Leptomeningeal Carcinomatosis Secondary to Esophageal Cancer Diagnosed on Cytology

Jagtap, Sunil Vitthalrao; Khoja, Shoaib; Jagtap, Shubham S.; Gudur, Rashmi; Janugade, Hemant B.

doi:10.1055/s-0040-1713576

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pretrained faster-RCNN network showed excellent performance on the COCO dataset. The weights from the pre-trained Resnet-Inception-V2, excluding the top layer, were set as the pretrained state of our network and then fine-tuned for the current task ( 29 ). A separate network was trained for CNN1 (lymphocytes, monocytes, neutrophils, red blood cells, and cancer cells) and CNN2 (lung cancer cells, gastric cancer cells, breast cancer cells, and pancreatic cancer cells), resulting in two trained CNN.…”

Section: Methodsmentioning

confidence: 99%

“…In that case, the RPN network in the neural network can be iteratively trained to well-frame the cells in the test set. ResNet-Inception-V2 network is the backbone network of faster RCNN ( 29 ). The top layer of the Resnet-Inception-V2 architecture is the softmax layer, which converts the output of the previous layer into a probability output to solve the classification problem.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Classification of Cancer Cell in Leptomeningeal Metastasis on Cytomorphologic Features of Cerebrospinal Fluid

et al. 2022

View full text Add to dashboard Cite

BackgroundIt is a critical challenge to diagnose leptomeningeal metastasis (LM), given its technical difficulty and the lack of typical symptoms. The existing gold standard of diagnosing LM is to use positive cerebrospinal fluid (CSF) cytology, which consumes significantly more time to classify cells under a microscope.ObjectiveThis study aims to establish a deep learning model to classify cancer cells in CSF, thus facilitating doctors to achieve an accurate and fast diagnosis of LM in an early stage.MethodThe cerebrospinal fluid laboratory of Xijing Hospital provides 53,255 cells from 90 LM patients in the research. We used two deep convolutional neural networks (CNN) models to classify cells in the CSF. A five-way cell classification model (CNN1) consists of lymphocytes, monocytes, neutrophils, erythrocytes, and cancer cells. A four-way cancer cell classification model (CNN2) consists of lung cancer cells, gastric cancer cells, breast cancer cells, and pancreatic cancer cells. Here, the CNN models were constructed by Resnet-inception-V2. We evaluated the performance of the proposed models on two external datasets and compared them with the results from 42 doctors of various levels of experience in the human-machine tests. Furthermore, we develop a computer-aided diagnosis (CAD) software to generate cytology diagnosis reports in the research rapidly.ResultsWith respect to the validation set, the mean average precision (mAP) of CNN1 is over 95% and that of CNN2 is close to 80%. Hence, the proposed deep learning model effectively classifies cells in CSF to facilitate the screening of cancer cells. In the human-machine tests, the accuracy of CNN1 is similar to the results from experts, with higher accuracy than doctors in other levels. Moreover, the overall accuracy of CNN2 is 10% higher than that of experts, with a time consumption of only one-third of that consumed by an expert. Using the CAD software saves 90% working time of cytologists.ConclusionA deep learning method has been developed to assist the LM diagnosis with high accuracy and low time consumption effectively. Thanks to labeled data and step-by-step training, our proposed method can successfully classify cancer cells in the CSF to assist LM diagnosis early. In addition, this unique research can predict cancer’s primary source of LM, which relies on cytomorphologic features without immunohistochemistry. Our results show that deep learning can be widely used in medical images to classify cerebrospinal fluid cells. For complex cancer classification tasks, the accuracy of the proposed method is significantly higher than that of specialist doctors, and its performance is better than that of junior doctors and interns. The application of CNNs and CAD software may ultimately aid in expediting the diagnosis and overcoming the shortage of experienced cytologists, thereby facilitating earlier treatment and improving the prognosis of LM.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Deep Learning-Based Classification of Cancer Cell in Leptomeningeal Metastasis on Cytomorphologic Features of Cerebrospinal Fluid

et al. 2022

View full text Add to dashboard Cite

show abstract

Transitional meningioma benign who grade 1 tumor-A case and review of the literature

Jagtap,

Sarkar,

Jagtap

2023

ACHR

View full text Add to dashboard Cite

Transitional meningioma (TM) is an uncommon benign meningioma. Transitional meningioma is a WHO grade I meningioma characterized by the coexistence of meningothelial cells and fibrous architectural patterns. A35 year female presented with history of intermittent fever, headache of 1 month duration. And since last 2 days with altered level of consciousness and vomiting.: MRI of the brain was performed using TI weighted spin echoI2 weighted turbo spin echo and turbo Fluid-attenuated inversion recovery: FLAIR diffusion sequences. It showed a large, lobulated, enhancing lesion in right fronto-temporal region, along right greater wing of sphenoid suggestive of meningioma. Surgical excision of tumor was done. On histopathology showed a benign tumor consists of meningothelial and fibrous proliferation. The meningothelial cells were arranged in fascicles, with the fibroblastic tumor in syncytial pattern. The nuclei were round, uniform without nucleoli. The chromatin was fine and open. The tumor cells were spindle having abundant pink cytoplasm, indistinguishable cell membranes and bland nuclear features. Mitotic figures and atypia were absent .Scattered Psammoma bodies were noted. Histopathological diagnosis was gives as benign WHO grade 1 tumor- transitional meningioma.Due to enhanced and improved imaging, histopathological techniques the increased incidence of meningiomas is observed and it will be helpful for better outcomes of patients. We are presenting this case of transitional meningioma benign tumor WHO grade1for its clinical, radioimaging and histopatholgical findings.

show abstract

HER2+ esophageal carcinoma leptomeningeal metastases treated with intrathecal trastuzumab regimen

Jia

Schwartz

et al. 2023

CNS Oncol.

View full text Add to dashboard Cite

Materials & methods: We recently reported the largest trial of breast cancer patients with HER2 positive leptomeningeal metastases (LM) treated with trastuzumab. An additional treatment indication was explored as part of a single institution retrospective case series of HER2 positive esophageal adenocarcinoma LM (n = 2). Results: One patient received intrathecal trastuzumab (80 mg twice weekly) as part of their treatment regimen with durable long-term response and clearance of circulating tumor cells in the cerebral spinal fluid. The other patient demonstrated rapid progression and death as previously described in the literature. Conclusion: Intrathecal trastuzumab is a well-tolerated and reasonable therapeutic option worthy of further exploration for patients with HER2 positive esophageal carcinoma LM. An associative, but not a causal relationship, can be made regarding therapeutic intervention.

show abstract

Leptomeningeal Carcinomatosis Secondary to Esophageal Cancer Diagnosed on Cytology

Cited by 3 publications

References 7 publications

Deep Learning-Based Classification of Cancer Cell in Leptomeningeal Metastasis on Cytomorphologic Features of Cerebrospinal Fluid

Deep Learning-Based Classification of Cancer Cell in Leptomeningeal Metastasis on Cytomorphologic Features of Cerebrospinal Fluid

Transitional meningioma benign who grade 1 tumor-A case and review of the literature

HER2+ esophageal carcinoma leptomeningeal metastases treated with intrathecal trastuzumab regimen

Contact Info

Product

Resources

About