. By extracting nuclear morphological and texture features and training machine learning classifiers, the researchers successfully improved the sensitivity and specificity of diagnosis.
Article
Computer Science, Artificial Intelligence
Yufei Zhou, Can Koyuncu, Cheng Lu, Rainer Grobholz, Ian Katz, Anant Madabhushi, Andrew Janowczyk
Summary: Deep learning performs well in computational pathology tasks but struggles with domain shift on whole slide images generated at external test sites. To address this, researchers propose using off-target organs from the test site for calibration, effectively mitigating the domain shift and improving the robustness of the model for skin cancer classification.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Oncology
Robert Serafin, Can Koyuncu, Weisi Xie, Hongyi Huang, Adam K. Glaser, Nicholas P. Reder, Andrew Janowczyk, Lawrence D. True, Anant Madabhushi, Jonathan T. C. Liu
Summary: Previous studies have shown that computational analysis of 2D histology images can improve prognostication of prostate cancer outcomes. This study expands on previous work by exploring the prognostic value of 3D shape-based nuclear features in prostate cancer. The results suggest that these features are associated with cancer aggressiveness and could be valuable for decision-support tools.
JOURNAL OF PATHOLOGY
(2023)
Article
Computer Science, Interdisciplinary Applications
Zhengyun Feng, Huan Lin, Zaiyi Liu, Lixu Yan, Yumeng Wang, Bingbing Li, Entao Liu, Chu Han, Zhenwei Shi, Cheng Lu, Zhenbing Liu, Cheng Pang, Zhenhui Li, Yanfen Cui, Xipeng Pan, Xin Chen
Summary: This study proposed an artificial intelligence-based Tumour-Lymphocyte Spatial Interaction score (TLSI-score) and found that a higher TLSI-score is associated with longer disease-free survival in patients with lung adenocarcinoma. The TLSI-score can improve the prediction model for disease-free survival and has important implications for characterizing the tumor microenvironment and guiding clinical decision-making.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Review
Oncology
Jeppe Thagaard, Glenn Broeckx, David B. Page, Chowdhury Arif Jahangir, Sara Verbandt, Zuzana Kos, Rajarsi Gupta, Reena Khiroya, Khalid Abduljabbar, Gabriela Acosta Haab, Balazs Acs, Guray Akturk, Jonas S. Almeida, Isabel Alvarado-Cabrero, Mohamed Amgad, Farid Azmoudeh-Ardalan, Sunil Badve, Nurkhairul Bariyah Baharun, Eva Balslev, Enrique R. Bellolio, Vydehi Bheemaraju, Kim R. M. Blenman, Luciana Botinelly Mendonca Fujimoto, Najat Bouchmaa, Octavio Burgues, Alexandros Chardas, Maggie U. Cheang, Francesco Ciompi, Lee A. D. Cooper, An Coosemans, German Corredor, Anders B. Dahl, Flavio Luis Dantas Portela, Frederik Deman, Sandra Demaria, Johan Dore Hansen, Sarah N. Dudgeon, Thomas Ebstrup, Mahmoud Elghazawy, Claudio Fernandez-Martin, Stephen B. Fox, William M. Gallagher, Jennifer M. Giltnane, Sacha Gnjatic, Paula Gonzalez-Ericsson, Anita Grigoriadis, Niels Halama, Matthew G. Hanna, Aparna Harbhajanka, Steven N. Hart, Johan Hartman, Soren Hauberg, Stephen Hewitt, Akira Hida, Hugo M. Horlings, Zaheed Husain, Evangelos Hytopoulos, Sheeba Irshad, Emiel A. M. Janssen, Mohamed Kahila, Tatsuki R. Kataoka, Kosuke Kawaguchi, Durga Kharidehal, Andrey Khramtsov, Umay Kiraz, Pawan Kirtani, Liudmila L. Kodach, Konstanty Korski, Aniko Kovacs, Anne-Vibeke Laenkholm, Corinna Lang-Schwarz, Denis Larsimont, Jochen K. Lennerz, Marvin Lerousseau, Xiaoxian Li, Amy Ly, Anant Madabhushi, Sai K. Maley, Vidya Manur Narasimhamurthy, Douglas K. Marks, Elizabeth S. McDonald, Ravi Mehrotra, Stefan Michiels, Fayyaz ul Amir Afsar Minhas, Shachi Mittal, David A. Moore, Shamim Mushtaq, Hussain Nighat, Thomas Papathomas, Frederique Penault-Llorca, Rashindrie D. Perera, Christopher J. Pinard, Juan Carlos Pinto-Cardenas, Giancarlo Pruneri, Lajos Pusztai, Arman Rahman, Nasir Mahmood Rajpoot, Bernardo Leon Rapoport, Tilman T. Rau, Jorge S. Reis-Filho, Joana M. Ribeiro, David Rimm, Anne Roslind, Anne Vincent-Salomon, Manuel Salto-Tellez, Joel Saltz, Shahin Sayed, Ely Scott, Kalliopi P. Siziopikou, Christos Sotiriou, Albrecht Stenzinger, Maher A. Sughayer, Daniel Sur, Susan Fineberg, Fraser Symmans, Sunao Tanaka, Timothy Taxter, Sabine Tejpar, Jonas Teuwen, E. Aubrey Thompson, Trine Tramm, William T. Tran, Jeroen van Der Laak, Paul J. van Diest, Gregory E. Verghese, Giuseppe Viale, Michael Vieth, Noorul Wahab, Thomas Walter, Yannick Waumans, Hannah Y. Wen, Wentao Yang, Yinyin Yuan, Reena Md Zin, Sylvia Adams, John Bartlett, Sibylle Loibl, Carsten Denkert, Peter Savas, Sherene Loi, Roberto Salgado, Elisabeth Specht Stovgaard
Summary: The clinical significance of tumor-immune interaction in breast cancer has been established. Tumor-infiltrating lymphocytes (TILs) have emerged as predictive and prognostic biomarkers for patients with triple-negative and HER2-positive breast cancer. The use of machine learning (ML) to automatically evaluate TILs has shown promising results. However, there are challenges in implementing this in trial and routine clinical management, including technical slide issues, ML and image analysis aspects, data challenges, and validation issues.
JOURNAL OF PATHOLOGY
(2023)
Review
Oncology
David B. Page, Glenn Broeckx, Chowdhury Arif Jahangir, Chowdhury Jahangir, Sara Verbandt, Rajarsi R. Gupta, Jeppe Thagaard, Reena Khiroya, Zuzana Kos, Khalid Abduljabbar, Gabriela Acosta Haab, Balazs Acs, Jonas S. Almeida, Isabel Alvarado-Cabrero, Farid Azmoudeh-Ardalan, Sunil Badve, Nurkhairul Bariyah Baharun, Enrique R. Bellolio, Vydehi Bheemaraju, Kim R. M. Blenman, Luciana Botinelly Mendonca Fujimoto, Octavio Burgues, Maggie Chon U. Cheang, Francesco Ciompi, Lee A. D. Cooper, An Coosemans, German Corredor, Flavio Luis Dantas Portela, Frederik Deman, Sandra Demaria, Sarah N. Dudgeon, Mahmoud Elghazawy, Scott Ely, Claudio Fernandez-Martin, Susan Fineberg, Stephen B. Fox, William M. Gallagher, Jennifer M. Giltnane, Sacha Gnjatic, Paula Gonzalez-Ericsson, Anita Grigoriadis, Niels Halama, Matthew G. Hanna, Aparna Harbhajanka, Alexandros Hardas, Steven N. Hart, Johan Hartman, Stephen Hewitt, Akira Hida, Hugo M. Horlings, Zaheed Husain, Evangelos Hytopoulos, Sheeba Irshad, Emiel A. M. Janssen, Mohamed Kahila, Tatsuki R. Kataoka, Kosuke Kawaguchi, Durga Kharidehal, Andrey Khramtsov, Umay Kiraz, Pawan Kirtani, Liudmila L. Kodach, Konstanty Korski, Aniko Kovacs, Anne-Vibeke Laenkholm, Corinna Lang-Schwarz, Denis Larsimont, Jochen K. Lennerz, Marvin Lerousseau, Xiaoxian Li, Amy Ly, Anant Madabhushi, Sai K. Maley, Vidya Manur Narasimhamurthy, Douglas K. Marks, Elizabeth S. McDonald, Ravi Mehrotra, Stefan Michiels, Fayyaz ul Amir Afsar Minhas, Shachi Mittal, David A. Moore, Shamim Mushtaq, Hussain Nighat, Thomas Papathomas, Frederique Penault-Llorca, Rashindrie D. Perera, Christopher J. Pinard, Juan Carlos Pinto-Cardenas, Giancarlo Pruneri, Lajos Pusztai, Arman Rahman, Nasir Mahmood Rajpoot, Bernardo Leon Rapoport, Tilman T. Rau, Jorge S. Reis-Filho, Joana M. Ribeiro, David Rimm, Anne-Vincent Salomon, Manuel Salto-Tellez, Joel Saltz, Shahin Sayed, Kalliopi P. Siziopikou, Christos Sotiriou, Albrecht Stenzinger, Maher A. Sughayer, Daniel Sur, Fraser Symmans, Sunao Tanaka, Timothy Taxter, Sabine Tejpar, Jonas Teuwen, E. Aubrey Thompson, Trine Tramm, William T. Tran, Jeroen van Der Laak, Paul J. van Diest, Gregory E. Verghese, Giuseppe Viale, Michael Vieth, Noorul Wahab, Thomas Walter, Yannick Waumans, Hannah Y. Wen, Wentao Yang, Yinyin Yuan, Sylvia Adams, John Mark Seaverns Bartlett, Sibylle Loibl, Carsten Denkert, Peter Savas, Sherene Loi, Roberto Salgado, Elisabeth Specht Stovgaard, Guray Akturk, Najat Bouchmaa
Summary: Modern histologic imaging platforms combined with machine learning methods offer new opportunities for studying the spatial distribution of immune cells in the tumor microenvironment. However, there is currently no standardized method for describing or analyzing spatial immune cell data, and most previous spatial analyses have been simplistic. In this review, two approaches (raster versus vector-based) for reporting and analyzing spatial data are outlined, along with a summary of reported spatial immune cell metrics and their prognostic associations in various cancers. Two well-described clinical biomarkers, the breast cancer stromal tumor infiltrating lymphocytes score and the colon cancer Immunoscore, are also discussed, along with potential research opportunities to improve the clinical utility of these spatial biomarkers.
JOURNAL OF PATHOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Zhenwei Shi, Xiaomei Huang, Ziliang Cheng, Zeyan Xu, Huan Lin, Chen Liu, Xiaobo Chen, Chunling Liu, Changhong Liang, Cheng Lu, Yanfen Cui, Chu Han, Jinrong Qu, Jun Shen, Zaiyi Liu
Summary: A quantitative measure of intratumoral heterogeneity (ITH) on pretreatment MRI scans, combined with conventional radiomics features and clinicopathologic variables, shows good performance in predicting pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC) in patients with breast cancer.
Article
Oncology
Abhishek Midya, Amogh Hiremath, Jacob Huber, Vidya Sankar Viswanathan, Danly Omil-Lima, Amr Mahran, Leonardo K. Bittencourt, Sree Harsha Tirumani, Lee Ponsky, Rakesh Shiradkar, Anant Madabhushi
Summary: The objective of this study was to quantify radiomic changes in prostate cancer progression on serial MRI among patients on active surveillance and evaluate their association with pathologic progression on biopsy. The study found that delta radiomics were more strongly associated with upgrade events compared to other clinical variables, and the combination of delta radiomics with baseline clinical variables showed the strongest association with biopsy upgrade prediction.
FRONTIERS IN ONCOLOGY
(2023)
Article
Oncology
Mohammadhadi Khorrami, Vidya Sakar Viswanathan, Priyanka Reddy, Nathaniel Braman, Siddharth Kunte, Amit Gupta, Jame Abraham, Alberto J. Montero, Anant Madabhushi
Summary: Imaging texture biomarkers before and after CDK4/6i therapy can predict early response and overall survival in MBC patients with liver metastases. Radiomic features can predict a lack of response earlier than standard anatomic/RECIST 1.1 assessment, highlighting the need for further study and clinical validation.
Article
Pathology
Chuheng Chen, Cheng Lu, Vidya Viswanathan, Brandon Maveal, Bhunesh Maheshwari, Joseph Willis, Anant Madabhushi
Summary: This study uses computer-extracted histomorphometric features to identify the primary site of origin for liver metastases. It found that features related to nuclear and peri-nuclear shape were the most important in classifying different metastatic tumors. Additionally, attention maps generated by a deep learning network can provide a composite feature similarity heat map between primary tumors and their associated metastases.
JOURNAL OF PATHOLOGY CLINICAL RESEARCH
(2023)
Article
Computer Science, Interdisciplinary Applications
Zelin Zhang, Sara Arabyarmohammadi, Patrick Leo, Howard Meyerson, Leland Metheny, Jun Xu, Anant Madabhushi
Summary: This article introduces a segmentation model based on conditional generative adversarial network for efficient segmentation of myeloblasts from slides of AML patients. Through validation experiments, it is confirmed that this method has better segmentation performance than other deep learning models, and prognostic models for predicting the risk of recurrence in AML patients have been constructed using the segmentation results.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Urology & Nephrology
Yijiang Chen, Jarcy Zee, Andrew R. Janowczyk, Jeremy Rubin, Paula Toro, Kyle J. Lafata, Laura H. Mariani, Lawrence B. Holzman, Jeffrey B. Hodgin, Anant Madabhushi, Laura Barisoni
Summary: Computational image analysis enables quantification of PTC attributes and the discovery of a previously unrecognized PTC biomarker (aspect ratio) associated with clinical outcome.