Article
Oncology
Yanjie Zhao, Jianfeng Xu, Boran Chen, Le Cao, Chaoyue Chen
Summary: The study aimed to predict the Ki-67 proliferative index in meningioma patients using machine learning technology. By analyzing clinical/radiological features, and building radiomic models, it provided a quantitative method for clinical decision making.
Article
Clinical Neurology
Omaditya Khanna, Anahita Fathi Kazerooni, Sherjeel Arif, Aria Mahtabfar, Arbaz A. Momin, Carrie E. Andrews, Karim Hafazalla, Michael P. Baldassari, Lohit Velagapudi, Jose A. Garcia, Chiharu Sako, Christopher J. Farrell, James J. Evans, Kevin D. Judy, David W. Andrews, Adam E. Flanders, Wenyin Shi, Christos Davatzikos
Summary: In this study, the authors identified multiparametric MRI radiomic signatures of meningiomas using Ki-67 as a prognostic marker of clinical outcomes. They developed a machine learning algorithm to stratify meningiomas based on Ki-67 indices and found that the Ki-67 proliferation index can serve as a surrogate marker of increased meningioma aggressiveness independent of WHO grade. Machine learning using radiomic feature analysis may be used for the preoperative prediction of meningioma Ki-67, providing enhanced analytical insights to help improve diagnostic classification and guide patient-specific treatment strategies.
NEUROSURGICAL FOCUS
(2023)
Article
Medicine, General & Internal
Talat Zehra, Mahin Shams, Zubair Ahmad, Qurratulain Chundriger, Arsalan Ahmed, Nazish Jaffar
Summary: The aim of this study was to validate the concordance of automated detection of Ki67 in digital images of breast cancer with the manual eyeball/hotspot method. The results showed strong positive concordance between the manual and automated scoring methods. Therefore, automated scoring of Ki67 staining has tremendous potential in eliminating issues of lack of consistency, reproducibility, and accuracy.
JCPSP-JOURNAL OF THE COLLEGE OF PHYSICIANS AND SURGEONS PAKISTAN
(2023)
Article
Oncology
Xavier Catteau, Egor Zindy, Sarah Bouri, Jean-Christophe Noel, Isabelle Salmon, Christine Decaestecker
Summary: This study aimed to develop an easy, automated, and reliable Ki-67 assessment approach for invasive breast carcinoma. The results showed that the DIA technique had good concordance with the indices evaluated by pathologists when the tumor area was previously identified by a pathologist. However, basing Ki-67 assessment on automatic tissue detection did not provide satisfactory results.
TECHNOLOGY IN CANCER RESEARCH & TREATMENT
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Tao Han, Xianwang Liu, Mengyuan Jing, Yuting Zhang, Bin Zhang, Liangna Deng, Junlin Zhou
Summary: ADC histogram analysis is a potential non-invasive tool for differentiating atypical meningioma from transitional meningioma preoperatively, and ADC histogram parameters are negatively correlated with the Ki-67 proliferation index.
Article
Medicine, General & Internal
Talat Zehra, Mahin Shams, Rabia Ali, Asad Jafri, Amna Khurshid, Humaira Erum, Hanna Naqvi, Jamshid Abdul-Ghafar
Summary: This study evaluates the performance of the open-source deep learning platform DeepLIIF in quantifying Ki-67 expression in neuroendocrine tumors and compares it with manual assessments. The results show that DeepLIIF achieves high accuracy and reduces analysis time, making it valuable for clinical practice. This study highlights the potential of open-source deep learning platforms in enhancing diagnostic accuracy and patient care in the field of neuroendocrine oncology.
INTERNATIONAL JOURNAL OF GENERAL MEDICINE
(2023)
Article
Pathology
Aqsa Nasir, Livia Hegerova, Hira Yousaf, Colleen L. Forster, Ryan Shanley, Michael A. Linden, Veronika Bachanova, Sophia Yohe
Summary: This study evaluated the correlation between Ki-67 proliferative index in follicular and interfollicular areas and clinical outcomes in patients with low-grade follicular lymphoma (FL). The study found that Ki-67 in the interfollicular areas was associated with progression-free survival, while Ki-67 in the follicular areas had no correlation with survival. Additionally, PD-L1 and LAG-3 were not associated with clinical outcomes.
AMERICAN JOURNAL OF CLINICAL PATHOLOGY
(2023)
Article
Pathology
Andrea Jones, Trynda N. Kroneman, Anthony J. Blahnik, Rondell P. Graham, Taofic Mounajjed, Michael S. Torbenson, Roger K. Moreira
Summary: This study investigated the utility of digital protocols for Ki-67 immunohistochemistry quantitative analysis in well-differentiated hepatocellular neoplasms, finding that the proliferative rate of typical hepatic adenomas was significantly lower than that of well-differentiated hepatocellular carcinomas. The study suggests that Ki-67 may be a useful adjunct marker in the evaluation of these neoplasms.
Article
Medicine, General & Internal
Talat Zehra, Nazish Jaffar, Mahin Shams, Qurratulain Chundriger, Arsalan Ahmed, Fariha Anum, Najah Alsubaie, Zubair Ahmad
Summary: Breast cancer is the most common cancer in women, and early detection of Ki-67 plays a crucial role in improving patient outcomes. In this study, a novel deep learning model was used to automate the detection of Ki-67 in breast cancer. The results showed strong correlation and high diagnostic accuracy compared to manual methods.
Article
Clinical Neurology
Ricardo Prat-Acin, Maria Juliana Guarin-Corredor, Inma Galeano-Senabre, Angel Ayuso-Sacido, Francisco Vera-Sempere
Summary: Simpson grading and Ki-67/MIB-1 index are predictive factors for intracranial meningioma recurrence. Patients with Ki-67/MIB-1 >3% in WHO grade I or grade II meningiomas may require similar management protocols to prevent recurrence.
JOURNAL OF CLINICAL NEUROSCIENCE
(2021)
Article
Medicine, General & Internal
Luis A. Rodriguez-Hernandez, Jorge Navarro-Bonnet, Alma Ortiz-Plata, Juan P. Gonzalez-Mosqueda, Pablo Martinez-Arellano, Metztli Calva-Gonzalez, Marcos V. Sangrador-Deitos, Michel G. Mondragon-Soto, Diego Lopez Mena, Lesly Portocarrero-Ortiz
Summary: The aim of this study was to assess dopamine receptor (DR) and Ki-67 expression in the MNGs of patients treated with surgery in the Instituto Nacional de Neurologia y Neurocirugia, Mexico. The results showed varied expressions of the studied receptors, but more studies are needed to confirm the findings. In contrast to previous studies, no relationship was found between D2 receptor and tumor characteristics.
CUREUS JOURNAL OF MEDICAL SCIENCE
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Mustafa Bozdag, Ali Er, Sumeyye Ekmekci
Summary: This study evaluated the utility of ADC in determining the histological grade of meningioma, showing that ADC values were significantly correlated with Ki-67 and mitotic index. Additionally, ADC values were lower in meningiomas with hypercellularity and necrosis features, but did not show a significant correlation with PR score.
Article
Obstetrics & Gynecology
Connie D. Cao, Jesus Rico-Castillo, Dan De Cotiis, Scott D. Richard, Norman G. Rosenblum, Joanna S. Y. Chan
Summary: The digital quantification of Ki-67 may potentially aid in the diagnosis of LMS, with high Ki-67 values associated with poorer clinical outcomes. Ki-67 is a better predictor of LMS compared to PHH3.
INTERNATIONAL JOURNAL OF GYNECOLOGICAL PATHOLOGY
(2021)
Article
Pathology
Carlos Lopez, Albert Gibert-Ramos, Ramon Bosch, Anna Korzynska, Marcial Garcia-Rojo, Gloria Bueno, Joan Francesc Garcia-Fontgivell, Salome Martinez Gonzalez, Laia Fontoura, Andrea Gras Navarro, Esther Sauras Colon, Julia Casanova Ribes, Lukasz Roszkowiak, Albert Roso, Marta Berenguer, Montserrat Llobera, Jordi Baucells, Marylene Lejeune
Summary: This study aimed to determine the differences in immune populations between primary tumors and ALNs(-) associated with luminal A or TNBC subtypes. The findings showed that TNBC samples had higher levels of immune markers in both primary tumors and ALNs(-) compared to luminal A, which partially explains the worse prognosis of TNBC patients.
AMERICAN JOURNAL OF PATHOLOGY
(2021)
Article
Multidisciplinary Sciences
Lukasz Roszkowiak, Anna Korzynska, Krzysztof Siemion, Jakub Zak, Dorota Pijanowska, Ramon Bosch, Marylene Lejeune, Carlos Lopez
Summary: This study introduces CHISEL, an end-to-end system for quantitative evaluation of benign and malignant digitized tissue samples with immunohistochemical nuclear staining. It incorporates seamless segmentation based on regions of interest cropping and nuclei cluster splitting, utilizing machine learning and recursive local processing to eliminate distorted outlines. Validation with labeled datasets showed comparable or better results than state-of-the-art methods, with a focus on achieving best results for DAB&H-stained breast cancer tissue samples.
SCIENTIFIC REPORTS
(2021)
Article
Oncology
Carlos Lopez, Ramon Bosch, Anna Korzynska, Marcial Garcia-Rojo, Gloria Bueno, Joan Francesc Garcia-Fontgivell, Salome Martinez Gonzalez, Andrea Gras Navarro, Esther Sauras Colon, Julia Casanova Ribes, Lukasz Roszkowiak, Daniel Mata, Meritxell Arenas, Junior Gomez, Albert Roso, Marta Berenguer, Silvia Reverte-Villarroya, Montserrat Llobera, Jordi Baucells, Marylene Lejeune
Summary: The study identifies the association between clinical-pathological and immune variables in primary tumors and non-metastatic axillary lymph nodes (ALNs(-)) with cancer-specific survival (CSS) and time to progression (TTP) in luminal A and triple-negative breast cancer (TNBC) patients. The study highlights the importance of macrophage and dendritic cell markers as prognostic factors for breast cancer relapse.
Review
Medicine, Research & Experimental
Krzysztof Siemion, Joanna Reszec-Gielazyn, Joanna Kisluk, Lukasz Roszkowiak, Jakub Zak, Anna Korzynska
Summary: This article reviews recent information on inflammatory myofibroblastic tumors (IMTs) to assist in their diagnosis and treatment. The terminology for inflammatory spindle cell lesions appears to be confusing, with the terms IMTs and inflammatory pseudotumors used interchangeably. However, a detailed analysis suggests that the term IMTs should be used for neoplastic lesions. IMTs are rare neoplasms that have not been extensively studied, and our knowledge about this disease is still unsatisfactory. Recently developed techniques such as next-generation sequencing and computer-aided histopathological diagnosis may help in understanding the etiopathology of IMTs and selecting appropriate therapy for patients.
ADVANCES IN MEDICAL SCIENCES
(2022)
Article
Engineering, Biomedical
Jakub Zak, Michal K. Grzeszczyk, Antonina Pater, Lukasz Roszkowiak, Krzysztof Siemion, Anna Korzynska
Summary: Data augmentation is one of the solutions to address the issue of insufficient training datasets in image processing. By generating artificial images that closely resemble the original ones, the size of the training dataset is artificially extended, leading to improved classification accuracy in cell classification tasks.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2022)
Article
Biochemistry & Molecular Biology
Marylene Lejeune, Laia Reverte, Noelia Gallardo, Esther Sauras, Ramon Bosch, Daniel Mata, Albert Roso, Anna Petit, Vicente Peg, Francisco Riu, Joan Garcia-Fontgivell, Fernanda Relea, Begona Vieites, Luis de la Cruz-merino, Meritxell Arenas, Valeri Rodriguez, Juana Galera, Anna Korzynska, Benoit Plancoulaine, Tomas Alvaro, Carlos Lopez
Summary: This study characterized the residual tumor microenvironment in 96 TNBC patients and evaluated its prognostic implications for partial responders vs. non-responders. Partial responders showed higher levels of CD83+ mature dendritic cells, FOXP3+ regulatory T cells, and IL-15 expression but lower CD138+ cell concentration, leading to improved overall survival and recurrence-free survival. However, MMP-9 expression in the residual tumor microenvironment was identified as an independent factor associated with the impaired response to neoadjuvant chemotherapy.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Mateusz Lysik, Zaneta Swiderska-Chadaj, Tomasz Markiewicz, Tomasz Les, Szczepan Cierniak, Malgorzata Lorent
Summary: This paper presents the evaluation of the accuracy of an automatic HE to PAS stain conversion, using a unique HE-PAS database for renal specimens. The evaluation includes numerical metrics and visual assessment, showing high accuracy in both aspects. The results provide insights into the potential of automatic stain transformations as a replacement for manual staining.
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2022)
Proceedings Paper
Computer Science, Cybernetics
Jakub Zak, Krzysztof Siemion, Lukasz Roszkowiak, Anna Korzynska
Summary: Sjogren's Syndrome is a systemic disease that can be diagnosed through examination of minor salivary gland biopsies. This paper presents a new method using neural networks and Fourier transform for fast foreground segmentation in Whole Slide Images.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING - CURRENT TRENDS AND CHALLENGES
(2022)
Review
Engineering, Biomedical
Anna Korzynska, Lukasz Roszkowiak, Jakub Zak, Krzysztof Siemion
Summary: With the advancements in deep learning methods, it is possible that these techniques can effectively assist pathologists in digital pathology. However, the high cost of data annotation remains a major obstacle in the development of computer-aided diagnostic systems for pathology. Various systems for image annotation are reviewed in this paper as a way to simplify the process of obtaining large datasets.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2021)