Rajiv Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Rajiv Kumar has a total of 101 co-authors. Here are the top co-authors by number of shared publications:
Ayushi Sahay
Department of Pathology, Tata Memorial Hospital, Homi Bhabha National Institute, Mumbai, India
4 shared publications- Kumar Prabhash
Department of Medical Oncology, Tata Memorial Hospital, Mumbai 400012, India
4 shared publications - Vanita Noronha
Department of Medical Oncology, Tata Memorial Centre, Homi Bhabha National Institute (HBNI), Mumbai, India
4 shared publications Amit Janu
Department of Radiodiagnosis, Tata Memorial Hospital, Homi Bhabha National Institute, Mumbai, Maharashtra, India
3 shared publications- Anuradha Choughule
Department of Medical Oncology, Tata Memorial Hospital, Mumbai, India
3 shared publications C.S. Pramesh
Department of Thoracic Surgery, Tata Memorial Hospital, Homi Bhabha National Institute, Mumbai, Maharashtra, India
3 shared publications
Latest Publications
- Open Access
- 8 July 2024
- Published by Elsevier in The Lancet Regional Health - Southeast Asia
- Vol. 27, 100430
Uniqueness of lung cancer in Southeast Asia
- 8 July 2024
- Published by Elsevier in The Lancet Regional Health - Southeast Asia
- Vol. 27, 100430
Open AccessUniqueness of lung cancer in Southeast Asia
- Open Access
Deep-Learning-Based Predictive Imaging Biomarker Model for EGFR Mutation Status in Non-Small Cell Lung Cancer from CT Imaging
Purpose: The authors aimed to develop and validate deep-learning-based radiogenomic (DLR) models and radiomic signatures to predict the EGFR mutation in patients with NSCLC, and to assess the semantic and clinical features that can contribute to detecting EGFR mutations. Methods: Using 990 patients from two NSCLC trials, we employed an end-to-end pipeline analyzing CT images without precise segmentation. Two 3D convolutional neural networks segmented lung masses and nodules. Results: The combined radiomics and DLR model achieved an AUC of 0.88 ± 0.03 in predicting EGFR mutation status, outperforming individual models. Semantic features further improved the model’s accuracy, with an AUC of 0.88 ± 0.05. CT semantic features that were found to be significantly associated with EGFR mutations were pure solid tumours with no associated ground glass component (p < 0.03), the absence of peripheral emphysema (p < 0.03), the presence of pleural retraction (p = 0.004), the presence of fissure attachment (p = 0.001), the presence of metastatic nodules in both the tumour-containing lobe (p = 0.001) and the non-tumour-containing lobe (p = 0.001), the presence of ipsilateral pleural effusion (p = 0.04), and average enhancement of the tumour mass above 54 HU (p < 0.001). Conclusions: This AI-based radiomics and DLR model demonstrated high accuracy in predicting EGFR mutation, serving as a non-invasive and user-friendly imaging biomarker for EGFR mutation status prediction.
Open AccessDeep-Learning-Based Predictive Imaging Biomarker Model for EGFR Mutation Status in Non-Small Cell Lung Cancer from CT Imaging
Purpose: The authors aimed to develop and validate deep-learning-based radiogenomic (DLR) models and radiomic signatures to predict the EGFR mutation in patients with NSCLC, and to assess the semantic and clinical features that can contribute to detecting EGFR mutations. Methods: Using 990 patients from two NSCLC trials, we employed an end-to-end pipeline analyzing CT images without precise segmentation. Two 3D convolutional neural networks segmented lung masses and nodules. Results: The combined radiomics and DLR model achieved an AUC of 0.88 ± 0.03 in predicting EGFR mutation status, outperforming individual models. Semantic features further improved the model’s accuracy, with an AUC of 0.88 ± 0.05. CT semantic features that were found to be significantly associated with EGFR mutations were pure solid tumours with no associated ground glass component (p < 0.03), the absence of peripheral emphysema (p < 0.03), the presence of pleural retraction (p = 0.004), the presence of fissure attachment (p = 0.001), the presence of metastatic nodules in both the tumour-containing lobe (p = 0.001) and the non-tumour-containing lobe (p = 0.001), the presence of ipsilateral pleural effusion (p = 0.04), and average enhancement of the tumour mass above 54 HU (p < 0.001). Conclusions: This AI-based radiomics and DLR model demonstrated high accuracy in predicting EGFR mutation, serving as a non-invasive and user-friendly imaging biomarker for EGFR mutation status prediction.
- 24 February 2024
- Published by Elsevier in Annals of Diagnostic Pathology
- Vol. 70, 152283
study: A retrospective analysis of 111 livary gland tumors of ung and racheobronchial ree
- 24 February 2024
- Published by Elsevier in Annals of Diagnostic Pathology
- Vol. 70, 152283
study: A retrospective analysis of 111 livary gland tumors of ung and racheobronchial ree
- Open Access
- 15 April 2023
- Published by Elsevier in Journal of Pathology Informatics
- Vol. 14, 100312
Validation of Remote Digital Pathology based diagnostic reporting of Frozen Sections from home
- 15 April 2023
- Published by Elsevier in Journal of Pathology Informatics
- Vol. 14, 100312
Open AccessValidation of Remote Digital Pathology based diagnostic reporting of Frozen Sections from home
- Open Access
- 23 May 2022
- Published by MDPI AG in Diagnostics
- Vol. 12  (5) , 1291
Comprehensive Development and Implementation of Good Laboratory Practice for NGS Based Targeted Panel on Solid Tumor FFPE Tissues in Diagnostics
The speed, accuracy, and increasing affordability of next-generation sequencing (NGS) have revolutionized the advent of precision medicine. To date, standardized validation criteria for diagnostic accreditation do not exist due to variability across the multitude of NGS platforms and within NGS processes. In molecular diagnostics, it is necessary to ensure that the primary material of the FFPE sample has good quality and optimum quantity for the analysis, otherwise the laborious and expensive NGS test may result in unreliable information. Therefore, stringent quality control of DNA and RNA before, during, and after library preparation is an essential parameter. Considering the various challenges with the FFPE samples, we aimed to set a benchmark in QC metrics that can be utilized by molecular diagnostic laboratories for successful library preparation and high-quality NGS data output. In total, 144 DNA and 103 RNA samples of various cancer types with a maximum storage of 2 years were processed for 52 gene focus panels. During the making of DNA and RNA libraries, extensive QC check parameters were imposed at different checkpoints. The decision tree approach can be set as a benchmark for FFPE samples and as a guide to establishing a good clinical laboratory practice for targeted NGS panels.
- 23 May 2022
- Published by MDPI AG in Diagnostics
- Vol. 12  (5) , 1291
Open AccessComprehensive Development and Implementation of Good Laboratory Practice for NGS Based Targeted Panel on Solid Tumor FFPE Tissues in Diagnostics
The speed, accuracy, and increasing affordability of next-generation sequencing (NGS) have revolutionized the advent of precision medicine. To date, standardized validation criteria for diagnostic accreditation do not exist due to variability across the multitude of NGS platforms and within NGS processes. In molecular diagnostics, it is necessary to ensure that the primary material of the FFPE sample has good quality and optimum quantity for the analysis, otherwise the laborious and expensive NGS test may result in unreliable information. Therefore, stringent quality control of DNA and RNA before, during, and after library preparation is an essential parameter. Considering the various challenges with the FFPE samples, we aimed to set a benchmark in QC metrics that can be utilized by molecular diagnostic laboratories for successful library preparation and high-quality NGS data output. In total, 144 DNA and 103 RNA samples of various cancer types with a maximum storage of 2 years were processed for 52 gene focus panels. During the making of DNA and RNA libraries, extensive QC check parameters were imposed at different checkpoints. The decision tree approach can be set as a benchmark for FFPE samples and as a guide to establishing a good clinical laboratory practice for targeted NGS panels.
- Open Access
- 1 January 2022
- Published by Medknow in Indian Journal of Pathology and Microbiology
- Vol. 65  (2) , 422-425
Pulmonary inflammatory myofibroblastic tumor coexisting with lymphangitis carcinomatosis: Mimicking metastatic papillary thyroid carcinoma with nodular fasciitis-like stroma
Carcinoma (PTC) is very uncommon. We present a case of a 26-year-old male, who presented with a solitary left lung nodule on radiological scans. There was also a past history of thyroid surgery done two years back for PTC. Histology revealed a soft tissue tumor reminiscent of IMT. The periphery of the IMT nodule showed metastatic PTC in the form of extensive PLC. In view of this unusual histology, a diagnosis of PTC with nodular fasciitis-like stroma (PTC-NFS) was initially considered. However, molecular studies for anaplastic lymphoma kinase (ALK) gene rearrangement confirmed the diagnosis of IMT. This case highlights the unusual occurrence of tumor-to-tumor metastasis causing diagnostic challenges and also the importance of molecular testing....
- 1 January 2022
- Published by Medknow in Indian Journal of Pathology and Microbiology
- Vol. 65  (2) , 422-425
Open AccessPulmonary inflammatory myofibroblastic tumor coexisting with lymphangitis carcinomatosis: Mimicking metastatic papillary thyroid carcinoma with nodular fasciitis-like stroma
Carcinoma (PTC) is very uncommon. We present a case of a 26-year-old male, who presented with a solitary left lung nodule on radiological scans. There was also a past history of thyroid surgery done two years back for PTC. Histology revealed a soft tissue tumor reminiscent of IMT. The periphery of the IMT nodule showed metastatic PTC in the form of extensive PLC. In view of this unusual histology, a diagnosis of PTC with nodular fasciitis-like stroma (PTC-NFS) was initially considered. However, molecular studies for anaplastic lymphoma kinase (ALK) gene rearrangement confirmed the diagnosis of IMT. This case highlights the unusual occurrence of tumor-to-tumor metastasis causing diagnostic challenges and also the importance of molecular testing....
- 1 August 2021
- Published by Elsevier in Annals of Diagnostic Pathology
- Vol. 53, 151763
Primary mediastinal germ cell tumours with high prevalence of somatic malignancy: An experience from a single tertiary care oncology centre
- 1 August 2021
- Published by Elsevier in Annals of Diagnostic Pathology
- Vol. 53, 151763
Primary mediastinal germ cell tumours with high prevalence of somatic malignancy: An experience from a single tertiary care oncology centre
- Open Access
- 1 January 2021
- Published by Elsevier in Journal of Pathology Informatics
- Vol. 12  (1) , 33
Validation of a Portable Whole-Slide Imaging System for Frozen Section Diagnosis
- 1 January 2021
- Published by Elsevier in Journal of Pathology Informatics
- Vol. 12  (1) , 33
Open AccessValidation of a Portable Whole-Slide Imaging System for Frozen Section Diagnosis
- Open Access
- 1 January 2021
- Published by Elsevier in Journal of Pathology Informatics
- Vol. 12  (1) , 25
Comparative Assessment of Digital Pathology Systems for Primary Diagnosis
- 1 January 2021
- Published by Elsevier in Journal of Pathology Informatics
- Vol. 12  (1) , 25
Open AccessComparative Assessment of Digital Pathology Systems for Primary Diagnosis
- Open Access
- 1 January 2021
- Published by Federation of Turkish Pathology Societies in Turkish Journal of Pathology
- Vol. 37  (1) , 71-77
ALK1 Gene Rearranged Pulmonary Sarcomatoid Carcinoma Masquerading as Tuberculosis in a Young Male
Pulmonary sarcomatoid carcinoma is rare, with limited treatment options and poor prognosis. In contrast to other non small cell lung carcinomas, not much is known about its molecular biology. In an endemic country like India, lung cancer is often masked by tuberculosis and presents in advanced stages. We report here an unusual case of pulmonary sarcomatoid carcinoma, in a young non-smoker male, who had co-existent tuberculosis masking and delaying the diagnosis of malignancy. On molecular study, the tumor showed ALK gene rearrangement, both by immunohistochemistry and fluorescence in-situ hybridization, which has been reported only twice previously. Presence of ALK gene rearrangements in sarcomatoid carcinoma has significant therapeutic implications and potential for altering the prognosis of this fatal disease. Hence we recommend performing ALK gene rearrangement analysis in all cases of sarcomatoid lung carcinomas. The report discusses the diagnostic approach and provides insight into the molecular pathogenesis of this exceedingly rare malignancy.
- 1 January 2021
- Published by Federation of Turkish Pathology Societies in Turkish Journal of Pathology
- Vol. 37  (1) , 71-77
Open AccessALK1 Gene Rearranged Pulmonary Sarcomatoid Carcinoma Masquerading as Tuberculosis in a Young Male
Pulmonary sarcomatoid carcinoma is rare, with limited treatment options and poor prognosis. In contrast to other non small cell lung carcinomas, not much is known about its molecular biology. In an endemic country like India, lung cancer is often masked by tuberculosis and presents in advanced stages. We report here an unusual case of pulmonary sarcomatoid carcinoma, in a young non-smoker male, who had co-existent tuberculosis masking and delaying the diagnosis of malignancy. On molecular study, the tumor showed ALK gene rearrangement, both by immunohistochemistry and fluorescence in-situ hybridization, which has been reported only twice previously. Presence of ALK gene rearrangements in sarcomatoid carcinoma has significant therapeutic implications and potential for altering the prognosis of this fatal disease. Hence we recommend performing ALK gene rearrangement analysis in all cases of sarcomatoid lung carcinomas. The report discusses the diagnostic approach and provides insight into the molecular pathogenesis of this exceedingly rare malignancy.