Acute Hemorrhage Related Colonic Injury Misdiagnosed as Signet-Ring Cell Carcinoma

Introduction/Objective

Hypovolemic shock/hypoperfusion-related gastrointestinal injury is an unusual event in the practice of oncological pathology. The histologic findings can be ambiguous, potentially masquerading other entities, especially epithelial neoplasms. One needs to pay close attention to the subtle microscopic features and the associated sudden clinical event(s). Concordant hypovolemic history will help decision-making but can be overlooked or unaware of.

Methods/Case Report

A 72-year-old gentleman with prostate hypertrophy, rheumatoid arthritis, and hypertension presented to the emergency room with palpitation, dizziness, and dyspnea. He was diagnosed with atrial fibrillation and started on anticoagulation. Unexpectedly, the patient returned 3 days later with sudden gastrointestinal hemorrhage and severe anemia (hemoglobin 2.7). Emergency colonoscopy identified mucosal hemorrhage, erosion, and a friable, mass-like area in the sigmoid colon; the corresponding biopsy was called signet-ring cell carcinoma. Subsequently, the patient was referred to our institution for consultation.

Results (if a Case Study enter NA)

The provided biopsy showed multiple clusters of signet-ring-like cells with extravasated mucin, detached or distributed within edematous colonic fragments, resembling signet-ring cell carcinoma. However, no overt cytologic or architecture atypia or mitosis was appreciated; instead, microscopic hemorrhage, capillary thrombi, withering and distorted crypts, and mucosal necrotic sloughing were present, worse on the luminal surface. Furthermore, no background dysplasia or adenoma was identified. These findings uncovered an originally misdiagnosed acute colitis due to hypoperfusion. Subsequent imaging studies detected no gastrointestinal mass/lesion. 22-months later, the patient’s clinical follow-up was unremarkable.

Conclusion

Severe hemorrhage/hypoperfusion-induced colitis may pose a dilemma clinically and histopathologically when the contributing event is underrecognized. Detailed history and laboratory review and astute microscopic inspection are warranted.

Unusual liver Involvement by Small Cell Carcinoma Arising in an Ovarian Malignant Mixed Mullerian Tumor

Introduction/Objective

Malignant mixed Mullerian tumor (MMMT) is a rare and aggressive tumor with patient survival of fewer than three years. MMMT harbors multilineage differentiation associated with malignant epithelial and stromal components. Awareness and familiarity with these characteristics are essential for patient stratification and clinical management.

Methods/Case Report

A 64-year-old female presented with refractory lower abdominal pain and bloating. Imaging studies revealed a 14-cm pelvic mass. The patient underwent urgent hysterectomy with salpingo-oophorectomy. She was diagnosed with ovarian MMMT(A) and received chemotherapy. The patient returned 2 months later with new- onset abdominal pain. CT detected numerous liver lesions; a biopsy was performed.

Results (if a Case Study enter NA)

The liver biopsy revealed metastatic small cell carcinoma (SCC[B], positive for synaptophysin and CD56; Ki67 >90%.). However, no concurrent lesions were identified on imaging. Further testing was attempted to locate the source of the SCC. Re-review of the MMMT with additional tissue sectioning identified sheets of high-grade pleomorphic malignant cells with a high N:C ratio, arranged in rosettes and without mucin. Additional immunohistochemistry labeled this MMMT diffusely with synaptophysin(C), chromogranin, and CD56. Furthermore, microscopic foci of MMMT showed higher grade histomorphology similar to the liver SCC which stained for PAX5(D). These findings illustrate a rare MMMT with a neuroendocrine carcinoma/SCC component which gave rise to liver metastasis.

Conclusion

This unusual liver SCC in a patient with prior MMMT exemplifies the multipotent malignant potential of MMMT and demonstrates the importance of having a spectrum of differentials and carrying out meticulous histomorphologic and ancillary analyses, especially when there is unusual histomorphology and discordance in clinical course.

Using Deep Learning for Whole Slide Image Prostate Cancer Diagnosis and Grading in South Florida Veteran Population

Introduction/Objective

Prostate cancer is the most common non-cutaneous malignancy in veterans, with approximately 11,000 new prostate cancer cases diagnosed in the Veteran’s Affairs system each year. Prostate cancer diagnosis and grading can be challenging even for experienced pathologists. Although large VA medical centers have pathologists that specialize in urologic pathology, the vast majority have not. We hypothesized that the AI-augmented diagnosis and grading may provide the solution for such situations.

Methods/Case Report

Dataset consisted of 10,000 prostate biopsy whole slide images (WSI) from the Kaggle PANDA challenge, and 6,000 WSI from the James A. Haley Veterans’ Hospital. Two Classification models were trained on the combined Kaggle and VA datasets using whole slide labels, and not annotated slides that resemble semi-supervised training.

Two-Class Classification to predict Benign: ISUP [0] / Cancerous: ISUP [1,2,3,4,5] Three-Class Classification to predict Benign: ISUP [0] / Low-grade: ISUP [1,2] / High-grade: ISUP [3,4,5] WSI split into “tiles” were used for training the models to reduce whitespace around samples, manage large images, and normalize dimensions/orientations.

Results (if a Case Study enter NA)

Models trained purely as binary and 3-class classifiers performed very well. Two-Class Model:

Accuracy = 0.937

Precision = 0.965

F1 = 0.94

AUC = 0.979

Three-Class Model:

Accuracy 0.89

o Benign:

Precision=0.897

f1=0.928

o Low-grade:

Precision=0.866

f1=0.841

o High-grade:

Precision=0.91

f1=0.878

We plan to develop multi-stage prediction models using these 2-Class and 3-Class classifiers as the first stage and a cancer grade predictor in the second stage.

Conclusion

We successfully showed that AI can augment pathologist’s diagnosis and grading of prostate cancer.