- Browse by Author
Browsing by Author "Gondim, Dibson D."
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item A deep learning framework for automated classification of histopathological kidney whole-slide images(Elsevier, 2022-04-18) Abdeltawab, Hisham A.; Khalifa, Fahmi A.; Ghazal, Mohammed A.; Cheng, Liang; El-Baz, Ayman S.; Gondim, Dibson D.; Pathology and Laboratory Medicine, School of MedicineBackground: Renal cell carcinoma is the most common type of malignant kidney tumor and is responsible for 14,830 deaths per year in the United States. Among the four most common subtypes of renal cell carcinoma, clear cell renal cell carcinoma has the worst prognosis and clear cell papillary renal cell carcinoma appears to have no malignant potential. Distinction between these two subtypes can be difficult due to morphologic overlap on examination of histopathological preparation stained with hematoxylin and eosin. Ancillary techniques, such as immunohistochemistry, can be helpful, but they are not universally available. We propose and evaluate a new deep learning framework for tumor classification tasks to distinguish clear cell renal cell carcinoma from papillary renal cell carcinoma. Methods: Our deep learning framework is composed of three convolutional neural networks. We divided whole-slide kidney images into patches with three different sizes where each network processes a specific patch size. Our framework provides patchwise and pixelwise classification. The histopathological kidney data is composed of 64 image slides that belong to 4 categories: fat, parenchyma, clear cell renal cell carcinoma, and clear cell papillary renal cell carcinoma. The final output of our framework is an image map where each pixel is classified into one class. To maintain consistency, we processed the map with Gauss-Markov random field smoothing. Results: Our framework succeeded in classifying the four classes and showed superior performance compared to well-established state-of-the-art methods (pixel accuracy: 0.89 ResNet18, 0.92 proposed). Conclusions: Deep learning techniques have a significant potential for cancer diagnosis.Item Artificial intelligence-based multi-class histopathologic classification of kidney neoplasms(Elsevier, 2023-02-16) Gondim, Dibson D.; Al-Obaidy, Khaleel I.; Idrees, Muhammad T.; Eble, John N.; Cheng, Liang; Pathology and Laboratory Medicine, School of MedicineArtificial intelligence (AI)-based techniques are increasingly being explored as an emerging ancillary technique for improving accuracy and reproducibility of histopathological diagnosis. Renal cell carcinoma (RCC) is a malignancy responsible for 2% of cancer deaths worldwide. Given that RCC is a heterogenous disease, accurate histopathological classification is essential to separate aggressive subtypes from indolent ones and benign mimickers. There are early promising results using AI for RCC classification to distinguish between 2 and 3 subtypes of RCC. However, it is not clear how an AI-based model designed for multiple subtypes of RCCs, and benign mimickers would perform which is a scenario closer to the real practice of pathology. A computational model was created using 252 whole slide images (WSI) (clear cell RCC: 56, papillary RCC: 81, chromophobe RCC: 51, clear cell papillary RCC: 39, and, metanephric adenoma: 6). 298,071 patches were used to develop the AI-based image classifier. 298,071 patches (350 × 350-pixel) were used to develop the AI-based image classifier. The model was applied to a secondary dataset and demonstrated that 47/55 (85%) WSIs were correctly classified. This computational model showed excellent results except to distinguish clear cell RCC from clear cell papillary RCC. Further validation using multi-institutional large datasets and prospective studies are needed to determine the potential to translation to clinical practice.Item Cervical cancer metastasis to the brain: A case report and review of literature(Medknow Publications, 2017-08-09) Fetcko, Kaleigh; Gondim, Dibson D.; Bonnin, Jose M.; Dey, Mahua; Neurological Surgery, School of MedicineBackground: Intracranial metastasis from cervical cancer is a rare occurrence. Methods: In this study we describe a case of cervical cancer metastasis to the brain and perform an extensive review of literature from 1956 to 2016, to characterize clearly the clinical presentation, treatment options, molecular markers, targeted therapies, and survival of patients with this condition. Results: An elderly woman with history of cervical cancer in remission, presented 2 years later with a right temporo-parietal tumor, which was treated with surgery and subsequent stereotactic radiosurgery (SRS) to the resection cavity. She then returned 5 months later with a second solitary right lesion; she again underwent surgery and SRS to the resection cavity with no signs of recurrence 6 months later. According to the reviewed literature, the most common clinical presentation included females with median age of 48 years; presenting symptoms such as headache, weakness/hemiplegia/hemiparesis, seizure, and altered mental status (AMS)/confusion; multiple lesions mostly supratentorially located; poorly differentiated squamous cell carcinoma; and additional recurrences at other sites. The best approach to treatment is a multimodal plan, consisting of SRS or whole brain radiation therapy (WBRT) for solitary brain metastases followed by chemotherapy for systemic disease, surgery and WBRT for solitary brain lesions without systemic disease, and SRS or WBRT followed by chemotherapy for palliative care. The overall prognosis is poor with a mean and median survival time from diagnosis of brain metastasis of 7 and 4.6 months, respectively. Conclusion: Future efforts through large prospective randomized trials are warranted to better describe the clinical presentation and identify more effective treatment plans.Item Comparing oncologic outcomes in patients undergoing surgery for oncocytic neoplasms, conventional oncocytoma, and chromophobe renal cell carcinoma(Elsevier, 2019-11) Flack, Chandra K.; Calaway, Adam C.; Miller, Brady L.; Picken, Maria M.; Gondim, Dibson D.; Idrees, Muhammad T.; Abel, E. Jason; Gupta, Gopal N.; Boris, Ronald S.; Urology, School of MedicineIntroduction Oncocytic neoplasms are renal tumors similar to oncocytoma, but their morphologic variations preclude definitive diagnosis. This somewhat confusing diagnosis can create treatment and surveillance challenges for the treating urologist. We hypothesize that these subtle morphologic variations do not drastically affect the malignant potential of these tumors, and we sought to demonstrate this by comparing clinical outcomes of oncocytic neoplasms to those of classic oncocytoma and chromophobe. Methods We gathered demographic and outcomes data for patients with variant oncocytic tumors. Oncologic surveillance was conducted per institutional protocol in accordance with NCCN guidelines. Descriptive statistics were used to compare incidence of metastasis and death against those for patients with oncocytoma and chromophobe. Three hundred and fifty-one patients were analyzed: 164 patients with oncocytoma, 28 with oncocytic neoplasms, and 159 with chromophobe tumors. Results Median follow-up time for the entire cohort was 32.4 months, (interquartile range 9.2–70.0). Seventeen total patients (17/351, 4.9%) died during the course of the study. In patients with oncocytoma or oncocytic neoplasm, none were known to metastasize or die of their disease. Only chromophobe tumors >6 cm in size in our series demonstrated metastatic progression and approximately half of these metastasized tumors demonstrated sarcomatoid changes. Conclusion Variant oncocytic neoplasms appear to have a natural course similar to classic oncocytoma. These tumors appear to have no metastatic potential, and oncologic surveillance may not be indicated after surgery.