Browsing by Author "Gondim, Dibson"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Author Correction: A pyramidal deep learning pipeline for kidney whole-slide histology images classification
    (Springer Nature, 2021-11-02) Abdeltawab, Hisham; Khalifa, Fahmi; Ghazal, Mohammed; Cheng, Liang; Gondim, Dibson; El‑Baz, Ayman; Pathology and Laboratory Medicine, School of Medicine
    This corrects the article "A pyramidal deep learning pipeline for kidney whole-slide histology images classification" in volume 11, 20189.
  • Thumbnail Image
    Item
    A pyramidal deep learning pipeline for kidney whole-slide histology images classification
    (Springer Nature, 2021-10-12) Abdeltawab, Hisham; Khalifa, Fahmi; Ghazal, Mohammed; Cheng, Liang; Gondim, Dibson; El‑Baz, Ayman; Pathology and Laboratory Medicine, School of Medicine
    Renal cell carcinoma is the most common type of kidney cancer. There are several subtypes of renal cell carcinoma with distinct clinicopathologic features. Among the subtypes, clear cell renal cell carcinoma is the most common and tends to portend poor prognosis. In contrast, clear cell papillary renal cell carcinoma has an excellent prognosis. These two subtypes are primarily classified based on the histopathologic features. However, a subset of cases can a have a significant degree of histopathologic overlap. In cases with ambiguous histologic features, the correct diagnosis is dependent on the pathologist's experience and usage of immunohistochemistry. We propose a new method to address this diagnostic task based on a deep learning pipeline for automated classification. The model can detect tumor and non-tumoral portions of kidney and classify the tumor as either clear cell renal cell carcinoma or clear cell papillary renal cell carcinoma. Our framework consists of three convolutional neural networks and the whole slide images of kidney which were divided into patches of three different sizes for input into the networks. Our approach can provide patchwise and pixelwise classification. The kidney histology images consist of 64 whole slide images. Our framework results in an image map that classifies the slide image on the pixel-level. Furthermore, we applied generalized Gauss-Markov random field smoothing to maintain consistency in the map. Our approach classified the four classes accurately and surpassed other state-of-the-art methods, such as ResNet (pixel accuracy: 0.89 Resnet18, 0.92 proposed). We conclude that deep learning has the potential to augment the pathologist's capabilities by providing automated classification for histopathological images.
  • Thumbnail Image
    Item
    Spontaneous resolution of inflammatory myofibroblastic tumor of the kidney
    (2014-12) Calaway, Adam C.; Gondim, Dibson; Idrees, Muhammad; Boris, Ronald S.; Department of Urology, IU School of Medicine
    Inflammatory myofibroblastic tumor (IMT) of the kidney is a rare and benign condition often confused with renal malignancy based on clinical presentation and radiologic evaluation that has commonly been treated with nephrectomy. Utilizing renal mass biopsy to help diagnose and guide therapeutic intervention is increasing but has not been universally adopted to this point. We present a case of an incidentally found atypical renal mass in a 71-year-old female diagnosed as inflammatory myofibroblastic tumor of the kidney after core needle biopsy. This tumor was managed conservatively without surgical intervention and resolved spontaneously.
  • Thumbnail Image
    Item
    Standardized Reporting of Microscopic Renal Tumor Margins: Introduction of the Renal Tumor Capsule Invasion Scoring System
    (Elsevier, 2017-01) Snarskis, Connor; Calaway, Adam C.; Wang, Lu; Gondim, Dibson; Hughes, Ian; Idrees, Mohammad; Kleithermes, Stephanie; Maniar, Viraj; Picken, Maria M.; Boris, Ronald S.; Gupta, Gopal N.; Department of Urology, School of Medicine
    Purpose Renal tumor enucleation allows for maximal parenchymal preservation. Identifying pseudocapsule integrity is critically important in nephron sparing surgery by enucleation. Tumor invasion into and through the capsule may have clinical implications, although it is not routinely commented on in standard pathological reporting. We describe a system to standardize the varying degrees of pseudocapsule invasion and identify predictors of invasion. Materials and Methods We performed a multicenter retrospective review between 2002 and 2014 at Indiana University Hospital and Loyola University Medical Center. A total of 327 tumors were evaluated following removal via radical nephrectomy, standard margin partial nephrectomy or enucleation partial nephrectomy. Pathologists scored tumors using our i-Cap (invasion of pseudocapsule) scoring system. Multivariate analysis was done to determine predictors of higher score tumors. Results Tumor characteristics were similar among surgical resection groups. Enucleated tumors tended to have thinner pseudocapsule rims but not higher i-Cap scores. Rates of complete capsular invasion, scored as i-Cap 3, were similar among the surgical techniques, comprising 22% of the overall cohort. Papillary histology along with increasing tumor grade was predictive of an i-Cap 3 score. Conclusions A capsule invasion scoring system is useful to classify renal cell carcinoma pseudocapsule integrity. i-Cap scores appear to be independent of surgical technique. Complete capsular invasion is most common in papillary and high grade tumors. Further work is warranted regarding the relevance of capsular invasion depth as it relates to the oncologic outcome for local recurrence and disease specific survival.