Tanaya Kondejkar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tanaya Kondejkar has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Saeed Amal
Department of Bioengineering College of Engineering The Roux Institute Northeastern University 02115 Boston MA USA
4 shared publications - Anne Breggia
MaineHealth Institute for Research, Scarborough, ME 04074, USA, USA
3 shared publications - Bilal Ahmad
Maine Medical Center, Portland, ME 04102, USA, USA
3 shared publications - Robert Christman
Maine Medical Center, Portland, ME 04102, USA, USA
3 shared publications - Salah Mohammed Awad Al-Heejawi
College of Engineering, Northeastern University, Boston, MA 02115, USA, USA
3 shared publications - Stephen T. Ryan
Maine Medical Center, Portland, ME 04102, USA, USA
3 shared publications
Latest Publications
- Open Access
Vision Transformers Based AI Models For Predicting Colorectal Cancer from Digital Pathology WSI: Use Case Of MHIST dataset
This study investigates the efficacy of transformer-based deep learning architectures—specifically, Vision Transformer (ViT), Class Attention in Image Transformers (CaiT), and Data-Efficient Image Transformers (DeiT)—for the binary classification of colorectal polyps using the Minimalist Histopathology Image Analysis Dataset (MHIST). The dataset comprises 3,152 hematoxylin and eosin (H&E)-stained Formalin Fixed Paraffin-Embedded (FFPE) images annotated as either Hyperplastic Polyps (HP) or Sessile Serrated Adenomas (SSA). A rigorous evaluation was conducted using a 5-fold stratified cross-validation methodology, and performance was quantified using metrics including accuracy, precision, recall, F1-score, and AUC-ROC. Experimental results revealed that transformer architectures, particularly CaiT (accuracy of 90.18%, AUC-ROC of 95.52%), outperformed traditional convolutional neural networks (CNNs). The superior performance of CaiT is attributed to its specialized class-attention mechanisms, effectively capturing nuanced morphological differences essential for accurate histopathological classification. These findings underscore the potential of transformer-based models to enhance diagnostic precision, reduce variability in pathological assessment, and facilitate earlier and more reliable colorectal cancer screening.
Open AccessVision Transformers Based AI Models For Predicting Colorectal Cancer from Digital Pathology WSI: Use Case Of MHIST dataset
This study investigates the efficacy of transformer-based deep learning architectures—specifically, Vision Transformer (ViT), Class Attention in Image Transformers (CaiT), and Data-Efficient Image Transformers (DeiT)—for the binary classification of colorectal polyps using the Minimalist Histopathology Image Analysis Dataset (MHIST). The dataset comprises 3,152 hematoxylin and eosin (H&E)-stained Formalin Fixed Paraffin-Embedded (FFPE) images annotated as either Hyperplastic Polyps (HP) or Sessile Serrated Adenomas (SSA). A rigorous evaluation was conducted using a 5-fold stratified cross-validation methodology, and performance was quantified using metrics including accuracy, precision, recall, F1-score, and AUC-ROC. Experimental results revealed that transformer architectures, particularly CaiT (accuracy of 90.18%, AUC-ROC of 95.52%), outperformed traditional convolutional neural networks (CNNs). The superior performance of CaiT is attributed to its specialized class-attention mechanisms, effectively capturing nuanced morphological differences essential for accurate histopathological classification. These findings underscore the potential of transformer-based models to enhance diagnostic precision, reduce variability in pathological assessment, and facilitate earlier and more reliable colorectal cancer screening.
- Open Access
- 28 June 2024
- Published by MDPI AG in Preprints.org
Segmenting Tumor Gleason Pattern using Generative AI and Digital Pathology: Use Case of Prostate Cancer on MICCAI Dataset
Prostate cancer (PCa) ranks as the second most fatal and sixth most prevalent cancer among males globally. This study focuses on leveraging deep learning networks to detect the Gleason grading of prostate cancer from histopathology images stained with Hematoxylin and Eosin (H&E). Six pathologists annotated the images, resulting in six distinct labels for each input image. A common ground truth label was established through majority voting approach. Subsequently, the dataset was trained using architectures: UNeT, UNeT++, DeepLabV3, DeepLabV3+, and GAN based segmentation network. Notably, GAN based network demonstrated superior performance, achieving an F1-score of 0.872 and a Jaccard Index of 0.777, outperforming the other architectures considered in this study.
- 28 June 2024
- Published by MDPI AG in Preprints.org
Open AccessSegmenting Tumor Gleason Pattern using Generative AI and Digital Pathology: Use Case of Prostate Cancer on MICCAI Dataset
Prostate cancer (PCa) ranks as the second most fatal and sixth most prevalent cancer among males globally. This study focuses on leveraging deep learning networks to detect the Gleason grading of prostate cancer from histopathology images stained with Hematoxylin and Eosin (H&E). Six pathologists annotated the images, resulting in six distinct labels for each input image. A common ground truth label was established through majority voting approach. Subsequently, the dataset was trained using architectures: UNeT, UNeT++, DeepLabV3, DeepLabV3+, and GAN based segmentation network. Notably, GAN based network demonstrated superior performance, achieving an F1-score of 0.872 and a Jaccard Index of 0.777, outperforming the other architectures considered in this study.
- Open Access
- 18 June 2024
- Published by MDPI AG in Bioengineering
- Vol. 11 (6) , 624
Multi-Scale Digital Pathology Patch-Level Prostate Cancer Grading Using Deep Learning: Use Case Evaluation of DiagSet Dataset
Prostate cancer remains a prevalent health concern, emphasizing the critical need for early diagnosis and precise treatment strategies to mitigate mortality rates. The accurate prediction of cancer grade is paramount for timely interventions. This paper introduces an approach to prostate cancer grading, framing it as a classification problem. Leveraging ResNet models on multi-scale patch-level digital pathology and the Diagset dataset, the proposed method demonstrates notable success, achieving an accuracy of 0.999 in identifying clinically significant prostate cancer. The study contributes to the evolving landscape of cancer diagnostics, offering a promising avenue for improved grading accuracy and, consequently, more effective treatment planning. By integrating innovative deep learning techniques with comprehensive datasets, our approach represents a step forward in the pursuit of personalized and targeted cancer care.
- 18 June 2024
- Published by MDPI AG in Bioengineering
- Vol. 11 (6) , 624
Open AccessMulti-Scale Digital Pathology Patch-Level Prostate Cancer Grading Using Deep Learning: Use Case Evaluation of DiagSet Dataset
Prostate cancer remains a prevalent health concern, emphasizing the critical need for early diagnosis and precise treatment strategies to mitigate mortality rates. The accurate prediction of cancer grade is paramount for timely interventions. This paper introduces an approach to prostate cancer grading, framing it as a classification problem. Leveraging ResNet models on multi-scale patch-level digital pathology and the Diagset dataset, the proposed method demonstrates notable success, achieving an accuracy of 0.999 in identifying clinically significant prostate cancer. The study contributes to the evolving landscape of cancer diagnostics, offering a promising avenue for improved grading accuracy and, consequently, more effective treatment planning. By integrating innovative deep learning techniques with comprehensive datasets, our approach represents a step forward in the pursuit of personalized and targeted cancer care.
- Open Access
- 8 May 2024
- Published by MDPI AG in Preprints.org
Multi-Scale Digital Pathology Patch Level Prostate Cancer Grading Using Deep Learning: Use Case Evaluation of DiagSet Dataset
Prostate Cancer remains a prevalent health concern, emphasizing the critical need for early diagnosis and precise treatment strategies to mitigate mortality rates. Accurate prediction of cancer grade is paramount for timely interventions. This paper introduces an approach to prostate cancer grading, framing it as a classification problem. Leveraging ResNet models on multi-scale patch-level digital pathology and the Diagset dataset, the proposed method demonstrates notable success, achieving an accuracy of 0.999 in identifying clinically significant prostate cancer. The study contributes to the evolving landscape of cancer diagnostics, offering a promising avenue for improved grading accuracy and, consequently, more effective treatment planning. By integrating innovative deep-learning techniques with comprehensive datasets, our approach presents a step forward in the pursuit of personalized and targeted cancer care.
- 8 May 2024
- Published by MDPI AG in Preprints.org
Open AccessMulti-Scale Digital Pathology Patch Level Prostate Cancer Grading Using Deep Learning: Use Case Evaluation of DiagSet Dataset
Prostate Cancer remains a prevalent health concern, emphasizing the critical need for early diagnosis and precise treatment strategies to mitigate mortality rates. Accurate prediction of cancer grade is paramount for timely interventions. This paper introduces an approach to prostate cancer grading, framing it as a classification problem. Leveraging ResNet models on multi-scale patch-level digital pathology and the Diagset dataset, the proposed method demonstrates notable success, achieving an accuracy of 0.999 in identifying clinically significant prostate cancer. The study contributes to the evolving landscape of cancer diagnostics, offering a promising avenue for improved grading accuracy and, consequently, more effective treatment planning. By integrating innovative deep-learning techniques with comprehensive datasets, our approach presents a step forward in the pursuit of personalized and targeted cancer care.