Alina Basnet
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
Alina Basnet has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
Michel R. Nasr
Department of Hematology and Oncology, SUNY Upstate Medical University, Syracuse, USA
3 shared publications- Tamara Jamaspishvili
Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, USA
3 shared publications Amber Bixby
Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, USA
2 shared publicationsChristopher Curtiss
Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, USA
2 shared publicationsPeter Choyke
Artificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of Health, Bethesda, USA
2 shared publications- Prashanth Ashok Kumar
Hematology-Oncology, George Washington University, Washington, D.C. 20037, USA
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 9 July 2025
- Published by Springer Nature in Nature Medicine
- Vol. 31 (9) , 1-9
Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection
Artificial intelligence models using digital histopathology slides stained with hematoxylin and eosin offer promising, tissue-preserving diagnostic tools for patients with cancer. Despite their advantages, their clinical utility in real-world settings remains unproven. Assessing EGFR mutations in lung adenocarcinoma demands rapid, accurate and cost-effective tests that preserve tissue for genomic sequencing. PCR-based assays provide rapid results but with reduced accuracy compared with next-generation sequencing and require additional tissue. Computational biomarkers leveraging modern foundation models can address these limitations. Here we assembled a large international clinical dataset of digital lung adenocarcinoma slides (N = 8,461) to develop a computational EGFR biomarker. Our model fine-tunes an open-source foundation model, improving task-specific performance with out-of-center generalization and clinical-grade accuracy on primary and metastatic specimens (mean area under the curve: internal 0.847, external 0.870). To evaluate real-world clinical translation, we conducted a prospective silent trial of the biomarker on primary samples, achieving an area under the curve of 0.890. The artificial-intelligence-assisted workflow reduced the number of rapid molecular tests needed by up to 43% while maintaining the current clinical standard performance. Our retrospective and prospective analyses demonstrate the real-world clinical utility of a computational pathology biomarker.
- 9 July 2025
- Published by Springer Nature in Nature Medicine
- Vol. 31 (9) , 1-9
Top Cited PapersOpen AccessReal-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection
Artificial intelligence models using digital histopathology slides stained with hematoxylin and eosin offer promising, tissue-preserving diagnostic tools for patients with cancer. Despite their advantages, their clinical utility in real-world settings remains unproven. Assessing EGFR mutations in lung adenocarcinoma demands rapid, accurate and cost-effective tests that preserve tissue for genomic sequencing. PCR-based assays provide rapid results but with reduced accuracy compared with next-generation sequencing and require additional tissue. Computational biomarkers leveraging modern foundation models can address these limitations. Here we assembled a large international clinical dataset of digital lung adenocarcinoma slides (N = 8,461) to develop a computational EGFR biomarker. Our model fine-tunes an open-source foundation model, improving task-specific performance with out-of-center generalization and clinical-grade accuracy on primary and metastatic specimens (mean area under the curve: internal 0.847, external 0.870). To evaluate real-world clinical translation, we conducted a prospective silent trial of the biomarker on primary samples, achieving an area under the curve of 0.890. The artificial-intelligence-assisted workflow reduced the number of rapid molecular tests needed by up to 43% while maintaining the current clinical standard performance. Our retrospective and prospective analyses demonstrate the real-world clinical utility of a computational pathology biomarker.
- Open Access
- 9 January 2025
- Published by Springer Nature in npj Precision Oncology
- Vol. 9 (1) , 1
Author Correction: Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images
- 9 January 2025
- Published by Springer Nature in npj Precision Oncology
- Vol. 9 (1) , 1
Open AccessAuthor Correction: Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images
- Open Access
- 19 December 2024
- Published by Springer Nature in npj Precision Oncology
- Vol. 8 (1) , 1-15
Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images
Immune checkpoint inhibitors (ICI) have become integral to treatment of non-small cell lung cancer (NSCLC). However, reliable biomarkers predictive of immunotherapy efficacy are limited. Here, we introduce HistoTME, a novel weakly supervised deep learning approach to infer the tumor microenvironment (TME) composition directly from histopathology images of NSCLC patients. We show that HistoTME accurately predicts the expression of 30 distinct cell type-specific molecular signatures directly from whole slide images, achieving an average Pearson correlation of 0.5 with the ground truth on independent tumor cohorts. Furthermore, we find that HistoTME-predicted microenvironment signatures and their underlying interactions improve prognostication of lung cancer patients receiving immunotherapy, achieving an AUROC of 0.75 [95% CI: 0.61-0.88] for predicting treatment responses following first-line ICI treatment, utilizing an external clinical cohort of 652 patients. Collectively, HistoTME presents an effective approach for interrogating the TME and predicting ICI response, complementing PD-L1 expression, and bringing us closer to personalized immuno-oncology.
- 19 December 2024
- Published by Springer Nature in npj Precision Oncology
- Vol. 8 (1) , 1-15
Open AccessPredicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images
Immune checkpoint inhibitors (ICI) have become integral to treatment of non-small cell lung cancer (NSCLC). However, reliable biomarkers predictive of immunotherapy efficacy are limited. Here, we introduce HistoTME, a novel weakly supervised deep learning approach to infer the tumor microenvironment (TME) composition directly from histopathology images of NSCLC patients. We show that HistoTME accurately predicts the expression of 30 distinct cell type-specific molecular signatures directly from whole slide images, achieving an average Pearson correlation of 0.5 with the ground truth on independent tumor cohorts. Furthermore, we find that HistoTME-predicted microenvironment signatures and their underlying interactions improve prognostication of lung cancer patients receiving immunotherapy, achieving an AUROC of 0.75 [95% CI: 0.61-0.88] for predicting treatment responses following first-line ICI treatment, utilizing an external clinical cohort of 652 patients. Collectively, HistoTME presents an effective approach for interrogating the TME and predicting ICI response, complementing PD-L1 expression, and bringing us closer to personalized immuno-oncology.
- 20 November 2024
- Published by Springer Nature in Nature Reviews Urology
- Vol. 22 (6) , 375-386
Metastasis development in non-muscle-invasive bladder cancer
Non-muscle-invasive bladder cancer (NMIBC) is the most common type of bladder cancer presentation and is characterized by a varying probability of recurrence and progression. Sporadically, patients with NMIBC might also develop tumour metastases without any pathological evidence of muscle-invasive disease within the bladder, a condition known as metastatic NMIBC. In the published literature, this phenomenon is limited to several case reports and small reviews, with few data regarding the possible aetiologies. Several possible factors can be potentially associated with metastatic NMIBC, including tumour understaging, the number of transurethral resection procedures received by the patient, the presence of circulating tumour cells, the modality used for diagnostic cystoscopy and possible gender-associated differences. In this Perspective, our aim was to integrate and report currently available data on this relatively rare entity and provide some potential aetiological explanations.
- 20 November 2024
- Published by Springer Nature in Nature Reviews Urology
- Vol. 22 (6) , 375-386
Metastasis development in non-muscle-invasive bladder cancer
Non-muscle-invasive bladder cancer (NMIBC) is the most common type of bladder cancer presentation and is characterized by a varying probability of recurrence and progression. Sporadically, patients with NMIBC might also develop tumour metastases without any pathological evidence of muscle-invasive disease within the bladder, a condition known as metastatic NMIBC. In the published literature, this phenomenon is limited to several case reports and small reviews, with few data regarding the possible aetiologies. Several possible factors can be potentially associated with metastatic NMIBC, including tumour understaging, the number of transurethral resection procedures received by the patient, the presence of circulating tumour cells, the modality used for diagnostic cystoscopy and possible gender-associated differences. In this Perspective, our aim was to integrate and report currently available data on this relatively rare entity and provide some potential aetiological explanations.
- Open Access
- 1 January 2017
- Published by Wiley in Case Reports in Oncological Medicine
- Vol. 2017 (1) , 4276435
Squamous Cell Carcinoma of the Thyroid as a Result of Anaplastic Transformation from BRAF‐Positive Papillary Thyroid Cancer
Papillary thyroid carcinoma (PTC) is the most common malignant neoplasm of the thyroid. Majority of the PTC carries an excellent prognosis. However, patients with tall cell variant (TCV) of papillary thyroid carcinoma have a worse prognosis than those with the classic variant. On the other hand, squamous cell carcinoma of the thyroid (SCT) is an unusual neoplasm thought to arise as a primary tumor or as a component of an anaplastic or undifferentiated carcinoma. We report a patient with TCV of PTC presenting years later with squamous transformation. In addition, the patient was found to have BRAF mutation. Such dedifferentiation is considered to be a rare phenomenon and has been reported only in the form of case reports in the literature. The relationship between BRAFV600E mutation and squamous cell transformation of papillary thyroid cancer is unknown at this time. Meticulous pathology is needed to identify such variants. Our patient responded to treatment with concurrent chemotherapy with carboplatin and paclitaxel along with radiation.
- 1 January 2017
- Published by Wiley in Case Reports in Oncological Medicine
- Vol. 2017 (1) , 4276435
Open AccessSquamous Cell Carcinoma of the Thyroid as a Result of Anaplastic Transformation from BRAF‐Positive Papillary Thyroid Cancer
Papillary thyroid carcinoma (PTC) is the most common malignant neoplasm of the thyroid. Majority of the PTC carries an excellent prognosis. However, patients with tall cell variant (TCV) of papillary thyroid carcinoma have a worse prognosis than those with the classic variant. On the other hand, squamous cell carcinoma of the thyroid (SCT) is an unusual neoplasm thought to arise as a primary tumor or as a component of an anaplastic or undifferentiated carcinoma. We report a patient with TCV of PTC presenting years later with squamous transformation. In addition, the patient was found to have BRAF mutation. Such dedifferentiation is considered to be a rare phenomenon and has been reported only in the form of case reports in the literature. The relationship between BRAFV600E mutation and squamous cell transformation of papillary thyroid cancer is unknown at this time. Meticulous pathology is needed to identify such variants. Our patient responded to treatment with concurrent chemotherapy with carboplatin and paclitaxel along with radiation.
- Open Access
- 31 May 2015
- Published by Hindawi Limited in Case Reports in Oncological Medicine
- Vol. 2015, 1-6
Malignant Triton Tumors in Sisters with Clinical Neurofibromatosis Type 1
Malignant triton tumors (MTTs) are rare and aggressive sarcomas categorized as a subgroup of malignant peripheral nerve sheath tumors (MPNSTs). MTTs arise from Schwann cells of peripheral nerves or existing neurofibromas and have elements of rhabdomyoblastic differentiation. We report the occurrence of MTTs in two sisters. The first patient is a 36-year-old female who presented with left sided chest wall swelling. She also had clinical features consistent with neurofibromatosis type 1 (NF-1). Debulking of the mass showed high-grade malignant peripheral nerve sheath tumor with skeletal muscle differentiation (MTT). The patient was treated with ifosfamide and adriamycin along with radiation. Four years after treatment, she still has no evidence of disease recurrence. Her sister subsequently presented to us at the age of 42 with left sided lateral chest wall pain. Imaging showed a multicompartmental retroperitoneal cystic mass with left psoas involvement. The tumor was resected and, similarly to her sister, it showed high-grade malignant peripheral nerve sheath tumor with rhabdomyoblastic differentiation (MTT). The patient was started on chemotherapy and radiation as described above.
- 31 May 2015
- Published by Hindawi Limited in Case Reports in Oncological Medicine
- Vol. 2015, 1-6
Open AccessMalignant Triton Tumors in Sisters with Clinical Neurofibromatosis Type 1
Malignant triton tumors (MTTs) are rare and aggressive sarcomas categorized as a subgroup of malignant peripheral nerve sheath tumors (MPNSTs). MTTs arise from Schwann cells of peripheral nerves or existing neurofibromas and have elements of rhabdomyoblastic differentiation. We report the occurrence of MTTs in two sisters. The first patient is a 36-year-old female who presented with left sided chest wall swelling. She also had clinical features consistent with neurofibromatosis type 1 (NF-1). Debulking of the mass showed high-grade malignant peripheral nerve sheath tumor with skeletal muscle differentiation (MTT). The patient was treated with ifosfamide and adriamycin along with radiation. Four years after treatment, she still has no evidence of disease recurrence. Her sister subsequently presented to us at the age of 42 with left sided lateral chest wall pain. Imaging showed a multicompartmental retroperitoneal cystic mass with left psoas involvement. The tumor was resected and, similarly to her sister, it showed high-grade malignant peripheral nerve sheath tumor with rhabdomyoblastic differentiation (MTT). The patient was started on chemotherapy and radiation as described above.
- Open Access
- 1 January 2014
- Published by International Scientific Information, Inc. in American Journal of Case Reports
- Vol. 15, 431-436
Hemophagocytic Lymphohistiocytosis in a Patient with Goodpasture’s Syndrome: A Rare Clinical Association
Rare disease Hemophagocytic lymphohistiocytosis (HLH) is a life-threatening clinical syndrome. HLH can occur in the setting of an autoimmune disease, chronic immunosuppression, malignancy, and infection. We discuss a rare case of a young woman who was diagnosed with Goodpasture’s syndrome that was most likely complicated by HLH. To the best of our knowledge, this is the first report of HLH in the setting of this rare autoimmune disease. A 31-year-old woman who was diagnosed with Goodpasture’s syndrome 7 years prior presented with febrile neutropenia. She was initially receiving treatment with azathioprine and prednisone, which was subsequently switched to hydroxychloroquine. Over time, she had developed polyarthritis and was later diagnosed with MPO-ANCA-positive vasculitides. On this admission, her clinical status deteriorated from persistent pancytopenia. This was initially attributed to the immunosuppressive effect of hydroxychloroquine. A bone marrow biopsy was performed and revealed hypercellular bone marrow without any cytogenetic abnormalities. Due to a prolonged pancytopenia thought to be of autoimmune etiology, treatment with high-dose steroids was initiated. With the persistent febrile episodes, hepatosplenomegaly on examination, and laboratory workup that revealed hyperferritinemia and pancytopenia, HLH syndrome was suspected. A repeat bone marrow biopsy confirmed this diagnosis with the presence of hemophagocytosis, demonstrated by the presence of histiocytes engulfing erythroid cells. She also met 5 of 8 diagnostic criteria, which confirmed the diagnosis of HLH. The patient eventually died despite aggressive treatment with high-dose steroid therapy for her autoimmune disorder, as well intravenous antibiotics and supportive care for her underlying infections. HLH is a syndrome marked by a hyper-inflammatory state aggravated by specific triggers. To make the diagnosis of HLH, at least 5 of the 8 criteria must be met. Treatment involves suppression of the overwhelming inflammatory response by the use of immunomodulators. The mortality rate can range from 50–90% due to delayed recognition and onset of treatment. Here, we present a rare case of Goodpasture’s syndrome with overlap and pauci-immune vasculitis, which may have triggered the HLH. This correlation has not been described before in the literature.
- 1 January 2014
- Published by International Scientific Information, Inc. in American Journal of Case Reports
- Vol. 15, 431-436
Open AccessHemophagocytic Lymphohistiocytosis in a Patient with Goodpasture’s Syndrome: A Rare Clinical Association
Rare disease Hemophagocytic lymphohistiocytosis (HLH) is a life-threatening clinical syndrome. HLH can occur in the setting of an autoimmune disease, chronic immunosuppression, malignancy, and infection. We discuss a rare case of a young woman who was diagnosed with Goodpasture’s syndrome that was most likely complicated by HLH. To the best of our knowledge, this is the first report of HLH in the setting of this rare autoimmune disease. A 31-year-old woman who was diagnosed with Goodpasture’s syndrome 7 years prior presented with febrile neutropenia. She was initially receiving treatment with azathioprine and prednisone, which was subsequently switched to hydroxychloroquine. Over time, she had developed polyarthritis and was later diagnosed with MPO-ANCA-positive vasculitides. On this admission, her clinical status deteriorated from persistent pancytopenia. This was initially attributed to the immunosuppressive effect of hydroxychloroquine. A bone marrow biopsy was performed and revealed hypercellular bone marrow without any cytogenetic abnormalities. Due to a prolonged pancytopenia thought to be of autoimmune etiology, treatment with high-dose steroids was initiated. With the persistent febrile episodes, hepatosplenomegaly on examination, and laboratory workup that revealed hyperferritinemia and pancytopenia, HLH syndrome was suspected. A repeat bone marrow biopsy confirmed this diagnosis with the presence of hemophagocytosis, demonstrated by the presence of histiocytes engulfing erythroid cells. She also met 5 of 8 diagnostic criteria, which confirmed the diagnosis of HLH. The patient eventually died despite aggressive treatment with high-dose steroid therapy for her autoimmune disorder, as well intravenous antibiotics and supportive care for her underlying infections. HLH is a syndrome marked by a hyper-inflammatory state aggravated by specific triggers. To make the diagnosis of HLH, at least 5 of the 8 criteria must be met. Treatment involves suppression of the overwhelming inflammatory response by the use of immunomodulators. The mortality rate can range from 50–90% due to delayed recognition and onset of treatment. Here, we present a rare case of Goodpasture’s syndrome with overlap and pauci-immune vasculitis, which may have triggered the HLH. This correlation has not been described before in the literature.